CN116777694A - Teaching auxiliary system and method based on self-adaptive learning - Google Patents
Teaching auxiliary system and method based on self-adaptive learning Download PDFInfo
- Publication number
- CN116777694A CN116777694A CN202310739912.XA CN202310739912A CN116777694A CN 116777694 A CN116777694 A CN 116777694A CN 202310739912 A CN202310739912 A CN 202310739912A CN 116777694 A CN116777694 A CN 116777694A
- Authority
- CN
- China
- Prior art keywords
- course
- data
- question
- label
- student
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000012360 testing method Methods 0.000 claims description 57
- 238000000605 extraction Methods 0.000 claims description 37
- 238000012545 processing Methods 0.000 claims description 20
- 238000000354 decomposition reaction Methods 0.000 claims description 19
- 238000004891 communication Methods 0.000 claims description 11
- 230000003044 adaptive effect Effects 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 2
- 238000013075 data extraction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
Abstract
The application belongs to the technical field of teaching assistance, in particular to a teaching assistance system and a method based on self-adaptive learning.
Description
Technical Field
The application belongs to the technical field of teaching assistance, and particularly relates to a teaching assistance system and method based on self-adaptive learning.
Background
Along with the development of society and education, the mode of teaching mainly in the class by teachers has gradually not satisfied the study demands of students, so that in order to better serve students, the teaching guidance outside class is provided, and the problem is well solved by the appearance of a teaching auxiliary system.
The existing teaching auxiliary system generally adopts intelligent products such as a tablet personal computer and a mobile phone which are convenient to carry, the system comprises contents such as teacher teaching videos and post-class homework, learning record, learning evaluation and the like, students learn some interesting teaching contents through the intelligent products after learning or after class, and can well find own learning weak points aiming at students with strong learning ability so as to conduct reinforcement learning in a targeted manner, but aiming at students with less ideal learning ability, the system also has some phenomena such as lost and disordered learning when the teaching auxiliary system is used, and the students can have anaerobic emotion after long time; the main reason is that the existing teaching auxiliary system has the problems of weak guidance and lack of targeted guidance for students of different categories.
Disclosure of Invention
The application aims to solve the technical problem of weak guidance and lack of targeted guidance for students of different categories in the existing teaching auxiliary system by providing a teaching auxiliary system and a method based on self-adaptive learning.
The basic scheme provided by the application is as follows: the teaching auxiliary system based on self-adaptive learning comprises a teacher end, a student end and a server, wherein the teacher end and the student end are both in communication connection with the server, and the server comprises a login module, an uploading module, an academic class classification module, a class type self-defining module, a question group classification module, a learning path generation module and a pushing module;
the login module is used for establishing communication with the server when a teacher logs in from a teacher end and establishing communication with the server when students log in from a student end;
the uploading module is used for receiving course data, student test paper data, question group data and custom data uploaded by a teacher from the teacher side;
the academic level classification module is used for classifying the corresponding academic level of the students according to a preset academic level threshold value by combining the student test paper data and the custom data to generate a classification result;
the course self-defining module is used for carrying out self-defining type division on course content according to preset self-defining rules and combining course data, student test paper data and self-defining data to generate a plurality of course group sets;
the question group classification module is used for carrying out knowledge point label marking processing on the question group data according to the preset course knowledge point labels and generating a question group set from the question groups of the same knowledge point label;
the learning path generation module is used for associating the course group set with the question group set according to the grading result to generate a corresponding learning path;
the pushing module is used for pushing the generated learning path to the corresponding student end.
Further, the custom data includes student hall data, and the student skill level classification module classifies the corresponding student skill level according to a preset skill level threshold value, by combining student test paper data and custom data, and the classification result is specifically:
according to the historical recording proportion of the academic level grade test, acquiring the average recording proportion of each academic level grade by a mean value method, and taking the average recording proportion as a preset academic level grade threshold;
score extraction and content extraction are carried out on student test paper data, and ordinary score extraction is carried out on student follow-up data in user-defined data;
presetting a classifier model I, taking the content extracted by the score extraction, the content extraction and the usual score extraction as input of the classifier model I, taking a preset academic level grade threshold as a label of the classifier model I, and outputting a grading result.
Further, the custom data includes course flow information; the course type classification is carried out on course contents according to preset self-defining rules in the course type self-defining module by combining course data, student test paper data and self-defining data, and the generation of a plurality of course group sets is specifically as follows:
obtaining a grading result, extracting a grading label, and decomposing knowledge points in course data;
presetting a scoring algorithm, and scoring the decomposed knowledge points in course data through the scoring algorithm;
presetting a second classifier model, taking a scoring result as input of the second classifier model, taking a grading label as a grading label of the second classifier model, outputting knowledge points with the grading label, and sequencing the knowledge points of the same grading label according to course flow information to generate a course group set.
Further, the course customization module performs customization type classification on course content according to preset customization rules in combination with course data, student test paper data and customization data, and generating a plurality of course group sets further includes:
performing error question analysis on the student test paper data to generate error question representative labels, wherein the error question representative labels comprise error question knowledge points, error question types and error question characteristics;
carrying out knowledge point decomposition on course data, and matching the decomposition result with wrong question knowledge points in wrong question representing labels;
and merging the matching result into a course group set, and inserting the matching result into a corresponding course flow.
Further, in the topic group module, knowledge point label marking processing is performed on the topic group data according to preset course knowledge point labels, and topic group generating topic group sets of the same knowledge point labels are specifically:
carrying out knowledge point decomposition on course data, extracting knowledge point keywords, and preprocessing to obtain a preset course knowledge point label;
reading the question group data, extracting keywords of the question group data and identifying the structure of the question group, and generating a processing result; the construction of the subject set includes a degree of redundancy;
constructing a classifier model III, taking a processing result as input of the classifier model III, taking a course knowledge point label as a classification label of the classifier model III, outputting a question group with the knowledge point label, and generating a question group set from the question group with the same knowledge point label.
Further, the learning path generation module associates the course group set with the question group set according to the classification result, and the generation of the corresponding learning path specifically includes:
obtaining a grading result and extracting a grading label;
and obtaining a corresponding course group set according to the grading label, obtaining a corresponding question group set according to the course group set, and generating a learning path of a corresponding grading result.
The teaching assistance method based on the self-adaptive learning comprises the following steps:
s1: establishing communication between a teacher end and a student end and a server, and receiving uploaded course data, student test paper data, question group data and custom data from the teacher end;
s2: presetting a student level grade threshold, and grading the corresponding student level grade by combining student test paper data and custom data to generate a grading result;
s3: presetting a custom rule, and carrying out custom type division on course content by combining course data, student test paper data and custom data to generate a plurality of course group sets;
s4: presetting course knowledge point labels, carrying out knowledge point label marking processing on the question group data, and generating a question group set from the question groups of the same knowledge point label;
s5: and associating the course group set with the question group set according to the grading result, generating a corresponding learning path, and pushing the learning path to a corresponding student end.
Further, the custom data includes student hall data, and the S2 includes:
s2-1: according to the historical recording proportion of the academic level grade test, acquiring the average recording proportion of each academic level grade by a mean value method, and taking the average recording proportion as a preset academic level grade threshold;
s2-2: score extraction and content extraction are carried out on student test paper data, and ordinary score extraction is carried out on student follow-up data in user-defined data;
s2-3: presetting a classifier model I, taking the content extracted by the score extraction, the content extraction and the usual score extraction as input of the classifier model I, taking a preset academic level grade threshold as a label of the classifier model I, and outputting a grading result.
Further, the custom data further includes course flow information, and the S3 includes:
s3-1: obtaining a grading result, extracting a grading label, and decomposing knowledge points in course data;
s3-2: presetting a scoring algorithm, and scoring the decomposed knowledge points in course data through the scoring algorithm;
s3-3: presetting a second classifier model, taking a scoring result as input of the second classifier model, taking a grading label as a grading label of the second classifier model, outputting knowledge points with the grading label, and sequencing the knowledge points of the same grading label according to course flow information to generate a course group set;
s3-4: performing error question analysis on the student test paper data to generate error question representative labels, wherein the error question representative labels comprise error question knowledge points, error question types and error question characteristics;
s3-5: carrying out knowledge point decomposition on course data, and matching the decomposition result with wrong question knowledge points in wrong question representing labels;
s3-6: and merging the matching result into a course group set, and inserting the matching result into a corresponding course flow.
Further, the S4 includes:
s4-1: carrying out knowledge point decomposition on course data, extracting knowledge point keywords, and preprocessing to obtain a preset course knowledge point label;
s4-2: reading the question group data, extracting keywords of the question group data and identifying the structure of the question group, and generating a processing result; the construction of the subject set includes a degree of redundancy;
s4-3: constructing a classifier model III, taking a processing result as input of the classifier model III, taking a course knowledge point label as a classification label of the classifier model III, outputting a question group with a knowledge point label, and generating a question group set from the question group with the same knowledge point label;
the step S5 comprises the following steps:
s5-1: obtaining a grading result and extracting a grading label;
s5-2: acquiring a corresponding course group set according to the grading label, acquiring a corresponding question group set according to the course group set, and generating a learning path of a corresponding grading result;
s5-3: pushing the generated learning path to the corresponding student end.
The principle and effect of the application are as follows: according to the technical scheme, the current academic level of the students is graded to generate the personalized and self-adaptive learning path of the current learning level of the students, so that the students have clear learning contents in learning careers, and the phenomenon of disordered learning and no learning direction can be avoided; the teaching auxiliary system can solve the problems that the existing teaching auxiliary system is weak in guidance and lacks of targeted guidance for students of different categories.
Drawings
FIG. 1 is a functional block diagram of a first embodiment of the present application;
fig. 2 is a flow chart of a first embodiment of the present application.
Detailed Description
The following is a further detailed description of the embodiments:
an example is substantially as shown in figure 1: the teaching auxiliary system based on self-adaptive learning comprises a teacher end, a student end and a server, wherein the teacher end and the student end are both in communication connection with the server, and the server comprises a login module, an uploading module, an academic class classification module, a class type self-defining module, a question group classification module, a learning path generation module and a pushing module; the teacher end is used by a teacher, the student end is used by a student, when the teacher uses the teacher end, the teacher end and the server are in communication connection through a login module of the server, and similarly, when the student uses the student end, the same is true, in the embodiment, the login module adopts unique credentials of the teacher or the student to log in, such as a student number, an identity card number or a mobile phone number.
After entering the server through the teacher end, the teacher can upload course data, student test paper data, question group data and custom data from the teacher end, wherein the custom data are data which are uploaded by the teacher and are other than the course data, the student test paper data and the question group data, the custom data comprise student hall following data and course flow information in the embodiment, and in other embodiments, the custom uploading data can be carried out according to actual conditions; specifically, the course data includes various kinds of teaching material data, including, for example, math teaching material, english teaching material, chinese teaching material and other teaching material, the student's examination paper data is the examination paper of student at each examination, there are the content of student's answer, examination paper content and teacher's comment content etc. in this examination paper, the problem group data is the post-class of each department teaching material, the student follows the appearance of the hall data including the student on the classroom, for example, active expression, teacher's answer to the question appearance and teacher's evaluation record to the student on the classroom, the student follows the video data of the teacher and draws, course flow information is teaching sequence, flow and progress etc. of teacher to each department teaching material.
After receiving the data uploaded by the teacher end, the server evaluates and classifies the student's level through a student level classification module, specifically, a student level threshold is preset in the student level classification module, the student level classification module classifies the corresponding student level according to the preset student level threshold in combination with student test paper data and student hall data to generate a classification result, in this embodiment, the preset student level threshold is generated according to the history recording proportion of the student level rating test, the student level rating test represents the stage graduation test of the student, for example, the student level rating test represents the stage graduation test which is initially raised for junior middle school, and the student level rating test represents the graduation test of the college university, namely, the college entrance examination; the average value of each stage is obtained by a mean value method in the embodiment, and the average value is used as the academic level threshold in the application.
The method comprises the steps of combining student test paper data with student hall data, namely, carrying out score extraction and content extraction on the student test paper data, and carrying out ordinary score extraction on the student hall data; the score in the student test paper data is extracted, whether the score of the student reaches a certain stage of the level grade test of the calendar of the academic industry or not can be known, for example, the level of the ordinary family is reached, the content is extracted, the content which the student does not grasp in the answering process of the test paper can be known, the ordinary score extraction is carried out on the student along with the hall data, the performance of courses corresponding to the grasped content in the study test paper in the class of the student can be obtained, after the data extraction is completed, the first classifier model is constructed, the score extraction, the content extraction and the ordinary score extraction are used as the input of the first classifier model, the preset academic grade threshold is used as the label of the first classifier model, namely, the current score of the student can reach the grade of the result test, and the classification result is output. The output grading result comprises grading labels of the student's academic level grade, and corresponding course weak points and error question sets, namely, the grading labels are different in the grading result, but each grading label has the corresponding course weak points and error question sets.
After the classification of the academic class classification module is completed, the class type custom module performs custom type classification on course content according to preset custom rules and combines the course data, student test paper data and course flow information to generate a plurality of course group sets, in the embodiment, the class type custom module mainly correlates the course data with the classification result of the academic class classification module to generate a course corresponding to the classification result, specifically, firstly, the classification result is obtained, the classification label is extracted, knowledge point decomposition is performed on the course data, then, the knowledge points in the course data are assigned by a preset assignment algorithm, the assignment flow of the custom rules is that different weights are implemented on the knowledge points according to the classification result, for example, the classification result is special, the proportion occupied by the difficulty degree of the knowledge points is different from the classification result, the classification result is special, the classification result is weak, and the basic knowledge of the students is indicated to be weak, so that the assignment ratio of the basic knowledge is more, the assignment of the difficulty point is less, and the basic knowledge is more difficult to assign the difficulty point, and the basic knowledge point is more difficult to the basic knowledge point is needed to be more difficult to be described.
Therefore, in this embodiment, after the assignment of the knowledge points is completed, a classifier model two is preset, the assignment result is used as input of the classifier model two, the classification label is used as the classification label of the classifier model two, the output content is the knowledge points with the classification label, and the classification label is ordered according to course flow information, so as to generate a course group set, if the classification label is the class one according to the classification label, the assignment result of the knowledge points of the duplicate book calculated by the assignment algorithm is output, the output data is ordered in sequence according to the course flow information uploaded by the teacher end, so that the generated course group set represents the learning flow of the duplicate student, and similarly, for the classmates classified as the special students, the learning flow of the special student is generated.
In addition, the lesson type self-defining module processes the student test paper data specifically by firstly carrying out error question analysis on the student test paper data to generate error question representing labels, wherein the error question representing labels comprise error question knowledge points, error question types and error question characteristics; then carrying out knowledge point decomposition on the course data, and matching the decomposition result with wrong question knowledge points in the wrong question representing label; finally, the matching result is integrated into a course group set and is inserted into a corresponding course flow; according to the application, the wrong questions in the student test paper are analyzed, the characteristics of the knowledge point type, the questions, the word number of the questions and the like of the wrong questions are judged, the corresponding knowledge points are searched, and the course content of the knowledge points is convenient for students to correct after each examination by independently generating courses marked by the wrong questions.
The method comprises the steps that a course knowledge point label is preset in a question group classification module, the preset course knowledge point label is generated after being decomposed according to knowledge points of a course custom module, the question group classification module carries out knowledge point label marking processing on question group data, and a question group set is generated by the same knowledge point label, specifically, the course data is subjected to knowledge point decomposition, knowledge point keywords are extracted, and the knowledge point label is used as the preset course knowledge point label after being preprocessed;
reading the question group data, extracting keywords of the question group data and identifying the structure of the question group, and generating a processing result; the construction of the subject set includes a degree of redundancy;
constructing a classifier model III, taking a processing result as input of the classifier model III, taking a course knowledge point label as a classification label of the classifier model III, outputting a question group with the knowledge point label, and generating a question group set from the question group with the same knowledge point label.
After the data uploaded by the teacher end is processed by the learning class classification module, the class type self-defining module and the question classification module, the learning requirements of students with different classification results are met through the generated learning path, and after the learning path is generated, the data is pushed to the corresponding student end through the pushing module so as to be learned by the students.
According to the technical scheme, the current academic level of the students is graded to generate the personalized and self-adaptive learning path of the current learning level of the students, so that the students have clear learning contents in learning careers, and the phenomenon of disordered learning and no learning direction can be avoided.
As shown in fig. 2, in another embodiment of the present embodiment, the teaching assistance method based on adaptive learning further includes:
s1: establishing communication between a teacher end and a student end and a server, and receiving uploaded course data, student test paper data, question group data and custom data from the teacher end; the custom data comprises student hall following data and course flow information;
s2: presetting a student level grade threshold, and grading the corresponding student level grade by combining student test paper data and custom data to generate a grading result;
s2-1: according to the historical recording proportion of the academic level grade test, acquiring the average recording proportion of each academic level grade by a mean value method, and taking the average recording proportion as a preset academic level grade threshold;
s2-2: score extraction and content extraction are carried out on student test paper data, and ordinary score extraction is carried out on student follow-up data in user-defined data;
s2-3: presetting a classifier model I, taking the content extracted by the score extraction, the content extraction and the usual score extraction as input of the classifier model I, taking a preset academic level grade threshold as a label of the classifier model I, and outputting a grading result;
s3: presetting a custom rule, and carrying out custom type division on course content by combining course data, student test paper data and custom data to generate a plurality of course group sets;
s3-1: obtaining a grading result, extracting a grading label, and decomposing knowledge points in course data;
s3-2: presetting a scoring algorithm, and scoring the decomposed knowledge points in course data through the scoring algorithm;
s3-3: presetting a second classifier model, taking a scoring result as input of the second classifier model, taking a grading label as a grading label of the second classifier model, outputting knowledge points with the grading label, and sequencing the knowledge points of the same grading label according to course flow information to generate a course group set;
s3-4: performing error question analysis on the student test paper data to generate error question representative labels, wherein the error question representative labels comprise error question knowledge points, error question types and error question characteristics;
s3-5: carrying out knowledge point decomposition on course data, and matching the decomposition result with wrong question knowledge points in wrong question representing labels;
s3-6: the matching result is integrated into a course group set and is inserted into a corresponding course flow;
s4: presetting course knowledge point labels, carrying out knowledge point label marking processing on the question group data, and generating a question group set from the question groups of the same knowledge point label;
s4-1: carrying out knowledge point decomposition on course data, extracting knowledge point keywords, and preprocessing to obtain a preset course knowledge point label;
s4-2: reading the question group data, extracting keywords of the question group data and identifying the structure of the question group, and generating a processing result; the construction of the subject set includes a degree of redundancy;
s4-3: constructing a classifier model III, taking a processing result as input of the classifier model III, taking a course knowledge point label as a classification label of the classifier model III, outputting a question group with a knowledge point label, and generating a question group set from the question group with the same knowledge point label;
s5: associating the course group set with the question group set according to the grading result, generating a corresponding learning path, and pushing the learning path to a corresponding student end;
s5-1: obtaining a grading result and extracting a grading label;
s5-2: acquiring a corresponding course group set according to the grading label, acquiring a corresponding question group set according to the course group set, and generating a learning path of a corresponding grading result;
s5-3: pushing the generated learning path to the corresponding student end.
Embodiment two:
the second embodiment is different from the first embodiment in that the second embodiment further includes a step-up planning module and an evaluation module, where the step-up planning module is configured to extract a step-up label in the step-up result, if the step-up label is not the highest level, raise the step-up label by one level, and perform matching between the course set and the question set according to the raised step-up result, and generate a step-up learning path.
In this embodiment, for students to increase their own classification in the teaching assistance system, the corresponding advanced learning path is pushed to the students through the advanced learning route, and the evaluation module is used to evaluate the staged learning result of the students at the user side; the evaluation module is generated by evaluation based on the modes of learning result assessment, teacher expert online evaluation and the like, so that a teacher or an expert can conduct a guidance on the post-class state of students.
The foregoing is merely exemplary of the present application, and specific structures and features well known in the art will not be described in detail herein, so that those skilled in the art will be aware of all the prior art to which the present application pertains, and will be able to ascertain the general knowledge of the technical field in the application or prior art, and will not be able to ascertain the general knowledge of the technical field in the prior art, without using the prior art, to practice the present application, with the aid of the present application, to ascertain the general knowledge of the same general knowledge of the technical field in general purpose. It should be noted that modifications and improvements can be made by those skilled in the art without departing from the structure of the present application, and these should also be considered as the scope of the present application, which does not affect the effect of the implementation of the present application and the utility of the patent. The protection scope of the present application is subject to the content of the claims, and the description of the specific embodiments and the like in the specification can be used for explaining the content of the claims.
Claims (10)
1. Teaching auxiliary system based on self-adaptation study, its characterized in that: the system comprises a teacher end, a student end and a server, wherein the teacher end and the student end are both in communication connection with the server, and the server comprises a login module, an uploading module, an academic class classification module, a class self-defining module, a question group classification module, a learning path generation module and a pushing module;
the login module is used for establishing communication with the server when a teacher logs in from a teacher end and establishing communication with the server when students log in from a student end;
the uploading module is used for receiving course data, student test paper data, question group data and custom data uploaded by a teacher from the teacher side;
the academic level classification module is used for classifying the corresponding academic level of the students according to a preset academic level threshold value by combining the student test paper data and the custom data to generate a classification result;
the course self-defining module is used for carrying out self-defining type division on course content according to preset self-defining rules and combining course data, student test paper data and self-defining data to generate a plurality of course group sets;
the question group classification module is used for carrying out knowledge point label marking processing on the question group data according to the preset course knowledge point labels and generating a question group set from the question groups of the same knowledge point label;
the learning path generation module is used for associating the course group set with the question group set according to the grading result to generate a corresponding learning path;
the pushing module is used for pushing the generated learning path to the corresponding student end.
2. The adaptive learning-based teaching assistance system of claim 1, wherein: the custom data comprises student hall data, and the student skill level classification module classifies corresponding student skill level grades according to a preset skill level grade threshold value by combining student test paper data and the custom data, and the specific classification result generation is as follows:
according to the historical recording proportion of the academic level grade test, acquiring the average recording proportion of each academic level grade by a mean value method, and taking the average recording proportion as a preset academic level grade threshold;
score extraction and content extraction are carried out on student test paper data, and ordinary score extraction is carried out on student follow-up data in user-defined data;
presetting a classifier model I, taking the content extracted by the score extraction, the content extraction and the usual score extraction as input of the classifier model I, taking a preset academic level grade threshold as a label of the classifier model I, and outputting a grading result.
3. The adaptive learning-based teaching assistance system of claim 2, wherein: the custom data comprises course flow information; the course type classification is carried out on course contents according to preset self-defining rules in the course type self-defining module by combining course data, student test paper data and self-defining data, and the generation of a plurality of course group sets is specifically as follows:
obtaining a grading result, extracting a grading label, and decomposing knowledge points in course data;
presetting a scoring algorithm, and scoring the decomposed knowledge points in course data through the scoring algorithm;
presetting a second classifier model, taking a scoring result as input of the second classifier model, taking a grading label as a grading label of the second classifier model, outputting knowledge points with the grading label, and sequencing the knowledge points of the same grading label according to course flow information to generate a course group set.
4. The adaptive learning-based teaching assistance system of claim 3, wherein: the course self-defining module performs self-defining type division on course content according to preset self-defining rules and combining course data, student test paper data and self-defining data, and the generating of a plurality of course group sets further comprises:
performing error question analysis on the student test paper data to generate error question representative labels, wherein the error question representative labels comprise error question knowledge points, error question types and error question characteristics;
carrying out knowledge point decomposition on course data, and matching the decomposition result with wrong question knowledge points in wrong question representing labels;
and merging the matching result into a course group set, and inserting the matching result into a corresponding course flow.
5. The adaptive learning-based teaching assistance system of claim 4, wherein: the topic group classification module carries out knowledge point label marking processing on topic group data according to preset course knowledge point labels, and the topic group generation topic group set of the same knowledge point label is specifically as follows:
carrying out knowledge point decomposition on course data, extracting knowledge point keywords, and preprocessing to obtain a preset course knowledge point label;
reading the question group data, extracting keywords of the question group data and identifying the structure of the question group, and generating a processing result; the construction of the subject set includes a degree of redundancy;
constructing a classifier model III, taking a processing result as input of the classifier model III, taking a course knowledge point label as a classification label of the classifier model III, outputting a question group with the knowledge point label, and generating a question group set from the question group with the same knowledge point label.
6. The adaptive learning-based teaching assistance system of claim 5, wherein: the learning path generation module associates the course group set with the question group set according to the grading result, and the generation of the corresponding learning path is specifically as follows:
obtaining a grading result and extracting a grading label;
and obtaining a corresponding course group set according to the grading label, obtaining a corresponding question group set according to the course group set, and generating a learning path of a corresponding grading result.
7. The teaching auxiliary method based on self-adaptive learning is characterized by comprising the following steps of: comprising the following steps:
s1: establishing communication between a teacher end and a student end and a server, and receiving uploaded course data, student test paper data, question group data and custom data from the teacher end;
s2: presetting a student level grade threshold, and grading the corresponding student level grade by combining student test paper data and custom data to generate a grading result;
s3: presetting a custom rule, and carrying out custom type division on course content by combining course data, student test paper data and custom data to generate a plurality of course group sets;
s4: presetting course knowledge point labels, carrying out knowledge point label marking processing on the question group data, and generating a question group set from the question groups of the same knowledge point label;
s5: and associating the course group set with the question group set according to the grading result, generating a corresponding learning path, and pushing the learning path to a corresponding student end.
8. The teaching assistance method based on adaptive learning according to claim 7, wherein: the custom data includes student hall data, and the S2 includes:
s2-1: according to the historical recording proportion of the academic level grade test, acquiring the average recording proportion of each academic level grade by a mean value method, and taking the average recording proportion as a preset academic level grade threshold;
s2-2: score extraction and content extraction are carried out on student test paper data, and ordinary score extraction is carried out on student follow-up data in user-defined data;
s2-3: presetting a classifier model I, taking the content extracted by the score extraction, the content extraction and the usual score extraction as input of the classifier model I, taking a preset academic level grade threshold as a label of the classifier model I, and outputting a grading result.
9. The teaching assistance method based on adaptive learning according to claim 8, wherein: the custom data further includes course flow information, and the S3 includes:
s3-1: obtaining a grading result, extracting a grading label, and decomposing knowledge points in course data;
s3-2: presetting a scoring algorithm, and scoring the decomposed knowledge points in course data through the scoring algorithm;
s3-3: presetting a second classifier model, taking a scoring result as input of the second classifier model, taking a grading label as a grading label of the second classifier model, outputting knowledge points with the grading label, and sequencing the knowledge points of the same grading label according to course flow information to generate a course group set;
s3-4: performing error question analysis on the student test paper data to generate error question representative labels, wherein the error question representative labels comprise error question knowledge points, error question types and error question characteristics;
s3-5: carrying out knowledge point decomposition on course data, and matching the decomposition result with wrong question knowledge points in wrong question representing labels;
s3-6: and merging the matching result into a course group set, and inserting the matching result into a corresponding course flow.
10. The teaching assistance method based on adaptive learning according to claim 9, wherein: the step S4 comprises the following steps:
s4-1: carrying out knowledge point decomposition on course data, extracting knowledge point keywords, and preprocessing to obtain a preset course knowledge point label;
s4-2: reading the question group data, extracting keywords of the question group data and identifying the structure of the question group, and generating a processing result; the construction of the subject set includes a degree of redundancy;
s4-3: constructing a classifier model III, taking a processing result as input of the classifier model III, taking a course knowledge point label as a classification label of the classifier model III, outputting a question group with a knowledge point label, and generating a question group set from the question group with the same knowledge point label;
the step S5 comprises the following steps:
s5-1: obtaining a grading result and extracting a grading label;
s5-2: acquiring a corresponding course group set according to the grading label, acquiring a corresponding question group set according to the course group set, and generating a learning path of a corresponding grading result;
s5-3: pushing the generated learning path to the corresponding student end.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310739912.XA CN116777694A (en) | 2023-06-20 | 2023-06-20 | Teaching auxiliary system and method based on self-adaptive learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310739912.XA CN116777694A (en) | 2023-06-20 | 2023-06-20 | Teaching auxiliary system and method based on self-adaptive learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116777694A true CN116777694A (en) | 2023-09-19 |
Family
ID=87985445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310739912.XA Pending CN116777694A (en) | 2023-06-20 | 2023-06-20 | Teaching auxiliary system and method based on self-adaptive learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116777694A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117114941A (en) * | 2023-10-25 | 2023-11-24 | 深圳市微校互联科技有限公司 | Education and teaching management platform based on dynamic learning condition data chain |
-
2023
- 2023-06-20 CN CN202310739912.XA patent/CN116777694A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117114941A (en) * | 2023-10-25 | 2023-11-24 | 深圳市微校互联科技有限公司 | Education and teaching management platform based on dynamic learning condition data chain |
| CN117114941B (en) * | 2023-10-25 | 2024-02-09 | 深圳市微校互联科技有限公司 | Education and teaching management platform based on dynamic learning condition data chain |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mao et al. | Validation of automated scoring for a formative assessment that employs scientific argumentation | |
| Kotsiantis | Use of machine learning techniques for educational proposes: a decision support system for forecasting students’ grades | |
| Reffay et al. | How social network analysis can help to measure cohesion in collaborative distance-learning | |
| CN105469662A (en) | Student answer information real-time collection and efficient and intelligent correcting system and use method in teaching process | |
| CN110633730A (en) | Deep learning machine reading understanding training method based on course learning | |
| CN111326040B (en) | Intelligent test and intelligent tutoring system and method for Chinese reading understanding | |
| CN106021347B (en) | It is a kind of to exempt from the online interaction answering system and method that information is bothered | |
| CN111831831A (en) | Knowledge graph-based personalized learning platform and construction method thereof | |
| CN109949637B (en) | Automatic answering method and device for objective questions | |
| CN110414837B (en) | Human-computer interaction system based on error cause analysis | |
| CN116777694A (en) | Teaching auxiliary system and method based on self-adaptive learning | |
| Gkontzis et al. | Polarity, emotions and online activity of students and tutors as features in predicting grades | |
| CN112764760A (en) | Program evaluation-based auxiliary question answering system | |
| Schönberger | ChatGPT in higher education: the good, the bad, and the University | |
| Niu | Classification of learning sentiments of college students based on topic discussion texts of online learning platforms | |
| Zang et al. | Investigation of web-based teaching and learning by boosting algorithms | |
| Wang et al. | Teacher Talk Moves in K12 Mathematics Lessons: Automatic Identification, Prediction Explanation, and Characteristic Exploration | |
| Gailey et al. | Exploring preservice teachers’ civic education beliefs with Q methodology | |
| Suresh et al. | Identifying teamwork indicators in an online collaborative problem-solving task: A text-mining approach | |
| TWM606688U (en) | Cloud intelligent item bank system for scoring knowledge point | |
| Doctor | A predictive model using machine learning algorithm in identifying students probability on passing semestral course | |
| Hall | Young children and resistance to punctuation | |
| Sevindik et al. | Using algorithms for evaluation in web based distance education | |
| Sherzad | Shaping the selection of fields of study in Afghanistan through educational data mining approaches | |
| Betaubun | The Implementation of SQ3R Technique in Teaching English to Support Third Class Students’ Ability in Reading Comprehension at State Vocational High School in Merauke-Papua Indonesia |
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 |