20 results about "Knowledge learning" patented technology

This invention relates to the field of intelligent training technology, specifically to an internet-based intelligent training system for the prevention and control of respiratory infectious diseases. In this invention, a long short-term memory network is used to deeply model learners' learning progress, identify weaknesses in the learning process, and accurately push corresponding content, effectively providing personalized learning path recommendations. A graph neural network-based learning resource scheduling and content push method dynamically adjusts the frequency and order of learning content pushes to match learners' progress, ensuring that learning content is pushed at the appropriate time and with suitable difficulty. By constructing an interaction graph among learners and combining it with influence assessment, key prevention and control knowledge is disseminated preferentially through learners with high influence, optimizing the knowledge dissemination path. Combined with the application of the SIR (Self-Improving Influence) propagation model, the system predicts learners' progress in learning prevention and control knowledge, identifies learning bottlenecks, and significantly improves learning effectiveness.

The application provides an intelligent substation anomaly detection method based on meta-learning technology, first, a multi-working condition task library is constructed for meta-training. Secondly, a double meta-knowledge learning framework is designed to learn task-level model initialization parameters suitable for rapid adaptation. Subsequently, online reconstruction error driven anomaly detection is deployed, and the adapted model is used to calculate data reconstruction error in real time, and combined with the adaptive threshold to accurately distinguish and alarm grading. Finally, the system supports a dynamic updating mechanism, which continuously collects verified samples and periodically triggers meta-updating. The application significantly reduces the data dependence and deployment cost in new scenarios, improves the model's generalization ability to multiple working conditions and sensitivity to rare anomalies through meta-knowledge sharing, and ensures the long-term effectiveness of the detection system through online learning mechanism, providing an efficient, adaptive and evolutionary security protection solution for intelligent substations.

The application discloses a kind of based on low-rank self-adaption's federal remote sensing big model training method and system, comprising: using respective remote sensing data, pre-training big model and local low-rank self-adaption model is carried out individualized heterogeneous data knowledge learning;Using the local low-rank self-adaption model parameter initialized global shared low-rank self-adaption model parameter after training, based on pre-training big model and global shared low-rank self-adaption model is carried out collaborative federal training, learns global remote sensing task field knowledge;By heterogeneous rank alignment fusion mode, the alignment of local heterogeneous data knowledge and global remote sensing task knowledge is realized after, output is composed of pre-training big model and the low-rank self-adaption model parameter of alignment after local by federal remote sensing big model, such as greatly reduce the parameter quantity and communication overhead of federal training upload, guarantee the efficient training of model, also realize local heterogeneous data and global remote sensing task self-adaption alignment, guarantee the versatility and robustness of model.

The application discloses a multi-dimensional student state knowledge tracking method fusing emotion and forgetting mechanism, relates to the field of intelligent education, and aims at the problems that the existing method ignores the dynamic influence of emotion on forgetting and lacks a learning feedback mechanism.The application proposes a multi-dimensional state collaborative evolution framework.The method firstly constructs an independent forgetting state which is explicitly regulated by emotion and establishes a knowledge state which is inhibited by the forgetting state;secondly, the knowledge learning gain is innovatively introduced into the emotion updating process, realizing deep coupling of the three-dimensional states of knowledge, emotion and forgetting;finally, the states are fused through cross-dimensional attention, and the basic prediction probability is dynamically calibrated by using subjective difficulty and a prediction uncertainty coefficient.The application effectively simulates a real cognitive psychological process, and significantly improves the accuracy, explainability and individualization level of knowledge state tracking.

The application discloses a kind of personalized federated continuous learning method and system based on dynamic clustering and multi-scale prototype, to solve the problem of spatiotemporal catastrophic forgetting in personalized federated continuous learning.The server initializes global model containing prompt parameters and cluster-level multi-scale prototype library, and the client generates routing histogram representing local data distribution and incremental prototype through a gated routing network and uploads it.The server calculates JS divergence based on routing histogram to detect drift, triggers K-Means online re-clustering, and dynamically updates the multi-scale prototype library containing short-term, long-term and drift prototypes in combination with the drift signal.The client uses long-term prototype to construct a joint loss optimization model.The application balances new knowledge learning and old knowledge retention while protecting data privacy and reducing overhead, and adapts to scenarios where data distribution continues to evolve.

This invention relates to the field of knowledge recommendation technology and provides a personalized medical knowledge recommendation method and system for medical students. The invention acquires periodic test data; performs phased progress learning planning; compares the overlap of knowledge digestion; acquires reference learning data from other medical students; analyzes knowledge learning gaps; selects multiple gap-filling medical knowledge areas; and recommends relevant knowledge to the target medical student. Based on the target test data, the invention compares the periodic test data for phased progress learning planning and knowledge digestion overlap, selects reference medical students, acquires reference learning data, analyzes knowledge learning gaps between the reference and target learning data, selects multiple gap-filling medical knowledge areas, and recommends relevant knowledge to the target medical student. This allows the invention to uncover the commonalities and differences in learning among different medical students, providing them with forward-looking and targeted learning improvement directions for rapid academic improvement, effectively enhancing the learning efficiency of the target medical students.

A frequency control method and device for a hydro-wind-solar-pressure storage system based on an improved PPO algorithm are disclosed. The method includes: constructing a frequency control model for the clean energy base; introducing an expert knowledge learning mechanism and a phased training mechanism based on the PPO algorithm to construct an improved PPO algorithm; the expert knowledge learning mechanism refers to fitting the mapping relationship between the state and action of an agent through supervised learning based on an expert dataset; the phased training mechanism refers to using a preset number of training rounds as a phase switching condition, automatically triggering parameter adjustment of the agent after reaching the preset number of training rounds, and triggering the expert knowledge learning mechanism when the training effect of the agent is poor; and intelligently controlling the frequency of the clean energy base based on the improved PPO algorithm. This invention employs a phased training strategy, enabling a single training process to cover multiple operating conditions, and combines expert guidance to meet diverse control needs, thereby improving convergence efficiency and strategy performance, and ultimately achieving intelligent frequency control of the clean energy base.

The present application relates to the technical field of precision grinding processing, and discloses a kind of self-adapting iterative optimization system of grinding wheel laser dressing process parameters, comprising: state acquisition module, the surface state data of grinding wheel is collected and multi-dimensional feature is extracted, data fusion and dimension reduction processing are carried out;Working condition identification module, identify working condition category and determine dressing target state parameter;Parameter optimization module, construct agent model and predict dressing effect, carry out quality evaluation and bayesian optimization search;Dressing execution module, execute laser dressing, identify abnormality and adjust parameters by feature matching;Quality evaluation module, carry out feature extraction, calculate single index compliance degree and gather layer by layer, combined with dressing process data package and correct;Parameter iteration module, identify defect index and generate adjustment scheme, iterative execution dressing and quality evaluation;Knowledge learning module, carry out knowledge mining and transfer learning;The present application realizes the self-adapting optimization and closed-loop quality control of dressing parameter.

The application provides a gastroscope large model based on course learning and reinforcement learning iteration and a training method. Applied to the technical field of data processing, the method comprises the steps of initializing a visual feature extraction submodel and a generative language submodel, and constructing a feature dimension alignment unit between the two; determining whether the image feature dimension and the word embedding dimension are consistent; determining the current training data type; after the model completes basic knowledge learning, performing concept anchoring based on medical term data; using clinical instruction data to perform instruction following training of response logic; obtaining the model after course learning as a base; constructing a reward evaluation system containing multiple dimensions of indexes; inputting difficult case samples into the model to generate a diagnosis result, and calculating the score of the diagnosis result under each evaluation index; and determining a comprehensive reward value based on the score corresponding to each evaluation index and the corresponding weight coefficient.

In various intelligent systems, responses to periodic or non-periodic events typically employ pre-set timed tasks or simple triggering mechanisms. The need for proactively executing response actions based on specific events is prevalent in various automated systems, intelligent devices, and service platforms. However, existing technologies suffer from static event responses, a disconnect between memory and response, knowledge gaps, a lack of initiative and adaptability, and limited application scenarios. Therefore, a universal method is needed that can sense events, retrieve historical records from the same period, learn relevant knowledge, and proactively generate response content to improve the intelligence level and user experience of various systems. This application provides an event-driven proactive response method, system, and computer-readable storage medium, aiming to achieve universal, intelligent, and personalized proactive interaction through event date determination, historical record retrieval, knowledge learning, and proactive response execution.

1. Name of the product in this design: Learning Robot (Owl). 2. Purpose of this design: For knowledge learning. 3. The key design features of this product are its shape and the camera located below the nose. 4. The image or photograph that best illustrates the design's key features: the front view.

This invention discloses a team-based dialogue generation and tutoring learning method and system based on a large language model. First, a rule-based expert course knowledge base is constructed according to course needs and knowledge structure. Second, in an observational learning context, personalized knowledge dialogues are generated between different teachers and a fixed set of students based on a generative teacher prompt instruction set, and personalized knowledge dialogues are generated between a fixed teacher and different students based on a generative student prompt instruction set. Then, in an interactive learning context, teaching statements from expert teachers are generated based on a generative interactive prompt instruction set, and personalized feedback statements from expert teachers are generated based on student feedback and the generative interactive feedback prompt instruction set. Finally, based on student user experience feedback, knowledge learning effectiveness is analyzed, and precise team-based learning contexts are optimized to achieve personalized tutoring for students.

The application discloses a kind of three-dimensional point cloud-oriented incremental semantic segmentation method and system, by establishing the two-stage segmentation framework of the link of basic training stage and incremental training stage, obtain stable representation in old class in basic stage, in incremental stage, through the old class pseudo-label recovery mechanism of cross-stage class semantic anchoring mechanism, spatial uncertainty and class prototype double constraint, and the local structure relationship distillation mechanism of new and old model, the balance between old class knowledge preservation and new class knowledge learning is realized.It is simultaneously introduced in the joint design of local geometry extraction and global state space modeling in point feature coding process, enhance the point-level representation capability in complex three-dimensional scene.The application explicitly solves the old class forgetting and semantic drift in three-dimensional point cloud class incremental semantic segmentation, improves the segmentation precision of easily confused class in complex scene, enhances the stability and robustness of sequence modeling process.

Embodiments of the present application disclose an electrocardiogram multi-label classification method based on knowledge coding and related devices. Embodiments of the present application include preprocessing the collected multi-lead electrocardiogram signal to obtain a preprocessed multi-lead electrocardiogram signal; constructing knowledge coding; based on a signal and knowledge embedding module, merging the preprocessed multi-lead electrocardiogram signal, lead knowledge coding, and time sequence knowledge coding into a signal data block; based on an encoder composed of a multi-head self-attention layer, performing feature learning on the signal data block to obtain a signal feature block; based on a knowledge learning module, classifying and identifying the signal feature block according to the category knowledge coding. The present application not only solves the problem of too few labels on data in the existing method, but also can be compatible with different lead formats. In addition, the present application also obtains high interpretability for each electrocardiogram label category, has good classification effect, and improves the accuracy of electrocardiogram multi-label classification.

The present application belongs to the field of distributed computing power network and network security technology, and particularly relates to a fraud detection method in a distributed computing power network environment. The method comprises the following steps: step 1, training data preparation stage: each local platform in the distributed computing power network collects local computing power transaction data and corresponding classification labels, and obtains a fraud detection model of each centralized computing power network platform; step 2, distributed collaborative training stage; step 3, inference deployment stage: after convergence through multiple rounds of training, the local platform directly uses the trained local model to perform fraud detection on new computing power transaction records, without the need to communicate with the basic model. The present application has the following advantages: through knowledge alignment, the cross-model integration capability is improved; through customized knowledge learning, the generalization capability of the local model is enhanced; and the data and resource limitation problem is solved.

1. The name of the design product: the graphical user interface of the knowledge learning and training of electronic equipment. 2. The use of the design product: an electronic device. 3. The design points of the design product: the graphical user interface. 4. The picture or photo that best indicates the design points: design 1 front view. 5. Design 1 is designated as the basic design. 6. The use of the graphical user interface: the graphical user interface for learning and training related knowledge. 7. The human-computer interaction mode of the graphical user interface: design 1 front view is the main interface of the product, and the user can click the corresponding module to enter the corresponding function. Design 2 front view is the main interface of the product, and the user can click the corresponding module to enter the corresponding function. The "xx" in the interface of the design represents text and / or numbers and / or letters and / or symbols. 8. Other circumstances that need to be explained Other explanations: the design 2 design includes color.

The application discloses a black-box home automation rule set reconstruction method based on interactive verification and belongs to the technical field of network security. In view of the deficiencies existing in the current intelligent home automation rule discovery and management, the confidence between the trigger attribute and the condition attribute is established through knowledge learning, the efficiency of obtaining rules is improved, and the inefficiency of exhaustion is effectively overcome. The application also proposes a rule causal chain modeling method based on event sequence analysis. By analyzing the time sequence of entity state interaction, different entity state changes occurring continuously are mapped into a "trigger entity-action entity" pair, and entities maintaining a stable state between the trigger and the action are automatically identified as condition candidate entities, so that the automatic generation and structured expression of the automation rule are realized. Experimental results show that the application achieves good results in collecting automation rules in the real world. Therefore, the application can be used for intelligent home system anomaly detection and network space security maintenance.

This invention belongs to the field of power system dispatching technology and discloses a method and apparatus for optimal dispatching of multi-regional interconnected power systems. The method includes the following steps: establishing constraints for the regional interconnected power system based on equality and inequality constraints; establishing a regional optimal dispatching model with the minimization of fuel costs of generator units in the multi-regional interconnected power system as the objective function; and solving the regional optimal dispatching model using a knowledge-learning linear population size reduction differential evolution algorithm to obtain the optimal dispatching scheme for each generator unit. This invention, by introducing a knowledge-learning strategy, avoids the situation where the fitness of particles cannot be improved during iterative evolution, saves iteration resources, and accelerates the convergence speed. This algorithm exhibits good performance in the optimal dispatching of multi-regional interconnected power systems.