Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

831results about How to "Reduce training time" patented technology

Robot agent reinforcement learning training method and system in complex scene

The invention discloses a robot agent reinforcement learning training method in a complex scene, and the method comprises the steps: constructing a reinforcement learning algorithm environment and a state transition model which comprise a barrier, a dynamic target, environment constraints and other complex scenes and are suitable for a multi-agent system; an independent neural network is constructed for each robot agent by adopting a reinforcement learning algorithm; taking vectors of a given state, time sequence information and historical state information of the intelligent agent as input of the state transition model, and outputting a state transition probability and reward information of a prediction state; the action strategy and the action value output by the neural network are executed in the state transition model, and a new prediction state and reward information are generated; through adjusting hyper-parameters of the neural network, a large-scale distributed training architecture is used to carry out cooperative training on the decision network and the evaluation network, parallel learning and cooperative decision of multiple agents are realized, and performance and generalization ability of the agents in a complex scene are improved.
Owner:XIAMEN YUANTING INFORMATION TECH CO LTD

Model pre-training method and device for multi-language task

The invention provides a model pre-training method and device for a multi-language task, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining a multi-modal training data set which comprises a plurality of pieces of sample text data and a plurality of pieces of sample image-text pair data with multi-language contents, and covers a universal field and a preset business field; based on a plurality of sample image-text pair data, performing comparative learning training of alignment of visual features and text features on the initial model, freezing model parameters of a decoding module and adjusting model parameters of a visual encoder and a projection module in the training process until a first ending condition is met; based on the multiple pieces of sample image-text pair data and the multiple pieces of sample text data, constraint training of content understanding is carried out on the initial model meeting a first ending condition, and model parameters of a visual encoder, a projection module and a decoding module are adjusted in the training process until a second ending condition is met to obtain a target model; the information extraction capability of the model in the specific field can be remarkably improved.
Owner:LIANLIAN YINTONG ELECTRONIC PAYMENT CO LTD +1

Seawall overtopping amount and overtopping risk calculation method considering mangrove forest wave dissipation effect

The invention discloses a seawall overtopping amount and overtopping risk calculation method considering a mangrove forest wave dissipation effect, and relates to the technical field of coast engineering. The method comprises the following steps: acquiring typhoon path data, inputting the typhoon path data into a Holland typhoon empirical model, and accurately generating a typhoon wind field; calculating coastal site tide level data in combination with a coastal storm surge numerical model; obtaining wave data during a typhoon by using a storm surge typhoon wave forecasting model based on the SWAN; historical typhoon data and relevant information of the seawall and the mangrove forest are collected, a water level-wave-vegetation-seawall coupling model is constructed, the wave dissipation effect of the mangrove forest is accurately simulated, and wave characteristic calculation is optimized; constructing a database, training the database through a CNN neural network model, and improving the prediction precision of seawall front wave height and wave force parameters; the wave overtopping amount is calculated based on the prediction parameters, a scientific basis is provided for wave overtopping risk assessment, it is ensured that real-time assessment of the wave overtopping risk is more accurate and efficient, and the disaster prevention and reduction capacity is effectively improved.
Owner:HOHAI UNIV

PCBA surface defect detection method and system based on image recognition

The invention provides a PCBA surface defect detection method and system based on image recognition, and the method comprises the steps: collecting and constructing a multi-class PCBA overall defect image data set, and carrying out the preprocessing; constructing a pre-training neural network model, and classifying the preprocessed PCBA overall defect image data set; constructing a local target identification method based on a YOLOX network according to an overall defect classification result; and carrying out local defect detection on the PCBA surface based on a local target identification method. According to the method, the overall classification and local detection strategies are comprehensively applied to reduce the burden of the model, and the detection precision and speed are improved. And an attention mechanism is introduced to improve the performance and generalization ability of the model. Data enhancement, consistency processing, classification labeling and the like are carried out on an image data set, and the defect detection effect of the model is improved. And multiple optimization strategies such as structure improvement, loss function improvement and pruning lightweight are adopted for the network model, so that the image target detection performance is effectively improved.
Owner:SHENZHEN FUYAN STAR TECH CO LTD

Recognition and detection system and method for AI voice dialogue scene application

InactiveCN119091880AHigh-quality voice interaction experienceImprove the level of intelligenceSpeech recognitionPattern recognitionPersonalization
The invention belongs to the technical field, and particularly relates to a recognition and detection system and method for AI voice dialogue scene application, and the system comprises an ASR automatic voice recognition unit which employs an advanced noise elimination algorithm to improve the definition of a voice signal; the NLP natural language processing unit adopts an intelligent recommendation analysis module; a machine learning unit; a TTS text-to-speech unit; a deep learning unit; an intelligent dialogue platform unit; a multi-modal interaction unit; a personalized customization unit; a dictionary noise elimination unit for eliminating noise by analyzing dictionary composition is arranged in the noise elimination algorithm; the intelligent recommendation analysis module comprises an intention recognition unit; and a feedback circulation unit. According to the method, the function of eliminating the noise by analyzing the composition of the dictionary can be realized, the noise and useful information are effectively distinguished, the application effect of the improved LMS algorithm and the improved RLS algorithm in noise elimination is remarkably improved, and in addition, a recommendation first choice for solving a problem can be selected according to secondary inquiry of a plurality of users.
Owner:Guochuang Future (Sichuan) Artificial Intelligence Technology Research Institute

Power distribution network fault recovery method and system based on multi-agent reinforcement learning

The invention belongs to the technical field of power distribution network fault recovery, and provides a power distribution network fault recovery method and system based on multi-agent reinforcement learning, and the method comprises the steps: taking a recovered load as a target function based on the load priority of a power distribution network, and taking the operation limitation of each node line in the power distribution network as a constraint condition; constructing a power distribution network fault recovery problem model; based on the power distribution network fault recovery problem model, constructing a multi-agent reinforcement learning agent set, and converting the power distribution network fault recovery problem into a Markov decision process; and a multi-agent reinforcement learning framework is constructed based on the agent set of multi-agent reinforcement learning, multi-agent training is carried out, each agent generates a decision according to respective observation information, and a fault recovery strategy is obtained. The objective function and the constraint condition constructed based on the load priority of the power distribution network and the node line operation limitation can ensure the accuracy and the feasibility of the recovery strategy. And the strategy generation time is shortened through the multi-agent parallel decision-making process.
Owner:CHINA ELECTRIC POWER RESEARCH INSTITUTE CO LTD +1

Large model increment training method and system based on dynamic sparsification

The invention belongs to the technical field of model training, and particularly relates to a large model increment training method and system based on dynamic sparsification. The method comprises the following steps: S1, evaluating the parameter importance of a large model by adopting a multi-dimensional evaluation method, and reflecting the contribution of parameters to the performance of the large model; s2, performing dynamic sparsification control on the large model structure by adopting a self-adaptive structure adjustment method; s3, performing incremental training management on the large model by constructing a capacity-adjustable empirical playback buffer pool and proposing a multi-objective loss function; and S4, carrying out model compression optimization on the large model by adopting a mixed precision quantification strategy. The method has the characteristics that the network structure can be dynamically adjusted by evaluating the importance of model parameters in real time, so that the efficient training is realized while the model performance is ensured.
Owner:HANGZHOU MICRO MACRO TECH CO LTD

Edge anomaly detection method based on global-personalized collaborative federated learning

The invention relates to an edge anomaly detection method based on global-personalized collaborative federated learning, and the method comprises the steps: enabling an edge server to generate a global model, and then releasing the global model; the client initializes a local model according to the global model; converting the traffic features into global and personalized feature vectors by using a condition calculation component at a client; the client introduces comparison and magnitude loss into a global category embedding module, guides the learning of global feature vectors according to the embedding of sample categories, and guides the learning of personalized feature vectors by using cross entropy loss; the client side judges whether loss replacement is executed or not by calculating the cosine similarity of the cross entropy loss and the total loss updating gradient, and then model training is accelerated; the client uploads the update of the model to the edge server after completing local training; performing global aggregation by the edge server, and updating a global model; and repeating the steps until the anomaly detection model converges. The method is beneficial for improving the edge anomaly detection precision and efficiency.
Owner:FUZHOU UNIV

Central air conditioner chilled water system and energy-saving optimization control method

The invention relates to a chilled water system of a central air conditioner and an energy-saving optimization control method. The energy-saving optimization method comprises the following steps: S1, establishing an energy consumption model of the chilled water system of the central air conditioner; s2, firstly performing correlation analysis on the selected cooling load influence factors by adopting a grey correlation analysis method, screening out strong correlation influence factors, and establishing a central air conditioner cooling load prediction model based on PSO-LSSVM (Particle Swarm Optimization-Least Square Support Vector Machine); s3, optimizing the energy consumption model parameters of the chilled water system of the central air conditioner while predicting the cooling load value of the next point by using an improved white whale algorithm, and enabling the output result of the energy consumption model to reach the minimum value; the system comprises an energy consumption modeling module, a cooling load prediction module and an energy-saving optimization module. According to the method, the energy consumption model and the cooling load prediction model are established, the cooling load value of the next point is predicted, parameter optimization is performed, and an optimization structure is output; the energy consumption model and the cold load prediction model can be updated periodically, and the problem of performance reduction caused by long-time equipment operation is avoided.
Owner:ACREL CO LTD +2

Medical spectrum reconstruction method and device

The invention relates to the technical field of image processing, in particular to a medical spectrum reconstruction method and device, and the method comprises the steps: firstly carrying out the dimension reduction and feature extraction of an original hyperspectral image, and generating a first image space; adding forward noise to the first image space to generate a noise-added image, and inputting the noise-added image and the first RGB image as joint training data into a to-be-trained residual denoising network model for training; based on the trained residual denoising network model and in combination with spectral information of the second RGB image, reverse iteration denoising processing is carried out on the target noise image to generate a second image space, and finally data reconstruction processing is carried out on the second image space to obtain a reconstructed hyperspectral image corresponding to the target noise image. According to the invention, the distribution and change of hyperspectral data can be better simulated, resolution balance is realized, and the accuracy and reliability of reconstruction are improved.
Owner:HANGZHOU HYPERSPECTRAL IMAGING TECH CO LTD

Mobile communication network load prediction and scheduling method and system based on deep learning

The invention relates to the technical field of network load prediction and scheduling methods, in particular to a mobile communication network load prediction and scheduling method and system based on deep learning, and the method comprises the steps: obtaining data from a plurality of edge computing nodes, including base station data, user behavior data and environment parameter data; constructing a multi-layer model for load prediction and resource scheduling based on cooperative work of the central system and the edge system; carrying out feature extraction by utilizing a dynamic feature embedding transformation module in the edge computing node; recursive spatial-temporal feature processing is carried out based on the optimized features; generating a network load prediction result through the prediction model; and resource scheduling optimization is performed through a reinforcement learning model based on a prediction result, and multi-dimensional features are nested and mapped to a high-dimensional feature space through dynamic feature embedding of original data. And the nested features are further optimized through a time-varying collaborative tensor optimization algorithm, so that the spatial relevance between different base stations can be enhanced while complex nonlinear features are captured.
Owner:SOUTHWEST FORESTRY UNIVERSITY

Multi-source ship target identification method based on two-stage collaborative fusion

The invention discloses a multi-source ship target identification method based on two-stage collaborative fusion, and relates to the technical field of signal processing, and the method comprises the steps: firstly collecting target sea area data, including original optical image and radar image data, by means of an optical camera and a radar sensor on an aircraft, and then carrying out the preprocessing of the collected data through Gaussian filtering; performing sea-land segmentation by using a deep learning algorithm, constructing a loss function optimization network parameter to obtain a segmentation mask, and removing a land background area according to a mask result to obtain processed optical and radar images; an improved SURF feature and graph cut algorithm combined registration method is adopted, optimal transformation parameters are obtained by screening feature point pairs and solving the minimum value of an energy function, and image registration is achieved; for the registered images, fusing the images based on an adaptive fusion rule; and finally, extracting corresponding features through manual feature extraction and feature extraction based on deep learning, and fusing the features to obtain a final target recognition result.
Owner:CHINA ACADEMY OF ELECTRONICS AND INFORMATION TECHNOLOGY OF CHINA ELECTRONICS TECHNOLOGY GROUP CORPORATION +1

Networked measurement and control data transmission task scheduling method for giant low-orbit satellite constellation

The invention discloses a networked measurement and control data transmission task scheduling method for a giant low-orbit satellite constellation, and solves the problem of low completion rate of measurement and control data transmission tasks caused by incapability of global station distribution in the prior art. Obtaining a resource attribute, a ground station state and a low earth orbit satellite state by using the task layer, the resource layer, the equipment state and the constellation state, performing data conversion to obtain input data, inputting the input data into the trained multi-agent network to obtain an action corresponding to the current time slot, and determining an entry low earth orbit satellite and an associated ground station according to the action; obtaining a routing path between the entry low earth orbit satellite and the task low earth orbit satellite according to the inter-satellite shortest path routing table, and determining a scheduling sequence according to the routing path and the associated ground station; the mutual influence between global tasks and resources is considered, the effectiveness of decision making during execution is reduced, and meanwhile, the scheduling efficiency of measurement and control data transmission tasks in a giant low-orbit satellite constellation scene is improved.
Owner:XIDIAN UNIV

BV-CNN-based analog circuit fault diagnosis method, electronic equipment and storage medium

The invention discloses an analog circuit fault diagnosis method based on BV-CNN, electronic equipment and a storage medium, and belongs to the technical field of analog circuit fault diagnosis. In order to efficiently carry out BV-CNN analog circuit fault diagnosis, an optimization objective function is defined, the number K of modes and a penalty parameter alpha are set as a Bayesian optimization parameter search space, the optimal combination of the number K of modes and the penalty parameter alpha of a VMD algorithm is searched by using a Bayesian optimization method, and the optimized parameters of the VMD algorithm are obtained. VMD parameters are automatically selected through Bayesian optimization, the problem of modal aliasing or excessive signal decomposition when parameter selection is improper is avoided, the signal decomposition effect is improved, the accuracy and robustness of fault diagnosis are greatly improved in combination with CNN automatic feature extraction and classification capacity, nonlinear and non-stationary signals can be well processed, and the fault diagnosis efficiency is improved. The method adapts to complex signals and multiple working conditions, and efficient parameter optimization and model training are achieved.
Owner:HARBIN INST OF TECH

Adaptive optimization method and system for training process of multi-modal large model

The invention provides an adaptive optimization method and system for a training process of a multi-modal large model. The method comprises the following steps: receiving a submitted training execution script and a training strategy of the multi-modal large model; according to the training execution script and the training strategy, utilizing a pre-stored large model training script to execute a distributed training task so as to generate a multi-modal large model; acquiring real-time monitoring data generated in the process of executing the distributed training task; adjusting a training strategy based on the real-time monitoring data, and continuing to execute the distributed training task by utilizing the large model training script according to the large model training execution script and the adjusted training strategy until a trained multi-modal large model is obtained. The training strategy is dynamically adjusted in real time, unnecessary computing resource waste is avoided, the training time of the model is shortened, and the training efficiency is improved; the model can be adaptively optimized according to the characteristics of the monitoring data, and the accuracy and generalization ability of the finally obtained multi-modal large model are improved.
Owner:SHANGHAI BIREN TECH CO LTD

PVA film gas permeability intelligent detection method based on machine learning

The invention discloses a PVA film gas permeability intelligent detection method based on machine learning, and relates to the technical field of material testing. The method comprises the following steps: acquiring experimental environment data, first detection data, first diffusion theory characteristic data and second detection data, and constructing and training a neural network model; setting application environment parameters, obtaining third detection data, and calculating second diffusion theory characteristic data according to the application environment parameters and the third detection data; and inputting the application environment parameters, the third detection data and the second diffusion theory characteristic data into a neural network model to obtain a gas permeability prediction value. According to the method, the neural network model is constructed and trained, and the gas permeability is predicted through the neural network model, the application environment parameters, the third detection data and the second diffusion theory characteristic data, so that the dependence on a differential pressure method gas permeability experiment is reduced, the time cost of material testing and experiment is reduced, and the test efficiency is improved. And meanwhile, online monitoring and adjustment of the production process are facilitated, and production benefits are improved.
Owner:SHANDONG SENGONG NEW MATERIAL TECH CO LTD

Blood vessel segmentation method, device and equipment based on large model fine tuning and medium

The invention discloses a blood vessel segmentation method and device based on large model fine tuning, equipment and a medium, and the method comprises the steps: obtaining a blood vessel image, carrying out the preprocessing of the obtained blood vessel image, and obtaining a training set; performing fine tuning on a pre-trained image segmentation model by adopting the training set, so that the image segmentation model learns related features of blood vessel segmentation; wherein the low-rank adaptive fine tuning technology is adopted to perform fine tuning on the image segmentation model: two parallel low-rank matrixes are inserted into a Transform layer in the image encoder, the input is processed by the two low-rank matrixes in sequence, and the processing result and the original output are added to obtain the final output. According to the method, the defects of a large model in a blood vessel segmentation task are overcome through efficient parameter fine tuning and a multi-scale feature fusion module. Accurate blood vessel segmentation can be realized under limited annotation data, the difficulty and cost of medical image segmentation tasks are greatly reduced, and the method can be widely applied to the technical field of medical image processing.
Owner:SOUTH CHINA UNIV OF TECH +1

Chinese electronic medical record named entity identification method based on multiple attention mechanisms and SNN network

The invention provides a Chinese electronic medical record named entity recognition method based on a multi-head attention mechanism and a pulse neural network (SNN), and the method comprises the steps: obtaining a dynamic word vector through a pre-training BERT model, obtaining a text code through a bidirectional long short-term memory network (BiLSTM) model, and screening the features of the code through the SNN network for a named entity in an electronic medical record; the multi-head attention mechanism calculates the dependency relationship between characters, enhances the relevance to the context, and finally outputs a final sequence through a conditional random field (CRF) module to obtain an entity recognition result. According to the method, the time cost is remarkably reduced, the efficiency and precision of identifying the named entities in the medical text are improved, and a more efficient and accurate technical solution is provided for the field of medical information processing.
Owner:CHINA THREE GORGES UNIV

Multi-modal model training fine tuning optimization method based on artificial intelligence

The invention relates to the technical field of artificial intelligence, and discloses a multi-modal model training fine-tuning optimization method based on artificial intelligence, which comprises the following specific steps: preparing and preprocessing data, collecting a large-scale multi-modal data set, constructing an image text data set containing one million high-quality images and text description accurately corresponding to the images, and performing fine-tuning optimization on the image text data set. According to the method, data are subjected to comprehensive and meticulous cleaning operation, noise data and mistakenly labeled data in the data are strictly removed, so that the accuracy and reliability of the data are ensured, and the effective utilization rate of the data can be increased by at least 20% through data cleaning; wherein the image data is screened, blurred, low-resolution and unclear-content images are removed, it is ensured that each image can clearly convey specific visual information, and text description, grammar error checking, spelling error and semantic ambiguity parts are corrected or deleted.
Owner:BEIJING TOWER VISION INTELLIGENT TECHNOLOGY CO LTD

Incremental multi-fidelity machine learning assisted hybrid optimization method and system

The invention discloses a hybrid optimization method and system assisted by incremental multi-fidelity machine learning. The method mainly comprises the steps of initial setting and initial sample acquisition, training of a global low-fidelity proxy model # imgabs0 # and a residual model # imgabs1 #, global optimization, training and optimization of a local proxy model, low-fidelity full-wave simulation, re-prediction of an updated proxy model # imgabs2 #, high-fidelity simulation and the like. According to the method, a multi-fidelity model and adaptive incremental learning are introduced in the process of training and updating the proxy model, the calculation complexity of sampling and training can be effectively reduced, meanwhile, a global multi-target and local single-target hybrid optimization algorithm is adopted in the optimization process, and the algorithm search efficiency can be improved. The method can be used in the field of optimization design of multi-target electromagnetic devices such as medium-scale antennas, arrays, filters and the like with design parameters in 20-50 dimensions.
Owner:SOUTHEAST UNIV +1

Large model cloud computing dynamic updating method based on elastic adaptive incremental learning

The invention discloses a large model cloud computing dynamic updating method based on elastic adaptive incremental learning, which comprises the following steps: S1, in a cloud computing platform, acquiring a current version of a large model and a new data stream to be processed; s2, local parameter updating is conducted on the large model according to the new data, and parameters or model layers needing to be updated are dynamically selected according to the characteristics of the data in the updating process; s3, introducing an adaptive learning strategy, and monitoring the change condition of data distribution in real time; s4, in a large model updating process, splitting a large model updating task to a plurality of computing nodes for parallel execution through a multi-node collaborative scheduling mechanism of the cloud; s5, after the large model is updated, the system verifies the performance of the large model; and S6, in the process of updating and deploying the large model, the system dynamically recycles computing resources which are not used any more. According to the method, idle computing resources can be fully utilized in a large-scale cloud computing environment, so that computing tasks are distributed in a balanced manner, and dynamic adjustment of task loads is ensured.
Owner:HUNAN UNIV OF SCI & ENG

Vegetation prediction model construction method, vegetation prediction method, device and equipment

The invention provides a vegetation prediction model construction method, a vegetation prediction method, a vegetation prediction device and vegetation prediction equipment, and relates to the technical field of data processing. The vegetation prediction model construction method comprises the following steps: taking ecological environment data of a target area as an independent variable, taking vegetation spatial distribution data corresponding to the target area as a dependent variable, and training a first random forest model to obtain a vegetation spatial distribution prediction model; taking the output of the vegetation parameter spatial distribution prediction model and the period-by-period meteorological data as independent variables, taking the period-by-period vegetation feature change data as dependent variables, training a second random forest model, and obtaining a vegetation feature time change prediction model; and splicing the vegetation spatial distribution prediction model and the vegetation feature time change prediction model to obtain a vegetation prediction model. According to the technical scheme, the data utilization efficiency can be improved, the model training time is shortened, and meanwhile the adaptability of the vegetation prediction model and the accuracy of vegetation prediction are improved.
Owner:NORTHWEST ENGINEERING CORPORATION LIMITED

Unmanned aerial vehicle autonomous navigation method based on fusion of imitation learning and reinforcement learning

PendingCN119665969AImprove autonomous navigation performanceOptimizing Navigation StrategiesNavigational calculation instrumentsInternal combustion piston enginesPattern recognitionData set
The invention discloses an unmanned aerial vehicle autonomous navigation method based on imitation learning and reinforcement learning fusion, and belongs to the technical field of unmanned aerial vehicle processing, and the method comprises the following steps: S1, collecting a data set of an unmanned aerial vehicle, and carrying out normalization processing on the data set to obtain a standard data set; s2, constructing an Actor network by utilizing expert operation data of the standard data set; s3, inputting the depth image and the state information of the standard data set into an Actor network, and generating a pre-judgment action; and S4, inputting the pre-judgment action into a discriminator to complete autonomous navigation. Through introduction of the generative adversarial imitation learning module, the unmanned aerial vehicle can continuously optimize a navigation strategy, and high robustness and adaptability can be maintained even in a complex environment.
Owner:CHENGDU UNIV OF INFORMATION TECH

UI effect picture recognition method and system based on multi-modal large model and medium

The invention discloses a UI effect picture recognition method and system based on a multi-modal large model, and a medium. The method comprises the following steps: constructing a multi-modal pre-training model based on image coding, multi-modal projection and text coding; performing fine tuning training according to the historical image data and the multi-modal pre-training model to obtain a multi-modal large model; constructing a vector database based on the built-in component data structure; obtaining a to-be-recognized UI effect picture, and outputting first recognition data based on the multi-modal large model and the to-be-recognized UI effect picture; and searching a vector database for the first identification data by using a retrieval algorithm, and outputting generation information corresponding to the UI effect picture to be identified. The method has the beneficial effect that the generation consistency and efficiency of the UI effect picture are ensured.
Owner:ZHEJIANG LANZHUO IND INTERNET INFORMATION TECH CO LTD

Equipment information management method and system based on multi-modal large model

The invention provides an equipment information management method and system based on a multi-modal large model in the technical field of equipment information management. The method comprises the following steps: S1, acquiring historical multi-modal data to construct a data set, and dividing the data set into a training set, a verification set and a test set; s2, creating a multi-modal large model based on a Vi T module, a Bert module, a numerical feature construction module, a feature fusion module and an output module, and setting hyper-parameters; s3, training and evaluating the multi-modal large model through the training set, the verification set and the test set; step S4, compressing the multi-modal large model which passes the evaluation; and S5, collecting real-time multi-modal data of installed equipment in the management area by each area server, and inputting the real-time multi-modal data into the multi-modal large model to obtain an equipment information analysis report. The method has the advantages that the efficiency, the quality, the traceability and the resource utilization rate of equipment information management are greatly improved, and then the reliability of equipment operation and maintenance is greatly improved.
Owner:FUJIAN NEWLAND SOFTWARE ENGINEERING CO LTD

Excavator control method and system oriented to non-structural working conditions

The invention provides an excavator control method and system oriented to non-structural working conditions. According to the excavator control method and system oriented to the non-structural working condition, on one hand, according to the dynamic remodeling characteristic of earthwork in the excavation process, the excavation action track is planned through the earthwork state obtaining model and the excavation action planning model, the excavator control method and system can adapt to the non-structural working condition, and it is ensured that the operation effect is stable; on the second aspect, through real-time sensing and data feedback, the excavation action track can be adjusted in real time in the operation process, optimization is conducted according to the earthwork state, and the operation flexibility and effect can be improved; thirdly, by autonomously planning an excavation action track, the dependence on a manual operator can be reduced, the requirement of manual intervention is reduced, and the autonomous operation capability is improved; and fourthly, the mining action track is optimized through the mining action planning model, so that the energy consumption in the mining process can be reduced, the operation efficiency can be improved, and the operation cost can be reduced.
Owner:ZHEJIANG UNIV

Heterogeneous computing power resource allocation optimization method for deep reinforcement learning model training

The invention discloses a heterogeneous computing power resource configuration optimization method for deep reinforcement learning model training, and the method comprises the steps: constructing a heterogeneous graph for describing the features of a module and a data flow relation for a core module of a model-based Muzero series algorithm, mapping the features of nodes and edges to a same hidden space through a node-edge encoder based on multi-head attention, and carrying out the optimization of the heterogeneous computing power resource configuration. And predicting algorithm training time under different configurations by using the summarized global features. And performing configuration optimization according to the prediction training time output by the model by using a simulated annealing algorithm. And allocating CPU resources, GPU resources and memory resources according to the optimized configuration, and carrying out a training task. And calculating a resource equalization factor according to a training result, evaluating a resource configuration scheme, and continuously monitoring and optimizing. According to the method, the optimal balance between the performance and the resource consumption in the model training process is realized, the efficiency and the effect of model training are remarkably improved, and the technical difficulty of resource configuration optimization in a complex scene is reduced.
Owner:HANGZHOU DIANZI UNIV

Equipment part fault diagnosis method, device and equipment based on sensing data mixed noise suppression

The invention discloses an equipment part fault diagnosis method, device and equipment based on sensing data mixed noise suppression, and relates to the field of fault diagnosis. The diagnosis method comprises the following steps: acquiring vibration signals of an equipment part under different fault types; performing data preprocessing on the vibration signal to obtain a sample, taking a fault type corresponding to the vibration signal as a real label, and constructing a training set and a verification set; using the training set and the verification set, and using a migratable Adaboost algorithm and an adaptive cost sensitive learning method to train a plurality of deep learning models to obtain a plurality of trained deep learning models; and performing fault diagnosis on the to-be-tested part of the equipment by using the plurality of trained deep learning models. According to the invention, the accuracy of equipment part fault diagnosis in the mixed noise environment is improved.
Owner:ZHEJIANG UNIV

Large model training data generation method in medical field and related equipment

The invention provides a large model training data generation method in the medical field, which takes real case data as reference, calls a large language model through an automatic program, enables the large language model to generate problem data, reference data and answer data in batches, and guides the large language model to generate and optimize model fine adjustment data through a set prompt prompt word. Therefore, the specialized model fine adjustment data is generated for the industry model in the medical field, and the training time of the subsequent industry large model is saved. In addition, due to the fact that the case data is high in obtaining difficulty and much in privacy information, compared with direct obtaining of real case information, the technical scheme disclosed by the invention has the advantages of being low in cost and high in privacy.
Owner:BEIJING UNIV OF POSTS & TELECOMM +1

Large model fine tuning method, system and device based on LoRA-MoE and medium

The invention relates to the technical field of artificial intelligence, in particular to a large model fine tuning method, system and device based on LoRA-MoE and a medium. According to the method, the characteristic that the LoRA technology can use smaller parameters to carry out fine adjustment on a large model is combined with the characteristic that the MoE architecture can enable the model to be higher in generalization ability and better in effect, and the LoRA-MoE technology is adopted to carry out fine adjustment on the large model; according to the method, the problems that a large number of video memories need to be consumed during fine adjustment of the large model and the effect is poor when fine adjustment is conducted through the LoRA technology can be solved, it is ensured that consumption can be reduced in the fine adjustment process of the large model, and a certain fine adjustment effect is ensured.
Owner:CLP JIUTIAN INTELLIGENT TECH CO LTD