15results about How to "Fast learning" patented technology

The utility model relates to the technical field of trademark pasting making discloses a longitudinal cutting mechanism of trademark machine, including setting up on the support plate of frame, two the side of facing of support plate all is provided with damping bearing, the damping bearing interval is provided with longitudinal cutting shaft, the longitudinal cutting shaft all uniformly distributed has a plurality of fixed clamps, the side of fixed clamp is provided with adjusting part. The utility model discloses the trademark machine stripping waste mechanism of setting can separate the plastic film roll paper after the film coating with waste film quickly, through the slitting force generated by stripping waste piece, make when separating can reduce the tensile force, thereby avoid the plastic film roll paper when separating and drag too big, cause the plastic film roll paper damage and scrap.

This invention discloses a supervised multimodal hash retrieval method and system based on label enhancement, belonging to the field of artificial intelligence and multimedia retrieval technology. The technical problem this invention aims to solve is how to better capture the similarity information between multimodal data points and achieve better performance and accuracy in multimodal retrieval tasks. The technical solution includes: data preprocessing: acquiring and organizing public datasets of image and text modalities, and dividing each public dataset into training, testing, and retrieval datasets; extracting deep features: using a pre-trained network model to extract features from the raw data of the public datasets of image and text modalities respectively, obtaining deep features of the image modality and the text modality; offline training; variable update and optimization; and online query. The system includes a data preprocessing unit, a feature extraction unit, an offline training unit, a variable update and optimization unit, and an online query unit.

The application provides a communication interference strategy generation method based on reinforcement learning, comprising the following steps: step one, constructing a system model of a communication party and a communication interference party; step two, based on the system model of the communication party and the communication interference party constructed in step one, learning an anti-interference scheme of the communication party by using a win-or-learn policy hill climbing algorithm, and designing a corresponding interference decision model; step three, using the interference decision model obtained in step two, learning an anti-interference strategy of a communication target and implementing interference according to a decision process of 'observation-adjustment-decision-action'. The application comprehensively considers interference basic principles and behavior changes of the communication target, combines a jam-to-noise ratio and anti-interference behaviors such as frequency change and transmission power increase of the communication target after being interfered, and uses the two as measurement indexes of interference effects, so that the purpose of real-time and rapid interference is achieved.

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.

The invention discloses a lithium battery micro internal short circuit fault diagnosis method based on dynamic mode decomposition and a radial basis function neural network. Comprising the following steps: S1, preprocessing original voltage time sequence data collected in an operation process of a lithium battery, and constructing an input matrix suitable for dynamic mode decomposition; s2, decomposing the input matrix based on a dynamic mode decomposition method, extracting a dominant dynamic mode, screening and recombining a key mode based on Pearson correlation analysis, and generating a low-dimensional and high-sensitivity fault feature vector; s3, taking the feature vector as an input of a radial basis function neural network, taking an internal short circuit equivalent resistance value as a label, and constructing a nonlinear mapping relation between the feature space and an internal short circuit state; and S4, comparing an internal resistance prediction value output by the radial basis function neural network with a set threshold value or a reference value, calculating a prediction error and evaluating the diagnosis precision. According to the invention, misdiagnosis caused by noise and aging effects is avoided.

This application discloses a remote control learning method. When the learning remote control receives an infrared signal from a target remote control, it determines the infrared protocol parameters and preliminary timing data of the infrared signals of the buttons to be learned. The preliminary timing data is preprocessed to obtain target timing data. A bitmap is constructed based on the infrared protocol parameters of the infrared signal, the target timing data, and a pre-stored remote control library on the learning remote control. The target timing data is decoded according to the infrared protocol parameters of the infrared signal to obtain the corresponding key values. Based on the one-to-one correspondence between key values ​​and the buttons to be learned, the bitmap is set to zero to obtain a set bitmap. Then, based on the number of 1 values ​​in the set bitmap, the infrared protocol parameters of the target remote control and the correspondence between all buttons and key values ​​are determined. The infrared protocol parameters of the target remote control and the correspondence between all buttons and key values ​​are configured on the learning remote control. This application can reduce timing data errors and reduce the number of remote control learning operations.

The invention provides a ternary collaborative multi-agent framework and an environmental assessment report intelligent auditing method, and belongs to the technical field of artificial intelligence and environmental assessment, the framework comprises a decision-making layer, an arbitration layer and an evolution layer, the decision-making layer performs parallel auditing with a dynamic weight revenue function through four agents, and the arbitration layer quantifies decision conflicts with OODA circulation based on conflict intensity, and performs review on the decision-making layer and the dynamic weight revenue function through the four agents. And the evolution layer adopts a DPO method with preference attenuation to realize model iteration. And the auditing efficiency and precision are obviously improved.

The present disclosure relates to an automatic driving evolution method and system based on a progressive expert hybrid network, which can solve the problems that the existing expert hybrid network is difficult to evolve with new driving conditions, has catastrophic forgetting and insufficient knowledge transfer. The method periodically trains the expert hybrid network: for new driving conditions, new experts are added to the existing expert network to form a new expert network, and the first layer of the new expert is connected to the first layer of the historical expert through a horizontal transfer interface. During training, the parameters of the historical experts are frozen, and the parameters of the new experts are optimized. The outputs of the new experts and the historical experts are input into the gate layer to obtain the control decision signal. Because the historical experts only participate in reasoning and do not update the weights, the existing knowledge can be stably retained to prevent catastrophic forgetting; and the new experts absorb existing knowledge in the initialization stage and learn differently for new conditions, achieving a balance between transfer and expansion, improving the accuracy and safety of automatic driving control.

The application relates to the technical field of direction of arrival estimation, and specifically discloses a cross-platform complex domain feature enhancement coherent super-resolution DOA estimation method, which comprises the following steps: firstly, a complex domain CVSIMO learning model is constructed; sampling data is preprocessed; forward propagation of the CVSIMO learning model is carried out; backward propagation and parameter optimization of the CVSIMO learning model are carried out; data reconstruction and signal separation are carried out; cross-platform super-resolution DOA estimation is carried out; and finally, model simulation experiments are carried out. The cross-platform complex domain feature enhancement coherent super-resolution DOA estimation method can realize feature mining of multiple point source signals, converts a multi-source estimation problem into a single point source DOA estimation problem by using a complex domain neural network model, enhances the features of coherent signals by using the advantages of the complex domain neural network, improves the performance and precision of the super-resolution DOA estimation algorithm, can also realize data separation of multiple coherent signals and cross-platform DOA estimation, and realizes real angle estimation through ingenious feature solving.

The application discloses a real-time scheduling method for same-track double cranes based on joint action space deep reinforcement learning, and belongs to the technical field of industrial scheduling. The method first acquires a real-time production state of double cranes; a mathematical model for real-time scheduling of double cranes is constructed, with the objective of minimizing the maximum completion time and the constraints of crane collision avoidance, workpiece process sequence and the like; then, a real-time scheduling model based on joint action space deep reinforcement learning is constructed, which adopts a joint action space mechanism; subsequently, historical data and a simulation environment are used to train the model by using a multi-agent deep reinforcement learning algorithm; finally, the real-time task and the system state are input into the trained model, so that the collaborative operation instructions of the double cranes can be output to guide the real-time operation of the production line. The application can effectively solve the path conflict, task allocation and real-time disturbance problems in the collaborative operation of double cranes, and provides reliable and efficient decision support for intelligent scheduling of the production line.

The invention discloses a grip strength training device. The grip strength training device comprises a holding part and a feedback part. A cavity is formed in the holding part, and the holding part is provided with a first opening communicating with the cavity. The feedback part is connected to the holding part and covers the first opening, and the holding part is configured to discharge internal air through the feedback part after being pressed and elastically contracted. And when the airflow velocity of the air discharged by the feedback part exceeds the discharge threshold value, feedback is carried out. According to the scheme, when the holding speed of the hand of the user is high, the compression speed of the inner space of the holding part is high, so that the exporting speed of the air in the holding part is increased, and when the airflow velocity of the air exhausted through the feedback part exceeds the threshold value, feedback can be conducted to the user. In other words, after the hand of the user holds the holding part, feedback can be obtained when the holding and pressing speed is high, the feedback can provide effective reference for rapid force exerting training of the user, and therefore the user can know whether the force exerting mode of the user is correct or not according to the feedback, and then the user can rapidly learn how to exert force correctly.

This invention discloses a method and system for predicting human hand movements based on surface electromyography (EMG) signals, belonging to the field of hand movement prediction technology. First, the temporal characteristics of the EMG signals are obtained; then, these temporal characteristics are input into a cross-individual lifelong network model to obtain the predicted human hand movements. During the training process of the cross-individual lifelong network model, a model structure and training method that can be adapted to multiple individuals simultaneously in a single training session are proposed. A lifelong learning strategy is designed, and the model is adapted to these adaptations, enabling the method to quickly learn new individuals while maintaining the model's performance on already trained individuals, effectively solving the catastrophic forgetting problem of the model.

This disclosure provides a method, apparatus, and electronic device for displaying session information. The method includes: displaying information about at least one session in which the current user participates in a session list, the displayed session information including a first set of information from the corresponding session; and displaying information about at least one second group session in which the current user is not a member, the displayed second group session information including a second set of information; wherein the amount of information in the second set is less than the amount of information in the first set. This helps users quickly understand group sessions they are not participating in, improving the convenience of joining groups.

This invention relates to a multi-agent consensus reinforcement learning method and system based on an improved Q-function. First, a dynamic model of a linear discrete-time heterogeneous multi-agent system is established. Second, a reliability factor ρ is introduced to compromise between two learning modes: non-policy Q-learning and policy Q-learning. A distributed control protocol based on the improved Q-function is designed. Finally, a Critic neural network is used to learn the optimal control protocol from data generated by the system's dynamic model. Consistency control of the heterogeneous multi-agent system is then performed according to this optimal control protocol. This invention proposes an improved Q-function-based heterogeneous multi-agent consensus reinforcement learning control method, enhancing the self-learning capability of reinforcement learning, making agents more sensitive to environmental changes, accelerating learning speed, improving learning reliability and efficiency, and simultaneously achieving consensus in the heterogeneous multi-agent system in an optimal manner.

This invention discloses a method for marking tobacco material information, including controlling the tobacco material to be conveyed on the discharge bottom conveyor at a certain stacking height I; controlling the next batch of tobacco material to be conveyed on the discharge bottom conveyor at another stacking height II; and so on, until all batches of tobacco material are discharged; the stacking height I, stacking height II, etc., change according to a certain pattern as the batch quantity of tobacco material is updated; by knowing the current stacking height of the tobacco material on the discharge bottom conveyor and the pattern of stacking height change, the batch data of this tobacco material can be obtained. This method aims to improve the efficiency of tobacco material tracking, management and traceability characterized by assembly line operations. By adopting dynamic stacking marking technology, this method can monitor and update tobacco material information in real time, providing more accurate and reliable data for production and supply chain management.