101results about How to "Fast learning" patented technology

The invention relates to the technical field of optimization methods, in particular to an action type model optimization method based on reward feedback, which comprises the following steps of: SI, constructing a multi-level reward function; s2, starting and initializing; s3, observing a current web environment state; s4, executing the action; s5, environment feedback; s6, constructing a Reward model reward signal processing module; s7, reward signal processing; s8, constructing an action evaluation network; s9, action evaluation; s10, updating the strategy; s11, judging whether the task is completed or a termination condition is reached; according to the method, a more comprehensive action feedback mechanism is established, the final reward is considered, the effect of the intermediate action is fully utilized, the action of the intelligent agent is evaluated and fed back more meticulously, the intelligent agent is guided to explore and utilize the environment more reasonably, and the user experience is improved. And an action feedback mechanism encourages the intelligent agent to try more actions which may contribute to realizing the target, and meanwhile, invalid or harmful actions are avoided, so that the exploration of the intelligent agent in the web environment is more efficient.

The invention provides a recommendation strategy generation method based on big language model enhancement and related equipment. The method comprises the steps of obtaining a recommendation task; inputting the recommendation task into an intelligent agent, and obtaining a recommendation strategy output by the intelligent agent; wherein the intelligent agent is obtained by training based on a sample recommendation task and a large language model, and the large language model is used for predicting user behaviors based on the sample recommendation task. According to the method, the big language model is combined with the reinforcement learning agent, so that the problem that an accurate recommendation strategy is difficult to quickly provide by a traditional method is effectively solved, and the efficiency and the adaptability of a recommendation system are improved while the accuracy and the individuation degree of the recommendation strategy are improved.

A mobile robot path planning method based on an SAC algorithm belongs to the technical field of deep reinforcement learning and mobile robot navigation, integrates the thought of hierarchical reinforcement learning skill combination into the SAC algorithm, and uses a time sequence abstraction method to integrate low-level fine-grained actions, so as to improve the precision of the SAC algorithm. A higher-level coarse-grained action with definite semantics can be learned; in reinforcement learning training, a distributed soft strategy iteration method is used, maximum entropy reinforcement learning is expanded into a distributed learning version, and variance and overestimation of a Q value are reasonably controlled through a learning state-action return distribution function, so that the overall strategy quality of robot path planning is improved. According to the method, training and testing are carried out in a simulation environment Image-Env, and the performance of the algorithm is verified on Turtlebot2. The method can efficiently avoid obstacles, is short in path, and has a good obstacle avoidance effect in a complex dynamic environment.

The invention relates to the field of electronic component workshop AGV logistics scheduling, and discloses an improved PPO scheduling method and system in an electronic component workshop AGV composite operation mode, a medium and equipment, and the method comprises the steps: carrying out the rasterization of a workshop environment map through grid modeling, enabling the AGV to carry out an A * search algorithm in a grid map through a plurality of task orders, obtaining batch sample data, and carrying out the calculation of the A * search algorithm in the grid map; pre-training is completed according to model parameters of the sample pre-training strategy network; according to the new task order, the AGV interacts with the environment, an observation state, an action space and a reward value are obtained, after matrix processing is carried out on the observation state, the observation state serves as input data of a PPO algorithm, a strategy network loss value and a value network loss value of the PPO algorithm are calculated, network model parameters are updated through a gradient descent method, and PPO training is completed; and generating a real-time task order on line, and guiding the AGV to complete path planning and scheduling tasks through the decision network models trained in the first two stages. According to the method, the electronic component workshop AGV scheduling strategy can be obtained through rapid learning, the learning efficiency is remarkably improved, and stability is achieved.

The invention provides a meta-learning-based continuous casting blank defect classification method, system and equipment. The meta-learning-based continuous casting blank defect classification method comprises the steps of 1, preprocessing an obtained public image classification data set and an obtained continuous casting blank image containing defects; 2, randomly forming a meta-task through meta-learning task allocation on the preprocessed public image classification data set, and inputting the meta-task to a preset image meta-learning classification model to obtain a trained image meta-learning classification model; step 3, performing meta-learning task allocation on the preprocessed continuous casting blank image containing defects to form a meta-task, and performing fine adjustment on the trained image meta-learning classification model by using the obtained meta-task; 4, classifying the defects of the continuous casting blank to be processed by utilizing the final image element learning classification model; according to the method, the problem of dependence on a large amount of labeled data in a traditional defect detection method can be effectively solved, and the classification capability of the model under the condition of few samples can be improved.

The invention discloses a brain-like edge calculation-driven multi-mode intelligent security method and system, and aims to improve the security capability in a complex dynamic scene. According to the method, multi-modal data of videos, audios, sensors and the like are collected, preprocessing is carried out by utilizing a brain-like edge computing gateway, dynamic behavior characteristics are extracted, secondary confirmation is carried out through a lightweight visual large model, and then formal early warning is generated. And the system executes intelligent linkage operation according to the early warning information risk level, and records false alarm information for model optimization. According to the invention, brain-like calculation and multi-modal fusion are adopted to improve the recognition precision, edge calculation reduces delay, an intelligent closed loop realizes differentiated treatment, a low-power design and a modular architecture reduce the cost, and the system has a self-learning capability. The defects of an existing security and protection system in the aspects of dynamic behavior recognition, response speed, disposal intelligence, cost control and the like are effectively overcome. The system is suitable for scenes such as a campus and a community, and provides an accurate, efficient and intelligent security solution.

The embodiment of the invention discloses a payment processing method and device, equipment and a medium. The scheme comprises the steps of obtaining a payment processing request; the payment processing request is triggered by a first device of a payer and a second device of a payee based on a near field communication mode; before a transaction resource corresponding to the payment processing request is transferred to a collection account of the payee, sending a first payment result page to a first device of the payer; the first payment result page is used for representing that a communication step based on near field communication is completed in an online transaction process; after the transaction resource is transferred to a collection account of the payee, sending a second payment result page to a first device of the payer; the second payment result page is used for indicating that the resource transfer step is completed.

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.

The invention relates to the technical field of internet of things equipment power consumption optimization methods, in particular to an internet of things equipment power consumption self-adaptive optimization method and system based on edge computing, and the method comprises the following steps: firstly, collecting historical operation data of different edge computing equipment, including but not limited to resource utilization rate, power consumption and network bandwidth; then, learning the historical operation data by using an improved multi-target deep reinforcement learning algorithm to obtain an equipment model; thirdly, predicting the optimal power value of the equipment through the equipment model; then, comparing the optimal power value with the actual operation power value of the current equipment, and when the optimal power value is inconsistent with the actual operation power value, sending an optimization instruction to the edge computing equipment; and finally, adjusting the parameter value of the edge computing device according to the optimization instruction to realize self-adaptive optimization of the power consumption of the device, so that the power consumption can be obviously reduced under various load conditions, and the task completion rate and the system response speed can be improved at the same time.

The invention provides a method for creating an item matching condition control model generation result based on a large model. The method comprises an item capturing module, an item splitting module, a condition expansion module, a model synchronization module, a reasoning control module, a result output module, a timing updating module and a reasoning monitoring module. A full-privatized operation ecology is created, user demand statements are analyzed through an artificial intelligence technology, a model is accurately matched, then completed items are pointed to corresponding item sources, real contents and intentions conveyed by the statements are accurately grasped, and convenience is brought to affair handling of the user; standard files are automatically collected through the RPA robot and added into the knowledge base, and therefore the knowledge base content of the government affair question-answering system is continuously maintained and enriched; according to the method, service items are collected, a service item list is formed, conditional expansion is carried out on the service items, conditional nature and description are carried out on the items, and therefore accurate matching and efficient management of service item conditions are achieved.

The invention aims to provide a white blood cell detection method based on FBDM-YOLOv8s, which comprises the following steps: A, constructing an improved YOLOv8s neural network model, and the improved YOLOv8s neural network model comprises a Backbond network, a Neck network and a Head network; the Backbond network takes a plurality of groups of Fasnet modules as a main framework, and finally, a group of BRA modules is arranged; b, the improved YOLOv8s neural network model is trained, and a trained improved YOLOv8s neural network model is obtained; and C, introducing a to-be-detected leukocyte image into the trained improved YOLOv8s neural network model, and sequentially processing the to-be-detected leukocyte image through a Backbond network, a Neck network and a Head network to obtain a detected image. According to the method, the edge detection precision can be improved while model parameters are optimized, the calculation speed is increased, and the problems that image cells are incomplete and two cells are mutually overlapped are better solved.

The invention relates to the technical field of medical science, in particular to a framework model based on neural network learning and an application method of the framework model. According to the model, a graph convolutional network (GCN, Transform architecture and long short-term memory network (LSTM) are fused, a multi-level analysis process is constructed, the spatial structure and sequence dynamics of drug molecules are deeply explored, and the model comprises the following specific steps: model training: performing model training by adopting data sets collected by people such as Cui, Q.Cui2020Improved and the like; the model test selects three independent test sets to comprehensively evaluate the performance of the model; according to the data preprocessing, an RDKit library is used, SMILES character strings are converted into molecular objects, a feature tensor is constructed and used for storing core features of each molecule in detail, data splitting is carried out, and the data splitting adopts versions, such as Ahmad, divided by people based on a Cui2020 data set to carry out training and testing of a machine learning model.

The invention is suitable for the technical field of data query, and provides a power marketing data query method and system based on a JointBERT model of a knowledge graph, and the method comprises the steps: obtaining field background knowledge related to the power industry, and constructing the knowledge graph; a JointBERT model is constructed and trained, and the model comprises an input layer used for processing input text data; the coding layer is used for carrying out fusion coding on rich general semantic knowledge in a corpus and domain knowledge in the knowledge graph; the decoding layer is used for generating field and intention corresponding to the input text and slot labels corresponding to words; compressing and optimizing the model by adopting an early leaving mechanism and a knowledge distillation method to obtain a target model; and the power demand problem of the user, which is received in real time, is used as the input parameter and is input into the target model for data query and analysis, so that the enterprise information query efficiency of related workers is improved.

The invention discloses an end-to-end calculation method for real-time prediction of an RC component explosion damage effect, and the method comprises the following steps: building an RC component explosion damage effect numerical value solving method, and obtaining RC component explosion damage effect numerical value simulation data; associating the numerical simulation data of the explosion damage effect of the RC component with the explosion working condition and the geometrical shape, the size and the material characteristics of the RC component, and obtaining an RC component explosion damage effect database comprising a training data set and a verification data set; training and optimizing the constructed neural network by using the training data set and the verification data set to obtain an end-to-end calculation model of the explosion damage effect of the RC component; and completing real-time prediction of the explosion damage effect of the target RC component by using the end-to-end calculation model of the explosion damage effect of the RC component. The method for predicting the explosion damage effect of the RC component is simple in process, high in speed and good in seaworthiness.

The invention provides a shoe tree glue spraying path automatic generation method based on point cloud data processing, and the method comprises the steps: carrying out the point cloud data preprocessing on the basis of scanning a shoe tree to obtain point cloud data, and obtaining a spatial motion track point mark and data; an approximate glue spraying attachment space track on the shoe tree is obtained through polynomial interpolation; then, orthogonal coordinate system NOA vectors corresponding to the glue spraying attachment space track points on all the shoe trees are sequentially solved, a mechanical arm tail end glue spraying space track obtained after the shoe tree glue spraying track NOA vector directions are offset by a certain distance is solved, and a mechanical arm tail end pose matrix is obtained through solving according to the orthogonal coordinate system NOA vectors and the mechanical arm tail end glue spraying space track; and finally, establishing an inverse kinematics mathematical model according to the D-H parameters of the robot, and substituting the inverse kinematics mathematical model into the tail end pose matrix of the mechanical arm for solving to obtain a shoe tree glue spraying movement track.

The invention relates to a multi-round dialogue intention recognition method and device based on small sample learning, computer equipment, a computer readable storage medium and a computer program product, and can be applied to the technical field of computers. The method comprises the following steps: performing intention labeling processing on historical dialogue data in the insurance field to obtain a labeled data set; selecting a training data set for model training from the annotated data set according to the data volume of each intention category in the annotated data set; according to preset data sampling information, sampling from the training data set to obtain a support sample set and a query sample set; according to the support sample set and the query sample set, performing iterative training on a to-be-trained small sample intention recognition model to obtain a trained small sample intention recognition model; and according to a preset model framework, performing model conversion processing on the trained small sample intention recognition model to obtain a target small sample intention recognition model. By adopting the method, the intention recognition efficiency can be improved.

The invention discloses a public health real information evaluation and early warning system based on an AI technology, and relates to the field of artificial intelligence technology application, and the system comprises a database module which is used for storing information collected by a collection module and providing powerful support for subsequent model construction and real-time response, and a data collection module which is used for collecting real-time information of public health. The invention discloses a public health data collection and processing method, which is used for collecting data related to public health from various sources (such as news, social media, professional forums and the like), including multi-modal data such as texts, pictures, videos and the like, and ensuring that the data sources cover data sources of a knowledge graph and data sources of a false information base. The information processing efficiency is greatly improved through a knowledge graph and advanced model construction, the system has strong adaptive capacity for novel false information, the system can rapidly learn and recognize a new false information mode through fusion of the knowledge graph and a large model, and the risk caused by the false information is effectively reduced.

The invention belongs to the technical field of aerospace, and particularly discloses a spacecraft cluster game method and system based on generative adversarial reinforcement learning, and the method comprises the steps: building a relative motion dynamics model of pursuit and escape parties, and building a game relation model of the pursuit and escape parties based on a two-person zero sum game model; solving a Nash equilibrium solution of the pursuit game by using a differential game method based on the game relationship model of pursuit and escape parties, and generating an expert database; designing and generating an adversarial reinforcement learning algorithm based on the expert database; and solving the game relationship between the pursuing and escaping parties by using a generative adversarial reinforcement learning algorithm to obtain an optimal game strategy. According to the method, the optimal control method and the artificial intelligence method are combined to solve the approaching strategy of the spacecraft cluster virtual main satellite to the non-cooperative target, the problems that convergence is difficult, reward setting is difficult and the effect is poor when the artificial intelligence method is used for solving the orbit game problem are solved, and finally efficient and accurate approaching to the target is achieved.

The invention discloses a construction method of a fish detection model based on deep learning and a fish detection method and system, a residual network ResNet is used as a main network structure of the fish detection model, and the residual network ResNet has a strong feature extraction capability and can capture features such as basic forms and textures of fishes; then a mixed attention mechanism is introduced to extract more effective feature quantities, a mixed attention module is connected behind each residual block of the residual network ResNet, key features can be further extracted and emphasized, and therefore a better effect is achieved on the residual network ResNet; the mixed attention is combined with an attention mechanism of two dimensions of channel attention of GRA and space attention based on CBP, the model can more comprehensively capture feature information of fish, algorithm complexity is effectively reduced, hardware requirements of actual deployment are further reduced, the requirements for depth and different level widths of a deep learning algorithm are reduced, and the method is suitable for being popularized and applied. And the purpose of algorithm weight reduction is achieved.

The present invention relates to the technical field of bird trajectory prediction, and specifically to a bird trajectory prediction system based on bird detection radar and big data model analysis, comprising a data acquisition module, a prediction model establishment module and a prediction model update module, wherein the data acquisition module acquires the speed, acceleration, trajectory and time point data of the bird; the prediction model establishment module uses the data to set a trajectory prediction model, and predicts the bird trajectory at the next time point based on the data of the previous time point, calculates the prediction error, and optimizes the error through the training strategy in the model to update the prediction parameters, and records the time required for the prediction; the prediction model update module calculates the influence coefficient according to the error and prediction time, so as to adjust and update the training strategy of the model; this process solves the problem that traditional systems are difficult to dynamically adapt to changes in bird movement, improves the accuracy and efficiency of prediction through adaptive training strategies, and achieves a more stable and reliable bird trajectory prediction effect.

The invention provides a method and a device for carrying out traffic safety accident attribution by using a Bayesian inference theory, relates to the technical field of traffic accident data processing, and aims to realize accurate traffic accident attribution analysis. The method comprises the steps that a plurality of video clip samples carrying labels in an input data set are sequentially input into a Bayesian perceptron one by one, the video clip samples are video clips where traffic safety accidents happen, and the labels are used for representing the occurrence reasons of the traffic safety accidents in the video clip samples; obtaining model parameters of a Bayesian perceptron based on a Bayesian inference theory, and obtaining a trained Bayesian perceptron; and inputting the video clip of the traffic safety accident into the trained Bayesian perceptron to obtain an attribution result which represents the probability of the occurrence reason of the traffic safety accident and a corresponding confidence interval.

The invention discloses an unmanned aerial vehicle acoustic signal identification method and system based on meta transfer learning, and relates to the signal identification technology, and the method comprises the steps: obtaining sound samples of an unmanned aerial vehicle in different environments, different flight states and distances in advance, and extracting the feature vectors of the sound samples; defining learning tasks of a plurality of meta transfer learning models, wherein each learning task is used for identifying different types of unmanned aerial vehicles or unmanned aerial vehicles under different environmental conditions from the feature vectors of the sound samples; for a newly obtained unmanned aerial vehicle sound signal, performing fine tuning on the pre-trained meta-migration learning model by using part of the annotated data; and performing sound signal identification of the unmanned aerial vehicle by using the fine-tuned meta transfer learning model. According to the invention, learning and adaptation can be carried out faster on a new task, and the accuracy of acoustic signal identification is improved.

The present invention proposes a reinforcement learning lane changing behavior planning method and system based on imitation learning initialization. The method maps the deformed posture and fuzzy speed of surrounding vehicles onto a grid map through gradient colors, represents traffic rules and road conditions with clear information using vectors, and connects the two to input into the imitation learning DAgger network, so that the autonomous driving vehicle learns to obey traffic rules and basic lane changing decisions. The imitation learning lane changing mechanism is then optimized by reinforcement learning to adapt to extreme and unknown traffic scenarios that are not included in the imitation learning data set. The potential lane changing driving mechanism can be learned from the driving mechanism and environment of vehicle interactions, simplifying the manual driving modeling, having good adaptability to the dynamic changes of the lane changing scene, and adopting a dynamic mixed reward mechanism for the lane changing task. A reinforcement learning initialization method based on imitation learning is introduced to solve the problem of low learning efficiency of reinforcement learning under sparse rewards, and only a small amount of scene data is required.

The invention relates to the technical field of medical training, in particular to an intravenous infusion treatment management training method and system based on a patient safety target. Presetting an evaluation time point, and carrying out capability evaluation on the nursing personnel based on a plurality of preset evaluation indexes; performing statistical analysis on an evaluation result of the evaluation index to obtain a first score corresponding to the evaluation index; setting a first weight for the evaluation index, and multiplying the first score by the first weight to obtain a first result; calculating a capability assessment score of the nursing personnel according to all the first results; dividing a plurality of ability grades based on the ability evaluation score, and determining a to-be-trained person according to the ability grades; determining training content based on the evaluation indexes of the to-be-trained personnel; acquiring a skill brief introduction of a nursing lecturer; matching the training content with the skill brief introduction, and determining a current training lecturer; a training time point is preset, and the current training lecturer trains the to-be-trained person based on the training content. The post competency of nursing personnel is rapidly improved, and the safety of patients is guaranteed.

The invention discloses a deep learning-based computing power infrastructure energy cost prediction method. The method comprises the steps of data acquisition, sub-model training, establishment of a computing power infrastructure energy cost prediction model and computing power infrastructure energy cost prediction. The invention belongs to the technical field of cost prediction, and particularly relates to a computing power infrastructure energy cost prediction method based on deep learning, and the method employs dynamic feature selection, LSTM-based sub-model training, data set distance design and an undersampling strategy, can better adapt to a continuously changing energy mode, and improves the prediction efficiency. The capability of capturing complex facility energy data features is improved, and the accuracy of final energy cost prediction is further ensured; the weight of the base classifiers is dynamically adjusted by evaluating the error prediction number of each base classifier, and finally prediction results are integrated, so that the accuracy of the prediction results is improved; and rapid convergence of the model is realized through a unique initial parameter adjustment strategy, so that the cost prediction efficiency is improved.

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 invention discloses a model optimization method and system for new energy station data processing, and the method comprises the steps: building a deep Q network reinforcement learning model according to an existing data sample, selecting an action based on a current state to calculate a reward function, and designing the reward function to measure the performance of an algorithm, awards are determined according to factors such as the accuracy of data recovery and the degree of help to a station operation decision, and in the training process, a higher extracted probability is given to important experience by calculating a TD error of each experience, playing back by using preferential experience and sampling according to the importance of the experience, so that a model learns key information more quickly, and the training efficiency is improved. Meanwhile, in the training process, a small batch of experiences are randomly extracted from a buffer area for learning, the correlation of data can be broken, finally, optimization training of the model is completed through iterative updating, and the model obtained through the method can solve the noise problem of data missing and the like in the new energy station data collection process.

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.