663 results about "Training time" patented technology

The invention discloses an industrial equipment fault prediction system based on federated learning and a privacy protection method, and relates to the field of industrial equipment fault prediction. The data acquisition preprocessing module extracts fault features through compressed sensing downsampling, screens and uploads the fault features; the federal learning training module adopts a layered architecture and a dynamic algorithm to schedule a learning rate; the fault prediction and diagnosis module constructs a space-time diagram neural network and fuses a physical model to improve generalization; the privacy protection security communication module performs homomorphic encryption storage and zero-knowledge proof verification update; the knowledge graph construction reasoning module constructs a dynamic graph, locates a fault root cause through causal reasoning, and supports cross-device knowledge migration. By adopting the quantum and federated learning technology, the industrial equipment fault diagnosis accuracy is high, the attack resistance is high, the encryption efficiency is greatly improved, the model training time is shortened, cross-equipment knowledge migration is realized, the operation and maintenance cost is reduced, and the intelligent operation and maintenance development of the industrial equipment is promoted.

The invention relates to the technical field of medical treatment, in particular to a child fracture rehabilitation management system based on virtual reality, which comprises a multi-modal sensing and data acquisition module, an intelligent rehabilitation training module, a multi-dimensional evaluation and feedback module and a data intelligent analysis and prediction module, compared with the defects that an existing rehabilitation training technology mainly depends on subjective experience of doctors to formulate a static scheme and lacks multi-source data dynamic feedback, the method comprises the steps that firstly, a comprehensive and accurate patient ability portrait is constructed; intelligent dynamic adjustment of training parameters is realized by utilizing an LSTM gating mechanism, a forgetting gate filters invalid historical data, an input gate fuses real-time action quality evaluation, an output gate generates a personalized difficulty gradient, and a patient ability threshold is continuously memorized in combination with a cell state, so that a training scheme has an adaptive evolution ability, and the training efficiency is improved. The parameter adjustment period of a traditional rehabilitation scheme is compressed from a week level to a real-time level, the accuracy rate of risk prediction of muscle strain and the like is improved, and the utilization rate of effective training time is increased.

The invention discloses a semi-centralized edge federated segmentation learning method of a federated learning system facing Internet of Things terminal equipment under a wireless network. The method comprises the following steps: establishing a to-be-trained model; splitting the to-be-trained model into a server-side first model and a client-side first model; distributing the client first model to each client in the to-be-trained client group; training each client first model to obtain a client second model and a first gradient corresponding to each client; according to the plurality of first gradients, updating the server-side first model to obtain a server-side second model and server-side second model features; according to the server-side second model features, updating each client-side second model to obtain a client-side third model corresponding to each client-side in the to-be-trained device group; repeating the execution; selecting the models meeting the first condition from the plurality of client third models for aggregation to obtain an aggregated client third model; and combining the aggregated third client model and the aggregated second server model to obtain a trained model. The method has the characteristics of low computing power consumption and short training time delay.

The invention discloses an image classification method and system based on pulse Transform of dynamic gradient adjustment. The method comprises the following steps: acquiring an image classification data set and randomly dividing the image classification data set into a training set, a test set and a verification set; the method comprises the following steps: designing MALIF neurons to reconstruct LIF neurons in an SNN network, introducing a dynamic time step mechanism module to construct a pulse Transform model for image classification, and training by using a training set; wherein the MALIF neurons can learn a membrane potential time constant and a voltage threshold, time and space information can be better utilized, and the MALIF neurons can efficiently transmit information; and obtaining a classification result of the to-be-tested image sample by using the trained pulse Transform model. The method is suitable for the field of image classification, reduces the training time of the model, has better performance, and improves the prediction precision and accuracy.

The invention discloses a search intention recognition method and device, equipment and a storage medium, and relates to the technical field of reinforcement learning, and the method comprises the following steps: generating training data based on an original corpus; performing supervision fine tuning processing on the lightweight language model based on the training data to obtain a fine tuning trained lightweight language model; performing strategy optimization on the lightweight language model subjected to fine tuning training through an improved GRPO reinforcement learning algorithm to obtain a lightweight language model subjected to reinforcement training; constructing a double-model hybrid architecture based on a short thinking chain model and a thinking chain-free model in the lightweight language model subjected to enhanced training; and outputting a final sequence of the related documents of the search terms of the user through the double-model hybrid architecture. According to the technical scheme of lightweight language model fine tuning, reinforcement learning optimization and double-model hybrid reasoning, the target search scene recognition accuracy is improved, the real-time response speed is high, and training time consumption and reasoning resource requirements are reduced.

The invention provides a parallel policy determination method, electronic equipment, a storage medium and a program product. The method comprises the following steps: determining cluster communication information, model calculation information and model resource occupation information according to information of a cluster used when a large model is trained and a structure of the large model; according to the cluster communication information and the model calculation information, modeling training time required by large model training to obtain a training time model; according to the model resource occupation information, carrying out modeling on resources occupied by large model training to obtain a resource occupation model; and according to the training time model and the resource occupation model, determining a target parallel strategy from multiple groups of parallel strategies as a parallel strategy used during large model training. Thus, by constructing the training time model and the resource occupancy model, the optimal parallel strategy can be automatically screened out from the multiple groups of parallel strategies, manual intervention is not needed, and therefore efficiency can be improved, and complexity can be reduced.

The invention provides a model training method. The method comprises the steps of collecting information of a first model; and making a re-calculation strategy according to the communication time of the first model in the communication stage and the execution time required by the plurality of operators in the first model. The information of the first model comprises execution time respectively required by a plurality of operators in the first model, the recalculation strategy comprises at least one recalculation operator in the plurality of operators and opportunity for executing a recalculation process by the at least one recalculation operator, the recalculation operator is an operator used for executing the recalculation process in the plurality of operators, and the opportunity for executing the recalculation process by the at least one recalculation operator in the plurality of operators is the opportunity for executing the recalculation process by the at least one recalculation operator. The opportunity at which the at least one recalculation operator performs the recalculation process includes performing the recalculation process in parallel with the communication phase of the first model. The recalculation process is parallel to the communication process of the model, so that the model training time is shortened, and the throughput of model training is improved.

The invention discloses a structure optimization method based on a mechanical embedded heterogeneous graph neural network. Comprising the following steps: pre-training a heterogeneous graph neural network, and carrying out transfer learning on the pre-trained heterogeneous graph neural network to obtain a pre-training model, and embedding a preset mechanical loss function in the pre-training model to obtain a mechanical embedded heterogeneous graph neural network, and inputting the real-time load condition of the engineering structure into the mechanical embedded heterogeneous graph neural network to output a second predicted value. According to the method and the device, the calculation efficiency and the calculation precision are considered in a mode of combining the pre-training model and neural network re-parameterization, the training time of the pre-training model is greatly shortened, the prediction precision is also improved, and based on the mechanical constraint and the adaptive weight coefficient in the improved loss function, the iteration process is more robust, and the prediction precision is improved. Therefore, the optimization of the engineering structure is realized.

The invention discloses an asynchronous hierarchical federated learning method, system, device and medium, and relates to the technical field of federated learning, and the method comprises the steps: clustering devices with similar training time in the same cluster at a client-edge end by using a mode based on a dynamic time window, and carrying out the clustering of the devices in the same cluster; dynamically grouping the equipment and asynchronously receiving local model update uploaded by the client; and at the edge end-central server, the performance evaluation and the historical participation degree of the edge server are dynamically scored, and the weight of the edge server participating in the global model aggregation is dynamically adjusted according to the score, so that a plurality of edge aggregation models are subjected to new global aggregation to obtain the global model; according to the method, the equipment is dynamically grouped, the local model is updated, the problem of equipment heterogeneity in the equipment is solved, the weight of the edge server participating in global model aggregation is dynamically adjusted according to the score, the heterogeneity condition existing in data is counteracted, and the federal learning aggregation efficiency is greatly improved.

The invention discloses an enterprise training evaluation system and method fusing RAG and an intelligent agent, and belongs to the technical field of training evaluation of artificial intelligence. The system comprises a computing node, a storage unit, a network interaction unit, a document vectorization processing module, a dynamic question setting module, a real-time semantic scoring module, a training effect visualization module and a learning recommendation module. The method comprises the steps of document preprocessing, dynamic question setting, real-time scoring, effect visualization and learning recommendation. Through deep fusion of RAG retrieval and agent decision, personalized question setting, multi-dimensional instant scoring, long-term knowledge state tracking and early warning and personalized learning recommendation based on student knowledge states are realized, and an evaluation-feedback-optimization closed loop is formed. According to the method, the question setting pertinence, the scoring accuracy (up to 92.3%) and the training efficiency (compressing the training time by 40%) are remarkably improved, and the method is suitable for various enterprise training scenes.

The invention provides a training method and device of a network poor quality analysis model, equipment, a medium and a product, and relates to the technical field of wireless communication. By training the time network and obtaining the backbone model, intelligent analysis and prediction of the operation indexes and the high-advance data can be realized, and improvement of the analysis efficiency of the poor-network-quality work order is facilitated. Through supervised training, fine tuning of an output layer of a backbone model, an anomaly detection branch, a root cause positioning branch and an index prediction branch, prediction of abnormal poor quality, network poor quality reasons and adjusted key operation indexes is further realized, so that intelligent analysis and processing of a network poor quality work order and evaluation of a processing result are realized; and the efficiency of processing the fault in the wireless poor-quality work order is improved.

The invention relates to the cross technical field of calculation of solid mechanics and deep learning, in particular to a self-adaptive mesh refining method, system and equipment for a physical information neural network, and the method comprises the steps: employing a coarse mesh physical information neural network model to discretize a mechanical problem, and building a mapping relation between node coordinates and node displacement; constructing a physical information function and a total loss function of the solid mechanics problem, and training the coarse mesh physical information neural network model to obtain a total loss function value and a change rate of the solid mechanics problem; if the coarse grid physical information neural network model meets a solving condition or the number of training times is greater than a preset number of times, outputting a displacement solution of the solid mechanics problem, otherwise, selecting a grid unit with a relatively large strain energy density value in the coarse grid physical information neural network model for refining to obtain a refined grid model; and migrating parameters of the coarse mesh physical information neural network model to the refined mesh model, and repeatedly executing the steps until a high-precision solution of the solid mechanics problem is output.

The invention discloses a multi-channel clock buffer test system and method, and relates to the technical field of electronic testing, and the method comprises the steps: collecting an original waveform data set, synchronizing a unified reference baseline, and generating a clock output data stream; performing frequency domain transformation on the clock output data stream, extracting dominant frequency drift, harmonic intensity change and phase fluctuation, and generating a spectrum disturbance feature vector sequence; performing recursive estimation on the spectrum disturbance feature vector sequence by using a Kalman filter, correcting state distribution in combination with a Bayesian probability updating method, and generating a health score drift trend vector; and performing multi-scale comparison on the health score drift trend vector, and identifying a channel entering a sub-health area by using an abnormal drift acceleration factor to generate an abnormal channel feature data set. According to the method, complex association between historical failure modes and features is mastered through the training time sequence prediction network, potential health score changes and failure time in the future are effectively predicted, and early warning is achieved.

The application discloses a short video code rate self-adaptive method based on meta learning, relates to the technical field of streaming media, and comprises the following steps: S1, offline training, a model is established to represent user characteristics and network prediction information; S2, online learning, according to the characteristics of the current user environment, the model parameters are adjusted and optimized. The short video code rate self-adaptive method based on meta learning is adopted, a new SABR framework based on meta learning is successfully realized, the framework can quickly adapt to different user demands, the practicability and the calculation speed of the system are improved, and the framework has industrial application; the offline training and the online learning technology are successfully combined, the generalization and the stability of the model are enhanced; the idea of action masking is introduced in pre-training, the rationality and the reliability of decision are enhanced, the data amount required by meta learning is effectively reduced, the learning efficiency and the accuracy are improved, and the data demand and the training time in the industrial environment are significantly reduced.

The invention discloses a cloud data server mixed training method and system, which are applied to a cloud data server cluster comprising a plurality of computing resources. According to the method, a model structure, a data set, a time delay constraint and an isolation constraint of a training task are analyzed to generate a task portrait, resource configuration, an operation state and an isolation capability of a calculation node are collected to generate a resource portrait, and a co-located interference degree index table of a task and resource combination is constructed based on historical monitoring data. During scheduling, a heterogeneous computing power utilization rate, an estimated training time delay deviation and a co-located interference degree are taken as indexes, a candidate resource allocation scheme is subjected to weighted evaluation to generate a mixed training scheduling strategy, and resource isolation is implemented through container and accelerator multi-instance division. In the operation process, the training time delay and the actual co-located interference degree are continuously monitored, the scheduling weight and the co-located interference degree index are dynamically adjusted according to the deviation, closed-loop optimization of multi-task mixed training is achieved, the heterogeneous resource utilization rate is increased, and time delay default and co-located interference are reduced.

The invention provides a cloud-edge collaborative heterogeneous graph neural network vehicle re-identification method, and relates to the technical field of intelligent traffic. The method comprises the following steps: constructing a knowledge structure through a multi-modal heterogeneous graph; extracting a multi-modal semantic relationship through a heterogeneous graph neural network to construct a cloud teacher model; in the method, a dynamic knowledge distillation mechanism driven by feature clustering is introduced to carry out knowledge fine-grained migration to generate a lightweight student model. Experiments are verified on VeRi-776, CityFlow-ReID and a self-built traffic data set, and results show that under the conditions that model parameters are compressed by 63% and a video memory is reduced by 64%, the total precision loss of a student model does not exceed 5%, and the reasoning speed reaches 213FPS. Compared with an existing traditional baseline method, the HGKDF has significant statistical advantages in RMSE and MAE indexes, is superior in training duration and video memory overhead, and is suitable for constructing the deployment of an integrated traffic large model system oriented to city-level intelligent interactive decision and safety monitoring.

The invention relates to a neural network model slope physical parameter inversion method based on data and physics hybrid driving. The problems that in the prior art, a slope parameter inversion method is high in dependence on monitoring data, large in calculation amount, low in efficiency and difficult to deal with complex geological conditions and sparse observation are solved. The method comprises the following steps: S1, selecting a slope and constructing geometric and physical models of the slope; s2, constructing a neural network model loss function according to the geometric and physical models of the slope; s3, defining a neural network model, input and output characteristics of the neural network model and model hyper-parameters; s4, monitoring data preprocessing and sample division; s5, converting the unbounded variable p of the to-be-inverted parameter into a bounded parameter value through a Sigmoid mapping function; S6, designing adaptive sampling of a neural network model; and S7, deploying the model and constructing an inversion-early warning closed-loop system. The method has the advantages that the training time and cost are reduced, and the prediction efficiency and precision are improved; and the engineering availability and stability are improved.

The embodiment of the invention provides a model training method, an information recommendation method, equipment, a storage medium and a program product. According to the embodiment of the invention, a multi-encoder-multi-sub-decoder-total decoder hybrid model architecture is provided, sample data of different information modes correspond to different encoders-sub-decoders, and a mode of processing all training sample data by a single model is converted into a divide-and-conquer mode. The internal complexity of each encoder-sub-decoder is relatively low, the complexity of model training can be reduced, resource consumption can be saved, and different encoder-sub-decoders can be trained in parallel, so that the model training time can be shortened; and furthermore, by utilizing a dual decoding mechanism of the sub-decoder and the global decoder, parameters of the encoder can be continuously adjusted through local optimization and global optimization, the performance of the model is optimized, the accuracy of a reasoning result is improved, the convergence speed of the model is accelerated, the model training efficiency is further improved, and the model training time is saved.

The invention discloses a photovoltaic power prediction method based on improved empirical mode decomposition and an optimized long short-term memory network, and the method comprises the steps: firstly carrying out the preprocessing of abnormal value elimination, missing value filling, normalization and the like of photovoltaic power and related meteorological data, and improving the data quality; then, an improved empirical mode decomposition (EE-ANEMD) algorithm is adopted to decompose the preprocessed power sequence into a multi-scale intrinsic mode function component and a residual term, and high-frequency noise, intermediate-frequency fluctuation and a low-frequency trend are effectively separated; global optimization is carried out on the hidden layer unit number, the initial learning rate and the maximum number of training times of the LSTM network through an improved sparrow search algorithm (ISSA), finally, the optimized LSTM is utilized to carry out training prediction on each component, and results are fused and subjected to reverse normalization to obtain a final value. Experiments show that the test set RMSE of the method is reduced compared with that of a single LSTM, the mid-term prediction precision is remarkably improved, and reliable technical support is provided for power system dispatching, new energy consumption planning and photovoltaic power station operation and maintenance.

The invention relates to the technical field of integrated energy systems, and provides an integrated energy system optimization method and system in multiple uncertain environments, and the method comprises the steps: obtaining the state of an integrated energy system, and obtaining a multi-energy-flow equipment action through an actor network; wherein MPC actors are embedded into a double-delay depth deterministic strategy gradient architecture, an actor network and transfer tuples of the MPC actors are respectively stored in an agent experience playback pool and an expert experience playback pool, a priority is given to each sample according to a time sequence difference error of the samples in the two experience playback pools, and a mixing ratio is determined according to a training time step; in combination with the mixing ratio and the priority, the sampling probability of samples is calculated, and then the degree of dependence of updating of the comment network on an expert experience playback pool in the initial training stage is controlled to be high, and the degree of dependence on an agent experience playback pool in the later training stage is controlled to be high. And the performance is better in a multi-uncertainty coupled IES environment.

The invention discloses a load identification method and system based on multi-view learning and a deep wide residual network. The method comprises the following steps: acquiring voltage and current data at an outlet of a current collector; extracting two types of load feature views from the collected data, and adding data labels to form a labeled data set; generating two training subsets from the labeled data set, wherein the initial training subset comprises a part of labeled samples and unlabeled samples; performing cross training on the two depth wide residual classification networks by using the training subset, and training to obtain a depth wide residual classification network model based on multi-view learning; and extracting two feature views from unknown electric appliance data collected in real time, inputting the two feature views as label-free data into the depth wide residual classification network model based on multi-view learning, updating the model, and obtaining a load identification result. The method has the advantages of improving the model recognition accuracy and generalization performance, enhancing the robustness of the model, improving the model recognition accuracy and saving the model training time.

The embodiment of the invention provides a slow node detection method and system, equipment, a storage medium and a program product, and the method comprises the steps: responding to the obtained training time consumption of a first node in target iteration, and determining a detection result of the first node based on the training time consumption of the first node in the target iteration; wherein the first node is a training node executing the model training task in the cluster, and the detection result of the first node represents whether the first node is a slow node or not.

The invention provides a penalty term-based gradient optimization neural network training method and a related device, which are applied to a server, a neural network model is constructed according to preset model architecture parameters, a training data set is acquired, the training data set is input to the neural network model, and a model output result is obtained. Determining an error loss function according to a model output result, determining an attenuation penalty term coefficient of the error loss function based on a preset weight attenuation algorithm and a preset number of iteration training times, determining a target loss function according to the error loss function and the attenuation penalty term coefficient, and training the neural network model based on a gradient descent method and the target loss function, and obtaining a target neural network model. The convergence rate is increased during neural network training, and the computing resources of the neural network during training are reduced.

The invention relates to the technical field of federated learning in an Internet of Vehicles scene, in particular to a federated learning method suitable for a high dynamic environment of a vehicle. According to the method, adaptive vehicle federation learning is provided, so that a local training period adapts to the vehicle capability, the scheduling flexibility is improved, the influence of insufficient local period on model updating is relieved, the training efficiency is improved, and the communication competition is reduced. Meanwhile, a federal learning scheduler based on an actor-commentator structure is designed to realize a dual-time scale optimization method, so that the training time is minimized and the model performance is maximized. According to the method, the vehicle federated learning performance reduction caused by the dynamic complex vehicle edge network is effectively relieved, and the training efficiency of the vehicle federated learning is improved.

The invention relates to a federal multi-language machine translation method based on efficient fine tuning, and belongs to the technical field of natural language processing. Aiming at the problems of high communication cost and long training time in a federated learning-based multi-language machine translation method, the invention provides a federated multi-language machine translation method based on efficient fine tuning, which comprises the following steps of: efficiently fine-tuning a multi-language translation model of a client; performing gradient similarity clustering on the fine-tuned multi-language translation model; carrying out average aggregation based on the clustered multi-language translation model; and deploying a federal multi-language machine translation device based on efficient fine tuning. According to the method, the calculation and communication overhead is greatly reduced while the translation performance is kept, and the method is suitable for distributed translation tasks in a multi-language scene.

How to reduce the error of visible light positioning is the technical problem focused in the current positioning technology, and reduction of the positioning error by adopting the neural network technology is an important scheme for solving the problem. The invention provides a deep learning fusion system for visible light positioning and a method thereof, and aims to solve the problems of unstable model training effect, insufficient positioning precision and poor generalization ability caused by insufficient data acquisition amount in the prior art, or the problems of long training time caused by overlarge data scale and the like. According to the method, the corresponding small model neural network or large model neural network is selected for training and prediction according to the scale of the collected data volume in different operation stages of the system, and a dynamic judgment and periodical comparison mechanism is combined, so that quick and stable positioning output is realized when the data is limited; when the data is sufficient, a high-precision and high-robustness positioning effect is realized, so that the adaptability and reliability of the system in practical application are improved.

The present invention discloses a method for optimizing infectious disease intervention measures based on reinforcement learning, comprising: adjusting parameters of an improved Covasim environment; training an intelligent agent: (1) the intelligent agent obtains state information s from the improved Covasim environment; t When the number of infected people exceeds the preset threshold, the intervention intensity value a is output according to the status information. t , according to a t Act on the environment and get the corresponding reward information r t , get the next state information s t+1 , the data group (s t , a t , r t , s t+1 ) is stored in the experience replay area; (2) when the data stored in the experience replay area reaches the preset data threshold, a Mini‑batch is randomly sampled to update the network parameters of the agent; (3) steps (1)‑(2) are repeated until the preset maximum training time is reached to obtain the trained agent; the trained agent outputs corresponding intervention measures according to the current epidemic status of the infectious disease.

An adaptive model partitioning method and system applied to distributed training, which method and system belong to the technical field of deep learning, and aim at solving the technical problem of how to implement, in respect of distributed training, distributed model training by means of combining deep reinforcement learning and a Bayesian optimization algorithm. The method comprises the following steps: constructing a Q network on the basis of a deep neural network, and defining state information, actions and a reward function, wherein the state information comprises feature vectors of partitioned models, and training times, resource utilization rates and inter-node communication overheads of when the partitioned models are subjected to distributed training by means of distributed computing nodes, each action is a partitioning strategy used by an agent under the current state information, the reward function R is used for evaluating the effect of the current partitioning strategy, and the Q network uses the state information as input to predict and output a Q value of each action that the agent may take; and performing multiple iterative training on a deep reinforcement adaptive model, so as to obtain a final partitioning strategy and parameters of the Q network.

The invention discloses an enhanced 3D (three-dimensional) surface reconstruction method based on 3D (three-dimensional) Gaussian Splitting. Global consistent depth priori is obtained through virtual stereo pair rendering; constructing a factor graph and introducing a cross-view geometry / luminosity consistency constraint to form local beam adjustment loss; the prior is used as a learnable parameter to be combined with 3DGS to be optimized, and meanwhile, the Pull loss is assisted to pull low-credibility pixels; and finally, multi-loss function end-to-end training is adopted. The method comprises the following steps of: in Tanksamp; the method has the advantages that F1 is equal to 0.58 and DTU Chamfer is equal to 0.48 mm on a Temples data set, the training time is only 20 min, compared with the prior art, geometric accuracy SOTA and speed magnitude improvement are achieved at the same time, and the method is suitable for VR / AR, robot and industrial measurement scenes.

The invention discloses an AI model parameter initialization method based on model parameter and structure multi-modal fusion, and belongs to the technical field of artificial intelligence. The method comprises the following steps: firstly, collecting historical pre-training model data of a cross-model architecture and a cross-data set, processing model parameters into a token sequence, training a Transform codec, converting a model structure into a graph, and training GAT to extract structural features; a multi-modal feature data set is constructed after a related network is frozen, structural features serve as core conditions, a conditional diffusion model DDPM is trained through AdaLN modulation and residual module coupling, and multi-modal feature fusion of'parameter feature-structural feature 'is established. In the reasoning stage, the structural features of the unknown model are extracted, the random parameters of the unknown model are combined with the submerged space shape determined by the encoder, sampling is conducted through the conditional diffusion model, anti-token processing is conducted through the decoder, and adaptive initialized model parameters are generated for the unknown model. According to the method, cross-model structure high-quality parameter initialization is realized, the model training time is shortened, and the large model training requirement is met.