51 results about "Cognitive diagnosis" patented technology

The invention provides a mathematical question and answer process teaching system, which comprises a user interaction module, a question analysis and standardization module, a cognitive diagnosis engine, a generative teaching module, a mathematical knowledge graph database and a user portrait database, teaching content and guiding questions are presented to the user in a multi-mode form; the question analysis and standardization module is used for performing semantic understanding and structured analysis on mathematical questions and generating standardized question description and at least one standard question solving path; according to the method, the structured reasoning of the knowledge graph is combined with the natural language generation ability of the generative AI, so that a closed loop from'problem solving 'to'diagnosis' to'heuristic teaching 'is realized, thinking blockage points of students can be accurately positioned and personalized tutoring can be provided like human teachers, and the learning efficiency and the autonomous thinking ability are remarkably improved.

The invention, which relates to the technical field of education recommendation, discloses a student portrait-driven education agent recommendation system based on a cognitive diagnosis map, comprising a time-frequency decomposition processing module, a weight rhythm matching module, a time sequence coupling damping module, a dynamic difference readjustment module and a time-frequency domain self-balancing control module. And the time-frequency decomposition processing module is used for establishing a time-frequency decomposition processing layer based on drifting characteristics of student portrait parameters in a time dimension, and performing energy distribution analysis on multi-source dynamic data streams from learning behaviors, test performance and emotion feedback according to time slices. Through time-frequency decomposition and non-resonance rhythm matching, dynamic coordination of weight adjustment and student portrait drifting is realized, characteristic fluctuation amplification is prevented, and the stability of a learning path is guaranteed; and a dynamic closed loop is formed through time sequence coupling damping and time-frequency domain self-balancing control, stable convergence of cognitive features is realized, and the accuracy and continuity of educational agent recommendation are improved.

The invention discloses a grassland desertification intelligent closed-loop management method and system based on multi-source remote sensing, and belongs to the technical field of ecological restoration and intelligent decision making. According to the method, technical breakthrough is realized by constructing an intelligent closed loop of perception, cognition, decision and optimization: firstly, multi-source data are fused to construct a dynamic ecological knowledge graph, and a desertification cause diagnosis report for quantifying the contribution rate of each driving factor is generated based on graph reasoning; calling a governance measure knowledge base to generate a scheme according to a diagnosis result, and optimizing a decision through digital twinborn rehearsal; finally, based on treatment effect feedback, the knowledge base is dynamically optimized through reinforcement learning; the corresponding system comprises a multi-source perception fusion module, an ecological cognitive diagnosis module, a decision rehearsal execution module and a self-learning optimization module. According to the method, the bottleneck of lack of causal diagnosis and system stiffness of a traditional method is overcome, the crossing from passive monitoring to active cognition and from static decision to dynamic self-learning is realized, and an innovative solution is provided for treatment of a degraded ecological system.

The invention discloses a learner cognitive diagnosis method oriented to an intelligent education scene, and belongs to the technical field of cognitive diagnosis and education data analysis. According to the method, concept-level multi-dimensional modeling is carried out on the ability and exercise difficulty of a learner by constructing multi-dimensional representation of concept perception so as to describe mastering characteristics of the learner on different cognitive levels; and meanwhile, distinguishing a pre-correction dependency relationship and a semantic approximation relationship, establishing a relationship-perceived concept dependency model, and deducing a potential exercise-concept association structure according to the relationship-perceived concept dependency model. Further, the annotated exercise-concept incidence matrix and the inference incidence matrix are fused in a unified diagnosis layer, and comprehensive evaluation of the knowledge mastering state of the learner is achieved. According to the method, an end-to-end mode is adopted for optimization, the fineness, knowledge coverage and stability of cognitive diagnosis can be effectively improved, better prediction performance and generalization ability are shown on multiple real education data sets, and the method is suitable for intelligent education application scenes such as learning analysis and personalized teaching.

The application provides a dynamic graph neural cognitive diagnosis method fusing multi-dimensional features, and the method comprises the following steps: collecting multi-modal data of an online learning platform, and obtaining a multi-dimensional feature splicing vector based on the multi-modal data; based on the multi-dimensional feature splicing vector and by using a graph neural network, obtaining an aggregation matrix from an embedding matrix of a current knowledge point, a hidden state matrix of the current knowledge point, an embedding matrix of a neighboring knowledge point, and a hidden state matrix of the neighboring knowledge point; performing a forgetting process on the embedding matrix of the knowledge point by using a forgetting vector, inputting the aggregation matrix into a memory gate structure model, and capturing a time sequence feature embedding matrix of the knowledge point; based on the time sequence feature embedding matrix and by using the graph neural network, constantly updating the hidden state matrix of the knowledge point, and obtaining an updated knowledge mastery degree of the learner at the next moment. The application comprehensively diagnoses the learning effect of the learner and updates the knowledge mastery state of the learner, and greatly improves the accuracy of the diagnosis result.

The application provides a cognitive diagnosis method and system based on causal inference to eliminate problem difficulty bias, relates to the technical field of educational data mining, and specifically includes the following steps: preprocessing the historical record of a student's answer to a problem to obtain a training set composed of a student, a problem, problem difficulty and a score; introducing a problem difficulty variable on the basis of an existing diagnosis model, eliminating bias by using causal inference, constructing a cognitive diagnosis model, and training the cognitive diagnosis model by using the training set; inputting a student to be diagnosed, a problem and problem difficulty into the trained cognitive diagnosis model to obtain a cognitive diagnosis result of the student output by the diagnosis model; the application provides a general cognitive diagnosis framework, creates a cognitive diagnosis model based on an existing diagnosis model, eliminates the adverse effects of problem difficulty bias by using causal inference technology, and performs unbiased training on the model to diagnose the cognitive level of the student, thereby improving the accuracy and efficiency of cognitive diagnosis.

This application belongs to the field of intelligent assessment technology, specifically disclosing a matrix optimization method, apparatus, and device based on a cognitive diagnostic model. This application removes the questions to be verified from the correlation matrix to be optimized and the corresponding answer data from the answer matrix; it determines the student's knowledge point mastery vector and question feature vector based on the target cognitive diagnostic model; and it sequentially verifies multiple knowledge points associated with the questions to be verified according to a preset positive testing strategy, optimizing the correlation matrix by correcting the knowledge points to be optimized. By removing the questions to be verified and their corresponding answer data from their respective matrices, the accuracy of the input model's data is improved. The preset positive testing strategy ensures that knowledge points in the correlation matrix to be optimized are corrected only when sufficient and significant statistical evidence is obtained, thereby effectively improving the accuracy and efficiency of the optimization matrix.

The invention relates to the technical field of education evaluation, in particular to an English reading understanding ability self-adaptive evaluation method and system. The method aims at solving the technical problems that the traditional fixed difficulty test is easy to cause inaccurate capability estimation, the existing adaptive test is rough in subject description difficulty, the reading skill diagnosis is fuzzy, and the question bank security is insufficiently considered. According to the technical scheme, the method comprises the steps that a pre-training language model is used for conducting word, syntax, chapter and subject multi-dimensional difficulty feature extraction on a reading material; correcting question parameters based on an item reaction theoretical model in combination with answer data; dynamic evaluation is realized by adopting a self-adaptive test engine based on Bayesian capability estimation and maximum information amount topic selection; outputting the fine-grained skill mastering degree through the cognitive diagnosis model with the Q matrix constraint; a question exposure control strategy is integrated to balance measurement precision and question bank safety. And the system finally outputs a capability level, a skill diagnosis radar map and personalized reading recommendation.

The invention discloses a neural network cognitive diagnosis system based on rule prior, and the system comprises a parameter initialization module which is used for loading and preprocessing student answer records and question related knowledge information, and constructing an embedded layer of a neural network, and the embedded layer corresponds to a student ability vector, a question difficulty vector and a question distinction degree vector; the rule constraint module is used for introducing an interpretable constraint item; comprising the following steps of: ensuring the ability sorting consistency constraint of consistent student ability sorting and actual answering performance, forcing the negative correlation discrimination-variance negative correlation constraint of question discrimination and reply ability variance, and calibrating the difficulty of questions as the difficulty threshold consistency constraint of a decision threshold of student ability; and the diagnosis network module is used for constructing an output layer of a neural network based on the two-parameter item reaction theory and calculating the answer probability. According to the method, the neural network model fusing rule constraints is constructed, so that high-precision answer prediction is realized, and meanwhile, student ability estimation and question parameters are ensured to be consistent with an education theory.

The invention belongs to the technical field of online education, and discloses an exercise recommendation system and method based on hierarchical reinforcement learning and multi-objective optimization, and the system comprises a multi-objective optimization index definition module which is used for defining exercise diversity, exercise novelty, recommendation accuracy, learner satisfaction, learner enthusiasm, learner score and system question setting time; a comprehensive objective function is formed through weighted summation; the three-layer reinforcement learning architecture module comprises a high-level strategy, a middle-level strategy and a low-level strategy which are respectively responsible for global optimization target planning, strategy execution and personalized exercise recommendation; the cognitive diagnosis model and Transform prediction model fusion module is used for evaluating the knowledge mastering condition of the learner and optimizing a recommendation strategy; and the improved Pareto optimization method module is used for processing uncertainty in multi-target optimization, solving target conflicts and improving the convergence speed of an algorithm through dynamic parameter adjustment. According to the invention, appropriate exercises can be accurately recommended according to the learning state of each student.

The invention provides a flight potential standardization evaluation method based on rapid teaching and flight path assistance, and relates to the technical field of flight simulation evaluation. The method comprises the following steps: firstly, establishing a target capability model including understanding and accepting capability, control capability, attention capability and strain capability, and compiling a simulated flight test according to a cognitive diagnosis theory; constructing a scene library based on the target capability model, configuring track assistance for each flight scene, and marking excitation intensity and discriminability parameters of each flight scene for each capability; short-time rapid pre-teaching is implemented according to a standardized teaching script before evaluation; during evaluation, a multi-capability probe is embedded in a flight scene, evaluation data is collected, a capability estimation value is updated based on a capability-scene matching model, a subsequent flight scene is adaptively selected or scene parameters are adjusted according to the capability estimation value to generate a personalized examination path, a comprehensive score is calculated, and a four-dimensional capability profile map is output. The objectivity of the evaluation result can be improved.

The application relates to the technical field of artificial intelligence, and discloses an emotional conversation generation method and device, electronic equipment and a storage medium, the method comprising the following steps: constructing an emotional conversation dataset and constructing a plurality of intelligent agents based on a pre-trained large language model, which respectively play the roles of a seeker and a consultant; obtaining current conversation text received by a first intelligent agent corresponding to the seeker, mapping a target cognitive distortion classification system of the current conversation text based on the emotional conversation dataset; determining the cognitive bias of the current user based on the target cognitive distortion classification system; determining a target intervention strategy of the current conversation text based on the cognitive bias by using a second intelligent agent corresponding to the consultant, a preset hybrid reward mechanism and a cognitive strategy reinforcement learning algorithm; and optimizing reply text in the target intervention strategy to generate a target reply text, so that the cognitive diagnosis and cognitive intervention strategy accuracy for the seeker are improved, and accurate identification and professional intervention of cognitive distortion of the seeker are realized.

This invention relates to the field of artificial intelligence-based educational assessment, and discloses a cognitive diagnostic model and method based on knowledge text. The model includes a text feature extraction module for extracting and generating knowledge point association vectors representing the degree of association between questions and preset knowledge points; a knowledge proficiency embedding module for mapping knowledge proficiency vectors; a question attribute embedding module for mapping question knowledge difficulty vectors and question discrimination scalars; a knowledge association attention module for adjusting attention weights and generating weighted knowledge representations; and an adaptive nonlinear prediction module containing a multi-layer KANLinear structure composed of B-spline basis functions and outputting the prediction probability of correct student answers. This invention solves the problem of fragmented internal module functions in existing models and features high interpretability and independence from manual annotation.

The application discloses a kind of adaptive cognitive diagnosis method based on double-layer confrontation, is through the way of adaptive learning to improve the precision of student cognitive diagnosis, its steps include:1, based on vector embedding method obtains the vector embedding representation of proficiency of knowledge point, exercise difficulty and exercise difference degree, and the target vector embedding representation is adaptively learned;2, the interaction of vector embedding representation is carried out, and adaptive learning is carried out after two layers of fully connected layer;3, the loss function design of double-layer confrontation adaptive cognitive diagnosis network is carried out, and the parameter of network is updated;4, the whole double-layer confrontation adaptive cognitive diagnosis network is optimized using cross-entropy loss.This application can realize adaptive cognitive diagnosis in the scene of missing problem-solving record by using other scenes, such as different students, different exercise records, so as to realize more accurate student performance prediction.

The invention relates to a cognitive diagnosis and reverse thinking training education system based on double AI cooperation, and belongs to the technical field of education technology and artificial intelligence. The system comprises the following steps: acquiring and preprocessing multi-modal data in a learning process of a student, and outputting a multi-dimensional cognitive feature vector; dynamically dividing cognitive hierarchies based on the vector, constructing differentiated cognitive portraits, and generating a personalized training task matrix in combination with a mapping rule base; positioning a cognitive vulnerability and logic error normal form, calling a meta-cognitive question chain library to generate a progressive question sequence, and matching with a scenarized verification task to form an error and omission repairing and knowledge strengthening set; and constructing a group cognition map pre-generality difficulty training module, constructing a dynamic mastery degree evaluation index system, and generating a multi-dimensional capability feedback report. Accurate diagnosis and personalized training adaptation of the cognitive state of the student are achieved, knowledge vulnerabilities are efficiently repaired, the reverse thinking ability is enhanced, and the pertinence and effectiveness of learning training are improved.

The application provides a kind of personalized learning path recommendation method based on reinforcement learning, it is related to educational data mining technical field.The method first constructs learner simulator according to the learning record of scholar, the simulator can judge the learning level of learner;Then the knowledge relationship graph between the knowledge points contained in the exercise is automatically constructed by the concept map automatic construction model based on text classification and association rule mining;Based on the knowledge relationship graph and the cognitive diagnosis model, an exercise navigation module is designed to select potential candidate exercises;After the reinforcement learning agent selects the action in the action space, the state transition is determined in the state space, the model parameters are updated according to the loss function and optimization strategy, and the reinforcement learning model is optimized;Finally, the designed reinforcement learning model is used to recommend exercises for learners, and the reinforcement learning model parameters are updated according to the learning situation of learners.The method can recommend efficient and reasonable learning path for learners.

The present application relates to a kind of fusion cognitive transfer teaching evaluation sentiment analysis method, belong to the field of educational informationization.The method includes: the data collected is cleaned and preprocessed;Unstructured teaching evaluation text is carried out word embedding using BERT language model, it is input in bidirectional GRU network and learns, the context hidden memory information of output text;Student historical practice record is modeled using neural cognitive diagnosis model, and the personalized cognitive ability vector of student is obtained as prior knowledge representation;The text hidden memory information extracted is fused into cognitive transfer matrix with prior knowledge information, and prior knowledge is transferred into text memory by attention mechanism, and the real emotional characteristics contained in text are enhanced.The present application can accurately classify the sentiment of teaching evaluation text carrying conflictive emotional characteristics, solve the problem that sentiment is misclassified due to the existence of conflictive emotional characteristics in teaching evaluation.

This invention relates to a deep cognitive diagnostic method based on graph neural networks, belonging to the field of deep learning technology. The invention aims to represent the cognitive diagnostic task as a representation learning and prediction problem on a heterogeneous graph composed of student nodes, item nodes, and ability nodes. While maintaining the student-item-score triplet input format, the item-ability mapping relationship represented by the Q-matrix is ​​transformed into an explicit connection relationship in the graph structure. Furthermore, the message passing mechanism of the graph neural network is used to achieve information interaction and joint modeling between different types of nodes, thereby improving the accuracy of student answer prediction, the granularity of student ability assessment, and the interpretability of the model output.

This invention discloses a dynamic teaching strategy optimization method for personalized learning, relating to the field of intelligent teaching optimization. The method includes acquiring emotional, behavioral, and academic data; using a cognitive diagnostic unit to perform correlation and feature fusion processing on the behavioral and academic data to obtain a knowledge point mastery probability matrix and a knowledge gap association strength matrix; using an affective computing unit to extract and fuse features from the emotional data to obtain affective fusion features; classifying and scoring the affective fusion features to obtain affective intensity and affective stability scores; constructing a fusion reinforcement learning model; and generating and adjusting dynamic teaching strategies based on the knowledge point mastery probability matrix, the knowledge gap association strength matrix, the affective intensity score, and the affective stability score. This invention improves the timeliness and accuracy of cognitive diagnostic parameters using the above method, supporting precise identification of knowledge weaknesses.

The present application belongs to the field of educational data mining, and provides a cognitive diagnosis method for long-period evaluation, comprising: (1) constructing a cognitive diagnosis framework for long-period evaluation; (2) fusing the extracted student features, test features, interaction features and time sequence features to obtain a final input representation vector; (3) using a neural network structure to model a diagnosis algorithm, taking the final input representation vector obtained in step (2) as the input of the network structure, and outputting the student answer result; the diagnosis algorithm is composed of a neural network structure and a loss function; (4) collecting a data set, training the network structure, and predicting the student answer response; (5) according to the specific application scene, designing a cognitive diagnosis system to obtain the student's diagnosis report. The present application method respectively meets the single education measurement demand without long-period evaluation data accumulation and the education diagnosis demand with long-period evaluation data accumulation, and better solves the new problems brought by the change of education data form.

The application discloses a kind of counterfactual fairness cognitive diagnosis method, comprising:1. Construct multi-source data: student-exercise interaction record, student-self attribute, sensitive attribute and the like data;2. Propose definition of fairness in cognitive diagnosis;3. In traditional cognitive diagnosis, calculate biased overall causal effect;4. In model inference stage, design counterfactual cognitive diagnosis model, calculate the false correlation effect of sensitive attribute to knowledge proficiency, while subtracting it from the biased overall effect calculated in step 3, realize the fairness of cognitive diagnosis.The application is based on the idea of counterfactual debiasing, by capturing the false correlation generated only by sensitive attribute, and then subtracting it from the biased overall effect, which can effectively alleviate the fairness problem in cognitive diagnosis while maintaining the usefulness of the model.

The invention relates to a comprehensive quality evaluation method and system for cross-platform learning behaviors and a medium. The method comprises the following steps: preprocessing heterogeneous original data corresponding to each learning platform to obtain a learning behavior event set; creating a dynamic multi-modal event atlas based on the learning behavior event set; inputting the dynamic multi-modal event atlas into a heterogeneous graph neural network to obtain an atlas-level learning behavior embedding vector; a learning intention probability classification result and a cognitive state recognition result are obtained based on the atlas-level learning behavior embedding vector, and a preset probability graph model is triggered to conduct reasoning and conflict resolution on the dynamic multi-mode event atlas to obtain an updated dynamic multi-mode event atlas; and pre-defined comprehensive quality dimension features are extracted from the updated dynamic multi-modal event atlas, and dimension evaluation is carried out to obtain a comprehensive quality evaluation report. By adopting the method, comprehensive quality evaluation can be upgraded to a deep cognitive diagnosis level from surface behavior description.

The application discloses a target language acquisition fostering system based on staged immersive context generation, comprising: a learning data acquisition module for collecting multi-source data and processing, outputting a standardized learning data set; a cognitive diagnosis module for outputting a staged ability label based on a hierarchical Bayesian cognitive diagnosis model; a stage context resource module for calling a learning resource set according to the staged ability label; an interactive training and feedback module for carrying out multi-modal interactive training, collecting performance data in real time, generating error correction information and minimum prompts; a stage updating module for executing latent variable posterior probability updating, generating a new staged ability label, and generating a migration signal; a migration control and path scheduling module for receiving the migration signal and controlling learning path scheduling. The hierarchical Bayesian diagnosis realizes target language immersive acquisition path optimization.

The application discloses a kind of multi-dimensional evaluation method and system of VR teaching based on user behavior feedback, according to Bloom's taxonomy of educational objectives, construct the multi-dimensional evaluation framework covering cognition, skill and emotion / meta-cognition, and set observable behavior proxy index for each dimension;Through VR equipment, real-time collection of user multi-modal behavior data and teaching context, knowledge state is identified and backstepped by using Transformer and cognitive diagnosis model;Combining graph neural network and attention mechanism, multi-granularity evaluation of micro, meso and macro three layers fusion is realized;At the same time, based on historical behavior, individualized ability curve is constructed, novice and expert behavior are dynamically distinguished, evaluation standard is adaptively adjusted, and growth is emphasized rather than absolute score;Finally, the intelligent feedback for students and teachers is generated, and teaching intervention is driven.The system realizes the whole process, objective and individualized VR teaching evaluation, effectively improves teaching accuracy and learning effectiveness.

The invention relates to the technical field of wisdom education, and discloses a computerized adaptive test depolarization method based on selective mixing, which comprises the following steps: constructing an interaction data set based on obtained historical answer records of examinees, and encoding to obtain answer state vectors; obtaining an ability vector representing the cognitive state of the examinee according to the answer state vector; defining a deviation alignment sample, an unbiased sample and a deviation conflict sample; selective mixing is carried out, and diversified problem characterization is generated by carrying out linear interpolation on problem parameters, so that deviation conflict samples are expanded, and a synthetic sample set is obtained; constructing final training loss including empirical loss and synthetic sample loss, and optimizing the selection network to relieve selection deviation; through cross-attribute retrieval and selective mixing, a small amount of deviation conflict samples can be fully utilized and expanded to cope with cognitive diagnosis challenges caused by unbalanced data distribution, so that more accurate cognitive diagnosis is realized, and more excellent test experience is brought to examinees.

The present disclosure provides a dynamic cognitive path modeling and prediction method, system, electronic device and storage medium; the method comprises the following steps: collecting learning interface interaction behavior of a learner in real time to generate an original interaction sequence containing multiple time-stamped ordered event tuples; streaming analysis is performed according to a preset behavior analysis rule library, the event tuples are aggregated / converted into semantic micro behaviors with cognitive psychology meaning to obtain a semantic micro behavior sequence; the semantic micro behavior sequence is input into a sequence modeling network to generate a dynamic cognitive path vector encoding the current complete interaction history at each time step; based on the vector, downstream tasks are processed through a prediction head to output real-time intervention signals or cognitive diagnosis reports. The technical scheme of the present disclosure models the fine-grained behavior of the learner during the problem-solving process, realizes dynamic tracking and forward-looking prediction of the cognitive state of the learner, and realizes active and timely personalized intervention.

The invention relates to the technical field of artificial intelligence education, and discloses a multi-agent collaborative education decision-making system and method. The method comprises the following steps: constructing a dynamic knowledge graph, and tracking the learning state of a student in real time; analyzing learning behavior data in parallel through a diagnosis agent, a resource agent and a path agent, and respectively outputting a knowledge weak point diagnosis vector, a personalized resource recommendation queue and an optimal learning path decision tree; based on a multi-target constraint strategy fusion algorithm, generating a dynamic teaching scheme in a collaborative decision center; and the execution engine monitors feedback in real time and triggers strategy re-planning. Through a multi-agent parallel collaboration mechanism, the technical problems of one-sided decision making of a single model and insufficient module collaboration are solved, the technical effects that the cognitive diagnosis accuracy is 72.3% and the path recommendation matching degree is 75.8% are achieved, and the personalized teaching precision and the resource utilization efficiency are remarkably improved.

The application discloses a kind of multi-modal online test question recommendation method, system and medium based on end cloud cooperation.The method obtains the test record of user, question attribute and expression information in the process of answering by obtaining the device end, carries out cognitive diagnosis to obtain user knowledge radar chart diagnosis result in the device end, and realizes adaptive test question recommendation according to diagnosis result.To solve the limitation of device end recommendation question bank, cloud end question selection strategy and device end question selection strategy are designed, and a variety of questions can be selected from the angle of question type and quality according to user demand, which are downloaded to the user by the cloud, and the redundant questions in the device end are removed.The method of the application realizes adaptive examination under the cooperation of end and cloud, accurately diagnoses by fusing user expression information, and realizes personalized test question recommendation according to diagnosis result, solves the problem that traditional method cannot be applied to large-scale question bank, and has the advantages of good recommendation effect, accurate diagnosis and the like.

The application discloses a kind of based on multi-objective optimization's selecting subject method, comprising:1 obtains student and subject relevant data;2 training bottom cognitive diagnosis model;3 based on accuracy, diversity and security constructs multi-objective optimization problem;4 using heuristic multi-objective evolutionary algorithm to solve multi-objective optimization problem, obtain the student's selecting subject set.The application based on multi-objective evolutionary algorithm balances test accuracy, diversity and security, and by calculating and the answer prediction accuracy of the student similar to its ability level to the test accuracy of the student more intuitive and effective modeling, to ensure the prediction accuracy of student knowledge level ability.

The present application relates to a kind of cognitive diagnosis method and system based on heterogeneous relationship graph embedding, it aims at by the combination of graph neural network and metric learning, improve the accuracy and efficiency of cognitive diagnosis.The present application is specifically divided into four technical implementation stages of constructing multiple cognitive relationship graph and carrying out embedding processing, relationship perception coding based on graph neural network, metric learning and answer mode discrimination and joint training and model optimization.Specifically, the present application constructs multiple cognitive relationship graph and carries out embedding processing, and finely depicts the complex interaction between student, test and knowledge point.Based on graph neural network, relationship perception coding is carried out, and node embedding representation is updated, and different types of relationship information are fused.Combined with metric learning technology, the correct and wrong answer behavior of student is accurately distinguished.Finally, through joint training optimization model, the precision and robustness of cognitive diagnosis are improved, and it is suitable for personalized learning evaluation and intelligent education and other fields.