51 results about "Knowledge state" patented technology

Systems and methods (e.g., utilities) for use in providing automated data quality detection that can be used multiple times across various domains and across multiple data quality spheres. A data structure or schema of an incoming data set is initially mapped to a desired data or knowledge state in a domain ontology made up of a number of TBox statements. Data quality issues in the incoming data set can then be detected as instances of the incoming data set are attempted to be inferenced against or otherwise matched to anticipated TBox statements of the domain ontology.

The invention discloses an online learning cognitive map generation system and method for representing the knowledge learning mastering state of a leaner in a specific field. The system comprises an intelligent terminal and a server. The intelligent terminal is used for online learning interaction. The online learning cognitive map generation system runs in the server comprising a knowledge graph construction module, a learning interaction data acquisition module, a knowledge state calculation and prediction module and a visual output module. The online learning cognitive map generation system and method are suitable for a common online learning platform and can simulate the cognitive structure of the learner and diagnose the learning defect of the leaner to provide personalized learning resources and social network services for the learner, so that learning confusion is reduced, cognitive loads are reduced, and learning pertinency and accuracy are improved.

A system and method of knowledge assessment comprises displaying to a learner a plurality of multiple-choice questions and two-dimensional answers, accessing a database of learning materials, and transmitting to the learner the plurality of multiple-choice questions and two-dimensional answers. The answers includes plurality of full-confidence answers consisting of single-choice answers, a plurality of partial-confidence answers consisting of one or more sets of multiple single-choice answers, and an unsure answer. The method further comprises scoring a confidence-based assessment (CBA) administered to the learner by assigning various knowledge state designations based on the learner's responses to the two-dimensional questions.

A method, a device and a computer readable storage medium for conducting a customized educational session to assess or teach a student by selecting contents for presentation to the student based on descriptors associated with questions and/or incorrect responses. The contents presented include both questions for assessing the student's knowledge state and intervention materials for teaching the student. The descriptors associated with the questions and incorrect responses are analyzed using one or more psychometric models to estimate the deficiency or weakness of the student's learning. Next contents are selected or created based on the estimated deficiency or weakness in the student's learning.

The invention discloses a self-adaptive network security knowledge evaluation method based on a cognitive diagnosis theory. The self-adaptive network security knowledge evaluation method based on thecognitive diagnosis theory comprises the following steps: S1, an evaluation system generates a network security knowledge graph according to the identity background of a user, and tests the user according to a preset sequence and a knowledge structure; S2, the test system generates a personal basic information database according to the personal identity background information uploaded by the userand a specific format; and S3, the test system traverses according to the structural sequence of the knowledge graph for item-by-item test, and accurate positioning of the knowledge level of the useris realized based on test question extraction of the corresponding difficulty standard. According to the method, a potential knowledge state is obtained through real-time feedback of a user in testing, and a novel cognitive diagnosis model PH-is utilized; And the real knowledge, skill level and corresponding short boards of the user are efficiently reasoned by the DINA, so that efficient and accurate education evaluation is realized, and the learning condition of the user is better reflected.

The invention relates to an exercise recommendation technology in the field of education and discloses a difficulty-based personalized exercise recommendation method and system and a medium. Accordingto the invention, subjective difficulty and objective difficulty of exercises are comprehensively considered. Knowledge points which are obtained based on respective knowledge states of students andare not mastered by the students are used as recommendation bases of exercises. The difficulty sequence of the knowledge points which are not mastered is obtained based on the pre-determined dependency relationship among the knowledge points and is used as a main recommendation sequence of exercises. A recommendation sequence of the exercises related to each unmastered knowledge point is determined according to the objective difficulty values of the exercises. Finally, personalized exercise recommendation based on difficulty is realized. The invention has the advantages that difficulty modeling has a basis and is comprehensive and reasonable, the effectiveness of the exercise-based autonomous learning effect of the students can be improved, and students are guided to complete exercise-based autonomous learning step by step from easy to difficult.

The invention discloses a knowledge tracking method. The method comprises the following steps: converting a learning sequence and an exercise sequence into dense vector representation by utilizing a feedforward neural network, obtaining a correlation relationship and a relative position relationship of exercises by utilizing an attention mechanism and absolute positions of the exercises respectively, and initially summarizing knowledge states of students at each learning node of the learning sequence according to the two relationships; then, carrying out deep fusion on the preliminarily summarized historical knowledge states of the students by utilizing a convolutional neural network, and tracking continuously changing knowledge states of the students in a learning process; compared with the prior art, the problem of accumulated deviation in the knowledge tracking process can be reduced, the accuracy of knowledge tracking can be improved, and the efficiency of knowledge tracking can beeffectively improved; meanwhile, the method also greatly improves the robustness of a student knowledge state tracking process and the accuracy of a tracking result.

The embodiment of the invention discloses a text processing method and device based on a fusion knowledge graph, relates to the field of intelligent interaction, and solves the problem of relatively low text matching degree. According to the specific scheme, firstly, word segmentation processing is conducted on an input text, a word segmentation text is obtained, and a serialized entity vector isobtained according to the word segmentation text; and then, Y target knowledge state sub-graphs are determined from the X knowledge state sub-graphs by utilizing a path matching algorithm according tothe serialized entity vector and the fused knowledge graph, and texts corresponding to the Y target knowledge state sub-graphs are determined as matching results of the input texts. The embodiment ofthe invention is used for a text matching process.

The invention discloses an adaptive learning method and system based on a knowledge model, and a storage medium. The method comprises the steps: collecting initial learning data, storing the initial learning data in a learning resource database, carrying out the ontology term extraction and marking, and building the knowledge model through an ontology editor; initializing a knowledge space of thelearner according to a pre-measurement result of the learner in the learning system; updating the learning process state data input into the learner in real time, performing DKT model modeling of multiple knowledge points on the learning process state data through a DKT algorithm, feeding back the mastering state of each knowledge point of the learner, and dynamically updating the knowledge spaceof the learner; and the adaptive engine compares the knowledge space of the learner with the knowledge model, matches a learning path corresponding to the learner, and pushes a learning path link to the learner. According to the method, the DKT is tracked through deep learning based on the knowledge model, multi-knowledge-point modeling is effectively carried out, the latest knowledge state of a learner is accurately mastered and updated, and a corresponding learning path is matched.

A patient information system for the provision of individual-specific information on the effects and risks of a medicament includes an expert system, in which relevant data on the medicament, for example, compositions, application area, contra-indications, mode of action, risks and side-effects are stored. The expert system is embodied such that, on a user inquiry about a particular medicament by inputting particular personal status data about the user, an individual user information reply, which matches the personal status data including the education and the knowledge state of the user-(a personalized enclosure) is generated including all relevant data, and excluding data on the medicament which need not be introduced according to the special requirements of the user.

The invention discloses a knowledge tracking method and system based on federated learning, and the method comprises the steps: employing a deep knowledge tracking model, carrying out the modeling ofthe knowledge state of a local student through combining with a recurrent neural network, and calculating the confidence of local data; finally, enabling the server take the confidence coefficient asa weight; and weighting and averaging the parameters of each model to obtain a global knowledge tracking model. The private data of each client is better utilized, the data privacy is kept, the ability of modeling students is finally tracked more accurately, and the defects of privacy information leakage, neglect of education data quality and the like of the existing method are overcome.

The invention relates to a knowledge tracking method and system based on a dynamic key value gating loop network. The method comprises the steps of obtaining a historical answer sequence of a studentin an interaction log data set; determining a knowledge point feature matrix and a knowledge state feature matrix according to the historical answer sequence; constructing a dynamic key value gating recurrent neural network according to the knowledge point feature matrix, the knowledge state feature matrix and the gating recurrent neural network; and carrying out knowledge tracking on the knowledge state of the student by utilizing the dynamic key value gated recurrent neural network. According to the knowledge tracking method and system based on the dynamic key value gating loop network, theaccuracy of knowledge tracking is improved.

A knowledge tracking method based on a heterogeneous structure comprises the following steps: obtaining practice history logs of students and knowledge points investigated by each exercise; obtaininga heterogeneous knowledge structure formed by relationships among the knowledge points; processing score logs of the students into a plurality of answering sequences arranged according to a time sequence, wherein each answering sequence comprises a series of answering results of the specific students at specific time; based on graph structure properties of knowledge, applying two different publicity models to track influences along different relationships, including a synchronous publicity method and an asynchronous publicity method; adopting a cascade influence publicity unit to jointly establish a model for the time effect and the space effect of the model, with the heterogeneous knowledge structure and the answering sequence of the students as input, and enabling the cascade influence publicity unit to extract the time sequence influence of each learning on the knowledge points from the answering situation at each moment; and updating the knowledge state of the students by adoptinga gating function to synthesize the comprehensive effect of the time sequence influence and the space sequence influence.

The invention provides a knowledge tracking method and system based on knowledge state evolution representation of learners. The method comprises the following steps: acquiring a statistical cognitive data set of a plurality of learners for a plurality of knowledge point samples; generating knowledge state representation of the learner, and building a knowledge tracking model; generating a predicted value of future answering performance of the learner and in the established knowledge tracking model, wherein the input of the Bayesian knowledge tracking algorithm is the state matrix, and the output of the Bayesian knowledge tracking algorithm is the predicted value of future answering performance of the learner; generating an evolution term; incorporating an evolutionary term and optimizing into a loss function, wherein the training goal of the knowledge tracking model is to generate an accurate predicted value of future answer performance of the learner and to accurately model a gentle change in the knowledge state, the goal being accomplished by defining the loss function.

The invention provides a learning companion recommendation system and method. The system comprises an intelligent terminal and a server. The intelligent terminal is used for online learning interaction, an online learning companion discovery system runs in the server, and comprises an information labeling module, a learning interaction and data acquisition module, a knowledge state and knowledge structure representation calculation module and a similarity calculation and learning companion recommendation module. The method is suitable for a common online learning platform, the knowledge stateand the knowledge structure of the learner in the online learning process can be dynamically represented, and the learning companions with the most similar level in the two dimensions of the knowledgestate and the knowledge structure are obtained according to the knowledge state and the knowledge structure.

The invention discloses a knowledge pushing method and device for a production employee, and the method comprises the following steps: obtaining an employee identification ID number of the production employee, and querying at least one knowledge skill state of the production employee according to the employee identification ID number; according to the at least one knowledge and skill state of the production employee, determining whether the production employee has a knowledge and skill short board; if the production employee has a knowledge skill short board in the target knowledge skill aspect, distributing a training task in the target knowledge skill aspect to the production employee; through the knowledge state of the production employee, different training tasks are pushed to the production employee, and corresponding production knowledge is pushed to the production employee, so that the employee can learn advanced production knowledge, and the production quality management level and the learning consciousness of the production employee are ensured.

The invention relates to a knowledge graph technology-based optical transport network knowledge test method which comprises the following steps: constructing a knowledge point graph in the field of optical transport network OTN, and designing a representation method of a knowledge space by combining knowledge points and association relationships thereof; further designing a rule for extracting a knowledge state set from the knowledge space, wherein each knowledge state element in the knowledge state set represents a knowledge state which a learner may have; finally, designing a calculation method of the current knowledge state of the learner, deducing the knowledge point mastering level of the learner according to the knowledge point test result on the basis of automatically designing theknowledge point test sequence, and determining the current knowledge state of the learner from the knowledge state set.

The invention discloses a knowledge tracking method and system based on a multivariate concept attention model. The method comprises the following steps: acquiring an interaction sequence of historical exercise answers of a learner; establishing a multivariate concept attention model, and dividing an interaction sequence of historical exercise answers into a plurality of attention modules with different sizes according to the exercise key indexes of the learner; establishing a multivariate semantic attention model, and integrating the content of the context and attention module data; calculating the knowledge concept distribution weight of the to-be-tested exercise key index through the attention classification layer; multiplying the classified attention score value by the historical answer vector to obtain a feature score value of the learner answering the new exercise; and according to the feature score value and the to-be-tested exercise key index, calculating the probability that the learner correctly answers the current question, traversing historical exercises similar to the current knowledge state, and updating the knowledge state, thereby accurately constructing a learning route suitable for the learner.

The invention relates to a dynamic perception test question recommendation method and system fused with deep knowledge tracking, and belongs to the field of computers. The method comprises the following steps of: 1, inputting test question interaction sequence data of students into an embedding layer, converting large-scale sparse features into low-dimensional dense features suitable for model input, and interactively sequencing test questions of the students according to time; 2, modeling a dependency relationship between test question interaction sequences by using a gating loop unit, and introducing an auxiliary loss function to supervise learning in a current hidden state by utilizing next test question interaction; 3, designing a gating circulation unit with a self-attention updating gate to model a knowledge evolution process related to the target test question; and 4, connecting the dynamic knowledge state of the student and the embedded vector of the target test question in series, and feeding into a multi-layer perceptron to carry out final Softmax judgment to determine whether the target test question needs to be recommended to the student or not. According to the method, the performance of test question recommendation prediction is effectively improved, and personalized test question recommendation for students is realized.

The invention provides a cognitive diagnosis method and system. The method comprises the following steps of: obtaining cognitive attribute information and reaction information of a subject; determining a project attribute relationship Q matrix according to the cognitive attribute information and determining a subject reaction X matrix according to the reaction information of the subject; constructing an OR-DINA model, wherein the model comprises an error parameter and a guess parameter; estimating the error parameter and the guess parameter by utilizing an expectation maximization EM algorithm; and calculating a knowledge state of the subject according to the estimated error parameter and guess parameter. According to the cognitive diagnosis method and system provided by the invention, anoptimized cognitive diagnosis model is disclosed, so that the probability of correctly answering projects can be increased along with the increase of attribute quantity tested by projects grasped by the subject, and weak knowledge points and skill point of the subject can be accurately diagnosed.

According to the adaptive learning support device and method based on deep knowledge tracking provided by the invention, through an improved knowledge tracking model, the current knowledge state of a learner is tracked in real time in a relatively accurate and practical manner. The device comprises an improved deep knowledge tracking model, a mastered knowledge point topic recommendation module and a knowledge level transition resource recommendation module. According to the invention, learning behaviors of students are fused into a knowledge tracking model, and an improved knowledge tracking model is provided based on an MANN. According to the method, the knowledge mastering degree of the student can be obtained based on the knowledge tracking model, and based on the trained knowledge tracking model, unfinished questions associated with mastered knowledge points are recommended to the student, and resources based on a knowledge level transition trajectory are recommended. According to the invention, the accuracy of the knowledge tracking model is improved, and the purpose of recommending learning resources for students based on collaborative filtering is achieved.

The invention discloses a student personalized time interval perception attention mechanism knowledge tracking method, which comprises the following steps of: 1) collecting historical interaction data of student learning and timestamps for completing learning, and designing and realizing a student learning time interval relation matrix; 2) carrying out vector coding on the exercise sequence, the learning sequence, the absolute position and the personalized time interval; 3) establishing a time-aware attention mechanism to calculate the influence weight of the historical completed exercises on the subsequent new exercises, and summarizing the initial knowledge state of each node student based on the weight; and 4) fusing the preliminarily summarized historical knowledge states of the students by using a full connection layer, and tracking continuously changing knowledge states in the learning process of the students. Compared with other technologies, the method has the advantages that different time intervals for students to practice each question are effectively utilized, different knowledge mastering conditions of different students under the same learning sequence are mined, and the knowledge tracking accuracy is improved.

The invention provides a hierarchical cognitive diagnosis method, a device and system, and relates to the technical field of cognitive diagnosis. The method comprises the following steps of: acquiringa correlation matrix of the test questions of a test paper and a target attribute; acquiring the step information of the test questions to be tested, and generating a hierarchical matrix by combiningthe correlation matrix; determining an ideal master mode of the target attribute and determining the capability vector of each ideal master mode; acquiring the tested answer information, and determining the tested capability vector according to the answer information; carrying out classification on the tested capability vector and the capability vector of each ideal master mode to determine a matched ideal master mode. According to the invention, heuristic information is provided to a testee through the mode of building a hand-and-foot rack, the testee is subjected to layered diagnosis, the knowledge state of the testee is diagnosed, the attribute which is not mastered by the testee is positioned, thereby providing a guide direction for the teacher based on the testee, a personalized remedy promotion exercise is provided to the testee.

The invention belongs to the field of education data mining, and provides a knowledge and skill dynamic diagnosis method oriented to space-time evolution. The method comprises the following steps of: firstly, constructing a knowledge heterogeneous graph according to resource characteristics, and then dynamically updating the knowledge and skill state of a learner in time and space dimensions, therefore, the future performance of the learner is predicted, and the knowledge mastering condition of the learner is diagnosed. According to the method, a big data technology, deep learning and a natural language processing technology are comprehensively utilized, knowledge points of a learner are modeled from time and space, the knowledge state of the learner is influenced by introducing learning features and forgetting features, and a knowledge structure of the learner is updated by providing space-time cascade operation, the knowledge and skills of the learner can be diagnosed scientifically and comprehensively, future performance of the learner can be predicted, personalized recommendation practice can be performed on knowledge points with low skill mastery, and personalized teaching can be performed on knowledge points with poor performance in the future.