101results about How to "Easy to learn" patented technology

The application discloses a lining cloth dyeing control method and system based on artificial intelligence, and is used for the control field, and the method comprises the following steps: real-time monitoring of multi-source data in the lining cloth dye vat, capturing the video stream inside the lining cloth dye vat; using a Gaussian mixture variational autoencoder model to extract features from the multi-source data, obtaining multi-source feature data; obtaining the changing moment of the fabric state in the video stream, and extracting the fabric state change feature data according to the observed fabric color change and the heterogeneity of the dye distribution in the video stream; fusion of multi-source feature data and fabric state change feature data; introducing a model predictive control layer, predicting the result to adjust the dyeing parameters in real time; establishing an intelligent feedback mechanism. The Gaussian mixture variational autoencoder model is trained and optimized through the small-batch stochastic gradient descent and back propagation algorithm, important features are learned and captured from the data.

This invention provides a power load forecasting method based on time series core fusion, belonging to the field of artificial intelligence technology. The method involves normalizing adjustable load data to obtain adjustable load data feature vectors; constructing an adjustable power load forecasting model using a multi-layer perception layer, a random pooling layer, and a fusion layer; inputting the adjustable load data feature vectors into the adjustable power load forecasting model; training the adjustable power load forecasting model based on an accuracy index; and finally, obtaining the adjustable power load forecasting result by performing inverse normalization calculation on the feature sequences containing the forecast group, thus completing the forecasting of adjustable power load. This invention solves the problem of low accuracy in adjustable power load forecasting results.

The invention discloses an accounting visual simulation bookkeeping teaching system, which comprises a teacher terminal, a transmission end and a student terminal, and is characterized in that the teacher terminal comprises a first display module and a second display module, the transmission end comprises a first transmission module and a second transmission module, and the student terminal comprises a third display module and a fourth display module. An information display module and a first sending module are arranged in the first display module, a first receiving module is arranged in the third display module, and the first sending module transmits display information in the information display module to the first receiving module through the first transmission module. The third display module is used for looking up teaching documents of a teacher, the fourth display module is used for watching demonstration steps of the teacher, and the teacher can independently perform interpretation through the third display module when encountering ununderstood places during operation, so that learning of students is facilitated, and the students can always keep up with the thinking of the teacher.

This invention discloses a specular removal method based on grouped enhanced convolutional attention feature fusion, belonging to the field of image processing technology. The method constructs a specular removal model based on a CycleGAN network, which consists of a generator, a discriminator, and a loss function optimization module. The generator includes detail enhancement depth downsampling, upsampling, and grouped enhanced convolutional attention fusion modules, effectively capturing image details, reducing checkerboard artifacts, and enhancing feature fusion and capture capabilities. The discriminator uses a PatchGAN structure to improve local detail capture capabilities. The optimized loss function integrates multiple losses to improve model performance. Experimental results show that compared with various traditional and deep learning methods, the method of this invention outperforms in PSNR and SSIM metrics, exhibits strong adaptability, and can provide high-quality image data for subsequent detection of elevator door components.

The invention discloses a training data balance processing method and device, equipment, a medium and a product. The invention relates to the technical field of data processing. The method comprises the following steps: when a user in a user set is associated with an object in an object set, generating associated data according to the associated user and object, and adding the associated data into an associated data set; acquiring other users of the same category as the target user corresponding to the to-be-supplemented data of the associated data set; obtaining a target object associated with the target user in the associated data set; according to each target object, determining candidate objects of the target user in other objects associated with the other users in the associated data set; and generating associated data according to the target user and each candidate object, and adding the associated data into the associated data set. The embodiment of the invention can balance the training data of the model.

The present application belongs to the technical field of federated learning, and discloses a foundation pit prediction model training method, a foundation pit monitoring method and a system. The training method comprises: local training of the edge device, so that the model predicts the foundation pit state of the future period based on the foundation pit information of the current period; the local training loss is a comprehensive loss considering the data fitting loss and the physical constraint loss; the edge device also maps the foundation pit geological information into a geological embedding vector, and sends the local model update parameter and the geological embedding vector to the cloud device; the cloud server clusters all the edge devices based on the similarity of the geological embedding vectors, aggregates the same local model update parameters to obtain the corresponding global model update parameters; during the aggregation calculation, the data quality evaluation score of the edge device is used as the weight coefficient of the corresponding local model update parameter. Based on the above method, the accuracy of the model prediction can be improved.

The utility model discloses a demonstration device for wafer loading port. The demonstration device includes: the substrate, the first surface of substrate is provided with at least two wafer card slot analog block, the second surface of substrate is provided with wafer loading port fixed structure and sensing trigger module, the analog wafer is set up on wafer card slot analog block, and the first surface of analog wafer, substrate and wafer card slot analog block form demonstration space, and the first mark is set up on the analog wafer, the wafer transfer mechanism is used to take and shift analog wafer, and the wafer transfer mechanism includes manipulator, and the manipulator has demonstration executor, and demonstration executor can stretch into, stretch out demonstration space and move in demonstration space, and, the second mark is set up on demonstration executor, and the second mark and the first mark can be aligned under the specified gesture. Through alignment mark, improve calibration accuracy, and it is convenient for operator to identify positioning quickly, and improve semiconductor equipment debugging and calibration efficiency.

The invention discloses a 3D speaking face generation method of emotion controllable VQ-VAE based on hierarchical decoupling. The method specifically comprises the steps of 1, preprocessing a data set; 2, constructing a first-stage model, setting a loss function and training the model; 3, constructing a second-stage model, setting a loss function and training the model; and step 4, constructing a generative model, and generating a 3D speaking face video. According to the method, through the condition decoupling based on VQ-VAE, facial expressions and actions generated by the 3D speaking face generation model based on condition guidance are more accurate and real, and accurate and stable 3D speaking face generation is realized.

The application belongs to the technical field of complex system organization modeling and simulation analysis, and particularly relates to a kind of airplane system fault simulation modeling method based on OPM, comprising the following steps: step one: selecting an airplane system to be simulated, determining the system function and system composition of the system;Step two: determining the OPM modeling object element according to the finished product, structural part and cable contained in the selected airplane system;Step three: defining and creating the OPD object process diagram of the system according to the system function of the selected airplane system and the finished product object;Step four: specifying the state of each object element in the airplane system to represent the actual working state of each finished product, structural part and cable in the system;Step five: taking the specified state of each object element as the state value of each object element in the OPD;Step six: matching the state change process for the object element with state;Step seven: connecting the object state with the matched process using the influence link in the OPD;Step ten: simulating and deducing the fault model.

The invention relates to a medicinal and edible composition for synergistically improving AD cognitive and affective disorders through three pathways, and belongs to the technical field of medicines. The composition comprises the following raw materials: 6-8 parts of ginseng, 4-6 parts of hovenia dulcis thunb, 4-6 parts of folium cortex eucommiae, 3-7 parts of lucid ganoderma, 1-3 parts of longan aril and 1-3 parts of liquorice. Ginseng and lucid ganoderma are used as monarch drugs to mainly tonify the kidney and nourish the heart; hovenia dulcis thunb or ampelopsis grossedentata leaves and folium cortex eucommiae are used as ministerial drugs and are mainly used for removing internal heat and tranquilizing mind and strongly inhibiting neuroinflammation and oxidative stress; the longan aril and the liquorice are used as assistant and conductant drugs to fix and protect the spleen and stomach and regulate the drug property. The preparation method comprises the following steps: compounding powder prepared by adopting a bacterium-enzyme combination technology and a phospholipid / beta-cyclodextrin embedding technology according to a ratio, and adding ergothioneine as required. According to the application disclosed by the invention, three pathways of beta amyloid protein deposition, Tau protein excessive phosphorylation and neuroinflammation are synergistically regulated and controlled, so that learning memory and cognitive dysfunction and related emotion and sleep disorder symptoms caused by AD and vascular dementia can be effectively intervened.

The utility model discloses a tree supporting device for garden maintenance relates to tree technical field, include: bottom assembly spare, bottom assembly spare includes the underframe, the outer wall of underframe is annular and is separated and is equipped with a plurality of insert installation hole and first screw hole, the insert installation hole is inserted and is equipped with height adjusting spare, height adjusting spare includes support rod, the outer wall of support rod is vertically and is separated and is arranged with a plurality of second screw hole, the outside of support rod is equipped with a plurality of spacing arrangement's limiting adjusting spare, limiting adjusting spare includes assembly clamping seat, the one end of assembly clamping seat is equipped with with support rod matched sleeve hole, the inner wall of sleeve hole is equipped with third screw hole, assembly clamping seat, underframe place all through fastener and support rod assembly combination. Solveed the tree supporting device volume bigger, the whole dismounting difficulty bigger, the problem of inconvenient operator carrying to the scene and installing.

The application is a medical image segmentation method based on multi-modal self-supervision. First, the multi-modal medical image of the lesion tissue is obtained, including A-mode image and B-mode image, and the image is preprocessed. Then, a cycle-consistent modal contrast domain translation network is constructed, including two generators and two discriminators. The generator is used to convert the image of one mode into the image of another mode, including an encoder, an intermediate shared module and a decoder. The discriminator is used to judge the source of the input. Then, the cycle-consistent modal contrast domain translation network is pre-trained, the training loss is calculated, and the loss function includes multi-modal semantic consistency loss, adversarial loss, cross-domain translation loss and cycle consistency loss. Finally, the A-mode segmentation network and the B-mode segmentation network are constructed, the pre-trained weights are migrated to the two segmentation networks, and the trained two segmentation networks are respectively used for medical image segmentation of the corresponding mode. The contrast cross-domain translation is used as a multi-modal self-supervised pre-training task to learn more comprehensive modal features, promote the network to better learn modal characteristics and common knowledge, and improve the segmentation ability.

The method belongs to the technical field of panoramic monitoring of ultra-high voltage converter station, and aims to solve the problem that panoramic monitoring image data is directly uploaded to the cloud, occupying a large amount of cloud resources. By adopting multi-scale convolution blocks in the deep multi-scale residual network model to construct low-order and high-order features of images of various scales, the incomplete phenomenon of image detail extraction is avoided, and the residual learning mechanism is adopted to retain low-order rough features, thereby improving the reconstruction ability of the image. Topology optimization constructs the topology structure of the heterogeneous network, and the framework combining deep reinforcement learning and Monte Carlo tree search is used to construct the network according to the pre-defined topology rules. The search result of the Monte Carlo tree strengthens the learning of the deep convolutional neural network, so as to obtain more accurate prediction in the next iteration. After the data is processed in the edge side, it is transmitted to the cloud storage, saving the cloud storage space and transmission bandwidth.

The invention relates to the technical field of remote sensing image fine-grained target detection, in particular to a two-way guided remote sensing image fine-grained target detection method. Comprising the steps of 1, acquiring image data, and dividing the image data into a training set and a test set; 2, constructing a target detection network, and obtaining image multi-scale features from the preprocessed image through a feature extraction network; then, a coarse-grained detector screens out a target candidate area and judges whether the target candidate area is a foreground or a background; then, a fine-grained detector carries out finer classification and positioning on the candidate areas; and step 3, carrying out performance evaluation on the test set so as to test the detection capability of the model on the fine-grained target in an actual scene. According to the method, for the problems of class sample imbalance and easy confusion of fine-grained classes in fine-grained target detection, the remote-sensing image fine-grained target detection capability is effectively improved by constructing a layered detection network architecture and combining an instantaneous confidence coefficient signal and class accumulation learning quality.

The application discloses a kind of weakly supervised image semantic understanding methods based on multi-task learning, comprising the following steps: obtaining task missing image, constructing multi-level task sharing encoder, extracting high-level semantic information layer by layer, input corresponding decoder branch;Construct public space-task space feature mapping module, through the unaligned task fusion module and task interaction mapping module, update each subtask feature by mapping;Task adaptive feature update module is constructed, and multi-level iterative update unaligned task feature;Task adaptive weakly supervised image semantic understanding framework is constructed, model loss function is established, image data with task missing is input into model, and obtains multi-task prediction result such as semantic segmentation, depth estimation, surface normal estimation.The application is according to the data information of task label unaligned, through the mapping interaction of public space and task space, fully fuses unaligned task feature, iteratively generates high-quality multi-task prediction result, can effectively handle weakly supervised problem with task missing, and simultaneously improves each task prediction accuracy.

This invention discloses an adaptive graph clustering method based on feature adversarial and graph Transformer, belonging to the field of image processing technology. The original graph is optimized by a feature adversarial autoencoder module to match prior distributions of representation features, obtaining attribute-level features. The feature adversarial autoencoder module includes an autoencoder and a feature adversarial module. The original graph is then processed by a graph Transformer autoencoder module to perform the convergence and fusion of local features and global structure, and information propagation, obtaining structural-level features. Adaptive fusion of attribute-level and structural-level dual-source features from the feature adversarial autoencoder module and the graph Transformer autoencoder module completes graph clustering. The training of the feature adversarial autoencoder module and the graph Transformer autoencoder module employs a self-supervised learning approach. A joint optimization loss function guides the joint optimization of graph representation learning and cluster assignment. The joint optimization loss function includes a feature adversarial loss function, an optimization loss function, and a self-supervised learning loss function. The feature adversarial loss function includes the feature reconstruction loss function of the autoencoder and the minimum cross-entropy loss optimization function of the feature adversarial module.

This specification provides a program development method, a program development system, a computing device, and a medium. The program development method includes: obtaining the program architecture of a target program, the program architecture including functional modules and a control module, wherein the functional code in the functional module has a calling dependency with the control module; responding to a decoupling instruction sent by the front end for the target function, determining the target functional code, and removing the calling dependency of the target functional code; encapsulating the target functional code after the dependency is removed into an independently deployed target component, and configuring a proxy access layer for the target component; registering the proxy access layer with the control module so that the control module routes to the proxy access layer, and the proxy access layer schedules the target component. This method can decouple the functions in the original program architecture while ensuring the stable operation of the original architecture, thereby improving the optimization efficiency of the original architecture.

The application discloses a quad-rotor formation obstacle avoidance control method based on an improved DDPG algorithm, and belongs to the technical field of unmanned aerial vehicle formation control. The method adopts an improved DDPG reinforcement learning algorithm to plan an obstacle avoidance path of the quad-rotor. When the improved DDPG reinforcement learning algorithm is executed, the priority weight of each quadruple experience in the experience replay pool is initialized. After the quadruple experience in the experience replay pool is sampled and trained, the priority weight of each quadruple experience is recalculated based on a TD error, and a Sum_Tree structure is updated. The method effectively alleviates the training instability caused by hyperparameter sensitivity, the misleading of policy updating caused by overestimation of Q values, and the problem that key experiences are not sufficiently learned, accelerates the convergence speed of the quad-rotor formation obstacle avoidance training, and improves the obstacle avoidance effect.

This invention discloses a pedestrian detection method and system based on head center point-assisted feature comparison. The method includes: constructing a new CSP network architecture by adding a head branch, a feature comparison branch, a detection confidence enhancer, and a head-aware NMS module to the original CSP network architecture; constructing a training sample set, where the head center point is used as the positive sample for the head branch, and non-head center points within the head bounding box are used as the negative sample for the head branch; using the training sample set as input to the CSP network for training to obtain a pedestrian detection network model; supervising network learning during the training phase using head branch loss and feature comparison loss; and enhancing the detection results during the training and testing phases using the detection confidence enhancer and the head-aware NMS method. This invention improves the detection accuracy of CSP and reduces the probability of false positives and false negatives by introducing head center point, feature comparison, detection confidence enhancer, and head-aware NMS methods.

This invention belongs to the field of wind power generation technology and provides a wind farm regulation method, system, electronic device, and storage medium based on neural networks. The method includes: raw dataset acquisition, regulation command evaluation and classification, neural network model training, and wind farm regulation model regulation. This invention evaluates the regulation commands generated by the preset regulation strategy by using two adjacent sets of data in the raw dataset, realizing real-time analysis of the preset regulation strategy. The generated dataset provides a foundation for subsequent model training based on historical effects. By using labeled data to train the pre-built neural network model, the judgment logic of the command is optimized, improving the model's dynamic regulation capability for different wavebands, the degree of development of historical regulation data experience, and the stability of system operation.

The application provides a permanent magnet synchronous motor state intelligent prediction method and system based on time-frequency-space analysis, and belongs to the field of permanent magnet synchronous motor state prediction.The method firstly extracts global time domain information of motor physical quantities, then extracts local time domain and space information and frequency domain information, fuses the obtained information, and corresponds with output physical quantities to construct a permanent magnet synchronous motor state intelligent prediction model; after training and testing the model based on historical data, a mature permanent magnet synchronous motor state intelligent prediction model is obtained; then input physical quantities to be tested are input into the mature permanent magnet synchronous motor state intelligent prediction model, output predicted output physical quantities are output, and motor state prediction is performed.The application captures high-frequency characteristics and mixed periodicity of motor physical quantities themselves, dynamically captures nonlinear coupling relationships among motor physical quantities, improves state prediction precision and accuracy, and improves real-time performance of permanent magnet synchronous motor state prediction.

The invention relates to a neural stem cell exosome miR-106b compound and application of the neural stem cell exosome miR-106b compound in treatment of neurodegenerative diseases. It is found for the first time that the miR-106b-carrying neural stem cell exosome compound can effectively reduce damage to neurons and synapses and relieve neuroinflammation in in-vitro and in-vivo experiments. Animal experiment results show that in-vivo injection of the compound or the miR-106b simulant can be used as a treatment means for inhibiting neuroinflammation, and cognitive function decline related to neurodegenerative diseases can be resisted.

The present application provides a kind of nutritional composition in the application of the product for improving learning, memory and cognitive ability.The nutritional composition includes animal bifidobacterium lactis subsp.CP-9 and 3'-sialyllactose.Animal bifidobacterium lactis subsp.CP-9 and 3'-sialyllactose can synergistically enhance the memory retention ability of the body, reduce the degree of learning and memory errors, and up-regulate the expression of oligodendrocyte transcription factor 2 coding gene, myelin basic protein coding gene and brain-derived neurotrophic factor coding gene, realize the double regulation of myelin formation and neurotrophic in hippocampus region of brain, synergistically improve the neural plasticity of central nervous system through gut-brain axis pathway, and then double improve the learning, memory and cognitive function of the body from the behavior and molecular level.

The invention relates to a WEEE recycling supply chain inventory optimization method based on evolutionary reinforcement learning, and belongs to the technical field of supply chain management and artificial intelligence. According to the method, a multi-level inventory cooperative control model is constructed, an inventory optimization problem is modeled as a Markov decision process, and an evolution reinforcement learning algorithm is utilized to train an intelligent agent to learn an optimal strategy. Core innovations include design state space capture inventory dynamics, action space processing continuation to discrete decision mapping, and cost-based minimization of reward functions. According to the algorithm, a population evolution mechanism and experience playback optimization are fused, and the learning efficiency and stability are improved through parallel exploration and sample screening. According to the method, the uncertainty of the recovery amount and demand can be effectively dealt with, the inventory cost is reduced, the supply chain robustness and sustainability are enhanced, and a self-adaptive intelligent solution is provided for WEEE management.

The invention belongs to the field of protein fluorescence intensity prediction, and particularly relates to a protein sequence fluorescence intensity prediction method, system and device and a storage medium, and the method comprises the steps: carrying out the feature extraction of a training data set, combining random noise, training a generator and a discriminator, obtaining a generative adversarial model, supplementing data through the generative adversarial model, and obtaining a protein sequence fluorescence intensity prediction result. The method comprises the steps of obtaining a prediction data set, then extracting semantic features of the prediction data set, performing local mode enhancement and fusion on hidden layer features to obtain final features, inputting the final features into a prediction network to train the prediction network to obtain an optimal prediction network, and inputting an actual protein sequence into the optimal prediction network. The fluorescence intensity corresponding to the actual protein sequence is obtained. The method has the effect of improving the accuracy of predicting the fluorescence intensity of the protein sequence.

The utility model relates to the technical field of protective jackets, in particular to a tablet personal computer with a protective jacket component, which comprises a protective jacket and a base, a first placing groove and a second placing groove are arranged on the front side of the protective jacket, a capacitance pen and a tablet personal computer are respectively arranged in the first placing groove and the second placing groove, and a turning cover is arranged at the bottom of the protective jacket. Connecting columns are arranged at the bottoms of the two sides of the protective sleeve, round through holes are formed in the two sides of the opening end of the base, the connecting columns penetrate through the round through holes and then are provided with fastening bolts in a threaded mode, the protective sleeve is rotationally connected with the base through the connecting columns, and supporting rods are rotationally installed at the two ends of the middle of the back face of the protective sleeve; a movable batten is transversely arranged in the base and can move front and back, clamping grooves are formed in the two ends of the top of the movable batten, and the end, away from the protective sleeve, of the supporting rod is clamped and installed in the clamping grooves, so that the tablet personal computer can be unfolded and erected, and use is convenient.

This invention provides a traffic flow speed prediction method and system based on directed hypergraphs and attention mechanisms, belonging to the field of traffic state prediction technology. Based on directed hypergraphs, it constructs the relationships between nodes in a road network; aggregates directed hyperedge information to characterize the complex spatiotemporal features of the road network; builds an encoder and decoder architecture; integrates an attention mechanism, constructs an attention module, and introduces an improved dense connection structure to enhance the method's accuracy. This invention effectively overcomes the shortcomings of methods based on traditional graph structures, achieves the extraction and fusion of temporal and spatial features, and solves problems such as gradient vanishing in deep neural networks. It is applicable to multi-step traffic flow prediction in real road networks and achieves good prediction accuracy.

A visual automobile oil nozzle teaching miniature model with adjustable speed control is characterized by comprising a bottom plate, a box body, an oil spraying assembly, an oil conveying assembly and a speed adjusting assembly, the box body is installed on the bottom plate, an automobile oil nozzle supporting piece is arranged on the box body, the oil spraying assembly is installed on the automobile oil nozzle supporting piece, and the speed adjusting assembly is installed on the oil conveying assembly. The oil injection assembly is connected with the oil transportation assembly, the oil transportation assembly is connected with the speed regulation assembly, the shell of the automobile oil injection nozzle is made of a visual material, so that internal parts of the automobile oil injection nozzle can be seen, and students can conveniently and visually know the structure in the oil injection nozzle during teaching; the oil pumping speed of the oil well pump is regulated and controlled through the voltage regulating power supply, so that teachers or students can flexibly adjust the oil injection speed of the automobile oil nozzle according to teaching requirements, the working states of the oil nozzle under different working conditions such as idling, acceleration and high-speed driving of an automobile are accurately simulated, oil injection characteristic changes are visually displayed, and the teaching efficiency is improved. The oil nozzle performance can be deeply explored, and the teaching quality can be powerfully improved.

The application discloses a Deepfake video detection method based on multi-domain feature region standard score difference, which comprises the following steps: data set division; video frame division and extraction of a region to be detected; construction of a double-branch convolutional neural network; calculation of the RGB feature and NSCT sub-band image of the region to be detected; frequency domain feature obtained by frequency band fusion of the NSCT sub-band image; response of different level texture features obtained through a texture feature extraction module; output features of the space domain and frequency domain feature branches are spliced along the channel dimension, and input into an abnormal feature discrimination module to obtain a tampered region prediction mask; the tampered region prediction mask is subjected to a full connection layer to obtain one-dimensional features, which are spliced with the output features of the texture feature extraction module, and then subjected to a full connection layer and a Softmax activation function to output a binary classification prediction result. The application can better combine the feature information of the space domain and the frequency domain, strengthen the response to the texture feature, discriminate abnormal tampering traces, and improve the generalization ability of the model.

This utility model discloses a set of chopsticks for learning and game training, and its auxiliary tools. The chopsticks include a fixed chopstick and a movable chopstick. The rear end of the fixed chopstick is fixed between the user's thumb and forefinger, and the front end of the fixed chopstick rests against the concave part of the first joint of the ring finger. The movable chopstick has a stop protrusion about 1 / 3 of its rear end. The lower edge of the stop protrusion includes a slanted clamping part, which is pressed by the user's thumb to form a pivot for the movable chopstick to rotate relative to the fixed chopstick. The user can operate the movable chopstick by pressing it with their index and middle fingers. This design guides the user to master the correct chopstick grip and force application. The auxiliary tool includes several rings of varying sizes, which can help users understand, learn, and inherit chopstick culture in an entertaining way.