64 results about "Real time learning" patented technology

The invention relates to the field of resource optimization, and discloses a supply chain full-link-oriented logistics resource optimization and matching method and system, and the method comprises the steps: generating a multi-dimensional logistics state feature vector according to full-link multi-source data of a target supply chain, constructing a multi-target optimization model according to a fuzzy inference rule and a fuzzy weight system, and carrying out the optimization of the multi-target logistics state feature vector; performing preliminary matching degree analysis on the multi-dimensional logistics state feature vector, performing resource allocation on a target supply chain by using a preliminary logistics resource allocation scheme generated according to a comprehensive matching score, and performing weight online learning and dynamic self-adaptive adjustment on a fuzzy weight system according to a performance error value of an actual performance parameter value, so as to obtain a multi-dimensional logistics resource allocation scheme; and obtaining a target matching weight system, optimizing the preliminary logistics resource allocation scheme, and matching the logistics resources of the target supply chain to obtain a target resource matching result. According to the invention, in a dynamic scene of a full link of a supply chain, real-time learning of a multi-target tradeoff relation and adaptive updating of a fuzzy weight can be realized.

The invention provides an artistic course personalized learning path method and system based on deep learning. Firstly, an artistic course learning basic information set of a learner and a preset artistic course module library are acquired; calling a pre-trained deep learning course dynamic association model to generate association strength description of the learning basis of the learner and each course module; screening and sorting based on association strength description to form an initial learning module sequence; acquiring a real-time learning behavior data set of the first course module learned by the learner, and generating a module adjustment signal; and adjusting the initial learning module sequence according to the module adjustment signal to obtain a personalized learning path adaptive to the real-time learning state of the learner, and generating a personalized learning path document comprising a course module learning sequence and module connection guidance, thereby realizing accurate customization and dynamic optimization of the learning path, and improving the learning efficiency. And the learning effect of artistic courses is improved.

The invention provides a power grid standard intelligent recommendation method based on reinforcement learning and post system management. The power grid standard intelligent recommendation method comprises the following steps of 1, collecting and cleaning power grid standard data; step 2, post-standard system knowledge graph construction; 3, designing a reward function for the power grid standard recommendation system, and realizing a personalized recommendation strategy by taking post responsibilities and skill levels as dynamic weight parameters; and step 4, post-driven online incremental training is carried out. According to the method, a reinforcement learning dynamic optimization engine is adopted to learn user behaviors (click rate and task completion score) in real time, and a standard recommendation strategy is adjusted; and when the standard is updated, the post capability weight is automatically adjusted, closed-loop feedback optimization is realized, and the problem of updating delay of a traditional system is solved.

The invention relates to the technical field of large language models, in particular to an AI large model course recommendation and adaptive learning path optimization system for multi-dimensional learning condition analysis. Comprising a learning condition data processing unit; a multi-dimensional learning condition analysis unit; an AI large model course recommendation unit; and an adaptive learning path optimization unit. According to the method, through a matching degree calculation module and a parameter optimization module of an AI large model course recommendation unit, cosine similarity is calculated based on course joint features and learning condition features, dynamic matching degrees are obtained in combination with course-geographical attention weights, courses with the dynamic matching degrees larger than a threshold value are screened, and the first N courses are taken in a descending order to generate a personalized recommendation list; and then real-time learning effect data when the user learns the recommendation list is received, the model parameters are iteratively updated by adopting an Adam optimizer after the optimization loss is constructed, and the problem of lack of iterative optimization of the model parameters based on the real-time learning effect data in the prior art is solved.

The invention relates to the technical field of intelligent education planning, and discloses a dynamic course planning method based on a knowledge graph. The method comprises the following steps: acquiring real-time learning data including knowledge point mastering degree, learning behavior and progress; and performing association analysis on the data by using the subject knowledge graph to generate a learning state representation vector reflecting knowledge point association strength and path dependency degree. And inputting the vector into a course planning model for calculation to obtain an adjustment scheme containing the knowledge points to be strengthened, the path rearrangement sequence and the resource index. According to the scheme, the node weight of the corresponding learner in the knowledge graph is updated, and a dynamically evolved personalized knowledge graph is formed. And generating a next-stage learning task instruction based on the graph, wherein a logic mapping relationship between the to-be-learned knowledge point sequence and a preset learning target is clearly revealed. According to the method, structured traceability and diagnosis of learning weak links are realized, and an interpretable personalized learning path with a clear logic basis can be provided.

The invention discloses a large language model generative recommendation method based on self-adaptive reflection mechanism driving, and relates to the technical field of recommendation. The method comprises the steps of performing online real-time learning on behavior data of a user, and determining an initial recommendation result through a large language model; performing automatic feedback learning through the initial recommendation result, and calculating a three-layer reflection score and a comprehensive reflection score; according to the three-layer reflection score and the comprehensive reflection score, executing total regeneration or local regeneration on the initial recommendation network, and regenerating an initial recommendation result; the newly generated initial recommendation result is evaluated again, a new comprehensive reflection score is determined, and if the new comprehensive reflection score is smaller than a comprehensive score threshold value, local fragments of the initial recommendation result are optimized, and a local generation result is obtained; and carrying out weighted fusion on the local generation result and the newly generated initial recommendation result to obtain a global recommendation result. According to the method, the recommendation efficiency can be improved while the recommendation precision is ensured.

The invention discloses a medical instrument supply chain tracing management system, and relates to the technical field of supply chain management, and the system comprises a supply chain management platform which is in communication connection with the following modules: a twinning perception intelligent control module which integrates a digital twinning and depth Q network, constructs a dynamic virtual mapping of a medical instrument supply chain transportation environment, and provides a dynamic virtual mapping module for a medical instrument supply chain. Environmental parameter changes are learned in real time, the in-transit state of the medical instrument is simulated, and risks are predicted. According to the method, the transportation environment virtual model is established, real-time and dynamic mapping and visual monitoring of the in-transit state of the medical instrument are achieved, a deep reinforcement learning algorithm is integrated, the quality risk in transit can be autonomously predicted based on historical and real-time environment data, an accurate regulation and control instruction is generated, and the transportation efficiency is improved. According to the method, cold chain equipment is actively adjusted, an alarm is triggered or a transportation path is optimized, a traditional passive and lagged monitoring mode is converted into self-adaptive intelligent regulation and control, and the quality guarantee capability and risk response efficiency of a transportation link are improved.

The invention discloses an intelligent self-adaptive learning method and system based on a course knowledge graph, and aims to construct a comprehensive knowledge graph through deep analysis of course contents, and the comprehensive knowledge graph comprises knowledge points, dependency relationships among the knowledge points, difficulty levels and learning sequences. By collecting and analyzing the learning behavior data of the students, the system can evaluate the mastering condition of the students on each knowledge point in real time, and further dynamically adjust learning paths and recommendation resources according to the individual requirements of the students. The system adopts an adaptive algorithm, optimizes a learning path and provides personalized learning resources according to the real-time learning progress and feedback of the students, so as to help the students to efficiently master knowledge in the shortest time. Meanwhile, the system further integrates a learning effect evaluation and feedback mechanism, and the accuracy and the intelligent degree of the learning scheme are gradually improved by continuously monitoring the learning process of the students.

The invention relates to the technical field of nuclear power plant automatic control and fluid regulation, in particular to a nuclear power plant condensation water regulating valve automatic control system which comprises a sensor data acquisition and synchronization module which acquires and synchronizes parameters in a nuclear power plant condensation water system; the reinforcement learning control module reads parameters of the sensor data acquisition and synchronization module, and generates a regulating valve control strategy by using a reinforcement learning algorithm; the real-time prediction and control decision module controls and predicts the opening degree of the condensed water regulating valve according to the regulating strategy of the reinforcement learning control module; and the anomaly detection and safety protection module reads the parameters acquired by the data acquisition and synchronization module, monitors the parameters and gives an alarm according to an anomaly monitoring result. According to the system, valve oscillation and unreasonable adjustment in a traditional method can be avoided while a valve adjustment strategy is learned and optimized in real time, and the precision and stability of condensed water flow adjustment are improved.

The invention belongs to the technical field of English teaching methods, and particularly relates to an intelligent English teaching method and system and a storage medium, and the method comprises the steps: constructing a multi-dimensional linguistic feature analysis model, and extracting lexical features, syntactic relationship features and semantic deviation features in a text input by a student through a natural language processing technology; dynamic student portraits are established based on the cognitive psychology theory, cognitive level labels are updated according to real-time learning data, and the data comprise grammar error clustering distribution, spoken language fluency indexes and vocabulary association response time; and generating a personalized teaching path, matching teaching materials from the hierarchical resource library according to the cognitive level label, and dynamically adjusting the complexity and presentation form of a teaching strategy. Lexical, syntactic and semantic deviation features are extracted through a natural language processing technology, student error types can be accurately positioned, the problem that traditional error correction only stays on surface modification is avoided, and cognitive tags are updated based on real-time learning data.

The present application relates to the technical field of large language model, specifically, to an AI large model course recommendation and adaptive learning path optimization system for multi-dimensional academic situation analysis, comprising: an academic situation data processing unit; a multi-dimensional academic situation analysis unit; an AI large model course recommendation unit; and an adaptive learning path optimization unit. Through the matching degree calculation module and the parameter optimization module of the AI large model course recommendation unit, the cosine similarity is first calculated based on the course joint features and the academic situation features, the dynamic matching degree is obtained by combining the course-geographical attention weight, the courses with a dynamic matching degree greater than a threshold value are screened, the top N personalized recommendation list is generated in descending order, and then the real-time learning effect data of the user learning the recommendation list is received, the model parameters are iteratively updated by using the Adam optimizer after constructing the optimization loss, and the problem of lacking iterative optimization of model parameters based on real-time learning effect data in the prior art is solved.

The invention provides an intelligent temperature control method for an injection molding machine. The intelligent temperature control method comprises the following steps: S1, collecting data to obtain a data set; s2, training a miniature neural network model according to the data set; s3, exporting the trained miniature neural network model, and deploying the miniature neural network model to the temperature controller; s4, reading data and inputting the data into the miniature neural network model; and S5, the micro neural network model outputs a duty ratio and outputs the duty ratio to a PWM controller, and then a heating ring on a charging barrel of the injection molding machine is automatically regulated and controlled to accurately operate according to the duty ratio. The micro neural network model is mainly introduced on the basis of a traditional injection molding machine temperature control system, and accurate control over heating of the injection molding machine charging barrel is achieved through real-time learning and adjustment. According to the system, by automatically adjusting the duty ratio and combining the actual temperature and the target temperature, the limitation that a traditional control method depends on fixed parameters is overcome, and therefore the heating process can be stably operated under various complex environment conditions.

The invention discloses an educational guidance scheme generation method and device based on causal inference, relates to the technical field of data mining, can be applied to the educational field, and mainly aims to solve the problem that a personalized educational guidance scheme lacks pertinence and effectiveness. The method mainly comprises the steps of constructing a feature marker causal relationship matrix; obtaining a target feature matrix, a target learning state marking matrix and real-time learning feedback data of the target education object; performing high-dimensional embedding representation learning on the target feature matrix to obtain a high-dimensional embedding representation matrix, and fusing the high-dimensional embedding representation matrix with the target learning state marking matrix and the target feature matrix to obtain a feature marking mapping matrix; generating an initial education guidance scheme through a high-dimensional geometric variational generation network according to the high-dimensional embedded representation matrix and the feature mark mapping matrix; and optimizing the initial education guidance scheme according to the real-time learning feedback data to obtain a target education guidance scheme. The method is mainly used for generating education guidance schemes.

The invention relates to the technical field of online education, in particular to a network course personalized recommendation path generation system, which comprises a student portrait module, a course knowledge balance weight module, a course path cluster module and an optimal course generation module: the student portrait module collects static and dynamic characteristics, and generates a standardized characteristic set through mutual information screening; a course knowledge counterweight module generates a standardized course feature vector, predicts the future learning demand intensity of the student, and calculates a course resource allocation coefficient in combination with a real-time learning load and a historical peak value; the course path cluster module outputs an initial course recommendation path set through a longest path greedy algorithm and reinforcement learning; and the optimal course generation module obtains a forgetting attenuation item and an interest matching item based on the cognitive state evaluation model, and embeds multi-objective optimization to generate an optimal course path. The system realizes personalized course path recommendation, and adapts to cognitive rules and learning requirements of students.

The present application relates to the technical field of teaching quality evaluation, in particular to a service quality dynamic evaluation method for an online teaching platform, comprising: collecting learning behavior data of an online education platform based on the scene of teaching task access; decomposing the obtained learning behavior data in multiple modal scenes to determine the scene feature matrix under each scene; integrating real-time learning behavior data based on the scene feature matrix under each scene to determine the real-time interaction degree of learning behavior, and constructing a learning behavior portrait according to the response time under real-time interaction; calculating the group response time of each teaching task based on the obtained learning behavior portrait, and determining the interaction mode exhibited by the teaching task according to the task completion status corresponding to the teaching task; and based on the interaction mode exhibited by the teaching task, using the isolation forest algorithm for time series regression verification to determine the evaluation score of each user. The efficiency and accuracy of data processing are improved.

The invention provides a dynamic CAN bus protocol confusion system and method based on artificial intelligence, and the system comprises a lightweight AI inference engine which is disposed in a gateway chip; the LSTM model is coupled with the lightweight AI inference engine and is used for learning a CAN bus normal flow mode in real time and outputting a dynamic confusion rule; the message ID dynamic generation module is used for generating a message ID in real time according to a dynamic confusion rule; and the load field confusion module is used for carrying out dynamic encryption and filling processing on the load of the CAN message according to the dynamic confusion rule. The technical problems that a static encryption or fixed authentication mechanism needs to store a large number of secret keys at each ECU node, so that the storage overhead is large, the secret key distribution time is prolonged, and the dynamic network environment is difficult to adapt are solved.

The invention relates to an intelligent reading recommendation method and system based on dynamic learning ability evaluation, and relates to the field of intelligent education technology.The method comprises the steps that current scanning content is extracted based on scanning behavior data, knowledge content mastered by a user is recognized in combination with historical learning records, and the knowledge content is removed to obtain an unmastered knowledge range; analyzing the current scanning content to identify knowledge entries and evaluating the learning difficulty of the entries; based on historical learning records and knowledge entries, evaluating expected time required for understanding the current scanned content; determining an actual understanding time based on the scanning behavior data; the real-time learning ability of the user is generated in combination with the actual understanding time, the expected time and the entry learning difficulty; and generating learning recommendation content based on the real-time learning ability and the unmastered knowledge range, and performing content recommendation based on the learning recommendation content. The method has the effect of improving the learning efficiency and experience of the user.

A data organizer, optimizing, reconciliation system (DOORS) / method / program, provides capability to merge intuitively datasets created over users' digital lifetimes from multiple devices. Finds and gathers files from devices and may create master copies in Cloud or local storage. Enhanced functionality via artificial intelligence or machine learning provides more intuitive merging of datasets including file and folder name selection and may operate autonomously at times of low usage. Optimized by learning from training data, or legacy data, or learning in real time from user preferences, practices, and habits. Reducing loses of treasured photographs and important documents via preventing files getting marooned on inaccessible legacy devices. Because devices get lost, replaced, or may suffer ransomware attacks or may need to be re-set and suffer data loss for a variety of reasons. Compatible and useable across the proliferating number of data producing devices, including smart phones, tablets, cameras, and computers.

The invention provides a course planning dynamic optimization method and system based on big data, and relates to the technical field of data processing. The method comprises the following steps: acquiring historical course learning record data of a plurality of users, performing structural difference analysis on a plurality of course units, and constructing a course structural difference matrix about the plurality of course units; constructing a course learning path of each user, determining a plurality of course jump units of each user according to the course learning paths, and extracting learning behavior fluctuation characteristics of each course jump unit; determining individual jump influence weights of the plurality of course jump units, and constructing a global course jump influence map about the plurality of course units; and after real-time learning record data of the to-be-analyzed user is collected, generating an optimization analysis result of the course planning path of the to-be-analyzed user based on the global course jump influence map. According to the invention, a personalized course planning optimization scheme is provided for the user.

The invention relates to the field of gas concentration detection and intelligent traceability, in particular to a gas traceability trajectory decision-making method based on a pulse neural network, and aims to solve the problems of low gas source traceability precision, slow response and poor adaptability in the prior art. According to the method, a plurality of gas sensors and wind direction sensors are arranged, gas concentration and wind direction data are collected in real time, pulse coding processing is adopted, and the data are converted into pulse signals to be input into a pulse neural network. The spiking neural network adopts a leakage integral and distribution neuron model, and can dynamically adjust the moving direction of the equipment according to the change of gas concentration and wind direction data. By training the neural network, the network can learn and make decisions in real time, and the equipment is controlled to accurately track the gas source along the gas concentration gradient. According to the method, through multi-sensor data fusion and real-time learning, the unmanned equipment can quickly adapt to and accurately execute a gas source tracing task in a complex environment, and the precision and efficiency of gas tracing are remarkably improved.

The invention is applicable to the technical field of wireless communication, and provides a high-reliability language signal transmission system, which comprises at least one user terminal and at least one relay station, the relay station comprises a signal receiving module, a signal processing module, a routing decision module and a signal transmitting module, the signal processing module adopts a decoding and forwarding strategy, and the signal transmitting module adopts a decoding and forwarding strategy. The routing decision module dynamically selects an optimal next-hop path according to preset or real-time learned network topology information, channel quality information and relay station load state information, and the signal transmitting module recodes and transmits regenerated signals according to a path and parameters specified by the intelligent routing decision module. According to the method and the system, noise is prevented from being amplified step by step, the end-to-end voice quality is ensured, dynamic routing selection can be automatically switched to a standby path when a certain path is interrupted or the quality is deteriorated, and multi-path redundant backup is provided.

Methods for controlling a mobility device are presented, the method including: providing the mobility device; selecting a mode of operation; and operating the mobility device in accordance with the selected mode. In some embodiments, the mode of operation is selected from the group consisting of: a learning mode, a novice mode, a standard mode, an advanced mode, and a default mode. In some embodiments, when the learning mode is selected, operating the mobility device includes: collecting real-time learning data for a learning interval; slotting the real-time learning data; averaging the real-time learning data; training a learned anomaly detection model; and establishing the novice mode, the standard mode, and the advanced mode.

The invention relates to a control method and device for a compressed air energy storage power station. The method comprises the steps that operation parameters of all components of the compressed air energy storage power station are collected in real time; the collected operation parameters are preprocessed; constructing a deep fusion network; establishing a dynamic parameter adjustment basic model based on a physical model; learning an optimal control strategy in real time; correcting and optimizing the basic model; establishing a nonlinear mapping relation of the rotating speed of the compressor; determining a division standard and characteristic parameters of each working condition; performing identification processing on the current working condition; judging the type of the current working condition and performing adjustment processing; the equipment is controlled in real time; calculating the value of each performance index; the power grid frequency and phase are monitored and adjusted in real time to ensure stable and reliable grid connection; the control strategy is automatically adjusted and processed; and fault information and an adjustment strategy are recorded in real time, and reference processing is provided for subsequent fault diagnosis and maintenance. According to the invention, equipment control is more accurate, and the operation performance of the compressed air energy storage power station is effectively improved.

The invention relates to the technical field of online education. The online education method and device based on the mathematical model, the equipment and the medium are provided, and the method comprises the steps that test sequence construction processing is carried out according to a preset educational psychology forgetting curve parameter library, and an antagonism evaluation sequence is generated; performing model compression processing on the knowledge state prediction model to generate a lightweight knowledge tracking model; inputting the antagonism evaluation sequence into a lightweight knowledge tracking model to carry out long-interval forgetting sensitivity test processing, and generating a long-term forgetting sensitivity attenuation rate; performing compression parameter adjustment processing according to the long-term forgetting sensitivity attenuation rate to generate a fidelity compression model; and performing real-time learning behavior data processing through the fidelity compression model to generate an anti-forgetting learning path so as to achieve the technical effects of improving the prediction fidelity of the compression model for the long-interval forgetting characteristic, optimizing the prediction accuracy of the knowledge point long-term memory state and realizing the dynamic anti-forgetting learning path adaptive to the individualized forgetting difference.

The invention discloses an MOOC course random topic generation and learning effect evaluation method, system and device and a medium, and the method comprises the steps: carrying out the transcription of audio content in a teaching video through calling a voice recognition Whisper model, and generating text data with a timestamp; on the basis of the transcribed text data, key knowledge points and learning key points in the video are dynamically extracted by using a pre-trained large language model, random questions conforming to a teaching target are generated, question setting time is assigned for each question, and the timeliness of the questions and video content is ensured to be matched with the learning state of students; and according to the real-time learning progress, the answering performance and the video content of the student, the course completion condition of the student is monitored and evaluated in real time. According to the method, the questions are dynamically generated by using the large language model, synchronous matching of learning contents and evaluation is realized, and the teaching flexibility and the learning effect are improved. The method can be widely applied to the field of online education and intelligent teaching.

The embodiment of the application provides a model training method and device based on dynamic rank adjustment and electronic equipment, wherein the rank value of the weight adapter injecting the pre-training weight matrix is dynamically adjusted according to the process of model training, wherein a first rank value is configured in the initial training stage, and a second rank value higher than the first rank value is configured in the later training stage; the singular value spectrum is dynamically reweighted through a task perception network, and the matrix parameters of the weight adapter are initialized by using the reweighted singular value spectrum, wherein the singular value spectrum is obtained by singular value decomposition of the pre-training weight matrix. Through the combination of dynamic rank control, task perception initialization and rank adaptive training, the model can dynamically adjust the rank value according to the training stage, task characteristics and real-time learning state in the fine-tuning process, so as to realize the optimal balance between suppressing overfitting and relieving underfitting, thereby significantly improving the training efficiency and model generalization performance.

This invention discloses an energy feedback algorithm for predicting deadbeat current. The energy feedback algorithm includes a deadbeat current prediction control algorithm, a voltage PI regulator, and a power grid self-learning algorithm. Specifically, it includes the following steps: S1, sampling the A and B phase currents of reactor L1. A i B and the DC voltage V on the bus side DC S2. Based on the coordinate transformation method from a three-phase coordinate system to a two-phase stationary coordinate system, calculate the actual two-phase current i in the two-phase stationary coordinate system. α i β This invention employs a deadbeat current prediction-based energy feedback algorithm, eliminating the need for a grid voltage detection device. It can learn the grid voltage and phase in real time and use the sampled voltage loop PI regulator output to control the magnitude of the feedback current.

The application relates to the technical field of intelligent evaluation, and particularly discloses a dynamic optimization method of an intelligent evaluation model based on reinforcement learning, which fine-tunes a basic intelligent evaluation model and general parameters thereof according to historical interaction data of a student object, performs prediction on current interaction data of the student object by using updated model parameters, calculates a benchmark prediction error between a benchmark prediction result and actual interaction, integrates recent performance statistical characteristics of the student object and current individualized adjustment parameters as a current reinforcement learning (RL) state, selects an adjustment action by using an RL Agent policy network, and calculates and updates the individualized adjustment parameters of the student object based on the adjustment action. The method performs individualized adjustment on the real-time learning state of each student, guarantees the stability and generalization ability of the basic model, and realizes rapid response and targeted adjustment on the state change of the student.

Disclosed herein is a method for learning to drive growing autonomous vehicles in real time based on driver interaction, which includes (a) an autonomous vehicle performing autonomous driving learning based on driving guidance information generated using information received from a driving expert, (b) the autonomous vehicle performing external driving environment recognition matching on a result of recognition of a recognition system and a result of recognition of the driving expert, and (c) the autonomous vehicle performing reviewing and learning after driving training to improve a level of autonomous driving.

The invention provides an intelligent emotional virtual human customer service system based on virtual reality and artificial intelligence technology, which comprises a virtual human display module used for creating a virtual human image, a voice recognition and text processing module used for converting voice input into a text and analyzing and understanding the text, and an emotion analysis module used for analyzing the text and analyzing the text. The system comprises a customer service strategy analysis module used for judging the emotional state and emotional intensity of a customer and adjusting a customer service strategy and a response mode according to an analysis result, a dynamic customer service strategy adjustment module used for dynamically adjusting the customer service strategy according to the emotional state of the customer and an identified demand, and a personalized recommendation module used for analyzing customer behavior data based on a customer historical record and a current demand. And a personalized product or service recommendation, real-time learning and optimization module is provided for automatically adjusting and improving customer service strategies through a customer feedback mechanism and improving the overall service quality and customer satisfaction. According to the invention, by constructing the intelligent emotional virtual human customer service, efficient, emotional and personalized customer service is realized.