131 results about "Learning resource" patented technology

The invention discloses a personalized learning resource recommendation method and system based on multi-agent collaboration and a dynamic knowledge graph, and the method comprises the steps: constructing the dynamic knowledge graph, enabling nodes to be associated with teaching resources (videos, test questions, teaching plans, PPT and the like), and enabling edges to represent the logic relation between the resources; collaborative decision is made through four layers of agents: a target determination agent generates a learning target based on student historical learning data and a graph node state; the path planning agent plans a learning path in combination with the target and the learner model; the resource screening agent matches personalized resources from the path nodes; the user portrait intelligent agent updates the learner model in real time; and finally, generating a dynamic recommendation result and feeding back the optimized knowledge graph. Through multi-agent hierarchical collaboration and dynamic interaction with the knowledge graph, the problems of cold start, incomplete resource coverage and path stiffness of a traditional recommendation system are solved, and precise and adaptive learning resource recommendation is realized.

The invention relates to the technical field of personalized learning. The method comprises the steps that a learning target and a cognitive state vector serve as joint input information to be sent into a large language model, and a knowledge point set and learning gap information corresponding to the learning target are generated; and aligning the knowledge point set with a pre-repair relationship and a dependency relationship in a preset educational knowledge graph to obtain an alignment result, and when a difference value between the updated cognitive state vector and the cognitive state vector exceeds a preset cognitive state change threshold value, determining a learning target based on the updated cognitive state vector and the learning target. And performing semantic analysis and reasoning of the large language model again to obtain a new knowledge point set, determining a new learning resource sequence according to the updated personalized learning path, and pushing the learning resource sequence to the user terminal. The method has the effect of realizing closed-loop optimization of the learning scheme.

The invention discloses a dynamic learning path planning method and system based on a learner portrait. The method comprises the steps of collecting learning behavior data, learning result data and background attribute data of a target scholar based on a plurality of data sources, and obtaining knowledge point mastery degree vector representation, learning style preference and cognitive ability level to construct a multi-dimensional dynamic portrait of the target scholar; generating an initial personalized learning path of the target scholar based on a preset learning target and the multi-dimensional dynamic portrait of the target scholar; learning process data of a target scholar for related learning resources is monitored in real time, a learning effect evaluation report is generated according to the learning process data, a multi-dimensional dynamic portrait is adjusted to trigger a path replanning mechanism to generate a brand new personalized learning path, and the brand new personalized learning path is pushed. The learning path and the current state of the learner are kept optimally matched all the time, and personalized static planning is upgraded to dynamic syndrome guidance.

The invention discloses a multi-modal learning resource intelligent recommendation method based on an AI large model, and relates to the technical field of educational information, and the method comprises the steps: collecting multi-modal learning resources, carrying out the semantic feature extraction and vectorization representation, and obtaining a structured resource set; constructing a knowledge mastering state vector based on the resource set, and determining a knowledge hole set; virtual nodes are generated according to the knowledge holes, and an enhanced knowledge graph is constructed; calculating semantic path correlation and a path comprehensive score in the enhanced knowledge graph, and screening a candidate resource set; calculating a personalized score based on the candidate resource set, and generating a final recommendation list; and acquiring feedback data of a learner to obtain a learning income index, performing node and edge level attribution analysis, and performing enhanced updating and weight normalization processing on the knowledge graph according to an increment contribution weight to form a new knowledge graph. According to the invention, through knowledge mastering state modeling and map enhancement, automatic identification and dynamic completion of knowledge holes of learners are realized.

The invention relates to the technical field of artificial intelligence and education technology cross fusion, and particularly discloses a new media course intelligent learning resource generation system based on generative AI, and the system obtains the multi-dimensional state data of a learner through the means of eye movement tracking, electroencephalogram collection, interaction behavior analysis and the like, and constructs a high-dimensional state space through fusion; differential induction logic programming and a depth feature extraction network are cooperatively compressed into a low-dimensional semantic meta-state space, and the model interpretability and decision-making efficiency are improved; dynamic matching of personalized resource types and difficulty levels is realized based on a graph neural network and reinforcement learning; calling a multi-modal generation model to generate texts, videos or interactive contents as required, and introducing a cross-modal consistency verification mechanism to guarantee the output quality; the system also has an online adaptive optimization capability, combines a symbol rule recombination mechanism and a differential privacy protection strategy, and takes account of user privacy security while ensuring long-term stable operation of the system.

The invention discloses a personalized learning scheme recommendation method and system based on artificial intelligence, and relates to the technical field of intelligent recommendation, and the method comprises the steps: collecting a learning behavior track and a knowledge mastering progress, carrying out the normalization processing, and generating structural feature input; performing multi-dimensional feature mapping and weight training on the structured feature input by using a reinforcement learning model to generate a learning preference vector; matching the learning preference vector with the weighted feature interaction matrix, calculating an adaptive score, and generating a candidate resource set; and performing iterative fusion on the candidate resource set and the real-time interaction feedback vector to generate a feedback fusion adaptive score matrix, updating adaptive scores by adopting a dynamic adjustment method, forming an optimized resource sequence, converting the optimized resource sequence into a task execution path, and generating personalized learning scheme recommendation. According to the invention, the accuracy of learning resource matching and the timeliness of personalized recommendation are improved.

The present application belongs to the technical field of resource allocation management, and provides a kind of intelligent campus teaching resource management method and system based on artificial intelligence, comprising: obtaining the learning resource search record in the present stage learning process of student, and the next stage teaching resource allocation situation of school, screening out main learning resource, according to the search record to carry out search effective frequency analysis, obtain search effective value, carry out search conversion analysis of main learning resource, obtain search conversion value, and determine search dominant platform and non-search dominant platform in combination with the reserve proportion of main learning resource in each resource platform, integrate to obtain search conversion platform group, carry out search jam risk analysis to search channel, judge whether conversion channel allocation is needed, if needed, according to search conversion record and conversion nearby analysis, in combination with search conversion value, conversion channel is distributed, which is beneficial to the rational allocation of teaching resources and improves resource utilization.

The invention discloses a training content planning and checking method and device and a medium, and the method comprises the steps: carrying out the data collection of a student according to a preset data type, so as to obtain multi-modal data corresponding to the data type, carrying out the feature extraction of the multi-modal data, so as to obtain a data feature, and determining a student portrait according to the data feature; determining a learning target according to the trainee portrait, determining knowledge graph navigation according to a predetermined knowledge dependency relationship and the learning target, and calling a resource library according to the knowledge graph navigation to obtain learning resources; and determining knowledge points according to the knowledge graph navigation, determining an assessment standard according to the knowledge points and the trainee portrait, assessing the trainee according to the assessment standard, and obtaining an assessment result. From data acquisition to assessment result acquisition, the system can accurately adapt to trainees, scientifically plan learning and reasonably assess and evaluate, and effectively improves the training effect and the learning efficiency of the trainees.

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 discloses a virtual power plant resource aggregation method and system based on a multi-relation space-time diagram neural network. The method comprises the steps of collecting operation characteristic data of adjustable resources and constructing a space-time data set; constructing a plurality of adjacent matrixes according to the geographical distance, the electrical distance and the historical correlation among the resources; inputting the spatio-temporal data set and the adjacent matrix into a multi-relation spatio-temporal diagram neural network, extracting spatio-temporal features through spatio-temporal convolution and diagram convolution, and performing multi-relation spatial dependence modeling; performing adaptive weighted fusion on the features under different relationships by using an attention mechanism to obtain a resource aggregation feature; based on the training model, learning a resource spatio-temporal evolution law to predict an aggregation power curve, and performing risk assessment in combination with confidence interval analysis; and finally outputting a power prediction result and a confidence interval thereof to provide decision support for market bidding. According to the method, the multivariate relationship is deeply fused, the uncertainty can be accurately quantified, and the precision of resource aggregation description and the decision reliability are remarkably improved.

The invention discloses a learning recommendation method and device based on education meta universe and knowledge tracking, and relates to the technical field of meta universe learning application. The method comprises the following steps: data collection and arrangement: continuously collecting learning behavior data of students on a platform by using various sensors and interactive interfaces in the education universe platform, collecting basic information of the students at the same time, and carrying out classified storage on the collected data according to a time sequence and a data type. Through comprehensive collection of student learning behavior data, basic information and intelligent interaction feedback, in combination with a knowledge tracking model and a comprehensive evaluation method, student knowledge states can be accurately evaluated, recommendation contents are screened and individually sorted according to evaluation results, students can obtain learning resources most suitable for themselves, and learning efficiency is improved. And the recommended contents are screened and individually sorted according to the evaluation result, so that the students can obtain learning resources most suitable for themselves, and the learning efficiency is remarkably improved.

The invention discloses a learning resource recommendation system based on deep learning, and relates to the technical field of resource recommendation, an online learning service module is arranged to provide online learning resource watching service for students, and a monitoring and recording module is arranged to record pull-back operation executed by learning resources. A pull-back analysis module is arranged to analyze pull-back monitoring data for all learning resources; in the analysis process, aiming at any learning resource, all knowledge points with recommendation qualification in the learning resource are judged by analyzing a plurality of knowledge points involved when the student executes the pull-back operation on the learning resource and the data capacity of the teaching video of the knowledge points; the online learning service module recommends the corresponding knowledge points to the students for all the knowledge points with the recommendation qualification in the learning resource playing process, so that the problem of time waste caused by repeatedly pulling back the same section of low-efficiency explanation by the students can be effectively reduced, and the students are helped to improve the learning efficiency.

The invention relates to an asynchronous federated learning method and system, and the method comprises the steps: firstly, obtaining the prediction training time of a client through employing an exponential smoothing method in combination with anomaly detection and mutation detection according to the federated learning reality conditions of data isomerism, system isomerism and the like; secondly, utilizing a dynamic threshold segmentation algorithm and Monte Carlo simulation to obtain a two-stage waiting time threshold; and finally, the server selects a local model uploaded by the client to perform parameter aggregation in combination with the training time predicted by the client and a two-stage waiting time threshold, and finally forms a self-adaptive federated learning resource scheduling strategy. According to the method, client node resources can be used to the maximum extent at low cost, the global model training efficiency and precision are improved, and the multi-scene adaptability of federal learning is effectively enhanced. Experimental results show that compared with a classical method, the method has higher accuracy.

The application provides a kind of method, equipment and storage medium based on knowledge graph mathematical resource recommendation, and the application relates to the field of online learning and mathematical resource personalized recommendation, which comprises: extracting the application mode of mathematical resources;According to the application mode, a multi-layer knowledge graph is generated;Diagnose the cognitive state of the learner, and plan the learning path according to the weak knowledge attribute of the cognitive state of the learner;According to the generated knowledge graph, the mathematical resources corresponding to the key application mode are found, and the online learners are personalized recommended based on the recent development zone and support degree.The technical effect of the application is that the interrelationship of knowledge attributes in mathematical learning resources is highlighted while ensuring good recommendation, and the corresponding resources are recommended through the application mode, making the recommendation more targeted and effectively helping online learners to flexibly use associated knowledge attributes.

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 a multi-service joint downlink resource allocation method, and belongs to the field of mobile communication; specifically, first, a communication scene including a base station and users is built, and the distance from all users to the base station is recorded in each time slot; then, the transmission model of eMBB users and URLLC users is quantitatively given, the maximum transmission rate of the users is respectively calculated, a neural network model is constructed, and a connection prediction matrix is output; an optimization target is established based on the high reliability requirement of the URLLC service and the high transmission rate requirement of the eMBB service, and a comprehensive decision is made in combination with the connection prediction matrix; finally, a reinforcement learning resource scheduling model is trained based on a Dueling Deep Q-Learning algorithm, the optimization target function is solved, and thus the optimal selection strategy of the URLLC and eMBB service preemption or shared resources is given, and a multi-service joint downlink resource allocation result is obtained; the application fully considers the coexistence problem of the actual communication scene of multi-cell and multi-service, efficiently utilizes the frequency domain resources, and has the significance of meeting the multi-service transmission index.

This disclosure presents a learning material recommendation method, device, and electronic device based on a smart education platform, relating to the field of educational technology. The method includes: acquiring a student's learning trajectory on a learning map; determining multiple knowledge point combinations and weak knowledge point combinations based on the trajectory from clusters of basic and key knowledge points; identifying target learning materials from a learning resource database based on the weak knowledge point combinations; designating these as target learning content; and generating recommendation information. Compared to existing technologies, this disclosure relies on a learning map to acquire a real trajectory, accurately extracting multiple knowledge point combinations, avoiding the limitations of traditional single-knowledge-point recommendations; it filters weak knowledge point combinations through error rate analysis, matches suitable materials, and generates recommendation information, solving the problems of scattered learning content and monotonous question types, helping students focus on core weaknesses, and significantly improving learning efficiency.

The invention relates to the technical field of intelligent analysis of children education data, in particular to a statistical analysis method for use data of a touch and talk pen for children learning behaviors, which comprises the following steps of: acquiring an original use record containing page codes, reading times and timestamps, and generating a structured touch and talk behavior record list through format standardization and content enhancement; quantized results are obtained through content field clustering, reading frequency mode recognition and reading duration stability measurement, the three types of quantized results are input into a behavior feature fusion processor to generate a comprehensive learning behavior feature graph, and a learning state evaluation list with page codes and state quantized values is generated through a learning state evaluation network. And outputting a personalized learning path of the to-be-reviewed content queue and the reading content sequence in the next stage through the learning resource planning derivation device. According to the method, accurate representation of behavior data, multi-dimensional association fusion and page-level learning state quantification are realized, and individual learning behavior characteristics of children are matched.

The application discloses a student programming answer prediction method combining semantic understanding and structured modeling, collects student programming homework data and pre-processes the data to obtain data samples, translates the data samples to obtain an English feature set; uses low-rank adaptation to fine-tune a pre-trained semantic understanding model, constructs input features, and predicts an answer correctness probability; performs graph neural network structured modeling based on the association relationship between problems and concepts, performs message propagation and feature updating to obtain an embedding set, inputs the embedding set and student embedding into a prediction layer to obtain a probability of answering a question correctly; and inputs the probability of answering a question correctly and the probability of answering a question correctly after fusion into a multilayer perceptron for nonlinear mapping to predict the probability of answering a question correctly. The application solves the problems of difficulty in effectively processing non-standardized codes submitted by students, insufficient semantic understanding of question texts and low prediction accuracy in programming knowledge tracking, and provides a scientific basis for personalized teaching and learning resource scheduling.

The invention relates to the technical field of artificial intelligence, and discloses an interactive application management method and system for an intelligent software tutoring learning robot, and the method comprises the steps: analyzing the learning features of a user through the tutoring learning robot, achieving the intelligent grouping of an auxiliary learning group, carrying out the teaching and training distribution, and matching learning resources, the method comprises the steps of analyzing a collaborative task sequence and interaction conditions, collecting interaction data in a tutoring task, analyzing collaborative performance and influence factors thereof, extracting key learning logic key points, and finally updating interaction configuration of a robot according to the key points, thereby optimizing personalized intelligent tutoring for an auxiliary learning group. The collaborative learning efficiency and the user participation degree of the tutoring learning robot can be improved.

Methods, systems, apparatuses, and computer program products are provided for evaluating a resource consumption of a query. A logical operator representation of a query generated to be executed (e.g., obtained from a query generating entity) may be determined. The logical operator representation may be transformed to a plurality of different physical operator representations for executing the query. A plurality of resource consumption models may be applied to each of the physical operator representations to determine a resource consumption estimate for the physical operator representation. The resource consumption models may be trained in different manners based at least on a history of query executions, such that each model may have different granularity, coverage and / or accuracy characteristics in estimating a resource consumption of a query. Based on the determined resource consumption estimates for the physical operator representations, a particular one of the physical operator representations may be selected to execute the query.

The invention discloses a knowledge concept sequence recommendation method and system based on a large language model, and the method comprises the steps: building a learning resource two-way graph attention mechanism, extracting video and knowledge concept features through a graph attention network, and achieving the two-way flowing of the features; constructing a sequence model to extract a hidden layer state of the interaction sequence, and calculating interest scores of the learner, the learning resources and the knowledge concepts; constructing a multi-objective optimization loss function optimization sequence model to generate high-quality cooperation features; designing a mixed prompt template, and aligning the collaboration features to a semantic space of the large language model; constructing a Token-level loss function and a learning resource comparison learning method, and training the recommendation generation capability of the large language model through a course learning strategy; and generating a recommendation list. According to the method, the preference of a learner to knowledge concepts can be mined from a learning resource sequence through two-step training of a sequence model and a large language model, and an efficient solution is provided for a dynamic recommendation system.

The application relates to an AI large model-based multi-modal learning resource intelligent recommendation method and system. The method comprises the following steps: obtaining an encrypted state feature vector generated by an original resource feature extraction and confusion coding of a client, constructing a heterogeneous interaction graph, enhancing the heterogeneous interaction graph through a guided diffusion model, and obtaining an aligned multi-modal resource representation, an updated user interest representation and a user modal preference vector through cross-modal contrast learning; constructing a knowledge graph, updating resource weights from bottom to top based on real-time behaviors, adjusting knowledge point weights from top to bottom combined with course objectives, outputting an evolved graph through cognitive load regularization, performing graph convolution propagation calculation on the graph to obtain a preference score, generating an encrypted recommendation list through cognitive load reordering, and outputting a final recommendation result through client decryption. By using the method, data privacy and copyright safety can be ensured, user interest, modal preference and cognitive level can be accurately adapted, and personalized learning resource intelligent recommendation can be realized.

The invention discloses a full-life-cycle personnel ability dynamic portrait generation method based on multi-source heterogeneous behavior data, and relates to the technical field of data processing and intelligent recommendation, and the method comprises the steps: collecting and uniformly marking multi-source behavior data in a learning and business system, extracting dominant scores, recessive behaviors and business efficiency characteristics, and generating a dynamic portrait of the full-life-cycle personnel ability dynamic portrait; constructing a multi-dimensional feature vector; correcting the dominant score based on the recessive behavior, obtaining a real ability evaluation value, and dynamically generating an ability portrait in combination with a forgetting rule and business efficiency; and further performing difference analysis with post capability requirements, identifying skill gaps, and forming an adaptive learning resource recommendation path. By fusing multi-source behavior data and recessive behavior characteristics, accurate evaluation of the real capability of the user is realized, a forgetting rule and business efficiency are introduced to dynamically describe a capability change process, and the timeliness and credibility of a capability portrait are improved; and through capability gap analysis and an adaptive recommendation mechanism, the learning efficiency and post competency are improved.

The application discloses a learning resource recommendation method and system based on project field knowledge and user comments, and the method comprises the following steps: collecting learner information, learning resource characteristic information and teacher information, wherein the learner information comprises learner description information and learner interaction information with the learning resource, and the learning resource characteristic information comprises learning resource description information and learning resource characteristic information; finding a teacher with the highest similarity to the learner according to the learner information, and obtaining a matching score of a target learning resource according to the teacher characteristics through a convolutional neural network; establishing a learner short-term preference model and a long-term preference model, and fusing the two models to obtain a learner personal preference model; establishing a learner group preference model, and fusing the learner personal and group models to obtain a learner preference model; and establishing a learning resource characteristic information model and a field knowledge model by using various information characteristics of the learning resource according to the learning resource characteristic information, so that the accuracy of learning resource recommendation is improved.

The invention discloses a personalized learning path dynamic adjustment method based on learning behavior analysis, relates to the technical field of online education learning analysis and intelligent recommendation, and is used for solving the problem that a personalized learning path is difficult to recommend stably in real time due to mastering evaluation distortion caused by a de-duplication gap and learning session fragmentation. Logs and evaluation are unified as learning events, and session segmentation and duplicate removal are carried out; calculating gap risk and session sensitive structure observation confidence, performing double-behavior source soft allocation and gating Bayesian recursion to obtain knowledge point mastering and updating portraits; generating a candidate path based on the revised graph, and fusing the mastering income and the learning value; and a session triggering strategy optimizes routing, outputs a next learning resource and performs stable iteration updating.

The invention discloses a learning efficiency improvement method and device based on big data analysis, and a medium, and relates to the technical field of learning behavior mining, and the method comprises the steps: building a learning interaction relation matrix with a learner as a node and interaction strength as a weight; calculating a learning motivation index according to the learning resource staying duration, the number of active learning times, the learning task completion proportion and the non-learning operation, calculating a learning efficiency index according to course knowledge points, learner answering records and homework scores in a teaching period, and in a time window, combining a learning interaction relation matrix to obtain a learning motivation index; establishing a time sequence causal correlation model of the target learner, calculating a theoretical promotion value for implementing learning motivation promotion intervention on the learner in a time slice, and generating intervention candidate points; and screening the minimum intervention point with the highest theoretical promotion value according to the intervention candidate points, and executing a matched intervention strategy on the learner. According to the invention, dynamic tracking of the learning motivation and the learning efficiency is realized, and the overall learning efficiency is improved.

This invention provides a multi-task learning resource optimization method based on the lottery hypothesis, belonging to the field of multi-task learning and neural network optimization technology. This method employs a sparse expert hybrid approach based on the lottery hypothesis to effectively prune neural network model parameters, thereby significantly reducing the computational cost and storage overhead of the neural network model. The sparse expert network structure retains high sensitivity to key task information. The introduction of a softmax-based router and mask matrix allows each task to select and activate suitable expert network components based on the features of its input data. Cross-training and iterative amplitude pruning optimize the omnipotent expert matrix, further enhancing the model's generalization ability in handling complex tasks and different data distributions. Task-specific layers independently process and optimize the features of each task, reducing mutual interference between tasks and improving the accuracy of feature extraction and the efficiency of task processing.

A machine learning resource management service allows customers to define machine learning projects and machine learning resource allocations for the machine learning projects, such that different levels of resources are allocated to different ones of the projects. Additionally, the machine learning resource management service enables burst capacity at respective ones of the machine learning projects using under-utilized resources of other ones of the machine learning resources, while ensuring the customer defined resource allocations for the different machine learning projects are enforced. Additionally, the machine learning resource management service may track usage of burst capacity among the projects to ensure fair sharing of burst capacity.

The invention belongs to the technical field of unmanned aerial vehicle communication networks, and discloses a federated learning resource management method for unmanned aerial vehicle assisted mobile edge computing MEC, and the method comprises the steps: modeling a federated learning resource management problem in an unmanned aerial vehicle assisted MEC system as a Markov decision process MDP; based on the Markov decision process, strategy optimization is carried out by using a deep reinforcement learning algorithm; according to the deep reinforcement learning algorithm, a framework based on a standard deviation Q target SQT is adopted, a plurality of Q networks are integrated, and the standard deviation of Q values of the Q networks is calculated, so that a target Q value containing uncertainty punishment is generated, and network parameters are updated; and outputting unmanned aerial vehicle selection and resource allocation actions according to the real-time unmanned aerial vehicle auxiliary MEC system state through the trained strategy network. According to the method, federal learning precision and system resource consumption can be effectively balanced, and resource management efficiency is improved.