23 results about "Human learning" patented technology

The invention belongs to the field of artificial intelligence and video anomaly detection, and discloses a weak supervision video anomaly detection method based on curriculum learning and contrast learning strategies. A course learning strategy is designed by simulating a human learning mode, an anomaly detection model is trained through a contrast learning method based on a normal prototype, and the method comprises the following steps: preprocessing a video and extracting an optical flow image; video appearance and motion features are extracted and fused; inputting into a pre-classifier to obtain a pseudo label; judging the anomaly detection difficulty according to the false label, and dividing a simple set and a difficult set; initializing a model by using a simple set; and performing two-stage training by using the difficult set, and updating model parameters through normal prototype contrast learning. According to the invention, the discrimination capability of a weak supervision video anomaly detection model can be effectively improved, the problems of model deviation, fuzzy positive and abnormal boundaries and insufficient model discrimination capability under the influence of noise in the prior art are solved to a great extent, and the accuracy of video anomaly detection is remarkably improved.

The invention relates to the technical field of intelligent prediction and control technologies, in particular to an industrial hearth temperature prediction system based on a reasoning human learning optimization algorithm, and aims to solve the problems that in the prior art, temperature change cannot be accurately predicted under complex working conditions, adaptive adjustment cannot be performed under dynamic working conditions, and the prediction efficiency is low. And accurate prediction of a temperature field and combustion control optimization cannot be realized. The hearth temperature prediction model is constructed through the prediction model construction module to achieve high-precision prediction of the hearth temperature, through combination of Bayesian reasoning and the self-adaptive reasoning network, the system can accurately predict temperature changes under the complex working condition, response is fast, optimal combustion control is achieved, the system can conduct self-adaptive adjustment under the dynamic working condition, and the system is suitable for being used in the dynamic working condition. Accurate prediction and combustion control optimization of the temperature field are achieved, and the method has high robustness and is suitable for various high-temperature industrial scenes.

A long-term continuous learning method based on task core memory management and consolidation aims to enable a model to sequentially learn from a large number of task sequences, new knowledge is obtained, information of previous learning is reserved, and the method is similar to a human learning mode. The method comprises the following steps: 1) task input and instruction fine tuning; 2) performing difference analysis on the model parameters of the current task and the previous task, identifying a task core memory unit, calculating an adaptive weight based on task prototype similarity, and dynamically updating the memory unit; 3) constructing an experience playback buffer area through a difficult sample selection strategy and a difference sample selection strategy; and 4) utilizing the joint loss function training model to keep the memory of the historical tasks while learning the new tasks. According to the method, the problem of disastrous forgetting in long-term continuous learning is mainly solved, and the performance of the model in a long-term sequence task is remarkably improved.

The invention discloses an ultra-supercritical unit rapid dynamic response method based on multiple models, and relates to the technical field of thermal power generation. According to the method, a nonlinear control method which unifies internal model control and generalized predictive control is provided, and nonlinear control over an ultra-supercritical unit (USC) system is effectively achieved: firstly, through internal model control based on LSTM-Transform, the USC system achieves rapid convergence to be close to an expected value, and the response speed of a load is remarkably increased; secondly, the model is further optimized by enhancing a composite weighted human learning optimization network (CWHLO), and the accuracy of the model is improved; and finally, a generalized predictive control (CWHLO-GPC) algorithm based on an enhanced composite weighted human learning optimization network is adopted to control the USC system, so that high-precision load tracking performance is realized, and the problem of slow dynamic response of the ultra-supercritical unit system is solved.

The invention provides a mathematical reasoning data synthesis method and system based on an intelligent agent simulation teaching scene, and relates to the technical field of large language models.The method comprises the steps that a public thinking chain data set is obtained, a large language model with the mathematical reasoning ability to be improved is reasoned on the thinking chain data set, and the mathematical reasoning ability of the large language model is improved; the error rate of the large language model on each question is obtained; creating a multi-role agent, and analyzing the problem of analysis errors of the large language model by using a teacher agent; obtaining an expected reasoning data size of each problem based on the error rate and a preset data set scale; and simulating various teaching scenes by using a multi-role intelligent agent, converting dialogue data in the various teaching scenes into data with the same format as the thinking chain data set, and synthesizing to obtain a mathematical reasoning data set with an expected reasoning data volume. According to the method, the problems of high construction cost, low mass density and serious data homogenization existing in an inference data synthesis method similar to human learning at present are effectively solved.

The application discloses a permanent magnet synchronous motor stator fault diagnosis method and system based on a human learning optimization algorithm, and the method comprises the following steps: obtaining a three-phase current signal of a stator of a permanent magnet synchronous motor, converting the signal into a two-dimensional time-frequency diagram after being decomposed by a variational mode and being demodulated by a Hilbert envelope; constructing a binary neural network for processing the two-dimensional time-frequency diagram and determining a search space; generating a candidate architecture by global search using a first human learning optimization algorithm; for each candidate architecture, fine-tuning the classification layer parameters thereof by proportional evolution using a second human learning optimization algorithm, taking the classification performance of a verification set as a fitness value, and iteratively obtaining an optimal model; inputting a current signal to be diagnosed into the model after the same preprocessing, and outputting a stator fault diagnosis result. Compared with the prior art, the application realizes low-overhead accurate diagnosis of weak faults of a permanent magnet synchronous motor stator by physical information driven preprocessing and double-layer human learning optimization.

1. Name of the product in this design: Desk (6120 extension). 2. Purpose of this design: For human learning purposes. 3. The key design feature of this product is its shape. 4. The picture or photo that best illustrates the key design points: Design 1 3D diagram 1. 5. Design 1 is designated as the basic design.

1. Name of the product in this design: Desk (5672). 2. Purpose of this design: For human learning purposes. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1.

The present invention belongs to the field of organic optoelectronic materials and relates to an optoelectronic device, which includes an anode, a hole transport layer, an active layer, an electron transport layer, and a cathode arranged in sequence. The active layer material is a mixture of a donor material PM6 and an acceptor material BSeC8-4F in a ratio of 1:1 to 1:1.5. The organic solar cell based on the optoelectronic device of the present invention achieves an energy conversion efficiency of 16.51%; the organic photodetector obtains a sensitivity of 0.504 A / W; the organic optoelectronic synapse can simulate human learning behavior.

The invention discloses a large language model training method, device and equipment applied to a professional field and a storage medium, and the method comprises the steps: obtaining a related document of a current field, and carrying out the chapter splitting of the related document, and obtaining a plurality of text blocks; generating a plurality of structured question and answer pairs based on each text block, wherein each structured question and answer pair comprises questions and answers corresponding to the document chapters to which each text block belongs; and inputting each text block and each structured question and answer pair into a basic language model, and performing iterative training on the basic language model according to a preset progressive fine tuning strategy to obtain a target large language model. The domain document can be subdivided according to chapters and sections, structured question and answer training is performed on each text block, and then the model is trained by simulating a human learning process through the preset progressive fine tuning strategy, so that terminologies and concepts can be integrated step by step and iteratively; therefore, the knowledge adaptability of the model in the specific field is remarkably improved.

The application discloses a kind of fusion course learning strategy's pulse neural network optimization method, including based on the training sample in training set to the initialized pulse neural network is trained, obtains prediction result;The prediction result is compared with the sample label in training set, and confidence loss is calculated;With confidence loss minimum as objective function, layer by layer forward derivation is carried out, and the parameter of each neuron in pulse neural network is updated;The parameter of optimization pulse neural network is constantly updated, until the iteration of the set round is completed.The application introduces course learning in pulse neural network, dynamically evaluates the difficulty of sample in the training process, expands the contribution of relatively simple sample in back propagation to the current state of model, and reduces the influence on parameter update for the current relatively difficult sample.The pulse neural network optimization strategy has high biological rationality, effectively realizes the process of simulating human learning new knowledge in pulse neural network.

1. Name of the product in this design: Study Desk (A13XT3406). 2. Purpose of this design: For human learning purposes. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1.

Anthropogenic heat has a significant impact on urban climate and air quality, but there is currently a lack of accurate and efficient estimation methods for multi-source anthropogenic heat. The present invention improves the process of anthropogenic heat modeling and proposes a multi-source anthropogenic heat spatiotemporal quantification method based on machine learning. The method comprises the following steps: step 1) calculating the county-level annual average anthropogenic heat flux (AHF) based on energy consumption and socioeconomic data; step 2) using alternative data to perform time dimension downscaling for anthropogenic heat from different sources to obtain the county-level monthly average AHF; step 3) calculating the monthly county-level average of anthropogenic heat-related multi-source data as explanatory variables, and forming training samples with the corresponding AHF; step 4) training models based on two machine learning algorithms, gradient boosting regression tree and Cubist, and performing error analysis to select the optimal algorithm modeling for different heat sources; step 5) inputting specific raster data into the optimal model to calculate the multi-source anthropogenic heat flux in a specific area at a specific time.

The application provides a kind of mathematical reasoning data synthesis method and system based on agent simulation teaching scene, it is related to big language model technical field, method includes: obtaining public thought chain data set, the big language model to be promoted mathematical reasoning ability is reasoned on thought chain data set, and the error rate of big language model on each question is obtained;Create multi-role agent, use teacher agent to analyze the problem of big language model analysis error;Based on the expected reasoning data amount of each question of error rate and preset data set size;Use multi-role agent to simulate multiple teaching scenarios, and convert the dialogue data in multiple teaching scenarios into the same data as the thought chain data set format, and synthesize the mathematical reasoning data set of the expected reasoning data amount.The application effectively solves the problems of high construction cost, low quality density and serious data homogenization in the current analogy human learning reasoning data synthesis method.

The present invention belongs to the field of organic / polymeric information storage devices, and specifically provides a poly(chalcogeno-viologen-triphenylamine) material-based polymer memristor for biological synapse simulation and neuromorphic computing and its preparation. The device structure is a classic sandwich structure, with the bottom electrode being ITO, the active layer being a PCVTPA thin film containing redox structural units of viologen and triphenylamine bridged by chalcogen elements (S, Se, Te) (including PSVTPA, PSeVTPA, PTeVTPA), and the top electrode being Al. By applying a continuously scanned cyclic voltage to the device, its current-voltage curve exhibits memristive performance based on history dependence, which can be used to simulate synaptic potential / inhibition, human learning and memory functions, the transition from short-term synaptic plasticity to long-term plasticity, and can also perform decimal arithmetic functions.

1. Name of the product in this design: Storage Desk (T07XX4803). 2. Purpose of this design: For human learning purposes. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D rendering 1.

The present invention discloses a green dynamic multi-objective scheduling method for a flexible assembly workshop under the human learning effect, and relates to the technical field of workshop scheduling. Based on the green dynamic multi-objective scheduling requirements of a flexible assembly workshop under the human learning effect, the present invention establishes a multi-objective dual-agent planning model. Under the dual resource constraints of machines and personnel, the model's dynamic multi-objective scheduling problem is solved based on a two-layer deep reinforcement learning framework method. The state space and action space are designed based on the workshop simulation environment, and a reward function combining immediate rewards and round rewards is combined. The agent interacts with the scheduling environment to obtain a more optimal scheduling rule at the scheduling point. Through the above method, the present invention improves the decision-making efficiency of manufacturing enterprises, can adaptively and quickly generate a more optimal solution, effectively reduce losses caused by delay time, and reduce energy consumption, while also having certain generalization and stability.

This invention discloses a cross-scenario autonomous driving decision-making method based on adaptive perception. This invention effectively transforms complex environmental information into basic scenarios and makes decisions based on these scenarios. Compared to traditional autonomous driving technologies, this invention shows significant advantages in complex traffic environments. When facing unfamiliar scenarios, this invention can utilize existing training experience and transformed perception images, reducing reliance on large amounts of data and long training times. By simulating the human learning and driving process, this invention enables the autonomous driving system to make accurate decisions using existing training knowledge in unfamiliar scenarios, thus avoiding dependence on large amounts of training data and long training times. Through this adaptive perception mechanism, it can also process and transform bird's-eye view images of varying complexity, providing more easily understood input to the decision-making module, resulting in a more efficient and adaptable autonomous driving solution.

The application relates to a four-legged robot motion control method based on a guided human learning optimization algorithm, which comprises the following steps: initializing a real number population of a continuous human learning optimization algorithm; controlling a four-legged robot to collect state transition data through a lower-layer proximal policy optimization algorithm; decoding a current candidate individual into a shaping reward weight value, constructing a total reward function with a fixed weight basic reward, and calculating an instant reward value; updating neural network weight parameters; after a preset gradient update period, collecting simulation trajectory data and calculating a comprehensive motion performance fitness value, and feeding back to an upper-layer algorithm; the algorithm updates a knowledge base and generates a next-generation candidate individual; whether a maximum iteration number is reached is judged, if not, iteration is continued, and if yes, an optimal shaping reward weight combination and corresponding neural network weight parameters are output. Compared with the prior art, the application has the advantages of high robustness, strong self-adaptation and good convergence.

Data-dependent node-to-node knowledge sharing to increase the interpretability of the activation pattern of one or more nodes in a neural network, is implemented by a set of knowledge sharing links. Each link may comprise a knowledge providing node or other source P and a knowledge receiving node R. A knowledge sharing link can impose a node-specific regularization on the knowledge receiving node R to help guide the knowledge receiving node R to have an activation pattern that is more easily interpreted. The specification and training of the knowledge sharing links may be controlled by a cooperative human-AI learning supervisor system in which a human and an artificial intelligence system work cooperatively to improve the interpretability and performance of the client system.

The invention discloses an optimization learning method based on a memory model, and the method comprises the steps: constructing a long memory learning model based on fractional differential; constructing a short memory model based on the long memory learning model and the attenuation characteristics; discretizing the short memory model to obtain a discrete memory model; and based on a particle swarm optimization algorithm and the discrete memory model, optimizing the memory parameters, and obtaining a memory optimization model. According to the method and the device, the memory learning of people is expanded to machine learning on the basis of memory characteristics based on the learning of people, so that the machine learning has better convergence and better learning speed at the same time. According to the method, the historical information is weighted according to the memory characteristics by utilizing the memory attenuation characteristics, the weight of the historical information exceeding a certain length is relatively small and can be ignored, and the learning speed and the learning efficiency are both considered.

1. Name of the product in this design: Desk with cabinet (X18XX3000). 2. Purpose of this design: For human learning purposes. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1.