21results about How to "Achieve generalization" patented technology

The invention belongs to the technical field of robots, and discloses a man-machine-data three-element integrated robot teleoperation and data acquisition system and method, and the system comprises a man-machine interaction module, a physical robot, a prediction simulation module, a digital robot, a virtual environment and a data management module. Wherein the prediction simulation module is used for aligning information of a natural person to execution action information of the physical robot, predicting an action instruction sequence and correcting the state of the digital robot in real time according to state information fed back by the physical robot; the digital robot is used for executing a corresponding action in the virtual environment according to the combined action instruction sequence, if a safety problem exists in the execution process, execution is stopped, and otherwise, the combined action instruction sequence is sent to the physical robot; the data management module is used for collecting data in the system operation process. The technical problems of operation delay and lack of humanoid robot training data in a traditional teleoperation system are solved.

The invention discloses a geographic network analysis method based on feature and structure distribution offset. The method comprises the following steps: S1, obtaining a traffic flow data set; s2, acquiring a causal attention sampling weight; s3, acquiring a target node; s4, performing sample reweighting; and S5, outputting a predicted traffic flow data set. According to the method disclosed by the invention, the attention mechanism and the causal-guided sampling technology are fused, the node sampling process is optimized, and the dependence of the model on background characterization is reduced. According to the method, an attention mechanism and a causal theory are combined, the sampling weights of target node neighbors of the same type and the sampling weights of target node neighbors of the different types are obtained respectively, and the purpose is that a model recognizes nodes having a strong causal relationship with labels or recognizes nodes more similar to the target nodes. In this way, the invariant characterization is significantly improved, and the dependence on the background characterization in accidental or specific modes is reduced.

The invention discloses a blast hole parameter adaptive tunnel smooth surface effect prediction method, which comprises the steps of constructing a smooth surface effect prediction model based on a graph neural network; predicting rock mass displacement data by using the smooth surface effect prediction model; and calculating a tunnel smooth surface effect in combination with a prediction result of the rock mass displacement data. According to the method, the adaptive blast hole parameter smooth surface effect rapid prediction model based on the depth map neural network is constructed, smooth surface blasting data are comprehensively extracted by using the map neural network, the accuracy of a deep learning-based calculation method is improved, and the method has important theoretical significance and application value for tunnel blasting construction.

The invention discloses a multi-agent hyperspectral band selection method based on a fusion state and a superior experience pool, and belongs to the field of remote sensing image processing. After a hyperspectral image is obtained, a sample set of the hyperspectral image is generated, and the sample set is divided into a training sample set and a test sample set; a multi-agent waveband selection model is constructed according to the training sample set, the state representation method comprises meta description statistics, an auto-encoder and a graph convolutional network, and the reward allocation strategy comprises an adaptive allocation strategy based on waveband importance; inputting the training sample set into a multi-agent waveband selection model for model training to obtain a trained multi-agent feature selection model, and optimizing a memory sample of an experience pool for model training by adopting a specific sample oriented experience pool optimization method based on a Gaussian mixture model; and inputting the test sample set into the trained multi-agent feature selection model for band selection, outputting a hyperspectral image band set, and classifying the hyperspectral image band set to obtain a classification result.

The invention relates to the technical field of artificial intelligence, and provides a medical image domain generalization method based on a diffusion probability model, and the method comprises the following steps: S1, obtaining image data needed by training; s2, extracting image structure information; s3, building a diffusion generation model network suitable for the image data size and characteristics; s4, using the extracted structure information as prompt information, and prompting and controlling a diffusion generation model learning process; and S5, using a diffusion generation model to realize data distribution transfer of structure information maintenance. Through the technical scheme of the invention, the diffusion generation model conforming to the medical image data is designed, and the image data structure information is extracted as a prompt, so that cross-image modal data conversion maintained by the structure information is realized, meanwhile, the diversity of training data is increased, the purpose of domain generalization in a reasoning stage is achieved, and the reasoning efficiency is improved. Therefore, the downstream segmentation task precision for various image modalities is improved, and rapid and accurate diagnosis is assisted.

The application discloses a kind of upper limb rehabilitation robot training method and system based on doctor-patient interactive behavior learning and LSTM generalization, method includes: obtaining the dynamic sensation and force sensation data of physician, robot and patient in hand-to-hand movement rehabilitation skill demonstration process;Based on the dynamic sensation and force sensation data of physician, robot and patient in hand-to-hand movement rehabilitation skill demonstration process, make robot perceive the dynamic sensation and force sensation behavior of doctor-patient interaction, form doctor-patient interaction behavior observation sequence;Based on dynamic motion primitive model, learn the doctor-patient interaction behavior in hand-to-hand movement rehabilitation skill demonstration process, obtain doctor-patient compliant interaction primitive sequence;According to the doctor-patient compliant interaction primitive sequence learned in hand-to-hand movement rehabilitation skill demonstration process, construct movement rehabilitation skill training data set, train LSTM network using the movement rehabilitation skill training data set, realize the generalization of the movement rehabilitation skill of upper limb rehabilitation robot under the condition of patient condition change.

The application relates to the field of battery life prediction, in particular to a multi-feature fuel cell life prediction method based on a long short-term memory network; the method comprises the following steps: collecting voltage attenuation data and collecting running state data to construct an original input data set; analyzing the running state data, calculating a correlation coefficient according to the voltage attenuation data and each running state data, analyzing the correlation coefficient, and obtaining an input feature set; processing the input feature set and the voltage attenuation data to construct a neural network training data structure; dividing the training data structure into a training set and a test set; constructing a network architecture solution space to be searched, analyzing the network architecture solution space, constructing a fitness function, and determining an optimal network architecture parameter combination based on the fitness function; and inputting the training set into the optimal network architecture parameter combination for training to generate a target detection prediction result. The application can improve the prediction accuracy of the voltage attenuation trend.

This invention provides an enzyme turnover rate prediction method based on a dual-route hybrid expert mechanism, belonging to the field of bioinformatics technology. It solves the problems of low data utilization, insufficient information mining, and poor robustness in existing prediction methods due to missing values ​​and temperatures. The technical solution includes the following steps: S1: Constructing a unified standard enzyme turnover rate dataset; S2: Extracting multimodal embedding features; S3: Constructing intra- / inter-modal encoders; S4: Combining modalities into an expert hybrid module; S5: Designing an attention fusion mechanism. This invention can achieve high-precision prediction under complex in vitro environmental conditions.

The utility model discloses a kind of controller upgrading system supporting multiple vehicle-mounted communication protocol, including microcontroller, man-machine interactive device, transceiver and power device;The microcontroller is electrically connected with man-machine interactive device and transceiver respectively, and the power device is electrically connected with microcontroller;Integrated controller and communication interface unit are equipped on the microcontroller;The integrated controller is electrically connected with transceiver, and the communication interface unit includes data storage interface, peripheral debugging interface and external upgrading interface;The integrated controller includes multi-protocol communication module, storage module, power management module;The power management module is electrically connected with power device;The storage module is electrically connected with data storage interface;Multi-protocol communication module is electrically connected with external upgrading interface, and the peripheral debugging interface is connected with external equipment.

The present application relates to the technical field of industrial automation detection, and particularly discloses a kind of vision detection system of foreign matter in tank, the system includes rotary positioning module, multi-source lighting module, multi-modal imaging module, image processing decision module and visual interface module;The present scheme integrates annular LED bright field light source, lateral dark field light source and polarized light source, dynamically switches illumination mode according to tank body material, cooperates with high-speed camera array to synchronously collect images from top-down and lateral oblique angle, realizes all-around coverage to tank wall, tank bottom, liquid level and the like;Pre-trained DINO model is used to extract multi-level visual token, all sequences are uniformly modeled using lightweight Mamba autoregressive model, effectively capturing the global dependence and local details of the spatial structure inside the tank, while introducing a dynamic anomaly threshold mechanism, effectively avoiding the problem of missing small foreign matter caused by image down-sampling.

The application discloses a product recommendation network hyperparameter optimization method and device and electronic equipment. The method comprises the following steps: obtaining a plurality of hyperparameter spaces of a plurality of product recommendation networks from historical tuning logs based on an LLM; clustering the hyperparameter spaces according to the outputs of the corresponding proxy models of the product recommendation networks; taking the plurality of clustered hyperparameter spaces and the corresponding cluster-level evaluation scores as sample data; enhancing the LLM based on a low-rank adaptive Lora module and the sample data to obtain an enhanced LLM; weighting the hyperparameter prediction value and the space exploration value of each candidate hyperparameter cluster in a plurality of candidate hyperparameter clusters based on the proxy model of the product recommendation network to be optimized to obtain the intra-cluster prediction score of the candidate hyperparameter cluster; and determining the sampling proportion of each candidate hyperparameter cluster based on the intra-cluster prediction score of the candidate hyperparameter cluster through the enhanced LLM to obtain the optimized hyperparameters of the product recommendation network.

A multi-task prompt decision transformer construction method and device, equipment and storage medium, relate to the field of robot control simulation environment, including constructing MPDT, MPDT includes multiple decision maker layers and triple prompt module constructed based on reward, state and action;Control target decision maker layer and triple prompt module are in active state, MPDT is trained based on offline training sample, and multi-task prompt fine-tuning is carried out based on triple prompt, specific task prompt and cross-task prompt are generated;After training is completed, the combination of cross-task prompt and test sample is used as the input of MPDT for testing, the hidden state test mean and hidden state test variance corresponding to the test sample are calculated, and the mean and variance of the offline training sample are aligned and calculated;Based on the alignment result, the cross-task prompt is updated, the target multi-task prompt decision transformer is generated, and the generalization ability of the transformer in the zero sample and multi-task scene is improved.

The invention relates to a rare disease identification method and system based on multi-scale vision-language prompt multi-instance learning, and the method faces a full-view digital pathological image (WSI), and introduces the prior knowledge of the pathological field under the weak supervision condition of only using a slice-level label, so as to identify the rare disease. Constructing a multi-scale vision-language collaborative prompt mechanism: generating descriptive text prompts corresponding to image blocks of different scales by utilizing a large language model, designing a prototype-guided image block decoder to aggregate massive image block features, and meanwhile, realizing cross-modal alignment in combination with a context-guided text decoder; the method simulates the diagnosis process of a pathologist, achieves high-precision classification under small samples, remarkably improves the recognition accuracy of rare diseases, has good cross-center generalization ability, supports interpretable evidence output, does not need large-scale data labeling or de novo pre-training, and facilitates clinical rapid deployment.

The present invention discloses a multi-factor ocean wave forecasting method based on signal decomposition, an electronic device, and a medium, comprising: performing adaptive noise complete empirical mode decomposition on effective wave height, effective wave period, and wave direction time series data respectively, dividing each intrinsic mode function obtained by decomposition into a high-frequency mode function and a low-frequency mode function; dividing the low-frequency mode function corresponding to the effective wave height, effective wave period, and wave direction time series data into K 11 , K 21 , K 31 The high-frequency modal functions corresponding to the effective wave height, effective wave period, and wave direction time series data are superimposed and then subjected to variational modal decomposition. The decomposed modal functions are divided into K 12 , K 22 , K 32 Group mode; K 11 , K 12 The group modes are input into the BiLSTM model in sequence, and the effective wave height prediction results are output; 21 , K 22 The group modes are input into the LSTM model in sequence, and the prediction results of the effective wave period are output; 31 , K 32 The group modes are sequentially input into the LSTM‑GRU model, and the wave direction prediction results are output.

The application discloses a multi-fingered hand operation reinforcement learning method based on a human motion prediction model and belongs to the field of humanoid robot dexterous hand body operation. A human motion prediction model is trained by using data with human hand and object three-dimensional pose annotation, which is used to generate three-dimensional trajectories of human hand and object interaction in a generalizable manner. A general reward function is constructed by using the trajectory, which is used to train a dexterous hand reinforcement learning strategy in simulation. Then, the migration ability of the strategy from simulation to reality is improved through simulation parameter domain randomization and curriculum learning, and the trained reinforcement learning strategy is deployed on a real-world robot. The scheme introduces the understanding of the future pose of the object to be operated, predicts the interaction process of the human hand and the object as a whole, and constructs a unified, simple, efficient reward function based on this, which is suitable for different operation tasks and different types of dexterous hands, and has the advantages of strong generalization, high success rate and strong reward function universality.

The invention discloses a data and knowledge bidirectional driving-based electric energy meter abnormal data repairing method. The method comprises the following steps of obtaining wind power time sequence data of a wind power plant; determining a vector set of data points in the normalized wind power time sequence data in a polar coordinate system; calculating a self-defined inner product of the first vector and the second vector in the vector set; according to the self-defined inner product, determining a Gramb angle field; empirical features are determined; respectively obtaining a data driving feature and a knowledge driving feature; constructing a joint training module, and processing the data driving features and the knowledge driving features by using the joint training module to obtain sample tags corresponding to the wind power time sequence data; and performing data repair on the wind power time sequence data of which the sample labels are abnormal data by using an abnormal data repair module to obtain wind power time sequence repair data. The method can improve the repairing precision and efficiency of the electric energy meter data of the wind power plant.

The invention discloses construction of a petroleum yield prediction model for domain knowledge migration in a multi-reservoir scene, and belongs to the technical field of petroleum engineering and intelligent prediction. According to the method, a domain knowledge migration mechanism is introduced, so that the model can share depth feature information among multiple oil reservoirs, the prediction precision and model robustness of small sample oil reservoirs are effectively improved, and the problems of poor model generalization, high training cost, unstable prediction and the like in a traditional method are solved. The method is clear in structure and moderate in calculation amount, has good interpretability and visualization ability, and can be widely applied to the fields of oil reservoir yield prediction, intelligent oil field management, production optimization decision making and the like.

The embodiment of the invention provides an information prediction method and device based on a deep learning model, and electronic equipment, and belongs to the technical field of financial science and technology. The method comprises the following steps: acquiring a plurality of financial materials, and performing information analysis on all the financial materials to obtain a feature set; selecting a separation value of the characteristic value through a decision tree algorithm, and dividing to obtain a first data set and a second data set; carrying out Gini coefficient calculation on the first data set and the second data set to obtain a target Gini coefficient; performing node screening on all financial materials according to the target Gini coefficient to construct a decision tree; performing node numbering on all leaf nodes in the decision tree to obtain a target material primary key; updating the financial material according to the target material primary key; and inputting the updated financial material to be predicted into the deep learning model, so that the deep learning model carries out information prediction based on the target material primary key, and a prediction result is displayed to a user. The information prediction accuracy can be improved, and the user experience is improved.

The invention belongs to the field of quality detection, and particularly discloses a deep learning film evaluation model training set feedback optimization method and device, and the method comprises the steps: carrying out the zooming, cutting and enhancement of a flaw detection image of a casting, and obtaining an enhanced sub-image; determining a mark file path of the flaw detection image, combining the mark file path with an image cutting mode, and utilizing a coordinate transformation algorithm to obtain a sub-image mark file of the cut sub-image; screening the enhanced sub-images according to the tag file, and inputting the screened enhanced sub-images as a training set into a neural network model for training to obtain a trained detection model; acquiring a model mark file corresponding to the verification set by using the detection model, and detecting and modifying the model mark file according to the created checking mark software to obtain a modified sub-image; and inputting the modified sub-images as an optimized training set into the neural network model for training. According to the invention, the accuracy of model detection and identification can be improved.

The invention discloses an edge federation continuous learning method based on a brain-like pulse neural network, and particularly relates to the field of machine learning. Comprising the steps that a central server issues a to-be-trained global model to each edge device; each edge device uses the sample set to train a to-be-trained global model; wherein when a new task is received, the sample set comprises a first sample set and a second sample set, the first sample set comprises all samples in a data set corresponding to the new task, and an acquisition mode of the second sample set is as follows: deleting each category of samples in the current sample set, selecting samples in the first sample set by adopting a sample selection strategy based on a sheep flock effect, and adding the samples into the current sample set to obtain a second sample set; each edge device uploads the parameters of the trained global model to a central server; and the central server integrates the model parameters of each edge device to generate a global model. The accuracy of edge equipment in continuous tasks can be improved.

A computerized method has the steps of generating an input computational graph (CG) for representing a neural architecture, and performing a plurality of optimization steps in at least one iteration to obtain a modified neural architecture represented by the modified CG, thereby obtaining a neural network for use in one or more computing devices. The optimization step includes identifying one or more sub-graphs in the input CG, obtaining the modified CG by replacing the identified one or more sub-graphs with one or more replacement sub-graphs, respectively, evaluating one or more indicators of the modified neural network architecture represented by the modified CG, and, in accordance with the evaluation, modifying the one or more indicators of the modified neural network architecture. And selecting the modified CG or the input CG. When the optimization step is performed in multiple iterations, the selected CG obtained in one iteration is used as the input CG in the next iteration.