440 results about "Test question" patented technology

The invention discloses a power market large language model evaluation method and device based on dynamic scene perception, and the method comprises the steps: building a large model evaluation system covering the three dimensions of understanding, generation and safety according to a power market application scene; the method comprises the following steps: constructing a test question bank, evaluating a power market large language model according to various evaluation methods, endowing three dimensions with different weights based on a large model evaluation system in the evaluation process, constructing a test question-scene label fine tuning data set, and performing scene classification fine tuning on the model by using a fine tuning method. Evaluating scene classification performance of the fine-tuned model, and distributing corresponding initial evaluation dimension weights for different scenes; according to the requirements and differences of different scenes, the initial evaluation dimension weight is adjusted, the scene is judged to be matched with the corresponding evaluation dimension weight according to the input content, weighted summation is carried out from the three dimensions of understanding, generation and safety, and an evaluation result is obtained. According to the method, accurate evaluation of the performance and reliability of the large language model in the power field can be realized.

The invention provides a clinical thinking examination question generation and step-by-step analysis construction method and system based on a large language model, and relates to the technical field of large language models. The method comprises the steps of analyzing a teaching outline and real questions over the years, constructing a multi-level clinical knowledge graph, intercepting a knowledge sub-graph according to target difficulty, and generating case question stems, candidate options and a preliminary reasoning path covering the sub-graph; the reasoning path consistency is verified through a logic engine, a simulation answer sample is constructed, item reaction modeling is executed, and the question difficulty is estimated; if the difficulty does not accord with the target difficulty, parameters are automatically fine-tuned and re-generated, and iteration is carried out until the standard is reached; performing error selection rate driven optimization on the interference options to form a final question version; and collecting student answering data feedback atlas weight and difficulty, and writing the content into the versioned question bank. According to the invention, the accuracy of examination question generation, the teaching suitability and the continuous updating ability are improved, and the intelligent evaluation of clinical thinking ability is realized.

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.

The invention provides a self-adaptive question bank test paper formation and difficulty evaluation method and system based on a knowledge point tree, and relates to the technical field of data processing, and the method comprises the steps: constructing a knowledge point relation tree, calculating a knowledge point path to group and cluster test questions, building a multi-layer test question index structure, and calculating a real-time difficulty correction coefficient in combination with historical answer data of examinees; dynamically adjusting the priority of the test questions, and finally screening and generating target test paper according to the distribution proportion of knowledge points. According to the method, personalized test paper composition is realized, the accuracy of test question difficulty evaluation and the rationality of test paper knowledge point coverage are improved, and the requirements of adaptive learning and accurate evaluation are met.

The invention provides an intelligent paper marking system based on a large language model. The intelligent paper marking system comprises an examinee test paper character recognition module used for carrying out image processing and content recognition on scanned or shot student answer sheets or answer sheets; the subject knowledge base is used for performing systematic arrangement and representation modeling on multi-subject teaching contents; the subject knowledge retrieval module is used for performing semantic analysis and matching on test paper questions and examinee answering contents to obtain subject knowledge related to the test questions and a scoring basis; a scoring template generator module; a large language model scoring module; and the comment correction module is used for optimizing and adjusting the preliminary comments generated by the large language model and outputting final comments with more pertinence and teaching guidance significance. The technical scheme can be widely applied to automatic evaluation scenes of subjective questions in the education field.

The invention discloses a middle and primary school test question intelligent generation method based on an education big model. The method comprises the steps of generating a structured education data set; constructing an education large model specially used for intelligent generation of middle and primary school test questions; inputting target knowledge points, question types, difficulty and grade parameters, and generating a candidate test question set; setting a test question fitness function, comprehensively evaluating the knowledge coverage rate, difficulty distribution and language expression indexes of the candidate test questions, screening and optimizing the candidate test question set, and generating an optimized candidate test question set; detecting semantic accuracy, logic preciseness and teaching conformity of the test questions by using an automatic quality evaluation mechanism, and outputting test question evaluation results; and continuous optimization and self-adaptive updating of test question generation are realized. According to the method, the optimal multi-question type test question set can be automatically output on the premise of ensuring comprehensive coverage of knowledge points, reasonable difficulty distribution and excellent language quality, and the quality, balance and diversity of automatically generated test questions are greatly improved.

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.

Provided in the embodiments of the present application are a large-model performance assessment method and a related device. The method comprises: acquiring structured text description of a test material, wherein the structured text description comprises information of the test material in a plurality of dimensions; inputting the structured text description and a test question into a large language model, so as to acquire an evaluation true value; inputting the test material and the test question into a large model under test, so as to acquire an answer under test of the test question; and inputting the evaluation true value, the test question and the answer under test into the large language model, so as to acquire an assessment result for the answer under test.

A test question recommendation method based on large language model adaptive multi-level evaluation constructs a multi-level architecture including semantic consistency verification, fine-grained fact alignment and dynamic cognitive evaluation, and comprises the following steps: constructing an initialized data stream and executing dynamic random sampling; calculating discrete semantic entropy by using NLI bidirectional implication clustering so as to quantify and eliminate illusion content with high uncertainty; under the RAG framework, the test questions are deconstructed into atomic statements, and a fact deviation is corrected by calculating a retrieval relevance vector and a logical implication consistency score; analyzing and screening low-quality texts based on multidimensional language features of syntax and logic; vector fusion is carried out on the generated intention and the cognitive portrait of the student, and a dynamic evaluation index system adaptive to a specific teaching scene is constructed in real time by utilizing context learning. The problems of accuracy and adaptability of automatic question setting are effectively solved, and intelligent closed-loop control from test question generation to cognitive alignment is realized.

The invention provides a multi-agent proposition method and system based on collaborative reinforcement learning. The method comprises the following steps: constructing a multi-agent proposition framework comprising a test question generation agent and a quality inspection agent based on a large language model; constructing training data on the basis of a target subject test question set, respectively supervising and adjusting large language models on which a test question generation agent and a quality inspection agent are based, and training a reward model for evaluating the output quality of each agent for the agent; and performing multi-agent collaborative reinforcement learning training on the test question generation agent and the quality inspection agent by using the reward model to obtain a trained agent model weight. And loading the trained agent model weight into a multi-agent collaborative proposition framework, and receiving proposition requirements to generate final test questions and reference answers. A multi-agent cooperative reinforcement learning mechanism is introduced into a multi-agent system, so that the agents can form a stable and efficient cooperation strategy in a real proposition task interaction environment.

The invention discloses a multi-modal large language model training method and system, and relates to the technical field of multi-modal large model data processing, and the method comprises the following steps: training a first large model through querying a question set, a positive sample and a hard negative sample; inputting the plurality of test samples into the trained first large model, and generating a plurality of second answers based on a first preset prompt; sorting each test sample based on the plurality of second answers, and retrieving to obtain a previous candidate multi-modal document related to the test question; and training the second large model through the test problem and the corresponding previous multi-modal document. According to the method, the positive samples and the hard negative samples are jointly used for training, the model is forced to capture the fine-grained semantic boundary of correlation judgment through a contrast learning mechanism, the distinguishing capacity of the model for difficult samples is remarkably improved, and the mistaken arrangement phenomenon is avoided.

The invention relates to the technical field of artificial intelligence, and particularly provides an intelligent proposition method, system and device for simulating expert propositions and a storage medium, and the method comprises the steps: constructing a structured knowledge network fusing knowledge points, cognitive levels and proposition specifications; establishing a material vector database associated with the knowledge point system; according to the target knowledge point, proposition constraint information is extracted from the knowledge network, related materials are retrieved from a vector library, and the related materials are combined into a generative prompt to be input into a large language model to generate a test question first draft; inputting the test question first draft into at least one large language model serving as a simulation answering agent, evaluating the quality of the test questions by analyzing the answering process and result, and outputting the test questions reaching the standard. According to the method, the proposition efficiency and consistency can be remarkably improved, absolute dependence on expert experience is reduced, and automatic output of high-quality test questions is achieved.

The invention discloses a personalized education examination management method based on artificial intelligence, relates to the technical field of education examination management, and introduces and fuses teaching program data and teaching calendar data, dynamically calculates teaching progress offset, accurately constructs a time sequence embedding space reflecting an actual teaching progress, and provides a personalized education examination management method based on artificial intelligence. The problem of proposition deviation caused by different teaching progresses of areas, schools or classes is fundamentally solved; the system can automatically sense and adapt to teaching plan changes such as course adjustment and course halt, and the generated test questions are strictly limited in a knowledge point range taught at the current stage, so that the examination evaluation result can truly and effectively reflect the mastering condition of students on the currently learned content, and the reliability and validity of the examination are greatly improved; the dynamically constructed teaching time sequence embedding space is used as a core constraint condition and is deeply integrated into a prompt project and decoding generation process of a large language model, so that accurate and intelligent control on test question generation content is realized.

The invention relates to the technical field of knowledge tracking, in particular to a knowledge tracking method and system based on multi-modal auxiliary information extraction, and the method comprises the steps: obtaining learning interaction data, test question data containing graphic and text information of test questions, and a step-by-step solving process corresponding to each test question, and carrying out the auxiliary feature extraction to obtain an auxiliary information set; constructing a knowledge tracking model embedded based on an auxiliary information set, obtaining question embedding of test questions from learning interaction data of students, and embedding of answer activities covering knowledge concepts and answers of the students; establishing an attention network model, and based on question embedding and answering activity embedding, determining the degree of mastering the question and the knowledge state of the student; and performing data enhancement on the learning interaction data, enhancing representation consistency of knowledge states before and after by utilizing comparison loss constraint data, and predicting subsequent answering performance based on the current knowledge state of the student. Through multi-modal information extraction and an attention network model, the knowledge state of the student is accurately evaluated, and the answering performance is predicted.

The invention provides a knowledge tracking method and device based on a large model and causal analysis, and relates to the technical field of knowledge tracking, and the method comprises the steps: driving a large language model to carry out the multi-dimensional analysis of historical answer content through zero sample prompt learning, and generating the attribution explanation of the historical answer content; performing quantitative analysis on association between attribution explanations of the to-be-tested question and the historical answer content by using a time sequence causal attention mechanism to obtain a causal explanation set comprising a causal explanation subset and a background explanation subset; processing the causal explanation subset and the background explanation subset through a causal intervention method to generate a plurality of virtual anti-fact sequences, and performing representation learning on the anti-fact sequences by using a hierarchical aggregation network to obtain global representation for the to-be-tested question; and predicting a reaction result of a target user on the to-be-tested question based on a multi-task learning mechanism in combination with the global representation, thereby realizing mining of deep causes after answering.

The invention discloses an intelligent question bank test question generation method, system, device and equipment applied to special equipment employees, and relates to the technical field of artificial intelligence, and the method comprises the steps: receiving a test question generation request containing an initial knowledge point; determining associated information corresponding to the initial knowledge point from a preset knowledge base, wherein the preset knowledge base at least comprises a preset database and a preset knowledge graph; determining a target test question generation model according to the data type of the initial knowledge point; generating a candidate test question set based on the initial knowledge points and the associated information through a target test question generation model; verifying the candidate test question set; and when the candidate test question set passes verification, adding the candidate test question set into the intelligent question bank. The candidate test question set is generated based on the initial knowledge points and the associated information through the target test question generation model, the candidate test questions are automatically generated, and the test question generation efficiency is effectively improved.

The invention belongs to the technical field of education artificial intelligence and deep learning model optimization, and discloses a thinking tree enhancement-based test question knowledge system intelligent labeling method and system.The thinking tree enhancement-based test question knowledge system intelligent labeling method comprises the steps of collecting question data by introducing a thinking chain enhanced data generation mechanism, and generating a high-quality training sample; and a control mechanism is set, a question generation process is optimized, and the generated question is ensured to accord with teaching specifications in the aspects of knowledge point coverage, grade adaptability, difficulty matching and the like. Through a text encoder based on comparative learning optimization, the model can accurately carry out semantic alignment on questions and knowledge point labels, and label path information is fused through a double-coding mechanism, so that the hierarchical relationship between the labels and the capture capability of semantic dependence are improved. Finally, the constructed multi-label prediction model significantly improves the accuracy and generalization ability of knowledge point labeling, and can provide accurate support for personalized learning recommendation and teaching resource allocation.

The invention discloses a multi-dimensional capability construction knowledge tracking method based on learning behavior decoupling, and belongs to the technical field of knowledge tracking. The method comprises the steps of obtaining test question embedding and test question-response embedding, and obtaining learning deviation behavior characterization and multi-scale behavior characterization based on the test question-response embedding; inputting the learning deviation behavior representation and the multi-scale behavior representation into a binary state model to obtain a knowledge construction representation; obtaining a test question sequence structure representation based on test question embedding, and performing multi-scale association on the test question sequence structure representation to obtain a multi-scale test question association representation; the multi-scale test question association representation and the knowledge construction representation are subjected to student ability modeling through frequency domain perception fusion, and differential learning ability is obtained; and predicting the student test question performance based on the differentiated learning ability to obtain a student test question performance prediction value. The method improves the accuracy of student test question performance prediction.

The invention relates to the field of safety practical training, in particular to an engineering construction safety practical training method and system based on big data, and the method comprises the steps: determining a preset analysis condition corresponding to a target person according to a frame selection duration characterization value and a frame selection duration fluctuation value when the answering frequency of the target person is equal to the optimization response frequency; under a first preset analysis condition, determining a compensation mode as point location array compensation or frame parameter compensation according to a point location aggregation similarity value and a point location aggregation representation value corresponding to the test question point location distribution diagram of the target person; when frame parameter compensation is carried out, a frame parameter compensation strategy is determined according to the number proportion of the first anchoring frames and the second anchoring frames, and compensation is carried out based on frame neighborhood parameters or frame areas; under a second preset analysis condition, increasing and adjusting the number of optimization response times; the test questions are dynamically adjusted to improve the safety training efficiency.

The embodiment of the invention discloses a test question output method and device based on multi-model collaboration, electronic equipment and a medium. A specific embodiment of the method comprises the steps of performing multi-source data fusion on a multi-source test question association data set, and then performing knowledge point association analysis to obtain a dynamic test question knowledge point graph; performing multi-hop graph reasoning query on the dynamic test question knowledge point graph to obtain a test question associated knowledge point set; performing model collaborative generation on the test question generation request information and the test question associated knowledge point set to generate an initial test question set; performing quality evaluation on the initial test question set to obtain a test question quality evaluation value set; dynamically adjusting the initial test question set to obtain an adjusted test question set and storing the adjusted test question set; and carrying out expansion adaptive test paper group rendering display on the adjusted test question set to obtain a test question test paper and printing the test question test paper. According to the embodiment, the test question quality can be improved, the test question generation efficiency is improved, the test question generation duration and display duration are shortened, the test question display quality is improved, and waste of display resources is reduced.

The embodiment of the invention discloses a question bank generation method and device, equipment and a storage medium, and the method comprises the steps: obtaining historical examination data of a target object, and determining an individual forgetting curve of the target object according to the historical examination data; wherein the individual forgetting curve is used for representing a forgetting rule of the knowledge point memory amount of the target object about time; determining a target test question difficulty corresponding to the target object according to the individual forgetting curve; and screening test questions in a preset question bank according to the target test question difficulty, and determining a target question bank corresponding to the target object. According to the technical scheme provided by the embodiment of the invention, the problem that the generated test questions are easy to deviate from the cognitive state of the learner in the prior art is solved, the individual forgetting curve about the target object can be constructed based on the historical examination data, and then the test questions with the corresponding difficulty are screened based on the individual forgetting curve; and the adaptation degree of the generated test question and the current cognitive state of the target object is improved, so that the learning efficiency is improved.

The invention relates to the technical field of information processing, in particular to an AI-based teaching information processing method. Comprising the steps of determining whether a generation parameter of an exclusive question set for a single user is qualified or not based on a score characterization value; when it is judged that the generation parameters of the exclusive question set are abnormal, the generation parameters of the exclusive question set for a single user are adjusted based on the wrong question discrete magnitude, and random knowledge points are added to serve as anchor points; or adjusting the preset selected number and the number of the obtained historical conventional test papers to corresponding values based on the data integrity, the identification abnormal data proportion and the historical test lack frequency, or deleting the hollow values of the historical conventional test papers used for determining the knowledge points corresponding to the wrong questions. The test question deployment of the latest knowledge points and the historical to-be-reviewed knowledge points is balanced, the processing efficiency for the teaching information is improved, and the portrait accuracy for the user is improved.

The invention discloses a big language model capability evaluation method and a related device, and relates to the technical field of model evaluation, and the big language model capability evaluation method comprises the steps: obtaining an answer generated by each big language model in a to-be-evaluated big language model set for each test question in a test data set; generating a corresponding answer quality evaluation rule for each test question by using the rule generation large model; combining every two large language models, and combining two answers generated by the same model pair for each test question to obtain an answer pair corresponding to each model pair on each test question; for each test question, judging the advantages and disadvantages of the two answers contained in each answer pair according to the judgment rule corresponding to the test question; and determining an ability evaluation result of each large language model according to an evaluation result of each answer pair. According to the evaluation method disclosed by the invention, the capability of a plurality of large language models can be automatically evaluated, the evaluation efficiency is relatively high, and the evaluation result is objective and reliable.

A system and method automatically evaluate participant online testing and automatically provide feedback regarding test results of a participant. Automatic evaluation includes processing video frames, audio, timestamped screenshots, and initial test results of the participant answering multiple test questions and transcribing audio. The system and method utilize optical character recognition on the screenshots to generate a set of text for each screenshot and compare the set of text from each timestamped screenshot to determine which screenshots are associated with each test question. The system and method further determine time periods for each question, segment the transcribed audio, the screenshots, and the video frames by question and select a screenshot and a video frame for each test question from the segmented screenshots and video frames. The system and method utilize a first AI tool and a second AI tool to determine whether the participant demonstrated mastery for each test question.

The invention relates to the technical field of question self-adaptive recommendation, in particular to an intelligent question searching and self-adaptive recommendation system. According to the system, related courses are recommended to a user by counting the question searching information during question searching, recommendation can be more accurately carried out in combination with user behaviors, and the number proportion of pushed test questions of a single subject is adjusted according to the number of types of knowledge points of each subject; after the number proportion of the pushed test questions of the single subject is adjusted, the number proportion of the pushed test questions of other subjects is adjusted in a self-adaptive mode, and therefore the test questions are recommended more effectively; meanwhile, whether recommendation of the test questions is qualified or not is determined according to the answer information of the recommended test questions answered by the user, and the corresponding adjustment instruction is generated based on the disqualification reasons, so that the effectiveness of the self-adaptive recommended test questions can be more accurately determined, and more effective adjustment can be performed for the disqualification reasons; and the learning efficiency of the user is further improved.

Disclosed in the present invention are an NL2SQL system capability improvement method and apparatus, a device and a medium. The method comprises: determining from a capability indicator library capability items required by a NL2SQL system to be improved in a target scenario; performing capability level assessment on the capability items on the basis of a preset scenario test question bank, so as to determine capability level details; determining capability improvement module matrices corresponding to the capability items on the basis of the capability level details; and, on the basis of task improvement categories to which capability improvement tasks in the capability improvement module matrices belong, selecting the optimal target capability improvement tasks to perform set grouping so as to obtain grouped target group combinations, and scheduling the target group combinations so as to perform capability awareness improvement on said NL2SQL system. By means of the technical solutions, the embodiments of the present invention can perform comprehensive and detailed quantitative measurement on NL2SQL systems, has an efficient group scheduling mode, and achieves high efficiency and refined improvement of capability awareness of NL2SQL systems when the improvement complexity is low.

The invention discloses a large model automatic evaluation method, apparatus and device, and a readable storage medium. The method comprises the steps of receiving an evaluation request for a target large model; based on the type of the evaluation request, determining a question and answer record of the target large model; wherein when the type of the evaluation request is model ability evaluation, the question and answer record comprises a plurality of test question and answer cases, and each test question and answer case comprises a test question, an expected answer of the test question and a final answer output by the target large model to the test question; when the type of the evaluation request is a model output decision, the question and answer record comprises a real-time question and answer case, and the real-time question and answer case comprises a question input by a user in real time and a plurality of candidate answers output by a target large model to the question in real time; determining an evaluation index set of the target large model based on the question and answer record; and based on the type of the evaluation request, the question and answer record and the evaluation index set, evaluating the target large model through a preset judgment large model, and obtaining an evaluation result.

The invention provides a mathematical test question generation and solution collaborative enhancement method and system based on a large model, and relates to the technical field of large language models.The method comprises the steps that multiple sets of annotation data are obtained and input into a basic large language model for fine tuning training, and a first large language model is obtained; generating a plurality of test question request instructions, inputting the test question request instructions into the first large language model, correspondingly outputting mathematical questions and solving processes, obtaining a plurality of groups of combined data, and screening the combined data to obtain a supervision fine tuning data set and a preference optimization data set; performing optimization training on the first large language model by utilizing the preference optimization data set to obtain a second large language model; inputting the supervision fine tuning data set into a second large language model for next round of iterative training; continuously repeating to obtain a target large language model; and inputting a current test question request instruction into the trained target large language model, and outputting a mathematical test question comprising a mathematical question and a solving process. According to the method, the problems of low big language model training efficiency and poor optimization effect are solved.

The application belongs to the technical field of personalized learning, and discloses a multi-level intelligent cognitive tracking method, system, storable medium and terminal, the method comprising: introducing Bloom cognitive domain education target classification, constructing test question knowledge cognitive tensor TKC, collecting learning resources and answer data of learners, and generating a sequence of learner time sequence answer pairs; introducing a multi-attribute cognitive diagnosis method, combining a deep neural network, and constructing a cognitive level mining model; sorting and encoding the cognitive level mining results of the learners to obtain deep representation features, combining a self-attention mechanism, constructing a multi-level intelligent cognitive tracking model, and further predicting the answer performance of the learners on the test questions. The application is beneficial to accurately and finely modeling the overall knowledge structure and specific level of the learners, thereby promoting personalized learning of the learners and providing a new idea for mining and tracking the cognitive state and level of the learners in an online learning platform.

The invention relates to the technical field of intelligent examination systems, in particular to an intelligent test paper composition method, a medical examination system, equipment and a medium. The method comprises the following steps: firstly, receiving department examination demand parameters, retrieving a test question set meeting conditions from a clinical case test question bank to form a candidate test question pool, and then intelligently screening candidate test questions by utilizing a preset clinical diagnosis and treatment dynamic model to obtain a preliminary test question combination; analyzing high-frequency clinical examination point features in hospital historical examination data, and performing optimization adjustment in combination with knowledge point distribution in the preliminary test question combination; and by evaluating the clinical difficulty balance degree and the diagnosis and treatment knowledge point coverage rate in real time, the test paper composition parameters are dynamically adjusted until preset standards are met. By introducing the clinical diagnosis and treatment dynamic model and historical examination data analysis, intelligent construction of clinical relevance between test questions and dynamic optimization of knowledge point distribution are realized, so that the generated test paper more accurately evaluates the actual diagnosis and treatment ability of medical personnel.