CN117892816A - System and method for generating school year knowledge graph based on multiple teaching styles - Google Patents

Abstract

The invention discloses a system and a method for generating a learning years knowledge graph based on multiple teaching styles, wherein the system comprises a characteristic evaluation unit, a teaching scheme generation unit, a course learning unit and a learning years knowledge graph generation unit; based on the output teaching scheme, entering a course learning unit to perform macroscopic evaluation and microscopic evaluation on the teaching scheme; generating a learning year knowledge graph by entering a learning year knowledge graph generating unit, and generating a multi-teaching-style course of a dedicated individual for each individual to guide students to understand and master knowledge from different angles and modes; through diversified learning experience, students can understand and apply the learning content more deeply, and the learning effect and the memory durability are improved; the method is beneficial to strengthening the generation precision of the multi-teaching-style course and tracking the change of the learning effect of the students under the multi-teaching-style course learning.

Description

A system and method for generating academic year knowledge graph based on multiple teaching styles

Technical Field

The present invention relates to the technical field of multi-style learning tutorial generation, and specifically to a system and method for generating a school year knowledge graph based on multiple teaching styles.

Background technique

Traditionally, education often adopts a single teaching method, ignoring the individual differences and diverse learning needs of students. However, with the deepening of research and the development of educational practice, people have gradually realized that each student is unique, with different intelligence types, learning styles, interests and hobbies, and ability levels. The emergence of multiple teaching styles is to better meet the diverse needs of students and provide more effective learning methods. It emphasizes personalized education, pays attention to students' individual differences and potential development, and aims to improve learning effects and students' overall development. Multiple teaching styles can guide students to understand and master knowledge from different perspectives and methods. Through diversified learning experiences, students can understand and apply what they have learned more deeply, improve learning effects and memory persistence. It is of great significance to promote the all-round development of students, improve the quality of education, and promote educational innovation.

However, today's personalized teaching process only starts from the individual differences of students, scientifically presenting learning paths suitable for individual differences or changing the teaching speed, increasing teaching interactions to improve students' attention. However, it ignores the differences in individual students' cognitive abilities and different receptive abilities to different teaching styles, which in turn leads to a decline in teaching effectiveness. Therefore, it is extremely important to provide multi-style teaching plans suitable for different students based on individual differences and cognitive levels of students. At the same time, collecting students' teaching knowledge maps every academic year is of great significance for long-term tracking of the effects of multiple teaching styles.

Summary of the invention

The purpose of the present invention is to provide a system for generating a knowledge graph for a school year based on multiple teaching styles, comprising:

The characteristic evaluation unit collects and records the students’ physiological characteristic data and the corresponding students’ learning characteristic data in the teaching system, and builds a priori knowledge base;

The teaching plan generation unit takes the teaching style library, the knowledge graph of the previous academic year and the prior knowledge base information as input, and outputs the corresponding teaching plan;

The course learning unit generates macro-evaluation and micro-evaluation based on the learning and examination of all knowledge points in the completed teaching plan;

The academic year knowledge graph generation unit outputs the corresponding academic year knowledge graph based on the macro-evaluation and micro-evaluation results and the corresponding teaching plan.

Preferably, the construction of the prior knowledge base is specifically as follows:

Students log in to the system and match the academic affairs system to obtain the corresponding student learning characteristic data;

Randomly extract the knowledge points to be learned and generate courses according to the styles in the teaching style library, and obtain the students' physiological characteristics data by learning the generated courses.

Preferably, the student's physiological characteristic data include EEG characteristics, ECG characteristics, body temperature characteristics, body posture characteristics and facial expression characteristics; the corresponding student learning characteristics in the teaching system include the teacher's evaluation, regular grades and paper grades of the corresponding students.

Preferably, the teaching style library is constructed by using a large language model to collect traditional teaching modes, and by analyzing their teaching characteristics, auxiliary tools, and whether or not there is interaction, the courses of traditional teaching modes are divided into voice and text presentation categories, including lectures and autonomous learning.

Preferably, the speech and text presentation types include teaching types and self-learning types;

The audio and video presentation categories include demonstration, experiment, performance, and practice;

Voice interactive presentation categories include question-and-answer, inspiration, discussion, and collaborative learning.

Preferably, the teaching mode classification standard is:

;

Among them, n is the number of participants in the class, , when n=1, it means that only the teacher participates, and there is no interaction between the teacher and the students; when n=2, it means that the teacher and the students participate together, and there is interaction between the teacher and the students;

m is the number of teaching aids, When m=1, it means that the auxiliary tools for class are only blackboard writing; when m=2, it means that the auxiliary tools for class are blackboard writing and multimedia; when m=3, it means that the auxiliary tools for class are blackboard writing, multimedia and teaching aids.

Preferably, the macro evaluation is: calculating the average scores of all students in multiple courses in this semester and this academic year, wherein the macro evaluation MA of course i is expressed as: ; Among them, p is the number of students and g is the students' grades.

Preferably, the micro-evaluation is: calculating all the grades of a student in multiple courses in this semester and this academic year; wherein the micro-evaluation MI of student k in each course can be expressed as: ;

Where, j=1, 2, ..., n, represents the jth course, n represents the number of courses, and r represents the score of student k in each course.

Preferably, in the academic year knowledge graph generation unit, the academic year knowledge graph is constructed with courses as entities, the learning sequence between courses as relationships, and students' macro-evaluations and micro-evaluations as course attributes. The learning sequence relationships include previous and next relationships, parallel relationships, and no relationship.

The present invention also discloses a method for generating a school year knowledge graph based on multiple teaching styles, comprising the following steps:

S1. Log in to the school year knowledge graph generation system and determine whether the user is a new user;

If it is a new user, enter the feature evaluation unit;

If you are not a new user, you will enter the teaching plan generation unit;

S2, obtain the user's prior knowledge base, and enter the teaching plan generation unit to take the teaching style library, the previous school year's knowledge map and the prior knowledge base information as input, and output the corresponding teaching plan;

S3. Based on the output teaching plan, enter the course learning unit, complete the learning of all knowledge points of this course and take the exam, and conduct macro-evaluation and micro-evaluation of the teaching plan;

S4. Enter the academic year knowledge graph generation unit, generate the academic year knowledge graph based on the macro-evaluation and micro-evaluation results and course-related attributes, and use it to generate the teaching plan for the next academic year.

Beneficial effects: By obtaining students' physiological information and past learning information, the personalized characteristics of each student are given, and personalized and accurate evaluation of students is achieved; by building a teaching style library, the traditional teaching model is mapped to a new generation of teaching style, and a multi-style teaching foundation is realized, which is easier to implement; by generating a personal multi-teaching style tutorial for each individual, students are guided to understand and master knowledge from different angles and methods; through diversified learning experiences, students can understand and apply what they have learned more deeply, improve learning effects and memory persistence; and the construction and recording of knowledge maps for the academic year are conducive to enhancing the accuracy of multi-teaching style tutorial generation and tracking changes in students' learning effects under multi-teaching style tutorial learning.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

In the attached picture:

Figure 1 is a schematic diagram of the system architecture for generating the academic year knowledge graph;

FIG2 is a schematic diagram of a priori knowledge base and a construction process of the present invention;

FIG3 is a schematic diagram of a teaching style library construction process of the present invention;

FIG4 is a schematic diagram of generating a knowledge graph for academic year teaching according to the present invention;

FIG5 is a flow chart of the method for generating a knowledge graph for a school year according to the present invention.

Detailed ways

The following describes the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. The terms used in the implementation mode of the present invention are only used to explain the specific embodiments of the present invention, and are not intended to limit the present invention.

As shown in Figure 1, it is an architecture diagram of the academic year knowledge graph generation system of the present invention, including a feature evaluation unit, a teaching plan generation unit, a course learning unit and an academic year knowledge graph generation unit; the feature evaluation unit collects and records students' physiological feature data and corresponding student learning feature-related data in the teaching system to construct a priori knowledge base; the teaching plan generation unit takes the teaching style library, the knowledge graph of the previous academic year and the prior knowledge base information as input, and outputs the corresponding teaching plan; the course learning unit generates macro-evaluation and micro-evaluation based on the learning and examination of all knowledge points of the output teaching plan; the academic year knowledge graph generation unit outputs the corresponding academic year knowledge graph based on the macro-evaluation and micro-evaluation results and the corresponding teaching plan.

As shown in Figure 2, it is a schematic diagram of the prior knowledge base construction process; the prior database includes students' physiological characteristics and the corresponding student learning characteristics in the teaching system; students' physiological characteristics are collected through the smart classroom, and the process is as follows: randomly extract the knowledge points to be learned and generate tutorials according to the styles in the teaching style library; equip students with head-mounted EEG devices, patch-type ECG devices, and hanging monitoring devices to collect students' physiological data, including EEG signals, ECG signals, and video signals; perform key feature extraction processing on the collected data signals to obtain students' key data features, including EEG features, ECG features, body temperature features, body posture features, and facial expression features;

The process of collecting student learning characteristics is as follows: students register with the system using their student ID, enter the knowledge base of the academic affairs system, and match student learning records based on their student ID to obtain student learning characteristics, including the corresponding student’s teacher evaluation, regular grades, and paper grades.

As shown in Figure 3, it is a schematic diagram of the teaching style library construction process; the large language model is used to collect traditional teaching modes, including 11 categories: lecture, autonomous learning, demonstration, experiment, performance, practice, inquiry learning, question and answer, inspiration, discussion, and cooperative learning; by analyzing their teaching characteristics, auxiliary tools, and whether there is interaction, the above courses are divided into voice and text presentation categories, including lecture, autonomous learning, voice and video presentation categories, including demonstration, experiment, performance, practice, inquiry learning, and voice interactive presentation categories, including question and answer, inspiration, discussion, and cooperative learning categories; the specific classification standards are as follows:

Define n as the number of participants in the class, , when n=1, it means that only the teacher participates, and there is no interaction between the teacher and the students; when n=2, it means that the teacher and the students participate together, and there is interaction between the teacher and the students;

m is the number of teaching aids, , when m=1, it means that the auxiliary tool for class is only blackboard writing; when m=2, it means that the auxiliary tools for class are blackboard writing and multimedia; when m=3, it means that the auxiliary tools for class are blackboard writing, multimedia and teaching aids;

By conducting statistical analysis on the number of n and m of the above 11 types of teaching videos, we can obtain:

;

Correspondingly, the voice and text presentation tutorials will use voice and text to present to students for learning; the voice and video presentation tutorials will use voice and animation to present to students for learning; the voice interaction presentation tutorials will use voice, animation and online interactive questions to present to students for learning.

The teaching style library, the knowledge graph of the previous school year and the prior knowledge base information are used as input to obtain the teaching plan; based on the output teaching plan, the learning of all knowledge points in this book is completed and the examination is conducted, and the teaching plan is evaluated macroscopically and microscopically;

Among them, the macro evaluation is: calculate the average score of all students in multiple courses in this semester and this academic year. In this semester and this academic year, it is defined that there are p students participating in the study of course i, and the score of each student is represented by g. Then the macro evaluation MA of course i can be expressed as: ;

Micro-evaluation is to calculate all the grades of a student in multiple courses in this semester and this academic year. It is defined that there are n courses in this semester and this academic year, and the grade of student k in each course is represented by r. Then the micro-evaluation MI of student k in each course can be expressed as: ;

Among them, j=1,2,...,n, represents the jth course.

Generate the knowledge graph for this academic year based on the macro-evaluation and micro-evaluation results and the corresponding teaching plan.

As shown in Figure 4, this is a schematic diagram of generating the knowledge graph for the academic year. The knowledge graph for the academic year is constructed with courses as entities, the learning sequence between courses as relationships, and students' macro-evaluations and micro-evaluations as course attributes. The learning sequence relationships include previous and next relationships, parallel relationships, and no relationships.

The present invention also discloses a method for generating a school year knowledge graph based on multiple teaching styles, as shown in FIG5 , comprising the following steps:

S1. Log in to the school year knowledge graph generation system and determine whether the user is a new user;

If it is a new user, enter the feature evaluation unit;

If you are not a new user, you will enter the teaching plan generation unit;

S2, obtain the user's prior knowledge base, and enter the teaching plan generation unit to take the teaching style library, the previous school year's knowledge map and the prior knowledge base information as input, and output the corresponding teaching plan;

S3. Based on the output teaching plan, enter the course learning unit, complete the learning of all knowledge points of this course and take the exam, and conduct macro-evaluation and micro-evaluation of the teaching plan;

S4. Enter the academic year knowledge graph generation unit, generate the academic year knowledge graph based on the macro-evaluation and micro-evaluation results and course-related attributes, and use it to generate the teaching plan for the next academic year.

In a specific embodiment: User A logs in to the system, and it is determined that User A is a new user, then enters the feature evaluation unit, and requires User A to wear a head-mounted EEG device, a patch-type ECG device, and an authorized monitoring device, and generates an evaluation tutorial based on all styles in the teaching style library. During the learning process, the EEG, ECG, body temperature, body posture, and facial expression features of User A are collected; at the same time, using the login student number information of User A, the teacher evaluation, regular grades, and paper grades of User A over the years are searched in the teaching affairs system, and the physiological characteristics and background characteristics of User A are integrated to obtain a priori knowledge base, which is expressed as follows:

Next, enter the teaching plan generation unit, with the teaching style library and prior knowledge base information as input, and the output is the proportion of three styles. According to the proportion, the academic year course teaching plan with different styles is generated in the corresponding courses; after completing all the courses of the academic year, the above-mentioned macro-evaluation and micro-evaluation are carried out. Finally, the academic year knowledge graph is generated as shown in the following table. The course is taken as the entity, the learning sequence between courses is the relationship, and the macro- and micro-evaluations of students are used as the course attributes to construct the academic year knowledge graph. The learning sequence relationship is defined as the before-after relationship c, the parallel relationship a, and the no relationship 0;

In a specific embodiment: user B logs in to the system, and it is determined that user B is an old user, then enters the teaching plan generation unit, takes the teaching style library, the knowledge graph of the previous school year and the prior knowledge base information as input, and outputs the proportion of three styles. According to the proportion, the school year course teaching plan represented by different styles is generated in the corresponding course; after completing the study of all courses in the school year, the above-mentioned macro-evaluation and micro-evaluation are performed, and finally, the school year knowledge graph is generated as shown in the following table, with courses as entities, the learning sequence between courses as relationships, and the macro and micro evaluations of students as course attributes to construct the school year knowledge graph, and the learning sequence relationship is defined as the before-after relationship c, the parallel relationship a and the no relationship 0;

The embodiments of the present invention are described in detail above in conjunction with the accompanying drawings, but the present invention is not limited to the above embodiments. For ordinary technicians in this technical field, after knowing the contents recorded in the present invention, they can make several equivalent changes and substitutions without departing from the principle of the present invention. These equivalent changes and substitutions should also be regarded as belonging to the protection scope of the present invention.

Claims (10)

1. The utility model provides a school year knowledge graph generation system based on many teaching styles which characterized in that includes:

The feature evaluation unit is used for collecting and recording the physiological feature data of the students and the corresponding learning feature data of the students in the educational administration system, and constructing a priori knowledge base;

The teaching scheme generating unit takes a teaching style library, a knowledge graph of the last school year and information of a priori knowledge library as inputs and outputs a corresponding teaching scheme;

Course learning unit, based on the learning and examination of all knowledge points of the teaching scheme of finishing output, produce macroscopic evaluation and microscopic evaluation;

And the school year knowledge graph generating unit outputs a corresponding school year knowledge graph based on the macro evaluation and micro evaluation results and the corresponding teaching scheme.

2. The multi-teaching-style-based academic year knowledge graph generation system of claim 1, wherein: the construction of the priori knowledge base is specifically as follows:

The students log in the system and are matched with the educational administration system to acquire corresponding student learning characteristic data;

randomly extracting knowledge points to be learned, generating courses according to styles in a teaching style library, and obtaining student physiological characteristic data through the courses generated by learning.

3. The multi-teaching-style-based academic year knowledge graph generation system of claim 2, wherein: the student physiological characteristic data comprise brain electrical characteristics, electrocardio characteristics, body temperature characteristics, posture characteristics and facial expression characteristics; the corresponding student learning characteristics in the educational administration system comprise teacher evaluation, ordinary achievements and rolling achievements of the corresponding students.

4. The multi-teaching-style-based academic year knowledge graph generation system of claim 1, wherein: the teaching style library is constructed by the following steps: the large language model is adopted to collect the traditional teaching modes, and the courses with the interactive traditional teaching modes are divided into voice and text display types including teaching types and autonomous learning types by analyzing teaching characteristics, auxiliary tools and the presence or absence of the interactive traditional teaching modes.

5. The multi-teaching-style-based academic year knowledge graph generation system of claim 4, wherein: the phonetic and text display class comprises a teaching class and an autonomous learning class;

the voice video presentation class comprises a demonstration class, an experiment class, a performance class and a practice class;

the voice interaction presentation class comprises a question and answer class, a heuristic class, a discussion class and a cooperative learning class.

6. The multi-teaching-style-based academic year knowledge graph generation system of claim 4, wherein: the teaching mode classification standard is as follows:

；

wherein n is the number of participants in the lesson, , and n=1 indicates that only teachers participate and teachers and students have no interaction; when n=2, the teacher and the student participate together, and the teacher and the student interact;

m is the number of the teaching aids, , and when m=1, the teaching aids are written on the blackboard only; m=2, indicating that the lesson aid is blackboard writing and multimedia; m=3, the teaching aid means blackboard writing, multimedia and teaching aid.

7. The multi-teaching-style-based academic year knowledge graph generation system of claim 1, wherein: the macroscopic evaluation was: calculating average score of all students in multiple courses in the academic period, wherein the macro evaluation MA of the course i is expressed as:

；

wherein p is the number of students, g is the score of the students.

8. The multi-teaching-style-based academic year knowledge graph generation system of claim 1, wherein: the microscopic evaluation was: calculating all the achievements of a student in a plurality of courses in the academic year; where the microscopic evaluation MI of student k at each course can be expressed as: ;

Where j=1, 2,..n, n represents the j-th lesson, n represents the number of lessons; r is the score of student k at each course.

9. The multi-teaching-style-based academic year knowledge graph generation system of claim 1, wherein: in the school year knowledge graph generating unit, school years knowledge graphs are built by using courses as entities and learning sequences among the courses as relations, wherein the macro evaluation and the micro evaluation of students are course attributes, and the learning sequence relations comprise front-back relations, parallel relations and no relations.

10. The school year knowledge graph generation method based on the multiple teaching styles is characterized by comprising the following steps of:

s1, logging in a knowledge graph generation system of the school year, and judging whether the user is a new user or not;

if the user is a new user, entering a characteristic evaluation unit;

if the user is not a new user, entering a teaching scheme generating unit;

s2, acquiring a priori knowledge base of a user, entering a teaching scheme generating unit, taking a teaching style base, a last school year knowledge graph and priori knowledge base information as inputs, and outputting to obtain a corresponding teaching scheme;

s3, entering a course learning unit based on the output teaching scheme, completing learning of all knowledge points of the course, performing examination, and performing macroscopic evaluation and microscopic evaluation on the teaching scheme;

and S4, entering a knowledge graph generation unit of the school year, and generating the knowledge graph of the school year according to macro evaluation and micro evaluation results and course related attributes for generating a teaching scheme of the next school year.