17 results about "Lesson study" patented technology

The invention relates to the field of curriculum personalized adjustment, in particular to a curriculum learning personalized adjustment method and system of an enabling system, and the method comprises the steps: obtaining user information and historical learning data of a user when a learning instruction of the user is received, and recognizing target curriculum data of the user according to the user information and the historical learning data; acquiring historical behavior data of the user, identifying a concentration attenuation trend of the user according to the historical behavior data, and segmenting the target course data into a plurality of course segments according to the concentration attenuation trend; when the user learns the curriculum segment, behavior data of the user is acquired in real time; judging the concentration feedback state of the user according to the behavior data; when the concentration feedback state of the user is positive feedback, generating a learning efficiency enhancement strategy and a composite excitation strategy; and when the concentration feedback state of the user is negative feedback, generating a cognitive load regulation strategy and a pressure balance strategy. The learning state of the user is judged according to the behavior data, and the system can flexibly adjust the learning strategy.

The invention relates to the field of content recommendation, and discloses an English-oriented learning content recommendation method and system, and the method comprises the following steps: collecting basic information when an English learning platform is registered, and the basic information comprises an age, a learning target and English basic self-evaluation information; according to the basic information, learning content is recommended according to a preset learning content recommendation strategy, and an English learning platform is used for collecting course learning records, learning duration, interruption times, practice completion conditions and wrong question records to construct a personal learning file; monitoring the learning progress in real time according to the personal learning file and the basic information, and performing evaluation to obtain a learning content recommendation evaluation index; evaluating a current learning content recommendation strategy according to the learning content recommendation evaluation index, and selecting whether to adjust the current learning content recommendation strategy according to an evaluation result; and displaying a progress bar and an achievement chart of individual learning through a visual interface.

The present application relates to the technical field of intelligent management of teaching data, and particularly relates to a method and system for integrated teaching intelligent management suitable for courses, posts, competitions and certificates, wherein the method for integrated teaching intelligent management suitable for courses, posts, competitions and certificates comprises the following steps: S1: obtaining a student portrait set containing multi-dimensional individual information of students, and connecting a preset external information base; S2: calling the external information base, and generating an optimal learning path for the students according to the student portraits and preset time nodes; S3: obtaining multi-dimensional individual information of the students when the students learn according to the optimal learning path, and updating the student portraits. The present application can integrate course learning, competition practice, certificate taking and post employment in the same framework, thereby solving the problem of fragmentation of each link in traditional teaching management, and enabling further optimization of the optimal learning path at different time nodes, so that the generated optimal learning path is always matched with the actual progress and final goal of the students.

The invention discloses a multi-dimensional education data analysis and decision support system, relates to the technical field of education decision support, and solves the technical problems that courses and even problems existing in a teaching method are difficult to identify and effective decision suggestions cannot be provided for an education platform in an existing scheme. The system comprises an analysis decision module and a data processing module connected with the analysis decision module. A learning state label is set by analyzing the performance of a target object in course learning, and a data basis is provided for analyzing whether personal problems exist or not; establishing learning state sequences according to the learning state labels, judging whether personal problems exist or not by comparing the learning state sequences of the target objects of the same class, judging whether class problems exist or course problems by comparing the learning state sequences of the target objects of different classes, and identifying the problems through multi-dimensional education data; and the reliability of related decisions can be improved.

The invention provides an education management optimization method for an AI learning-aided virtual teacher, and relates to the technical field of data processing, and the method comprises the steps: obtaining the cumulative learning duration, course learning task load and grasp condition score of each course of a user, evaluating the task progress of each course, calculating the learning efficiency value of each course, and calculating the learning efficiency value of each course; splitting the total course task amount of each course to obtain an uncompleted learning task data set, judging whether the uncompleted learning task data can be completed before the examination date according to the learning efficiency value, obtaining a learning completion reachability identifier, and distributing the uncompleted learning task data set to obtain a learning completion reachability identifier; and ensuring that the data set of the uncompleted learning tasks is completed before the examination date, generating a seven-day learning distribution data set, monitoring daily learning of the user, and adjusting daily tasks of remaining days in the seven-day learning distribution data set to ensure that the user completes the seven-day learning distribution data set. The learning progress of the user can be optimized and managed.

The application discloses a small sample text classification method fusing data expansion and course learning, first expands data of a labeled sample set by using a strategy, then divides the data set according to a change degree of the expanded sample, then constructs a neural network classifier and trains a classification model, and finally classifies new samples by using the trained model. The learning method is improved and reconstructed, on one hand, data expansion is performed by using multiple strategies, and on the other hand, samples are divided into grades according to change degrees from small to large, and in the learning process, a course learning strategy is used to learn gradually from easy to difficult, and the classification accuracy is significantly improved.

The invention discloses an audit field-oriented data distillation method based on knowledge enhancement and course learning. The method comprises the steps of inputting unknown audit data into a trained small model; wherein the trained small model is obtained through training according to the large language model, the fusion data and the thinking chain; the fused data is obtained by performing semantic fusion on audit data in a pre-established audit database and corresponding law and policy knowledge; the auditing database is constructed according to bidding and tendering files, contract performance data and compliance review records; the thinking chain is obtained according to the large language model and the fusion data; and obtaining a reasoning result of the unknown audit data. According to the method, a high-quality and highly-adaptive data basis is provided for small model training; the reliability of the model in a complex audit reasoning scene is effectively improved; the migration capability and the generalization level of the small model are enhanced, and the stability and the high efficiency of the data distillation process are realized; and the bottleneck of the small model in auditing application is broken through.

The invention discloses a heterogeneous edge calculation multi-teacher federated distillation method based on course learning, and aims to reduce the influence of statistical heterogeneity on model performance on the premise of protecting the heterogeneity of an edge device model. The method specifically comprises the following steps: S1, a client performs local training by using a private data set and global knowledge, and then transmits output obtained by reasoning on a public data set to a server; s2, the server evaluates the quality of the output uploaded by each client by taking a sample as a unit, and then performs weighted aggregation to generate comprehensive knowledge; and S3, the server follows the thought of course learning, dynamically trains a global model by using comprehensive knowledge, and then sends global knowledge output by the global model to the client. And repeating the above process, and training until the global model converges. Compared with a previous federated learning method, the method has the advantages that the performance on four data sets is obviously improved, and the method is generally suitable for various training tasks.

The invention discloses a course recommendation method and system for a teaching integrated platform, and belongs to the technical field of teaching recommendation. The method comprises the following steps: establishing a link between a user port and a course interface, generating an initialized course learning packet set, collecting user learning behaviors to form a behavior chain, verifying a user learning behavior state, evaluating the acceptability of a course learning packet in a user group, and quantifying and displaying a collaborative recommendation degree based on a knowledge point nesting relationship. The corresponding system comprises a port link and course package initialization module, a learning behavior chain processing module and a course recommendation evaluation module. According to the method, accurate curriculum recommendation can be realized, the learning efficiency of the user is improved, the problem that the existing recommendation technology neglects knowledge point association and lacks group acceptance evaluation is solved, and the method is suitable for curriculum recommendation scenes of various teaching integrated platforms.

An entity relationship extraction method based on semi-supervised learning and curriculum learning is characterized in that a given sentence S is equal to {e1, e2,..., en}, and the target of entity relationship joint extraction is to comprehensively extract all entities and relationships thereof, so that all possible triples in a (s, r, o) form are identified; an overall framework of the entity relationship extraction method based on semi-supervised learning and curriculum learning comprises the following five steps: (1) based on an entity and relationship overlapping condition, dividing initial labeled data into data sets with different difficulties; (2) training a teacher network model by using the course classification data set; (3) screening a high-confidence pseudo-tag triple through a semi-supervised learning strategy; (4) adding the pseudo label as a real label into the original training set, and training a student network by adopting extended data of course classification; (5) taking the trained student network as a new teacher network for iterative optimization; and carrying out relation extraction by using the finally constructed large-scale entity relation extraction model with better performance. The model provided by the invention effectively solves the problem of insufficient label data in the entity relationship extraction task.

We provide the system. [Solution] A means for the user to input the desired program learning content, A generative artificial intelligence means that generates customized lesson content based on the input preferences, A means for providing the user with lesson content generated by the aforementioned generative artificial intelligence means, A system that includes this.

This invention discloses a teaching evaluation method for reinforced concrete structure courses, comprising: collecting teaching process data generated by students during their learning of reinforced concrete structure courses; the teaching process data including theoretical test data, experimental operation data, and structural design result data; preprocessing the teaching process data to generate a standardized teaching evaluation dataset; extracting feature parameters reflecting students' theoretical mastery, practical operation stability, and structural design rationality from the standardized teaching evaluation dataset; inputting the feature parameters into a pre-established teaching evaluation model to output theoretical ability scores, practical ability scores, and innovation ability scores respectively; and generating a comprehensive evaluation result for students based on the theoretical ability scores, practical ability scores, and innovation ability scores. This invention can integrate multi-source teaching process data to achieve quantitative analysis of multi-dimensional abilities, thereby improving the objectivity and accuracy of the evaluation.

The invention relates to the technical field of intelligent teaching systems, and particularly discloses a self-adaptive learning content generation method and device for an intelligent teaching system. Comprehensively mastering a knowledge mastering degree index, a learning state evaluation coefficient and a knowledge migration capability corresponding to the current course learning content of the target learning user, and constructing a learning feature vector corresponding to the target learning user based on the knowledge mastering degree index, the learning state evaluation coefficient and the knowledge migration capability; and by analyzing the content difficulty adaptation index, the learning excitation degree and the knowledge association richness of each specified course learning content matched with the current course learning content, constructing a content feature vector of each specified course learning content based on the content difficulty adaptation index, the learning excitation degree and the knowledge association richness, and finally calculating the adaptation degree based on a cosine similarity algorithm. And the pushed learning content and the sequence thereof are screened and determined according to the degree of adaptation, so that the learning content which is highly personalized and meets the learning requirements of students is provided for the students, and the pertinence and effectiveness of learning are improved.

This invention provides an e-commerce teaching system and method based on ADDIE, relating to the field of e-commerce service technology. The system includes: an acquisition unit for acquiring first interactive data; a capability analysis unit for obtaining corresponding capability analysis results based on the first interactive data; a course matching unit for performing course recommendation analysis based on the capability analysis results to conduct course testing and obtain simulated test results; and a teaching evaluation unit for matching and detecting the second interactive data during the course learning process with the business capabilities corresponding to each business project type. When the second interactive data matches the target business capability, a comprehensive evaluation of the learning effect is performed based on the second interactive data and the simulated test results corresponding to the target learning course group to update the advanced courses for continued teaching. The system and method of this invention can ensure the reliability of students' knowledge and skills mastery during e-commerce learning.

The invention discloses an achievement-oriented teaching evaluation analysis method and a related device, and relates to the technical field of data processing, and the method comprises the steps: carrying out the standardization processing of the learning achievement data and learning video data of each teaching object; performing learning performance evaluation based on the standardized learning result data; performing concentration analysis and psychological state analysis based on the standardized learning video data; performing learning individual difference analysis based on the learning performance evaluation result and the psychological state data in combination with learning participation degree analysis; based on the learning performance evaluation result and the psychological state data of course learning in each stage, performing learning condition change analysis on each teaching object; and based on the learning individual difference analysis data and the learning condition change analysis data, teaching improvement analysis is carried out to improve teaching videos and assessment contents. According to the method, the initiative of a teaching object to course learning can be stimulated, and achievement-oriented teaching evaluation analysis achieves an ideal effect.

The invention relates to the technical field of large model training, in particular to a large model customized training method and system for industry application, by constructing a hierarchical knowledge graph, a model can systematically master an internal organizational structure and complex association of industry knowledge, an association prediction auxiliary task based on the graph is introduced in the training process, and the training efficiency is improved. The method comprises the following steps of: firstly, selecting a lesson and integrating the lesson into main semantic understanding, and meanwhile, ensuring progressive and stable convergence of model learning by adopting a dynamic course learning strategy; finally, optimization is carried out by fusing a loss function of knowledge association constraints, so that the model not only deeply understands a hierarchical system of industry knowledge, but also can reliably generate answers which conform to industry specifications, are strict in logic and are high in specialty; in this way, the technical problems that in the prior art, it is difficult to deeply understand and follow the internal hierarchical structure and complex incidence relation of domain knowledge, and consequently the output of the domain knowledge is insufficient in professionality, consistency and logicality are solved.