Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

79 results about "Educational assessment" patented technology

Educational assessment or educational evaluation is the systematic process of documenting and using empirical data on the knowledge, skill, attitudes, and beliefs to refine programs and improve student learning. Assessment data can be obtained from directly examining student work to assess the achievement of learning outcomes or can be based on data from which one can make inferences about learning. Assessment is often used interchangeably with test, but not limited to tests. Assessment can focus on the individual learner, the learning community (class, workshop, or other organized group of learners), a course, an academic program, the institution, or the educational system as a whole (also known as granularity). The word 'assessment' came into use in an educational context after the Second World War.

Dynamic vocational ability and post matching education evaluation method based on knowledge graph

The invention discloses a knowledge graph-based dynamic vocational ability and post matching education evaluation method. The method comprises the steps of S1, constructing a vocational ability knowledge graph; s2, constructing a post demand knowledge graph; s3, designing and training a double-layer generative adversarial network model; s4, matching the vocational ability enhancement scheme and the post demand change generated by the double-layer generative adversarial network model with the existing vocational ability knowledge graph and post demand knowledge graph; s5, updating the vocational ability knowledge graph and the post demand knowledge graph in real time based on the dynamic change of the market demand and the development condition of the individual vocational ability, generating a new matching relationship by using a double-layer generative adversarial network model, and continuously optimizing a matching result; and S6, according to the optimized matching result, generating an education evaluation report and an occupational planning suggestion. According to the invention, the dynamic adaptability and the matching accuracy of vocational ability and post matching are remarkably improved, and accurate docking between job seekers and post requirements is realized.
Owner:GUANGXI POLICE ACAD

Whole-cycle intelligent education evaluation system based on knowledge graph

The invention provides a full-cycle intelligent education evaluation system based on a knowledge graph, and relates to the technical field of data processing, and the system is used for carrying out the correlation analysis of a learning behavior data set and a knowledge point data set of a student, calculating the mastering degree of the student on each knowledge point, recognizing the relation between the student and each knowledge point, and carrying out the calculation of the mastering degree. The method comprises the following steps: acquiring knowledge points of students, mapping the knowledge points into a graph structure to obtain a staged knowledge graph, updating the staged knowledge graph, adjusting the relationship between the students and each knowledge point to obtain a dynamic knowledge graph, extracting the real-time mastery degree of each knowledge point according to the dynamic knowledge graph, and periodically analyzing the knowledge points in combination with time dimensions. And obtaining periodic evaluation data, analyzing the mastering degree, the progress trend and the weak knowledge points of the students at each knowledge point, and generating an individual evaluation data set. According to the invention, the knowledge graph can be constructed to periodically evaluate the learning condition of the student.
Owner:XIAMEN YIXUE SOFTWARE CO LTD

Education evaluation and feedback system based on artificial intelligence

The invention, which relates to the technical field of artificial intelligence, discloses an artificial intelligence-based education evaluation and feedback system comprising a data acquisition module, a vector generation module, a prediction module, an error region positioning module and a feedback module. The system constructs a unified high-dimensional cognitive state vector by collecting answering behaviors, eye movement tracks, facial micro-expressions, voices and intonations and electroencephalogram signals of students; generating a learning evolution path map based on a dynamic Bayesian network and a causal reasoning mechanism, and predicting future learning bottleneck nodes; an error region is recognized through semantic deconstruction and graph matching, and context-associated personalized feedback content is generated in combination with a generative language model; according to the system, an evaluation feedback closed loop of cognitive state modeling, accurate identification of an erroneous region and intelligent feedback pushing is realized, and the accuracy of education evaluation and the effectiveness of intervention are improved.
Owner:JINING POLYTECHNIC

Job semantic evaluation method based on multi-modal large model

The invention discloses a homework semantic evaluation method based on a multi-modal large model, and relates to the technical field of education intelligent evaluation, and the method comprises the steps: 1, normalizing multi-modal answers into a step sequence, a scoring key point map, an acceptable answer set and an initial scoring anchor point, and building a step and key point bidirectional index; 2, performing consultation according to teacher roles, generating candidate scores and key credits, and calculating a key point coverage degree, a consistency degree and a contradictory proportion; and step 3, reading the conditional reliability ledger, generating a comprehensive weight, aggregating the comprehensive weight to obtain a final score, and outputting an uncertainty index at the same time. 4, giving out hierarchical personalized explanation, determining a minimum correctable step, executing step-level echoing, and generating a training list; 5, carrying out anchor question online calibration and fusion parameter updating, and setting a trigger proportion upper limit and an early stop threshold according to a budget perception route; the link realizes unified measuring scale, steady decision, traceable learning and controllable cost.
Owner:北京爱宾果科技有限公司

Metacognitive level prediction method based on sounding thinking driven retrieval enhancement

The invention discloses a meta-cognition level prediction method based on voiced thinking driven retrieval enhancement, which is characterized in that an information extraction method in a deep learning technology is adopted to extract answer features, a voiced thinking response analysis library is constructed, a correlation mode between various answer contents and corresponding meta-cognition scores is established, and a prediction result is obtained. The method comprises the following steps: establishing a mapping model, bridging the internal relation between the answer content and the meta-cognitive level by using the established mapping model, matching the sound thinking answer with the existing answer sample in a sound thinking response analysis library to realize the prediction of the meta-cognitive level, and specifically comprising the steps of data collection, data enhancement, big five personality correction, mapping model establishment, matching, retrieval and the like. Compared with the prior art, the method has the advantages that a more scientific and targeted problem design scheme can be provided on the basis of real-time evaluation of the meta-cognition level of the student when the type of problems proposed to the student is determined, so that the method has remarkable advantages in the aspects of education evaluation and personalized learning support.
Owner:EAST CHINA NORMAL UNIV

Educational Evaluation Method for Dynamic Vocational Competence and Post Matching Based on Knowledge Graph

ActiveCN119228609BData processing applicationsBiological modelsCareer planningEducational evaluation
The present invention discloses an educational evaluation method for dynamic vocational ability and job matching based on a knowledge graph. S1. Construct a vocational ability knowledge graph; S2. Construct a job requirement knowledge graph; S3. Design and train a double-layer generative adversarial network model; S4. Match the vocational ability enhancement plan and job requirement changes generated by the double-layer generative adversarial network model with the existing vocational ability knowledge graph and job requirement knowledge graph; S5. Based on the dynamic changes in market demand and the development of individual vocational abilities, update the vocational ability knowledge graph and job requirement knowledge graph in real time, and use the double-layer generative adversarial network model to generate new matching relationships to continuously optimize the matching results; S6. Generate an educational evaluation report and career planning suggestions according to the optimized matching results. The present invention significantly improves the dynamic adaptability and matching accuracy of vocational ability and job matching, and realizes the precise docking between job seekers and job requirements.
Owner:GUANGXI POLICE ACAD

Intelligent student test paper marking and multi-dimensional evaluation system based on artificial intelligence large language model

The invention relates to an intelligent student test paper marking and multi-dimensional evaluation system based on an artificial intelligence large language model. The system comprises a plurality of functional modules: a test paper content input module, an automatic marking module driven by a large language model, a personalized feedback module, a multi-dimensional evaluation module, a self-adaptive scoring module, an open question marking module, a transparent scoring report generation module and a teacher intervention module. The system can automatically process various types of test questions, especially complex open problems, and performs intelligent review and evaluation through a large language model. Through the multi-dimensional evaluation module, the system not only evaluates the answer correctness of the students, but also can perform comprehensive evaluation from multiple aspects of logical thinking, analysis ability, innovation ability and the like. And the personalized feedback module provides customized learning suggestions based on historical performance for the students, so that the learning efficiency of the students is improved. The self-adaptive scoring module dynamically adjusts the scoring standard according to the answer condition of the student to ensure fairness and reasonability. The system also generates a transparent scoring report, and allows the teacher to intervene and adjust the scoring result, so as to form a cooperation mode combining intelligentization and manual evaluation. The test paper marking efficiency and evaluation quality can be greatly improved, and the method is suitable for various education evaluation scenes.
Owner:LIAONING UNIVERSITY OF PETROLEUM AND CHEMICAL TECHNOLOGY

Education evaluation system based on artificial intelligence

The invention provides an artificial intelligence-based education evaluation system, which establishes a multi-dimensional student evaluation standard feature set and a multi-dimensional teacher evaluation standard feature set by crawling historical data, and respectively substitutes collected data uploaded by a teacher terminal, a school terminal, a student terminal and a parent terminal into an education matching degree model for matching degree calculation. The multi-dimensional student evaluation matching degree and the multi-dimensional teacher evaluation matching degree are subjected to weighted calculation according to a preset weight value to obtain a student learning evaluation result and a teacher teaching evaluation result, and the results are fed back to the teacher terminal, the school terminal, the student terminal and the parent terminal. According to the invention, the evaluation of student learning and teacher teaching is more objective and reasonable, and students, parents, teachers and schools are all used as participants of evaluation, so that the students, parents, teachers and schools can know education conditions in time, close connection among the students, parents, teachers and schools is increased, and good sustainable development of education relationships is facilitated.
Owner:XIANYANG VOCATIONAL TECHN COLLEGE

Personalized semantic evaluation system combined with knowledge graph

ActiveCN119540007AData processing applicationsSemantic analysisPersonalizationEducational evaluation
The invention discloses a personalized semantic evaluation system combined with a knowledge graph, and relates to the technical field of educational evaluation, and the system comprises the steps: obtaining a pre-constructed mathematical knowledge graph and a preset mathematical knowledge point set, and determining a target knowledge point frame; obtaining a test paper sequence and a test paper standard answer sequence of the target user in historical time, and performing matching analysis to obtain a test question score set sequence; performing test question semantic analysis, and determining a test knowledge point set sequence; respectively mapping and inputting the test knowledge point set sequence and the test question score set into a target knowledge point framework to obtain a test knowledge point score framework sequence; and performing iterative association interaction analysis, determining a target interaction test knowledge point score framework, performing analysis, and determining a target mastery degree evaluation result. The technical problem that the knowledge point mastering degree of a user cannot be accurately evaluated in the prior art is solved, and the technical effect of providing an accurate basis for learning condition evaluation is achieved.
Owner:SHANDONG SHUNSHI EDUCATION TECH GRP CO LTD

Digital informatization physical education comprehensive management system

The invention relates to the technical field of physical education management, and particularly discloses a digital informatization physical education comprehensive management system, which comprises a user interaction module, a data acquisition module, a data processing module, a system optimization module and a distributed database, the data acquisition module acquires teaching content, motion completion degree and user physiological data through a camera, a motion capture sensor and wearable equipment; the data processing module cleans and converts the data, and quantitatively evaluates whether the learning results of the students are qualified or not by using a constructed education evaluation coefficient mathematical model; the system optimization module calculates a scene optimization coefficient by analyzing a user favorable comment trend and multimedia loading performance, and automatically identifies a teaching scene needing to be optimized; the distributed database adopts a master-slave replication and fragmentation technology to improve data access efficiency and fault tolerance, digital management of physical education is achieved, and therefore the quality and efficiency of physical education are improved.
Owner:SHANDONG UNIV OF FINANCE & ECONOMICS

Automatic test paper marking method and system based on generative artificial intelligence

ActiveCN119540972Aimprove interpretabilityOvercome the limitations of traditional systemsInstrumentsLearning machineEducational evaluation
The invention provides an automatic test paper reviewing method and system based on generative artificial intelligence, and relates to the technical field of artificial intelligence and educational evaluation, and the method comprises the steps: obtaining an image of a paper answer test paper, carrying out the content recognition of the processed image, and obtaining the content of an answer image; performing anomaly detection and correction on the content of the answer image through a generative artificial intelligence large model; performing feature extraction on the content of the corrected answer image; extracting key information from the corrected content of the answer image by using a generative artificial intelligence large model, and embedding the key information to form a new feature vector of the content of the answer image; calculating a cosine similarity score and a generative artificial intelligence large model prediction score; when a serious gap exists, a collaborative active learning mechanism is introduced, and the answer confidence of the examinee is evaluated; and when the confidence coefficient is higher than a given threshold value, outputting a prediction score. According to the method, the generative artificial intelligence large model technology is applied to the review process in a full cycle, and automatic test paper review is achieved.
Owner:SHANDONG JIANZHU UNIV

Cognitive function digital evaluation system and method based on dynamic visual tracking

The invention discloses a cognitive function digital evaluation system and method based on dynamic visual tracking, four attention function tests are integrated in one system for the first time, the attention function of an individual can be comprehensively evaluated, and a more comprehensive and more systematic cognitive function evaluation report is provided; compared with a traditional single-function test, the cognitive condition of an individual can be known more comprehensively, and a more valuable reference is provided for the fields of educational evaluation, clinical diagnosis, human resources and the like; for example, in education evaluation, a teacher can comprehensively understand attention characteristics of students through the system and make a more targeted teaching plan; in clinical diagnosis, a doctor can comprehensively evaluate the cognitive function of a patient to assist diagnosis and treatment.
Owner:BEIJING INST OF TECH

Teaching evaluation system based on artificial intelligence and big data

InactiveCN119809461AData processing applicationsEducational evaluationEngineering
The invention discloses a teaching evaluation system based on artificial intelligence and big data, relates to the field of education evaluation, solves the problems that existing teaching evaluation depends on artificial questionnaire survey or examination scores, and is high in subjectivity and single in data dimensionality, and comprises a data processing module, a basic analysis module, an expansion analysis module and a comprehensive evaluation module, the data processing module is used for processing the average score of each culture course test of the class, sending the score data obtained by processing to the basic analysis module, and sending the expansion data obtained by processing to the expansion analysis module; the basic analysis module is used for analyzing the score level and stability of a class, the expansion analysis module is used for analyzing the expansion ability of students, and the result output module is used for generating comprehensive teaching evaluation for a class owner of the class, and comprehensive evaluation of the teaching condition is realized based on artificial intelligence and big data.
Owner:BEIJING XIQI NETWORK TECH CO LTD

A cross-time point cognitive diagnosis method considering students' influencing factors

The present invention discloses a cross-time point cognitive diagnosis method that considers student influencing factors, belonging to the field of educational assessment technology, comprising: obtaining student answer data at several time points, fitting the student answer data at each time point respectively; assigning each student to a potential knowledge mastery state based on the fitting results, and calculating the classification error probability; constructing a potential transfer cognitive diagnosis model, optimizing the potential transfer cognitive diagnosis model based on the classification error probability, obtaining an estimated initial state probability and an estimated transfer probability based on the optimized potential transfer cognitive diagnosis model; and performing cross-time point cognitive diagnosis on students based on the estimated initial state probability and the estimated transfer probability. The present invention can effectively analyze the impact of covariates on students' initial state, as well as the changing pattern of potential knowledge mastery state at different time points.
Owner:JINAN UNIVERSITY

English reading understanding ability analysis system based on deep learning

The invention relates to the technical field of education evaluation, in particular to an English reading understanding ability analysis system based on deep learning, which comprises the following steps: an answer text analysis module, a reading mode analysis module, an attention ability evaluation module, an efficiency score calculation module, an understanding obstacle recognition module and a reading ability evaluation module. According to the method, the keyword in the answer text of the student is extracted and compared with the preset answer, so that the understanding degree of the student on the English reading understanding text is effectively identified, and the reading behavior of the student is monitored in real time, so that the attention of the student can be identified in a concentrated and dispersed time period; the attention level and the reading efficiency of the student are effectively evaluated, and in combination with the detection of reading disorder and the analysis of the ability level of the student, an educator is helped to quickly and accurately grasp the learning condition of the student and adjust the teaching strategy and content, so that the individualized requirements of the student are met, and the learning efficiency and the education quality are effectively improved.
Owner:CHANGCHUN UNIV OF CHINESE MEDICINE

Higher education textbook quality evaluation method and system based on particle swarm big language model

The invention provides a higher education textbook quality evaluation method and system based on a particle swarm big language model, and relates to the technical field of education evaluation. The method comprises the steps of collecting text data of higher education textbooks; preprocessing the text data by using a particle swarm optimization algorithm to obtain preprocessed data; constructing a large language model based on a particle swarm, and performing feature extraction on the preprocessed data through the large language model to obtain feature data; the feature data comprises semantic features, structural features and quality features; performing comprehensive evaluation on the feature data through the evaluation function to obtain a comprehensive evaluation score; and comparing the comprehensive evaluation score with a preset standard score to determine the quality grade of the textbook. By comprehensively evaluating the textbook features, flexibly optimizing feature selection and scientifically setting the quality standard, the accuracy and practicability of textbook quality evaluation are remarkably improved.
Owner:ZUNYI NORMAL COLLEGE

Education evaluation method and system based on visual identification data analysis

The invention discloses an education evaluation method and system based on visual identification data analysis, and relates to the technical field of education analysis, and the method comprises the steps: presetting the understanding difficulty for each mapping node, and taking the understanding difficulty as a teaching path reference; performing semantic analysis on the explanation scheme, extracting knowledge points and secondary and supplementary key phrases, and associating the knowledge points and the secondary and supplementary key phrases to corresponding mapping nodes to realize content structuring; acquiring real-time classroom voice information, extracting and analyzing characters to determine real-time keywords, positioning corresponding nodes in the mind map, sequentially connecting the nodes to form a real-time map node sequence line, and capturing an actual explanation path; calculating student initial state evaluation, combining node difficulty correction to obtain final evaluation, and accumulating all student evaluation as a teaching effect; taking a preset explanation order line teaching effect corresponding to the real-time order line as a standard, determining the relative positioning of actual evaluation, and achieving deviation quantification; according to the invention, through multi-modal fusion and a dynamic order line mechanism, the real-time performance and accuracy of evaluation are improved, and teaching improvement guidance is provided.
Owner:SHENZHEN POLYTECHNIC

Digital archive management system based on multi-modal knowledge graph and block chain

The invention relates to the technical field of educational informatization and block chain technology fusion, and particularly discloses a digital archive management system based on a multi-modal knowledge graph and a block chain, which comprises four core layers: a self-adaptive block chain evidence storage layer ensures credible sharing of cross-mechanism data; the multi-modal knowledge graph intelligent construction layer realizes unified understanding and correlation analysis of multi-modal data; an evaluation engine driven by deep learning completes intelligent evaluation and personalized recommendation; and the intelligent education evaluation support layer provides decision support and risk early warning. According to the method, Transform, a graph neural network, a time sequence graph neural network and the like are fused, the problems that in the prior art, achievement verification is difficult, multi-modal processing is weak, graph construction is immature, evaluation is rigid and the like are solved, data credibility, system adaptability, decision making scientificity and user experience are remarkably improved, and advanced technical support is provided for educational informatization.
Owner:HUACHEN ZHIYU (BEIJING) TECHNOLOGY CO LTD

Method for evaluating vocational education effect based on learning behavior data mining

This invention relates to the field of computer technology and discloses a method for evaluating the effectiveness of vocational education based on learning behavior data mining. The method includes: collecting learners' full-domain learning behavior data sequences; generating cognitive style feature vectors through a self-attention sequence encoder; dynamically weighting the behavioral features using style gating units to form a style-weighted effective behavioral feature matrix; combining a pre-constructed vocational skills knowledge graph and aggregating the behavioral features layer by layer through a graph neural network to calculate the mastery score of each skill node; and finally generating an evaluation report containing multi-dimensional evaluation results and personalized suggestions. This invention achieves accurate, objective, and personalized skills assessment for learners with different cognitive styles, improving the fairness and diagnostic value of vocational education evaluation.
Owner:NANCHONG VOCATIONAL & TECH COLLEGE

system

PendingJP2026073334AData processing applicationsInformation processingEducational evaluation
We provide the system. [Solution] Equipped with an information processing device for automating educational evaluation, A means for selecting multiple educational issues based on one or more conditions and automatically generating an educational assessment test, A means of performing automatic scoring by comparing the received answer data with the model answer, A system including means for generating and presenting scoring results and feedback.
Owner:SOFTBANK GROUP CORP

A Likelihood-Based Q-Matrix Estimation Method for Cognitive Diagnosis

ActiveCN120596861BData processing applicationsQ-matrixMedicine
The application discloses a likelihood-based cognitive diagnosis Q matrix estimation method, belongs to the field of cognitive diagnosis evaluation, and comprises the following steps: obtaining response data of students to questions and a partially defined Q matrix, fitting a G-DINA model to obtain a posterior distribution of a student attribute vector, and calculating a marginal likelihood based on the posterior distribution. Furthermore, the fitting degrees of different q vectors are evaluated through AIC or BIC values, the optimal q vector is selected to gradually fill unknown parts of the Q matrix, and the process is continued until convergence. The method reduces the dependence on experts, improves the accuracy and efficiency of Q matrix estimation, and is suitable for large-scale education evaluation scenarios.
Owner:JINAN UNIVERSITY

Examination proposition person behavior model construction method and system based on deep learning

ActiveCN120822160ABiological modelsKnowledge representationEducational evaluationAlgorithm
The invention provides an examination proposition person behavior model construction method and system based on deep learning, and relates to the field of artificial intelligence and educational evaluation, and the method comprises the steps: obtaining proposition records, constructing a knowledge application graph, analyzing proposition preferences based on a time window, training a proposition behavior recognition network, and optimizing a migration path and difficulty distribution. And anomaly detection of proposition behaviors is realized. According to the method, the knowledge preference and the behavior mode of the proposition person can be accurately described, the proposition quality monitoring efficiency is improved, the proposition risk is reduced, and the examination fairness is guaranteed.
Owner:ATA ONLINE (BEIJING) EDUCATION TECH LTD

Education evaluation and feedback system based on artificial intelligence

The invention relates to the technical field of artificial intelligence and education, in particular to an education evaluation and feedback system based on artificial intelligence. Comprising a multi-modal data acquisition module, a data preprocessing and fusion module, a dynamic knowledge graph construction module, a multi-dimensional evaluation analysis module, a personalized feedback generation module, a teaching intervention push module and a system iteration optimization module, all the modules are linked in sequence, and the system iteration optimization module and the data preprocessing and fusion module form a closed loop. According to the method, the traditional score only theory is broken through, a knowledge-ability-thinking-emotion four-dimensional evaluation system is constructed, three-dimensional cognition of students is realized in combination with multi-modal data, the evaluation result better meets the essential requirements of education, the learning process of the students is tracked in real time through the dynamic knowledge graph and the improved Bayesian network model, and the learning efficiency of the students is improved. The evaluation result is adjusted according to the knowledge mastering condition and ability growth, and the defect of staticization of traditional evaluation is overcome.
Owner:YUNNAN MINZU UNIV

A knowledge text-based cognitive diagnosis model and a cognitive diagnosis method thereof

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.
Owner:GUANGDONG UNIV OF TECH

Labor education practice self-adaptive evaluation system and device based on multi-source perception

The invention discloses a labor education practice self-adaptive evaluation system and device based on multi-source perception, and relates to the technical field of intelligent management, and the system comprises a perception terminal module which is used for collecting student labor data and environment change data in real time; the data processing module is used for carrying out deep integration analysis on the multi-source sensing data and establishing a labor behavior portrait of the student; the self-adaptive evaluation module is used for carrying out self-adaptive labor evaluation according to the labor behavior portrait of each student; and the feedback interaction module is used for performing periodic assessment summarization and multi-party information interaction according to the personalized labor assessment report. The technical problems that existing labor education evaluation depends on subjective judgment, interference factors are many, real-time feedback cannot be achieved, and the reliability of the evaluation result is poor are solved, comprehensive and real-time student labor performance evaluation and personalized feedback are achieved through a self-adaptive evaluation mechanism relying on multi-source perception and robustness artificial intelligence, and the evaluation efficiency is improved. And the reliability of the evaluation result is improved.
Owner:SHANDONG HOUCHENG INTELLIGENT TECH CO LTD

Systems and methods for extended reality educational assessment

A system and associated methods facilitate administration of assessments within an extended reality learning environment. Assessment recordings captured during administration of an assessment module to a first user are used for providing feedback information to the first user from a second user that can view the first user's interactions with the assessment module.
Owner:CURIOXR INC

A Deep Learning-Based Method and System for Constructing a Behavioral Model of Exam Question Setters

This invention provides a method and system for constructing a deep learning-based model of exam question setter behavior, relating to the fields of artificial intelligence and educational assessment. The method includes acquiring question-setting records to construct a knowledge application graph, analyzing question-setting preferences based on time windows, training a question-setting behavior recognition network to optimize transfer paths and difficulty distribution, and achieving anomaly detection in question-setting behavior. This invention can accurately characterize the knowledge preferences and behavioral patterns of question setters, improve the efficiency of question-setting quality monitoring, reduce question-setting risks, and ensure exam fairness.
Owner:ATA ONLINE (BEIJING) EDUCATION TECH LTD

Multi-modal data fusion-based multi-element intelligent evaluation and career planning consultation system

The invention discloses a multivariate intelligent evaluation and career planning consultation system based on multi-modal data fusion, and belongs to the crossing field of artificial intelligence and education evaluation. The system comprises a multi-modal data acquisition module, a preprocessing module, a multivariate intelligent evaluation module, a cross combination analysis module, a dynamic updating module and a personalized recommendation module. The acquisition module integrates structured data (questionnaires, academic data and genes) and unstructured data (behaviors, voices and images); the preprocessing module cleans, converts and fuses data; the evaluation module constructs an'intelligence-capability 'secondary model, and quantifies 8 items of intelligence and 40 items of core capability; the cross analysis module generates a potential label; the dynamic updating module iterates the result in real time; and the recommendation module outputs interest, academic, professional and career planning suggestions. The system solves the problems of single traditional evaluation data, rough evaluation, poor dynamics and the like, and improves the planning precision and timeliness.
Owner:GUANGDONG HUAQIFU CAREER PLANNING CONSULTING CO LTD

A cognitive analysis system that focuses on ability changes and item characteristics

The application belongs to the technical field of education evaluation, and discloses a cognitive analysis system focusing on ability change and question characteristics, which comprises an interactive coding network module, an ability acquisition module, an ability prediction module, an ability rationality module, a question prediction module, a knowledge point prediction module and a multi-task fusion module. The ability prediction module, the question prediction module and the knowledge point prediction module are used to respectively predict the probability of answering the next exercise correctly. Finally, the multi-task fusion module balances the three types of prediction probabilities through a fusion training mode to obtain the final probability of answering the next exercise correctly, and the final probability is used for cognitive analysis of the subject. The application can track the ability change of the subject in real time, provide dynamic ability value evaluation, and better reflect the ability development in the learning process.
Owner:BEIJING CENTURY TAL EDUCATION TECH CO LTD

Large model generation text detection method based on multi-agent cooperation

The invention discloses a large model generation text detection method based on multi-agent cooperation. The method comprises the following steps: 1) input text processing: carrying out differential disturbance processing on an input text through three heterogeneous agents; 2) semantic similarity evaluation: performing similarity scoring on an original text and a modified text generated by each agent by using a scoring method BARTScore based on a sequence-to-sequence pre-training model, and normalizing to an interval of [0, 1]; 3) threshold value judgment: determining the optimal threshold value of each agent through the Youden's J statistical magnitude; and 4) a voting decision mechanism: performing final classification judgment by adopting a majority voting mechanism according to judgment results of the three agents. The method does not need to depend on annotated data and field fine tuning, through multi-dimensional feature decoupling and a dynamic adaptive strategy, the detection accuracy and cross-field robustness in a zero sample scene are remarkably improved, and the method is suitable for practical scenes such as educational evaluation and content auditing.
Owner:YANGZHOU UNIV