CN117291775A - Depth knowledge tracking accurate teaching method - Google Patents
Depth knowledge tracking accurate teaching method Download PDFInfo
- Publication number
- CN117291775A CN117291775A CN202311584767.9A CN202311584767A CN117291775A CN 117291775 A CN117291775 A CN 117291775A CN 202311584767 A CN202311584767 A CN 202311584767A CN 117291775 A CN117291775 A CN 117291775A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- learner
- matrix
- answer
- kth
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 239000011159 matrix material Substances 0.000 claims abstract description 212
- 230000004927 fusion Effects 0.000 claims abstract description 40
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 20
- 239000013598 vector Substances 0.000 claims description 57
- 230000006870 function Effects 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 230000004044 response Effects 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 5
- 238000007670 refining Methods 0.000 claims 1
- 230000008569 process Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000003930 cognitive ability Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers
- G09B7/02—Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
- G09B7/04—Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student characterised by modifying the teaching programme in response to a wrong answer, e.g. repeating the question, supplying a further explanation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Primary Health Care (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of precision teaching, and discloses a precision teaching method for depth knowledge tracking, which comprises the following steps: collecting answer records of learners and carrying out knowledge coding; constructing a depth knowledge tracking model to generate a knowledge level matrix of a learner; performing similarity clustering on learners based on a knowledge level matrix of the learners; and carrying out knowledge level matrix decomposition on the knowledge level matrix with the similarity fusion to obtain the correct answer rate of the learner on the problem which is not done, constructing the completed knowledge level matrix, generating the knowledge mastering condition of the learner and determining the pushed problem. According to the invention, the deep knowledge information of the learner is tracked by adopting an effective information tracking record mode, the question answering accuracy of the learner on the condition that the learner does not do exercises is obtained by adopting a matrix decomposition mode, the accuracy of knowledge mastering condition judgment is improved, the exercises pushing which accords with the current knowledge level of the learner is selected, and the accurate teaching is realized.
Description
Technical Field
The invention relates to the technical field of precision teaching, in particular to a precision teaching method for depth knowledge tracking.
Background
With the increasing scale of educational resources, it is difficult for learners to find resources meeting their own needs among a huge number of educational resources. Likewise, it is difficult for teachers to provide accurate teaching for each learner in the face of a large number of learners. Particularly, in the present day of information overload, in order to meet the needs of learners with different cognitive abilities and knowledge levels, a precise teaching mode suitable for the cognitive knowledge levels of the learners is needed. Aiming at the problem, the invention provides a depth knowledge tracking accurate teaching method, which realizes accurate teaching through depth analysis of the knowledge level of a learner.
Disclosure of Invention
In view of this, the present invention provides an accurate teaching method for depth knowledge tracking, which aims to: 1) Obtaining answer records of learners, respectively extracting answer pair problem information and answer error problem information of the learners, realizing answer accuracy vector tracking iteration in an effective information tracking record mode, constructing a knowledge level matrix representing the depth knowledge information of the learners, and realizing the depth knowledge tracking of the learners; 2) According to the similarity clustering result of the learner, the knowledge level information of the similarity is fused into a knowledge level matrix to obtain a knowledge level matrix fused with the knowledge level information of the similar learner, the knowledge level matrix is decomposed in a matrix decomposition mode to obtain the correct answer rate of the learner on the problem, the accuracy of knowledge mastering condition judgment is improved, and according to the point of the learner which does not master knowledge, the problem pushing conforming to the current knowledge level of the learner is selected to realize accurate teaching.
The invention provides an accurate teaching method for depth knowledge tracking, which comprises the following steps:
s1: collecting answer records of learners and carrying out knowledge coding to obtain answer record coding data of the learners;
s2: constructing a depth knowledge tracking model to generate a knowledge level matrix of the learner, wherein the depth knowledge tracking model takes answer record coding data of the learner as input and takes the knowledge level matrix as output;
s3: carrying out similarity clustering on the learner based on the knowledge level matrix of the learner, calculating to obtain a knowledge level vector after similarity fusion according to a clustering result, and converting the knowledge level vector into the knowledge level matrix after similarity fusion;
s4: carrying out knowledge level matrix decomposition on the knowledge level matrix with the similarity fusion to obtain the correct answer rate of the learner on the problem which is not done, and further obtaining the completed knowledge level matrix;
s5: and generating knowledge mastering conditions of learners according to the completed knowledge level matrix, and determining the pushed exercises to carry out accurate teaching.
As a further improvement of the present invention:
optionally, in the step S1, a answer record of the learner is collected and knowledge encoding is performed, including:
collecting answer records of K learners, wherein the answer records of the learners are in the form of:
wherein:
representing the acquired answer records of the kth learner;
a question answering record for indicating the k-th learner in N questions,/question answering record for indicating the k-th learner in N questions>A question answering record for showing the nth question of the kth learner;
representing knowledge contained in the nth problemDot sequence,/->Indicating the response of the kth learner in the nth problem,/for the kth learner>Indicating that the kth learner did not answer the nth exercise,/>Indicating that the kth learner answers the nth question->Indicating the kth learner to answer the nth problem;
carrying out knowledge coding on the answer records of the learners to obtain answer record coding data of the learners, wherein the answer record knowledge coding flow of the kth learner is as follows:
s11: initializing and generating double-layer answer record knowledge coding matrix;
S12: double-layer answer record knowledge coding matrix according to answer records of kth learnerThe matrix elements in (a) are subjected to amplitude values, wherein a matrix element assignment formula is as follows:
wherein:
coding matrix for representing answer record knowledge>Assignment results of matrix elements in the ith row and the jth column;
coding matrix for representing answer record knowledge>Assignment results of matrix elements in the ith row and the jth column;
in the embodiment of the invention, the answer record knowledge coding matrixKnowledge coding result for representing k-th learner's answer to question part, answer record knowledge coding matrix +.>The knowledge coding result is used for representing the part of the k learner answering the wrong question;
s13: coded data for forming answering records of kth learner。
Optionally, constructing the depth knowledge tracking model in the step S2 generates a knowledge level matrix of the learner, including:
the method comprises the steps of constructing a depth knowledge tracking model to generate a knowledge level matrix of a learner, wherein the depth knowledge tracking model takes answer record coding data of the learner as input and takes the knowledge level matrix as output, the depth knowledge tracking model comprises an input layer, an iteration tracking layer and an output layer, the input layer is used for receiving the answer record coding data of the learner, the iteration tracking layer is used for carrying out multiple rounds of answer accuracy vector tracking iteration on the answer record coding data, and the output layer is used for outputting the knowledge level matrix of the learner;
the knowledge level matrix generation flow of the kth learner based on the depth knowledge tracking model is as follows:
s21: the input layer receives the answer records of the kth learnerEncoding data;
S22: iterative tracking layer for recording coded data of answer questionsAnd carrying out K rounds of answer accuracy vector tracking iteration, wherein the answer accuracy vector tracking iteration formula is as follows:
wherein:
the d round answer accuracy vector tracking iteration result of the kth learner is represented;
representing a matrix of coding weights->Representing the coding offset;
representing an iteration weight matrix;
s23: the output layer tracks the correct rate vector of the last round of answer to the iterative resultConversion into a knowledge level matrix:
wherein:
a knowledge level matrix representing a kth learner;
representing a matrix of knowledge weights->Representing knowledge offset;
representing an activation function; in the embodiment of the invention, the selected activation function is a Sigmoid function.
Optionally, in the step S3, similarity clustering is performed on the learner based on the knowledge level matrix of the learner, and a knowledge level vector after similarity fusion is obtained by calculation according to a clustering result, including:
carrying out similarity clustering on learners based on a knowledge level matrix of the learners, wherein the similarity clustering flow is as follows:
s31: calculating the similarity of knowledge level matrix between any two different learners, wherein the knowledge level matrixAnd->The similarity between the two is as follows:
wherein:
representing a knowledge level matrix->And->Similarity between;
an exponential function that is based on a natural constant;
represents an L1 norm;
s32: for arbitrary knowledge level matrixSelecting M knowledge level matrixes with highest similarity as +.>Is a similarity matrix of->Is a set of similarity matrices;
s33: calculating to obtain arbitrary knowledge level matrixIs used as knowledge level matrix +.>Knowledge level vector +.>。
Optionally, in the step S3, converting the knowledge level vector into a knowledge level matrix after similarity fusion includes:
converting the knowledge level vector into a knowledge level matrix after similarity fusion, wherein the knowledge level matrix conversion formula after similarity fusion of the kth learner is as follows:
wherein:
a knowledge level matrix after similarity fusion of the kth learner is represented;
representing a fusion proportion parameter;
and the knowledge level vector after similarity fusion of the kth learner is represented.
Optionally, in the step S4, performing knowledge level matrix decomposition on the knowledge level matrix after similarity fusion to obtain a question answering accuracy of the learner on the problem, including:
carrying out knowledge level matrix decomposition on the knowledge level matrix after similarity fusion to obtain the question answering accuracy of the learner on the non-exercise questions, wherein the knowledge level matrix after similarity fusionThe knowledge level matrix decomposition flow of (1) is as follows:
s41: calculating to obtain matrixMatrix->Wherein T represents a transpose;
s42: respectively to a matrixMatrix->Performing feature decomposition to respectively obtain M feature values and feature vectors corresponding to the feature values;
s43: according to the sequence of characteristic values from big to small, respectively for matrixMatrix->The feature vectors corresponding to the feature values of (2) are ordered:
wherein:
representing the ordered matrix +.>Is the m-th feature vector of (a);
representing the ordered matrix +.>Is the m-th feature vector of (a);
s44: generating the question answering accuracy rate of the kth learner in the mth channel of non-answer questions:
wherein:
the question answering accuracy of the kth learner in the mth channel is represented;
and completing the answer records of the learner according to the answer accuracy of the learner on the condition that the learner does not do exercises, and generating a completed knowledge level matrix.
Optionally, in the step S4, the completion of the learner answer record is performed according to the answer accuracy of the learner on the problem that is not done, and the generating the completed knowledge level matrix includes:
and (3) completing the answer records of the learner according to the answer accuracy of the learner on the non-doing exercises, namely taking the answer accuracy of the learner on the non-doing exercises as the answer condition of the learner on the non-doing exercises, carrying out knowledge coding on the completed answer records to obtain the completed answer record coded data of the learner, and generating a completed knowledge level matrix of the learner by using a deep knowledge tracking model.
Optionally, in the step S5, generating a knowledge mastering situation of the learner and determining the pushed problem to perform the precise teaching according to the completed knowledge level matrix, including:
generating knowledge mastering conditions of learners and determining pushed problems according to the completed knowledge level matrix, wherein the knowledge mastering conditions of the kth learner and the generation flow of the pushed problems are as follows:
according to the knowledge point sequence contained in each problem acquired in the step S1, traversing to obtain the answering situation of the problem corresponding to any h knowledge point of the k learner, and calculating to obtain the mastering situation of the k learner at the h knowledge point:
wherein:
representing the mastery of the kth learner at the h knowledge point,/for the kth learner>H represents the total number of knowledge points of the problem;
representing a set of problems comprising an h knowledge point, wherein the set of problems +.>Subset of N questions for learner>,/>Representing problem set +.>Any one of the problems;
difficulty of indicating problem w->Representing the response condition of the kth name in the problem w;
if it isIf the learning degree is higher than the preset threshold, the kth learner is informed of the kth knowledge point, otherwise, the kth learner is not informed of the kth knowledge point, and the difficulty in the question bank is pushed to be +.>And contains the problem of the h knowledge point, wherein the difficultySatisfies the following formula:
wherein:
indicating that the k-th learner answers push difficulty is +.>The accuracy of the problem of (2);
representing the completed knowledge level matrix for the kth learner.
In order to solve the above-described problems, the present invention provides an electronic apparatus including:
a memory storing at least one instruction;
the communication interface is used for realizing the communication of the electronic equipment; and
And the processor executes the instructions stored in the memory to realize the accurate teaching method for depth knowledge tracking.
In order to solve the above-mentioned problems, the present invention further provides a computer-readable storage medium having at least one instruction stored therein, the at least one instruction being executed by a processor in an electronic device to implement the above-mentioned method of teaching with precision of depth knowledge tracking.
Compared with the prior art, the invention provides an accurate teaching method for depth knowledge tracking, which has the following advantages:
firstly, the scheme provides a learner knowledge level information extraction method, which carries out knowledge coding on a learner answer record to obtain learner answer record coding data, wherein the k-th learner answer record knowledge coding flow is as follows: initializing and generating double-layer answer record knowledge coding matrixThe method comprises the steps of carrying out a first treatment on the surface of the Double-layer answer record knowledge coding matrix according to answer records of kth learner>The matrix elements in (a) are subjected to amplitude values, wherein a matrix element assignment formula is as follows:
wherein:coding matrix for representing answer record knowledge>The ith row and the jth column of the matrixAssignment results of matrix elements;coding matrix for representing answer record knowledge>Assignment results of matrix elements in the ith row and the jth column; coded data for answering records of k-th learner>. The method comprises the steps of constructing a depth knowledge tracking model to generate a knowledge level matrix of a learner, wherein the depth knowledge tracking model takes answer record coding data of the learner as input and takes the knowledge level matrix as output, the depth knowledge tracking model comprises an input layer, an iteration tracking layer and an output layer, the input layer is used for receiving the answer record coding data of the learner, the iteration tracking layer is used for carrying out multiple rounds of answer accuracy vector tracking iteration on the answer record coding data, and the output layer is used for outputting the knowledge level matrix of the learner; the knowledge level matrix generation flow of the kth learner based on the depth knowledge tracking model is as follows: the input layer receives the coded data of the answer record of the kth learner>The method comprises the steps of carrying out a first treatment on the surface of the The iterative tracking layer records coded data for questions>And carrying out K rounds of answer accuracy vector tracking iteration, wherein the answer accuracy vector tracking iteration formula is as follows:
wherein: />The d round answer accuracy vector tracking iteration result of the kth learner is represented; />Representing a matrix of coding weights->Representing the coding offset; />Representing an iteration weight matrix; the output layer tracks the correct rate vector of the last round of answer to the iterative result +.>Conversion into a knowledge level matrix:
wherein: />A knowledge level matrix representing a kth learner; />Representing a matrix of knowledge weights->Representing knowledge offset; />Representing an activation function. According to the scheme, the answer records of the learner are obtained, answer pair problem information and answer error problem information of the learner are respectively extracted, answer correct rate vector tracking iteration is realized by adopting an effective information tracking record mode, a knowledge level matrix representing the depth knowledge information of the learner is constructed, and the depth knowledge tracking of the learner is realized.
Meanwhile, the scheme provides a knowledge level matrix decomposition and accurate teaching mode, and the learner answer records are completed according to the answer accuracy of the learner on the problem which is not done, namely, the answer accuracy of the learner on the problem which is not done is used as the answer condition of the learner on the problem which is not done, the completed answer records are subjected to knowledge coding, the completed answer record coded data of the learner are obtained, and the depth knowledge tracking model is utilized to generate the completed knowledge level matrix of the learner. Generating knowledge mastering conditions of learners and determining pushed problems according to the completed knowledge level matrix, wherein the knowledge mastering conditions of the kth learner and the generation flow of the pushed problems are as follows: according to the knowledge point sequence contained in each problem acquired in the step S1, traversing to obtain the answering situation of the problem corresponding to any h knowledge point of the k learner, and calculating to obtain the mastering situation of the k learner at the h knowledge point:
wherein: />Indicating the mastery condition of the kth learner at the h knowledge point,h represents the total number of knowledge points of the problem; />Representing a set of problems comprising an h knowledge point, wherein the set of problems +.>Subset of N questions for learner>,/>Representing problem set +.>Any one of the problems; />Difficulty of indicating problem w->Representing the response condition of the kth name in the problem w; if->If the learning degree is higher than the preset threshold, the kth learner is informed of the h knowledge point, otherwise, the kth learner is not informed of the h knowledge point, and the difficulty in the question bank is pushedAnd comprises the problem of the h knowledge point, wherein the difficulty +.>Satisfies the following formula:
wherein: />Indicating that the k-th learner answers push difficulty is +.>The accuracy of the problem of (2); />Representing the completed knowledge level matrix for the kth learner. According to the scheme, the knowledge level information of the similarity is fused into the knowledge level matrix according to the similarity clustering result of the learner, so that the knowledge level matrix fused with the knowledge level information of the similar learner is obtained, the knowledge level matrix is decomposed in a matrix decomposition mode, the question answering accuracy of the learner on the questions which are not made is obtained, the accuracy of knowledge mastering condition judgment is improved, and the questions which accord with the current knowledge level of the learner are selected to push according to the knowledge points which are not mastered of the learner, so that accurate teaching is realized.
Drawings
FIG. 1 is a schematic flow chart of a depth knowledge tracking and accurate teaching method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an electronic device for implementing an accurate teaching method for depth knowledge tracking according to an embodiment of the present invention.
In the figure: 1 an electronic device, 10 a processor, 11 a memory, 12 a program, 13 a communication interface.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the application provides a depth knowledge tracking accurate teaching method. The execution subject of the depth knowledge tracking precision teaching method includes, but is not limited to, at least one of a server, a terminal, and the like, which can be configured to execute the method provided by the embodiment of the application. In other words, the method of teaching the depth knowledge tracking may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Example 1:
a depth knowledge tracking accurate teaching method comprises the following steps:
s1: and collecting answer records of the learner and carrying out knowledge coding to obtain answer record coding data of the learner.
And S1, collecting answer records of learners and carrying out knowledge coding, wherein the S1 comprises the following steps:
collecting answer records of K learners, wherein the answer records of the learners are in the form of:
wherein:
representing the acquired answer records of the kth learner;
a question answering record for indicating the k-th learner in N questions,/question answering record for indicating the k-th learner in N questions>A question answering record for showing the nth question of the kth learner;
representing the knowledge point sequence contained in the n-th problem,/i>Indicating the response of the kth learner in the nth problem,/for the kth learner>Indicating that the kth learner did not answer the nth exercise,/>Indicating that the kth learner answers the nth question->Indicating the kth learner to answer the nth problem;
carrying out knowledge coding on the answer records of the learners to obtain answer record coding data of the learners, wherein the answer record knowledge coding flow of the kth learner is as follows:
s11: initializing and generating double-layer answer record knowledge coding matrix;
S12: double-layer answer record knowledge coding matrix according to answer records of kth learnerThe matrix elements of (a) are subjected to amplitude values, wherein the matrix elements are endowed withThe value formula is:
wherein:
coding matrix for representing answer record knowledge>Assignment results of matrix elements in the ith row and the jth column;
coding matrix for representing answer record knowledge>Assignment results of matrix elements in the ith row and the jth column;
in the embodiment of the invention, the answer record knowledge coding matrixKnowledge coding result for representing k-th learner's answer to question part, answer record knowledge coding matrix +.>The knowledge coding result is used for representing the part of the k learner answering the wrong question;
s13: coded data for forming answering records of kth learner。
S2: and constructing a depth knowledge tracking model to generate a knowledge level matrix of the learner, wherein the depth knowledge tracking model takes the coded data of the answer records of the learner as input and takes the knowledge level matrix as output.
And in the step S2, a depth knowledge tracking model is constructed to generate a knowledge level matrix of the learner, which comprises the following steps:
the method comprises the steps of constructing a depth knowledge tracking model to generate a knowledge level matrix of a learner, wherein the depth knowledge tracking model takes answer record coding data of the learner as input and takes the knowledge level matrix as output, the depth knowledge tracking model comprises an input layer, an iteration tracking layer and an output layer, the input layer is used for receiving the answer record coding data of the learner, the iteration tracking layer is used for carrying out multiple rounds of answer accuracy vector tracking iteration on the answer record coding data, and the output layer is used for outputting the knowledge level matrix of the learner;
the knowledge level matrix generation flow of the kth learner based on the depth knowledge tracking model is as follows:
s21: the input layer receives the coded data of the answer records of the kth learner;
S22: iterative tracking layer for recording coded data of answer questionsAnd carrying out K rounds of answer accuracy vector tracking iteration, wherein the answer accuracy vector tracking iteration formula is as follows:
wherein:
the d round answer accuracy vector tracking iteration result of the kth learner is represented;
representing a matrix of coding weights->Representation braidingCode offset;
representing an iteration weight matrix;
s23: the output layer tracks the correct rate vector of the last round of answer to the iterative resultConversion into a knowledge level matrix:
wherein:
a knowledge level matrix representing a kth learner;
representing a matrix of knowledge weights->Representing knowledge offset;
representing an activation function.
S3: and carrying out similarity clustering on the learner based on the knowledge level matrix of the learner, calculating to obtain a knowledge level vector after similarity fusion according to a clustering result, and converting the knowledge level vector into the knowledge level matrix after similarity fusion.
In the step S3, similarity clustering is performed on the learners based on the knowledge level matrix of the learners, and a knowledge level vector after similarity fusion is obtained through calculation according to a clustering result, wherein the method comprises the following steps:
carrying out similarity clustering on learners based on a knowledge level matrix of the learners, wherein the similarity clustering flow is as follows:
s31: calculating the similarity of knowledge level matrix between any two different learners, wherein the knowledge levelMatrix arrayAnd->The similarity between the two is as follows:
wherein:
representing a knowledge level matrix->And->Similarity between;
an exponential function that is based on a natural constant;
represents an L1 norm;
s32: for arbitrary knowledge level matrixSelecting M knowledge level matrixes with highest similarity as +.>Is a similarity matrix of->Is a set of similarity matrices;
s33: calculating to obtain arbitrary knowledge level matrixIs used as knowledge level matrix +.>Knowledge level vector +.>。
In the step S3, converting the knowledge level vector into a knowledge level matrix after similarity fusion, including:
converting the knowledge level vector into a knowledge level matrix after similarity fusion, wherein the knowledge level matrix conversion formula after similarity fusion of the kth learner is as follows:
wherein:
a knowledge level matrix after similarity fusion of the kth learner is represented;
representing a fusion proportion parameter;
and the knowledge level vector after similarity fusion of the kth learner is represented.
S4: and decomposing the knowledge level matrix after similarity fusion to obtain the correct answer rate of the learner on the problem which is not done, and further obtaining the completed knowledge level matrix.
And S4, carrying out knowledge level matrix decomposition on the knowledge level matrix after similarity fusion to obtain the question answering accuracy of the learner on the problem which is not done, wherein the method comprises the following steps:
carrying out knowledge level matrix decomposition on the knowledge level matrix after similarity fusion to obtain the question answering accuracy of the learner on the non-exercise questions, wherein the knowledge level matrix after similarity fusionThe knowledge level matrix decomposition flow of (1) is as follows:
s41: calculating to obtain matrixMatrix->Wherein T represents a transpose;
s42: respectively to a matrixMatrix->Performing feature decomposition to respectively obtain M feature values and feature vectors corresponding to the feature values;
s43: according to the sequence of characteristic values from big to small, respectively for matrixMatrix->The feature vectors corresponding to the feature values of (2) are ordered:
wherein:
representing the ordered matrix +.>Is the m-th feature vector of (a);
representing the ordered matrix +.>Is the m-th feature vector of (a);
s44: generating the question answering accuracy rate of the kth learner in the mth channel of non-answer questions:
wherein:
the question answering accuracy of the kth learner in the mth channel is represented;
and completing the answer records of the learner according to the answer accuracy of the learner on the condition that the learner does not do exercises, and generating a completed knowledge level matrix.
And S4, completing the answer records of the learner according to the answer accuracy of the learner on the condition that the problem is not done, and generating a completed knowledge level matrix, wherein the method comprises the following steps of:
and (3) completing the answer records of the learner according to the answer accuracy of the learner on the non-doing exercises, namely taking the answer accuracy of the learner on the non-doing exercises as the answer condition of the learner on the non-doing exercises, carrying out knowledge coding on the completed answer records to obtain the completed answer record coded data of the learner, and generating a completed knowledge level matrix of the learner by using a deep knowledge tracking model.
S5: and generating knowledge mastering conditions of learners according to the completed knowledge level matrix, and determining the pushed exercises to carry out accurate teaching.
In the step S5, according to the completed knowledge level matrix, generating knowledge mastering conditions of learners and determining the pushed problems for precise teaching, including:
generating knowledge mastering conditions of learners and determining pushed problems according to the completed knowledge level matrix, wherein the knowledge mastering conditions of the kth learner and the generation flow of the pushed problems are as follows:
according to the knowledge point sequence contained in each problem acquired in the step S1, traversing to obtain the answering situation of the problem corresponding to any h knowledge point of the k learner, and calculating to obtain the mastering situation of the k learner at the h knowledge point:
wherein:
representing the mastery of the kth learner at the h knowledge point,/for the kth learner>H represents the total number of knowledge points of the problem;
representing a set of problems comprising an h knowledge point, wherein the set of problems +.>Subset of N questions for learner>,/>Representing problem set +.>Any one of the problems;
difficulty of indicating problem w->Representing the response condition of the kth name in the problem w;
if it isIf the learning point is higher than the preset threshold value, the kth learner grasps the kth knowledge point, otherwise, the kth learner does not grasp the kth knowledge pointh knowledge points, and pushing the difficulty of the question bank to be +.>And contains the problem of the h knowledge point, wherein the difficultySatisfies the following formula:
wherein:
indicating that the k-th learner answers push difficulty is +.>The accuracy of the problem of (2);
representing the completed knowledge level matrix for the kth learner.
Example 2:
fig. 2 is a schematic structural diagram of an electronic device for implementing a depth knowledge tracking and precise teaching method according to an embodiment of the present invention.
The electronic device 1 may comprise a processor 10, a memory 11, a communication interface 13 and a bus, and may further comprise a computer program, such as program 12, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may in other embodiments also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a secure digital (SecureDigital, SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only for storing application software installed in the electronic device 1 and various types of data, such as codes of the program 12, but also for temporarily storing data that has been output or is to be output.
The processor 10 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects respective parts of the entire electronic device using various interfaces and lines, executes or executes a program or a module (a program 12 for implementing precision teaching of depth knowledge tracking, etc.) stored in the memory 11, and invokes data stored in the memory 11 to perform various functions of the electronic device 1 and process the data.
The communication interface 13 may comprise a wired interface and/or a wireless interface (e.g. WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device 1 and other electronic devices and to enable connection communication between internal components of the electronic device.
The bus may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.
Fig. 2 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 2 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.
For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to each component, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device 1 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.
The electronic device 1 may optionally further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device 1 and for displaying a visual user interface.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The program 12 stored in the memory 11 of the electronic device 1 is a combination of instructions that, when executed in the processor 10, may implement:
collecting answer records of learners and carrying out knowledge coding to obtain answer record coding data of the learners;
constructing a depth knowledge tracking model to generate a knowledge level matrix of the learner, wherein the depth knowledge tracking model takes answer record coding data of the learner as input and takes the knowledge level matrix as output;
carrying out similarity clustering on the learner based on the knowledge level matrix of the learner, calculating to obtain a knowledge level vector after similarity fusion according to a clustering result, and converting the knowledge level vector into the knowledge level matrix after similarity fusion;
carrying out knowledge level matrix decomposition on the knowledge level matrix with the similarity fusion to obtain the correct answer rate of the learner on the problem which is not done, and further obtaining the completed knowledge level matrix;
and generating knowledge mastering conditions of learners according to the completed knowledge level matrix, and determining the pushed exercises to carry out accurate teaching.
Specifically, the specific implementation method of the above instruction by the processor 10 may refer to descriptions of related steps in the corresponding embodiments of fig. 1 to 2, which are not repeated herein.
It should be noted that, the foregoing reference numerals of the embodiments of the present invention are merely for describing the embodiments, and do not represent the advantages and disadvantages of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (8)
1. The method for teaching the depth knowledge tracking is characterized by comprising the following steps:
s1: collecting answer records of learners and carrying out knowledge coding to obtain answer record coding data of the learners;
s2: constructing a depth knowledge tracking model to generate a knowledge level matrix of the learner, wherein the depth knowledge tracking model takes answer record coding data of the learner as input and takes the knowledge level matrix as output;
s3: carrying out similarity clustering on the learner based on the knowledge level matrix of the learner, calculating to obtain a knowledge level vector after similarity fusion according to a clustering result, and converting the knowledge level vector into the knowledge level matrix after similarity fusion;
s4: carrying out knowledge level matrix decomposition on the knowledge level matrix with the similarity fusion to obtain the correct answer rate of the learner on the problem which is not done, and further obtaining the completed knowledge level matrix;
s5: and generating knowledge mastering conditions of learners according to the completed knowledge level matrix, and determining the pushed exercises to carry out accurate teaching.
2. The method for teaching deep knowledge tracking according to claim 1, wherein the step S1 of collecting answer records of learners and performing knowledge coding comprises the steps of:
collecting answer records of K learners, wherein the answer records of the learners are in the form of:
wherein:
representing the acquired answer records of the kth learner;
a question answering record for indicating the k-th learner in N questions,/question answering record for indicating the k-th learner in N questions>A question answering record for showing the nth question of the kth learner;
representing the knowledge point sequence contained in the n-th problem,/i>Indicating the response of the kth learner in the nth problem,/for the kth learner>Indicating that the kth learner did not answer the nth exercise,/>Indicating that the kth learner answers the nth question->Indicating the kth learner to answer the nth problem;
carrying out knowledge coding on the answer records of the learners to obtain answer record coding data of the learners, wherein the answer record knowledge coding flow of the kth learner is as follows:
s11: initializing and generating double-layer answer record knowledge coding matrix;
S12: double-layer answer record knowledge coding matrix according to answer records of kth learnerThe matrix elements in (a) are subjected to amplitude values, wherein a matrix element assignment formula is as follows: />
Wherein:
coding matrix for representing answer record knowledge>Assignment results of matrix elements in the ith row and the jth column;
coding matrix for representing answer record knowledge>Assignment results of matrix elements in the ith row and the jth column;
s13: coded data for forming answering records of kth learner。
3. The method for teaching and accurately tracking depth knowledge according to claim 1, wherein the step S2 of constructing the depth knowledge tracking model to generate the knowledge level matrix of the learner comprises:
the method comprises the steps of constructing a depth knowledge tracking model to generate a knowledge level matrix of a learner, wherein the depth knowledge tracking model takes answer record coding data of the learner as input and takes the knowledge level matrix as output, the depth knowledge tracking model comprises an input layer, an iteration tracking layer and an output layer, the input layer is used for receiving the answer record coding data of the learner, the iteration tracking layer is used for carrying out multiple rounds of answer accuracy vector tracking iteration on the answer record coding data, and the output layer is used for outputting the knowledge level matrix of the learner;
the knowledge level matrix generation flow of the kth learner based on the depth knowledge tracking model is as follows:
s21: the input layer receives the coded data of the answer records of the kth learner;
S22: iterative tracking layer for recording coded data of answer questionsAnd carrying out K rounds of answer accuracy vector tracking iteration, wherein the answer accuracy vector tracking iteration formula is as follows:
wherein:
the d round answer accuracy vector tracking iteration result of the kth learner is represented;
representing a matrix of coding weights->Representing the coding offset;
representing an iteration weight matrix;
s23: the output layer tracks the correct rate vector of the last round of answer to the iterative resultConversion into a knowledge level matrix:
wherein:
a knowledge level matrix representing a kth learner;
representing a matrix of knowledge weights->Representing knowledge offset;
representing an activation function.
4. The method for teaching deep knowledge tracking according to claim 1, wherein in the step S3, similarity clustering is performed on learners based on a knowledge level matrix of the learners, and a knowledge level vector after similarity fusion is obtained by calculating according to a clustering result, comprising:
carrying out similarity clustering on learners based on a knowledge level matrix of the learners, wherein the similarity clustering flow is as follows:
s31: calculating the similarity of knowledge level matrix between any two different learners, wherein the knowledge level matrixAnd->The similarity between the two is as follows:
wherein:
representing a knowledge level matrix->And->Similarity between;
an exponential function that is based on a natural constant;
represents an L1 norm;
s32: for arbitrary knowledge level matrixSelecting M knowledge level matrixes with highest similarity as +.>Is a similarity matrix of->Is a set of similarity matrices;
s33: calculating to obtain arbitrary knowledge level matrixIs used as knowledge level matrix +.>Knowledge level vector +.>。
5. The method for teaching and refining depth knowledge tracking according to claim 4, wherein the step S3 of converting the knowledge level vector into a knowledge level matrix after similarity fusion comprises:
converting the knowledge level vector into a knowledge level matrix after similarity fusion, wherein the knowledge level matrix conversion formula after similarity fusion of the kth learner is as follows:
wherein:
a knowledge level matrix after similarity fusion of the kth learner is represented;
representing a fusion proportion parameter;
represent the firstAnd the knowledge level vector after similarity fusion of k learners.
6. The method for teaching deep knowledge tracking according to claim 5, wherein in the step S4, knowledge level matrix decomposition is performed on the knowledge level matrix after similarity fusion to obtain a correct answer rate of the learner on the problem not being done, and the method comprises the following steps:
carrying out knowledge level matrix decomposition on the knowledge level matrix after similarity fusion to obtain the question answering accuracy of the learner on the non-exercise questions, wherein the knowledge level matrix after similarity fusionThe knowledge level matrix decomposition flow of (1) is as follows:
s41: calculating to obtain matrixMatrix->Wherein T represents a transpose;
s42: respectively to a matrixMatrix->Performing feature decomposition to respectively obtain M feature values and feature vectors corresponding to the feature values;
s43: according to the sequence of characteristic values from big to small, respectively for matrixMatrix->The feature vectors corresponding to the feature values of (2) are ordered: />
Wherein:
representing the ordered matrix +.>Is the m-th feature vector of (a);
representing the ordered matrix +.>Is the m-th feature vector of (a);
s44: generating the question answering accuracy rate of the kth learner in the mth channel of non-answer questions:
wherein:
the question answering accuracy of the kth learner in the mth channel is represented;
and completing the answer records of the learner according to the answer accuracy of the learner on the condition that the learner does not do exercises, and generating a completed knowledge level matrix.
7. The method for teaching deep knowledge tracking according to claim 6, wherein in the step S4, the learner answer record is completed according to the answer accuracy of the learner on the non-doing exercises, and the completed knowledge level matrix is generated, which comprises:
and (3) completing the answer records of the learner according to the answer accuracy of the learner on the non-doing exercises, namely taking the answer accuracy of the learner on the non-doing exercises as the answer condition of the learner on the non-doing exercises, carrying out knowledge coding on the completed answer records to obtain the completed answer record coded data of the learner, and generating a completed knowledge level matrix of the learner by using a deep knowledge tracking model.
8. The method for teaching the advanced knowledge tracking according to claim 1, wherein in the step S5, according to the completed knowledge level matrix, generating knowledge mastering conditions of learners and determining the pushed problems for teaching the advanced knowledge tracking comprises:
generating knowledge mastering conditions of learners and determining pushed problems according to the completed knowledge level matrix, wherein the knowledge mastering conditions of the kth learner and the generation flow of the pushed problems are as follows:
according to the knowledge point sequence contained in each problem acquired in the step S1, traversing to obtain the answering situation of the problem corresponding to any h knowledge point of the k learner, and calculating to obtain the mastering situation of the k learner at the h knowledge point:
wherein:
representing the mastery of the kth learner at the h knowledge point,/for the kth learner>H represents the total number of knowledge points of the problem;
representing a set of problems comprising an h knowledge point, wherein the set of problems +.>Subset of N questions for learner>,/>Representing problem set +.>Any one of the problems;
difficulty of indicating problem w->Representing the response condition of the kth name in the problem w;
if it isIf the learning degree is higher than the preset threshold, the kth learner is informed of the kth knowledge point, otherwise, the kth learner is not informed of the kth knowledge point, and the difficulty in the question bank is pushed to be +.>And comprises the problem of the h knowledge point, wherein the difficulty +.>Satisfies the following formula: />
Wherein:
indicating that the k-th learner answers push difficulty is +.>The accuracy of the problem of (2);
representing the completed knowledge level matrix for the kth learner.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311584767.9A CN117291775B (en) | 2023-11-27 | 2023-11-27 | Depth knowledge tracking accurate teaching method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311584767.9A CN117291775B (en) | 2023-11-27 | 2023-11-27 | Depth knowledge tracking accurate teaching method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117291775A true CN117291775A (en) | 2023-12-26 |
CN117291775B CN117291775B (en) | 2024-03-01 |
Family
ID=89241173
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311584767.9A Active CN117291775B (en) | 2023-11-27 | 2023-11-27 | Depth knowledge tracking accurate teaching method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117291775B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111898803A (en) * | 2020-07-09 | 2020-11-06 | 西北大学 | Exercise prediction method, system, equipment and storage medium |
CN113793239A (en) * | 2021-08-13 | 2021-12-14 | 华南理工大学 | Personalized knowledge tracking method and system fusing learning behavior characteristics |
CN114742292A (en) * | 2022-03-31 | 2022-07-12 | 四川生学教育科技有限公司 | Knowledge tracking process-oriented two-state co-evolution method for predicting future performance of students |
KR20220166606A (en) * | 2021-06-10 | 2022-12-19 | 오준서 | A system that provides artificial intelligence-based learning problem solving services |
WO2023277614A1 (en) * | 2021-07-01 | 2023-01-05 | (주)뤼이드 | Method, device, and system for recommending solution content maximizing education effect to user |
CN116361541A (en) * | 2023-01-28 | 2023-06-30 | 西安电子科技大学 | Test question recommendation method based on knowledge tracking and similarity analysis |
-
2023
- 2023-11-27 CN CN202311584767.9A patent/CN117291775B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111898803A (en) * | 2020-07-09 | 2020-11-06 | 西北大学 | Exercise prediction method, system, equipment and storage medium |
KR20220166606A (en) * | 2021-06-10 | 2022-12-19 | 오준서 | A system that provides artificial intelligence-based learning problem solving services |
WO2023277614A1 (en) * | 2021-07-01 | 2023-01-05 | (주)뤼이드 | Method, device, and system for recommending solution content maximizing education effect to user |
CN113793239A (en) * | 2021-08-13 | 2021-12-14 | 华南理工大学 | Personalized knowledge tracking method and system fusing learning behavior characteristics |
CN114742292A (en) * | 2022-03-31 | 2022-07-12 | 四川生学教育科技有限公司 | Knowledge tracking process-oriented two-state co-evolution method for predicting future performance of students |
CN116361541A (en) * | 2023-01-28 | 2023-06-30 | 西安电子科技大学 | Test question recommendation method based on knowledge tracking and similarity analysis |
Non-Patent Citations (2)
Title |
---|
闾汉原;申麟;漆美;: "基于"态度"的知识追踪模型及集成技术", 徐州师范大学学报(自然科学版), no. 04, pages 54 - 57 * |
马骁睿;徐圆;朱群雄;: "一种结合深度知识追踪的个性化习题推荐方法", 小型微型计算机***, no. 05, pages 990 - 995 * |
Also Published As
Publication number | Publication date |
---|---|
CN117291775B (en) | 2024-03-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110941723A (en) | Method, system and storage medium for constructing knowledge graph | |
US11631338B2 (en) | Deep knowledge tracing with transformers | |
CN111159419B (en) | Knowledge tracking data processing method, system and storage medium based on graph convolution | |
CN110991645A (en) | Self-adaptive learning method, system and storage medium based on knowledge model | |
CN113486665B (en) | Privacy protection text named entity recognition method, device, equipment and storage medium | |
CN111695354A (en) | Text question-answering method and device based on named entity and readable storage medium | |
CN102112942A (en) | Computer-based abacus training system | |
CN108228674A (en) | A kind of information processing method and device based on DKT | |
CN116383481A (en) | Personalized test question recommending method and system based on student portrait | |
CN110852071A (en) | Knowledge point detection method, device, equipment and readable storage medium | |
CN117291775B (en) | Depth knowledge tracking accurate teaching method | |
WO2021047376A1 (en) | Data processing method, data processing apparatus and related devices | |
CN112988844A (en) | Knowledge concept representation learning method based on student exercise sequence | |
JP2018155871A (en) | Learning support terminal, learning support server, learning support system, learning support method and learning support program | |
CN111639166A (en) | Mathematical oral calculation formula result error factor analysis method, device, equipment and storage medium | |
JP2020166046A (en) | Thinking power/judgment training system | |
CN111738198B (en) | Intelligent rapid calculation system and method | |
CN117114495B (en) | Professional education quality assessment method for capability generation analysis | |
CN118097761B (en) | Classroom teaching difficulty analysis method and system for attention analysis | |
CN117689117B (en) | Intelligent chemical industry planning consultation method and system | |
CN117094863B (en) | Intelligent learning behavior analysis system based on intelligent learning | |
CN117056452B (en) | Knowledge point learning path construction method, device, equipment and storage medium | |
CN117557426B (en) | Work data feedback method and learning evaluation system based on intelligent question bank | |
CN116541766B (en) | Training method of electroencephalogram data restoration model, electroencephalogram data restoration method and device | |
CN117726082B (en) | Teaching resource recommendation method and device, electronic equipment and readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |