126 results about "Knowledge state" patented technology

The invention discloses an intelligent question bank retrieval and recommendation system based on an artificial intelligence knowledge graph, and relates to the technical field of artificial intelligence education. Comprising a knowledge graph construction module which is used for processing original education data and constructing a neighborhood knowledge graph comprising a hard preposition relation and a soft incidence relation; the user knowledge state graph construction module is used for constructing a user personal knowledge state graph isomorphic to the domain knowledge graph, and dynamically calculating a mastery index of each knowledge node through a deep knowledge tracking model based on user historical answer data; according to the method, by constructing the domain knowledge graph containing the hard preposition relation and the soft incidence relation, discrete knowledge points are organized into the structured network conforming to the cognitive law, so that the system can understand and follow the internal logic between knowledge, and a learning path which is clear in organization, efficient and coherent is generated.

The invention relates to the technical field of test question generation, in particular to an intelligent test question generation method and system based on learning behavior analysis. The method comprises the following steps: acquiring interactive behavior data and score data of learners in a user online learning platform in real time; inputting the interactive behavior data and the score data into a pre-trained knowledge state analysis model to generate a user knowledge state matrix; based on the knowledge state matrix and in combination with a preset teaching target library, identifying a target knowledge point set which needs to be strengthened currently and a corresponding cognitive training type; according to the target knowledge point set needing to be strengthened and the corresponding cognitive training type, a test question element combination algorithm is called, question stems, interference items and question solving path prompts are dynamically assembled, and personalized test questions are generated. The method has the advantages that full-closed-loop intelligent teaching from behavior analysis of the user to targeted training is achieved, and personalized test questions adaptive to individual cognitive vulnerabilities are dynamically generated.

Embodiments are directed toward a blockchain system including a global state and an assemblage of blocks, each block representing a collection of state transformation records, each state transformation record describing a state transformation performed on the global state, where preceding blocks referenced by any given block contain state transformation records describing state transformations performed on the global state prior to the evaluation of the given block, and where at least one state transformation record is a zero-knowledge transformation record encoding a zero-knowledge state transformation description, which zero-knowledge transformation record comprises at least the following elements: paths identifying the locations of the elements of a discrete data subset, a revised data subset, and a transition proof implemented as a non-interactive zero-knowledge proof, which transition proof proves that the transition from the discrete data subset to the revised data subset follows the established rules of the blockchain system.

The invention relates to the technical field of hydrological survey skill training, in particular to a construction method and system of a hydrological survey knowledge model based on a large model. The method comprises the following steps: acquiring multi-source hydrological data, and constructing a hydrological knowledge graph; generating a confusion sample corresponding to the hydrological knowledge graph, and performing adversarial training on the confusion sample; according to the confrontation training result and historical test questions in the multi-source hydrological data, obtaining bidirectional mapping test questions; inputting the bidirectional mapping test questions into a question setting interface of a hydrological survey learning platform; collecting answer data and student physiological data corresponding to the bidirectional mapping test questions in real time, and updating a student knowledge state according to the answer data and the student physiological data; constructing a hydrological survey knowledge model based on the updated student knowledge state; and generating a student recommendation learning scheme by using the hydrological survey knowledge model. According to the invention, the intellectualization and practicability of hydrological survey education can be improved.

The invention relates to a knowledge graph-based teaching resource database construction method and system, and belongs to the technical field of data resource processing, and the method comprises the following steps: S1, obtaining and preprocessing a multi-source heterogeneous teaching resource: carrying out the natural language processing of an unstructured text to recognize the association of an entity and a key concept, analyzing the user behavior log to extract hidden knowledge point association; s2, defining a multi-dimensional teaching knowledge graph mode layer: constructing a multi-dimensional graph mode layer; s3, collaborative extraction and fusion of graph entities and relationships: collaborative extraction of core teaching entities and specific relationship types from the preprocessed teaching resources to construct a knowledge graph; s4, adaptive graph updating and teaching path generation: taking the constructed knowledge graph as an underlying database, and responding to knowledge state query of a user; the method has the beneficial effects that massive and heterogeneous teaching resources and the knowledge graph are effectively fused.

The invention discloses an Agent-based education evaluation method and system, and relates to the technical field of artificial intelligence and education evaluation, and the method comprises the steps: obtaining historical evaluation data and knowledge graph labeling data of students, constructing a student knowledge state matrix, calculating a mastering probability value and a forgetting attenuation coefficient of each knowledge point, and generating an evaluation question recommendation sequence; inputting the question text and the student answering text into a multi-Agent collaborative evaluation model to generate a multi-dimensional scoring result; dynamically updating the knowledge point mastering probability value of the student in the continuous answering process, calculating the mastering degree change rate of each knowledge point node, constructing an adaptive difficulty adjustment function, and generating a question difficulty parameter and a knowledge point coverage range parameter of the next round of evaluation; and taking the question difficulty parameter and the knowledge point coverage range parameter as constraint conditions, screening a candidate question set meeting the conditions from a question bank, and generating a self-adaptive evaluation path and a capability diagnosis report. The invention also discloses a method.

The invention relates to the technical field of artificial intelligence education, and discloses a personalized online education system and method based on artificial intelligence, and the system comprises a data collection and perception module which is used for collecting the dynamic behavior data and multi-mode perception data of a learner; the knowledge processing and constructing module is used for processing teaching contents to construct a structured knowledge graph; the user modeling module is used for constructing a dynamic learner portrait comprising a knowledge state model and a cognitive-emotional state model for the learner based on the collected data and the constructed knowledge graph; and the intelligent decision and intervention module is used for generating and executing personalized learning intervention based on the dynamic learner portrait. According to the method, by fusing multi-mode cognitive state perception, reinforcement learning intervention decision and a knowledge graph dynamic evolution mechanism, accurate and timely personalized intervention for learners and intelligent guidance of optimal learning strategies are realized.

The invention discloses a time enhanced knowledge tracking method based on dual-channel deentanglement, and belongs to the technical field of education data mining and cognitive modeling. According to the technical scheme, the method comprises the steps that time dynamic features and behavior reaction features in a learning interaction sequence are extracted and coded through a time domain encoder and a behavior domain encoder respectively; separating long-term trends and short-term fluctuations in the input features by using a multi-scale decoupling layer based on causal convolution; a time perception dual-channel attention module is adopted to independently decouple time and behavior characteristics after decoupling, and a nonlinear attenuation item based on a real interval is introduced to simulate memory forgetting; and finally, integrating dual-channel information through a gating fusion mechanism and predicting future answering performance of the learner. According to the method, optimization conflicts are effectively relieved, the robustness to a complex learning mode is enhanced, and knowledge state modeling which better accords with a cognitive law is realized.

The invention discloses a knowledge graph teaching path dynamic recommendation method and system based on reinforcement learning. The method comprises the following steps: constructing a cognitive adaptive dynamic knowledge graph; obtaining an individual multi-dimensional state vector of a student to be recommended; obtaining a trained student state perception model and a trained teaching path reinforcement learning model; inputting the individual multi-dimensional state vector of the to-be-recommended student into a trained student state perception model to obtain cognitive state information of the to-be-recommended student; and calling the trained teaching path reinforcement learning model by taking the cognitive adaptive dynamic knowledge graph as an environment and combining cognitive state information of the to-be-recommended student, so as to obtain a current personalized teaching path recommendation result of the student individual. The teaching content sequence can be dynamically adjusted according to the knowledge state and the learning behavior of the student, and the teaching integrating degree is improved; the teaching path is continuously optimized through learning, and different types of students can be adapted.

The invention relates to the technical field of computers, and discloses a fragmentation block chain federal learning method based on a large language model multi-agent, and the method comprises the steps: S1, initializing a client; s2, dynamic fragmentation scheduling and distribution; s3, generating and uploading local knowledge; s4, intelligent agent collaborative routing and knowledge acquisition; s5, knowledge fusion and model updating; and S6, repeatedly executing the steps S3 to S5 until the model converges or reaches a preset number of iterations. According to the invention, under a decentralized and fragmented federated learning architecture, the complex reasoning ability of a large language model and the autonomous cooperation mechanism of three multi-agent systems, namely a fragmented scheduling agent, a fragmented knowledge state agent and a global knowledge routing agent, are deeply fused; according to the mechanism, dynamic optimization of a bottom layer fragment structure and intelligent routing of high-value knowledge are achieved in an intelligent mode, and therefore the overall efficiency and model performance of a system under the condition of heterogeneous data and heterogeneous equipment are remarkably improved.

The invention discloses an enterprise training evaluation system and method fusing RAG and an intelligent agent, and belongs to the technical field of training evaluation of artificial intelligence. The system comprises a computing node, a storage unit, a network interaction unit, a document vectorization processing module, a dynamic question setting module, a real-time semantic scoring module, a training effect visualization module and a learning recommendation module. The method comprises the steps of document preprocessing, dynamic question setting, real-time scoring, effect visualization and learning recommendation. Through deep fusion of RAG retrieval and agent decision, personalized question setting, multi-dimensional instant scoring, long-term knowledge state tracking and early warning and personalized learning recommendation based on student knowledge states are realized, and an evaluation-feedback-optimization closed loop is formed. According to the method, the question setting pertinence, the scoring accuracy (up to 92.3%) and the training efficiency (compressing the training time by 40%) are remarkably improved, and the method is suitable for various enterprise training scenes.

The invention discloses a university education personalized learning path generation method and system based on artificial intelligence, and relates to the technical field of personalized learning path generation, and the method comprises the steps: collecting the multi-modal data of students, obtaining an input vector, and constructing a pre-constructed knowledge graph; performing knowledge state modeling through TransformerEncoder on the basis of the input vector, performing knowledge state updating through graph attention based on a pre-constructed knowledge graph to generate a knowledge state containing a knowledge point relationship, and predicting a mastering probability of each knowledge point; using CNN to extract behavior characteristics of students, generating a cognitive load state through Transform, and finally outputting a cognitive load value; on the basis of the knowledge state and the cognitive load value, constructing double-target learning path optimization, and searching and solving through a Monte Carlo tree to generate a next personalized learning task; the learning effect and the learning experience are remarkably improved.

The invention provides a learning resource recommendation method based on knowledge tracking and retrieval enhancement generation, and belongs to the technical field of education. The method comprises the steps of obtaining data of a user learning platform and / or learning content uploaded by a user, and constructing a background knowledge base related to a current learning task of the user; acquiring learning interaction behavior data of the user, constructing a knowledge state tracking model, and forming a current knowledge mastering state of the user; wherein the learning interaction behavior data of the user comprises knowledge points, exercises, videos and texts; and outputting personalized learning resource recommendation and question and answer response by utilizing a retrieval enhancement generation model in combination with the background knowledge base and the knowledge mastering state. Therefore, dynamic, personalized and knowledge-accurate learning content recommendation can be realized.

The invention discloses a smart course personalized resource label classification and recommendation system based on teaching practical experience, and relates to the technical field of smart education, and the system comprises a knowledge graph construction module, a resource labeling module, a user capability modeling module, a recommendation core module, a system interaction module and a parameter optimization module. The working process of the system is as follows: extracting a knowledge point set from a course standard, defining a relationship type between knowledge points, constructing a weighted directed graph, and calculating a shortest path distance between the knowledge points; marking a knowledge point set which is directly explained, a knowledge point set which needs to be mastered in advance, cognitive difficulty and a resource type for resources in the resource library; initializing a user knowledge state matrix, updating the mastery degree according to a test result, and calculating a current capability threshold value of the user; preliminarily screening a candidate resource set, calculating a knowledge migration intensity score, and grouping and sequencing according to resource types to generate a final recommendation list; and adjusting core parameters of a knowledge migration intensity algorithm according to user behavior data generated by a recommendation result.

The invention discloses an online training course personalized recommendation method and system, and relates to the technical field of online education. The method comprises the following steps: acquiring multi-modal learning interaction data of a user, and constructing a course knowledge graph comprising courses, knowledge components and relationships between the courses and the knowledge components; processing the course knowledge graph by adopting a heterogeneous graph attention network so as to track the dynamic knowledge state of the user; estimating the cognitive load level of the user through a pre-trained cognitive load classification model based on the multi-modal learning interaction data; and based on the dynamic knowledge state and the cognitive load level, generating a personalized learning path in a deep reinforcement learning framework by maximizing a cumulative reward function combining knowledge gain reward and cognitive load balance reward.

The invention discloses a generative agent cognitive diagnosis framework fusing teacher thinking, and the framework is used for modeling a cognitive judgment process of a teacher in a real teaching scene, systematically constructing task-aware thinking modeling, a behavior track-based observation reflection mechanism, and a causal-driven explanation generation module. Therefore, dynamic modeling and deviation diagnosis of the cognitive state of the student are realized. The method has the advantages that firstly, the method has good cold start capability, and reasonable judgment can be made even if complete historical behavior data is lacked; 2, the method has relatively high interpretability, can output a causal chain of'knowledge state-behavior process-task performance ', and supports accurate teaching intervention; and thirdly, the method has the ability of distinguishing the thinking levels of students, can assist in completing Bloom cognitive classification, and provides effective support for task layering and teaching design.

The invention discloses a knowledge tracking method and system based on group and individual dual-path collaborative evolution, which are used for modeling the knowledge mastering condition of a learner from a problem state, a concept state and an overall knowledge state and comprehensively capturing the dynamic evolution process of the knowledge state. According to the method, the complex interaction relationship among different knowledge dimensions is effectively captured by fusing the LSTM network, the Transform encoder, the multi-head attention mechanism and the MALA linear attention module. Multi-dimensional feature representation is constructed by using question embedding, concept embedding and answer embedding, and fine adjustment of knowledge states is realized through a gating mechanism and a state updating module. The linear attention calculation and rotation position coding technology of amplitude perception is adopted, so that the capturing capability of the model on the long-term dependency relationship is enhanced while the calculation efficiency is ensured. A knowledge forgetting rule is dynamically reflected through a time decay factor and a state updating mechanism, the ability and problem characteristics of a learner are quantified in combination with an IRT model idea, and accurate modeling and performance prediction of the learning process of the student are achieved.

The invention discloses a search engine user intention recognition method based on multi-agent collaboration. The search engine user intention recognition method comprises the following steps: S1, constructing a state vector and generating a session pulse sequence; s2, constructing a multi-agent liquid state machine set, initializing parameters and establishing a communication channel; s3, inputting the pulse sequence into a session understanding state machine, outputting a semantic slot vector, and combining state vector scoring and searching to generate a candidate intention; s4, inputting the candidate intention and the semantic slot vector to a task planning state machine, constructing an intention graph and generating an evidence list; s5, inputting the state vector and the evidence list to an evidence retrieval state machine to obtain an evidence set; s6, inputting a state vector to a knowledge state machine to generate prior bias, and combining evidence and intention to perform aggregation; and S7, outputting an intention label according to a gating mechanism and updating parameters. According to the method, high-precision intention recognition in a multi-round search scene is realized, and the timeliness and credibility of a retrieval result are improved.

The invention provides a knowledge base content controllable generation method and system based on a large model, and the method comprises the steps: obtaining multi-source forestry data, carrying out the standardization processing, and constructing graph structure data; based on the graph structure data, knowledge representation learning is carried out through a graph neural network model, and a node-level knowledge representation set and a region-level knowledge representation set are generated; based on the region-level knowledge representation vector, fusing semantic vectors of the target region and the adjacent region to generate region fusion knowledge representation of the target region, and performing reasoning in combination with data uncertainty to generate a trigger probability of a target region management action; constructing a historical cache according to the historical change represented by the regional fusion knowledge, and generating a regional knowledge state cache and a locally optimized reasoning parameter; and generating a personalized action management scheme based on the regional knowledge state cache and the locally optimized reasoning parameters. According to the invention, efficient integration, intelligent reasoning and dynamic decision-making of multi-source forestry data can be realized.

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 present application relates to the technical field of knowledge tracking, and relates to a method for dynamically evaluating student knowledge level based on a double attention mechanism, comprising the following steps: S1. obtaining interactive information of a student learning process, and grouping the interactive information into a sequence; S2. dividing the interactive sequence into three parts, namely a dynamic problem level sequence, an average skill level sequence and an additional feature sequence; S3. inputting different sequences into corresponding modules for training, and obtaining a student knowledge state through a long short-term memory network and multiple attention mechanisms; S4. inputting the knowledge state into an interpretability module to evaluate the knowledge level; and S5. recording training model evaluation indexes, verifying the interactive sequence of the student through a model updated by parameters, and evaluating the knowledge level of the student. The present application fully mines the interactive information of the student, evaluates the knowledge state of the student from different angles, and improves the accuracy of predicting the future performance of the student.

The invention discloses a personalized smart course recommendation system for oral medicine based on a knowledge graph, and belongs to the technical field of course recommendation, and the system comprises a collection module which collects and fuses dominant static features and recessive behavior features of a user to form preliminary capability evaluation data; the analysis module is used for matching the preliminary capability assessment data with a preset oral internal medicine knowledge graph to generate a knowledge state mapping graph; the generation module is used for generating an optimal learning path from the current knowledge state to the target knowledge state according to a preset teaching strategy and a learning target on the basis of the knowledge state mapping graph; and the recommendation explanation module is used for analyzing the optimal learning path, enabling a preset course unit to correspond to the knowledge node to be consolidated or the association relationship, generating natural language description and completing personalized course recommendation. According to the method, the dominant static characteristics and the recessive behavior characteristics of the user are collected and fused to form the preliminary capability evaluation data, so that the accuracy of the initial recommendation stage is remarkably improved.

The application relates to the technical field of decision management, and provides a phosphorus mine industrial internet intelligent decision method and system based on a knowledge graph. Production data in a phosphorus mine industry is collected through intelligent sensors, and decision information is generated by performing edge processing on the production data through an edge computing node; knowledge tuples are generated based on the production data and the decision information; entity devices and their relationship information are mapped into device nodes and edges of a Bayesian network, a knowledge state code and a hidden state at a set time are generated based on a confidence weight of the device nodes; the knowledge state and probability of the device nodes at a next time are predicted based on the hidden state at the set time; and a dynamically evolved knowledge graph is generated based on the hidden state at the set time and the knowledge state and probability at the next time, so that the phosphorus mine industrial production is decided through the knowledge graph. The dynamically evolved knowledge graph generated by the scheme can assist decision making, and the efficiency and accuracy of dynamic decision making in the phosphorus mine industrial production are improved.

The invention discloses a difference privacy knowledge tracking method and system considering a forgetting factor and a medium, and the method comprises the steps: carrying out the embedding of knowledge points of a target question, obtaining a knowledge point embedded vector, extracting the forgetting factor through combining with a forgetting matrix which records the timestamps of the last learning of all knowledge points by all students, and obtaining the forgetting factor; performing inner product operation with a knowledge state matrix recording the mastering degrees of all students on all knowledge points to obtain a knowledge state matrix considering forgotten knowledge, and performing differential privacy protection to generate knowledge state representation of the students; fusing with the question embedding vector of the target question to generate a feature vector, and calculating the question doing ability of the students on the knowledge points; and calculating the answering probability of the student to the target question according to the question answering ability. The invention aims to realize knowledge tracking oriented to forgetting demands, and balance between privacy protection and model prediction effectiveness is realized in an actual scene of a student continuous'question-answer 'sequence flow on which knowledge tracking depends.

The invention relates to the technical field of computer data processing, in particular to an anti-factual knowledge tracking method and system based on consistency constraint. The method comprises the following steps: S1, constructing knowledge mastering degree representation of a tracking object; s2, constructing an anti-fact knowledge mastering degree of the tracking object under the condition of an opposite answer result; s3, constructing a consistency constraint condition: regarding knowledge mastering degrees under an actual answer result and an anti-fact answer result as negative sample pairs, and constraining a difference value of the knowledge mastering degrees under different answer conditions by comparing a loss function; and S4, based on the consistency constraint condition, establishing an evaluation index for evaluating the accuracy of the knowledge state. According to the method, the modeling accuracy and the interpretability of an existing knowledge tracking model are improved by proposing the consistency constraint condition between the dominant answering behavior and the invisible knowledge state of the tracking object.

The invention relates to the technical field of reinforcement learning, and discloses a deep reinforcement learning-based team knowledge gap dynamic prediction method, which comprises the following steps of S01, performing team real-time data knowledge graph coverage analysis, S02, performing multi-layer deep neural network feature extraction to obtain a team knowledge environment, and S02, performing multi-layer deep neural network feature extraction to obtain a team knowledge gap. S03, comprehensively sensing and outputting a current execution action by a team knowledge environment, S04, predicting and obtaining an instant reward of environment interaction through knowledge state information, S05, updating parameters of a neural network based on a loss function, and S06, completing team knowledge gap dynamic prediction according to the updated parameters of the neural network. The multi-layer deep neural network is used for carrying out feature extraction on the team knowledge environment, instant rewards of environment interaction are obtained, the accuracy of the prediction model is further optimized, parameters of the neural network are updated based on a loss function, and dynamic prediction of the team knowledge gap is completed according to the updated parameters of the neural network.

The invention relates to the technical field of ship design knowledge management, and discloses an incremental knowledge operation management method for ship design knowledge big data, and the method comprises the steps: firstly obtaining initial knowledge data of a ship design knowledge base, setting an incremental label, obtaining meta-information records, carrying out the classification processing, and carrying out the hierarchical storage; an operation terminal update label is set to be associated with the increment label, knowledge data is synchronized, and an update period is matched according to time information; comparing the knowledge state of the operation terminal with the updating period, and generating an updating prompt instruction; and obtaining the use frequency to calculate the knowledge activity index, transmitting the knowledge activity index to the management background terminal in combination with the operator identifier, verifying the updated knowledge, and then adjusting the knowledge priority. According to the method, ordered storage, timely updating and reasonable utilization of knowledge data are realized, the retrieval efficiency is improved, the knowledge timeliness is ensured, the knowledge management is optimized, and the overall level of ship design is improved.

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

The invention discloses a target-driven exercise recommendation method based on cognitive attention enhancement. The method comprises the steps of data acquisition and processing, key feature extraction, cognitive attention depth Q network construction, cognitive attention depth Q network training and cognitive attention depth Q network testing. According to the method, the cognitive enhanced attention network which takes the time forgetting effect and the practice history effect as learnable bias items and is integrated with attention score calculation is constructed, so that the dynamic knowledge state of the student is accurately evaluated; a target condition depth Q network is constructed, and a current knowledge state of a student and a preset target knowledge state are spliced as input so as to generate a recommendation decision oriented to a long-term target; and a dual decoupling reward mechanism is constructed to guide the target condition depth Q network to perform efficient learning. The problem that a traditional recommendation method lacks long-term planning is solved, the method has the advantages of being accurate in diagnosis, efficient in recommendation, high in target guidance and the like, and an efficient learning path sequence is generated for students.

The invention belongs to the field of knowledge cognition level mining and adaptive teaching systems, and provides a personalized cognition level mining method based on subjective and objective test question collaborative modeling. Obtaining learner-test question interaction data, constructing a knowledge point vector according to the Q matrix, and generating an initial mastering vector based on the student ID; three types of personalized parameters including slip, guess and difficulty are introduced, and the difficulty and the mastery degree are modulated and then spliced with the Q matrix to form a feature sequence; a bidirectional LSTM is adopted to extract time sequence dependence, a knowledge state input update network is combined, and state estimation is dynamically generated; and splicing with a test question Q vector, inputting into a score prediction network, and fusing slip and guess to construct an improved IRT function. Training is supervised by using historical answer records, prediction errors are minimized, an early stop mechanism is introduced, objective question accuracy and subjective question mean square errors are output, multi-dimensional evaluation is realized, and prediction performance and universality are improved.