CN115660129A - Method and system for feeding back classroom efficiency based on electronic whiteboard and face recognition - Google Patents
Method and system for feeding back classroom efficiency based on electronic whiteboard and face recognition Download PDFInfo
- Publication number
- CN115660129A CN115660129A CN202210790578.6A CN202210790578A CN115660129A CN 115660129 A CN115660129 A CN 115660129A CN 202210790578 A CN202210790578 A CN 202210790578A CN 115660129 A CN115660129 A CN 115660129A
- Authority
- CN
- China
- Prior art keywords
- data
- classroom
- students
- conversion rate
- emotion
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of intelligent teaching. The problem that the learning effect of students is influenced due to insufficient control of teachers with insufficient experience on classroom efficiency is solved. The invention provides a method and a system for feeding back classroom efficiency based on an electronic whiteboard and face recognition, which have the core ideas that: collecting a large number of different student numbers, school classes, male and female proportions of students and classroom facial expressions and post-classroom test data of areas to which the students belong, carrying out model training, establishing a knowledge conversion rate prediction model, collecting facial expression data of the students in the current classroom by using an electronic whiteboard, converting the facial expression data into emotion data, predicting the knowledge conversion rate of the current classroom by using the established knowledge conversion rate prediction model, and calculating the efficiency of the current classroom by combining different weights occupied by facial emotions and the like. The method and the system for feeding back the classroom efficiency based on the electronic whiteboard and the face recognition are mainly used in a classroom for teaching by using the electronic whiteboard.
Description
Technical Field
The invention relates to the field of intelligent teaching, in particular to a method and a system for feeding back classroom efficiency based on an electronic whiteboard and face recognition.
Background
With the wide application of the electronic whiteboard technology in teaching, the face recognition, the data modeling and the increasing maturity of the data analysis technology, the classroom teaching data are analyzed by using scientific and technological means, and the prediction of the knowledge conversion rate and the classroom efficiency calculation become a feasible auxiliary teaching solution.
Disclosure of Invention
The technical problems to be solved by the invention are as follows:
the method and the system for feeding back classroom efficiency based on the electronic whiteboard and the face recognition are provided, and the problem that the learning effect of students is influenced due to insufficient control of teachers with insufficient experience on classroom efficiency is solved.
The invention adopts the technical scheme for solving the technical problems that:
in one aspect, the invention provides a method for feeding back classroom efficiency based on an electronic whiteboard and face recognition, which comprises the following steps:
establishing a knowledge conversion rate prediction model: establishing different knowledge conversion rate prediction models according to different collected student face information and post-class test data of the number of students, the school time, the male and female proportions of the students and the areas to which the students belong;
collecting face information of the current classroom: the electronic whiteboard records the face information of the students in the current classroom according to a certain time interval, and performs data integration on the face information;
the face information is arranged into face expression data, emotion change data of each student are analyzed, and emotion change data of the whole classroom are obtained;
selecting a knowledge conversion rate prediction model corresponding to the current classroom to predict emotion transformation data to obtain a knowledge conversion rate prediction result;
and (4) calculating the classroom efficiency according to different weights occupied by the knowledge conversion rate and the emotion change data of the students and the current classroom student number and the learning section and male and female proportion.
Further, the result obtained by data integration of the face information, the emotion change data of each student and the whole classroom, the knowledge conversion rate prediction result and the classroom efficiency are all generated into visual data in a data report form.
Further, the step of establishing the knowledge conversion rate prediction model is as follows:
step 1: acquiring a large amount of face data and post-class test data according to the number of students, school class, male and female proportion of the students and different areas of the students, and generating a data set;
step 2: screening and preprocessing the data set;
and step 3: making a face data part in the data set into a face data subset, obtaining corresponding face emotion attributes according to different feature analysis strategies, and sorting the obtained emotion attributes into a specific emotion data set;
and 4, step 4: processing emotion data and post-lesson test data under different lesson durations, lesson types and teacher types to construct a data set;
and 5: constructing a characteristic project, extracting various characteristic data in a data set according to a specific rule, and performing model training;
step 6: and testing and optimizing the model.
On the other hand, the invention also provides a system for feeding back classroom efficiency based on an electronic whiteboard and face recognition, which comprises:
a knowledge conversion rate prediction model generation module: and establishing different knowledge conversion rate prediction models according to the number of students, the school time, the male and female proportions of the students and different collected face information and post-class test data of the areas to which the students belong.
A data acquisition module: the system is used for collecting face information of students in the current classroom, teacher names, teacher ages, student numbers, course names, course types and course duration;
an emotion data generation module: and calling the face recognition api provided by the online AI platform by using the collected data to obtain face expression data, extracting and analyzing the characteristics of the data, and finally obtaining emotion transformation data of each student expression and comprehensive emotion change data of the whole classroom.
Knowledge conversion rate prediction module: after the emotion data is input, other information acquired in data acquisition is integrated, and a knowledge conversion rate prediction model obtained through training is used for prediction to obtain a knowledge conversion rate prediction result;
classroom efficiency calculation module: calculating the classroom efficiency according to different weights occupied by the knowledge conversion rate result and the emotion change data of students in combination with the number of students in the current classroom, the school section and the male and female proportion;
a report generation module: and making data reports of the data acquired by the data acquisition module, the emotion data generated by the emotion data generation module, the knowledge conversion rate prediction result obtained by the knowledge conversion rate prediction module and the classroom efficiency calculated by the classroom efficiency calculation module.
The invention has the beneficial effects that:
according to the method and the system for feeding back the classroom efficiency based on the electronic whiteboard and the face recognition, a knowledge conversion rate prediction model is established, the knowledge conversion rate is obtained through analysis of classroom expressions of students, the classroom efficiency is calculated by combining specific conditions, and teachers can effectively help young teachers to improve classroom teaching ability through checking recorded data, and can observe the relation between changes of learning emotion and learning achievement of different students to obtain a more suitable teaching method.
Drawings
Fig. 1 is a flowchart of a method for feeding back classroom efficiency based on an electronic whiteboard and face recognition according to the present invention.
Detailed description of the invention
The system for feeding back the classroom efficiency based on the electronic whiteboard and the face recognition comprises a data acquisition module, an emotion data generation module, a knowledge conversion rate prediction module, a classroom efficiency calculation module, a report generation module and a knowledge conversion rate prediction model generation module, wherein as shown in figure 1, all the modules are matched with each other to complete the feedback of the classroom efficiency.
Firstly, establishing a knowledge conversion rate prediction model: establishing different knowledge conversion rate prediction models according to different collected student face information and post-class test data of the number of students, the school time, the male and female proportions of the students and the areas to which the students belong;
step 1: acquiring a large amount of face data and post-class test data in a classroom according to the difference of the number of students, school class, male and female proportion of the students and the areas where the students are located; the number of students in middle class, the age of the students, the class of the student, the male and female proportion of the students and the area of the student all affect the classroom knowledge conversion rate of the students in the actual teaching, so that the knowledge conversion prediction model is established respectively aiming at different numbers of students, classes of students, male and female proportions of the students and the area of the students. Meanwhile, in order to ensure the accuracy of the knowledge conversion rate prediction model, the data sample is ensured to be large enough when face data and after-class test results are collected.
Step 2: screening and preprocessing a data set; and screening out some data which obviously deviate from normal values, such as 0 score in a post-class test and corresponding student expression information, and preprocessing the data.
And step 3: and making the facial expression data part in the data set into a facial data set, obtaining facial emotion attributes according to different characteristic analysis strategies, and sorting the obtained facial emotion attributes into a specific emotion data set.
And 4, step 4: and processing the emotion data set and the post-lesson test data under the conditions of different lesson durations, lesson types and teacher types to construct a data set.
And 5: and (4) constructing a characteristic project, extracting various characteristic data in the data set according to a specific rule, and performing model training.
Step 6: and testing and optimizing the model.
After a knowledge conversion rate model is established, facial expression data of the current classroom are collected, a knowledge conversion model matched with the number of students, the school time, the male and female proportions of the students and the region where the students are located in the current classroom is selected to predict the knowledge conversion rate of the current classroom, and the specific mode is as follows:
the electronic whiteboard is opened in class, after the class feedback system is opened, the system defaults to silent background operation, the data acquisition module records face information of students in a certain time interval (the time interval is a fixed value which is most beneficial to prediction and is obtained through a large number of experiments), other information of the current class is collected, such as teacher names, teacher ages, student numbers, course names, course types, course duration and the like, the collected data is automatically summarized and sorted, and a corresponding report is generated through the data report module.
After classroom data is collected, summarized and sorted, the data is automatically input into an emotion data generation module, the module calls a face recognition api provided by an online AI platform by using the collected data to obtain face expression data, the data is subjected to feature extraction and analysis, emotion transformation data of each student expression is finally obtained, emotion change data of each student is analyzed to obtain emotion change data of the whole classroom, the two data are subjected to data processing and then input into a knowledge conversion rate prediction module, and meanwhile, the emotion change data of each student and the emotion change data of the whole classroom are input into a data report module and are sorted and output in a data report form.
After emotion data are input, the knowledge conversion rate prediction module integrates other information acquired in data acquisition, prediction is carried out by using a knowledge conversion rate prediction model obtained through training, after a prediction result is obtained, the prediction result is generated into corresponding data to wait for input into a classroom efficiency calculation module, and meanwhile, the data are automatically sorted and added into a report module.
The classroom efficiency calculation module can start working after the input of the knowledge conversion rate prediction data, the classroom efficiency is calculated according to different weights of the knowledge conversion rate and the emotion change data of students in the current classroom in combination with the number of students in the current classroom, the learning period and the male-female ratio, and finally the data is automatically sorted and input into the report module.
The report module can be checked after the system finishes working every time, the problem of inaccurate data may occur during checking in the working process, the report data comprises all key process data, the emotion change data of students and the like can be used for analyzing the individual class efficiency of the students, the result data of prediction and calculation can be used for a teacher to review the class and refer to review learning, and can also be used as a standard for teacher assessment, the visual data generated by the report module can be shared by other teachers or parents through the Internet, and the understanding degree of the teachers and the parents on the class efficiency of the students is improved.
Claims (4)
1. A method for feeding back classroom efficiency based on an electronic whiteboard and face recognition is characterized by comprising the following steps:
establishing a knowledge conversion rate prediction model: establishing different knowledge conversion rate prediction models according to different collected student face information and post-class test data of the number of students, the school time, the male and female proportions of the students and the areas to which the students belong;
collecting face information of the current classroom: the electronic whiteboard records the face information of the students in the current classroom according to a certain time interval, and performs data integration on the face information;
the face information is arranged into face expression data, emotion change data of each student are analyzed, and emotion change data of the whole classroom are obtained;
selecting a knowledge conversion rate prediction model corresponding to the current classroom to predict emotion transformation data to obtain a knowledge conversion rate prediction result;
and (4) calculating the classroom efficiency according to different weights occupied by the knowledge conversion rate and the emotion change data of the students and the current classroom student number and the learning section and male and female proportion.
2. The method according to claim 1, wherein the result of data integration of the face information, the emotion change data of each student and the whole classroom, the prediction result of knowledge conversion rate, and the classroom efficiency are all generated into visualized data in the form of data report.
3. The method for feeding back classroom efficiency based on electronic whiteboard and face recognition as claimed in claim 1, wherein the step of establishing the knowledge conversion rate prediction model is:
step 1: acquiring a large amount of face data and post-class test data according to the number of students, school time, male and female proportions of the students and different areas to which the students belong to generate a data set;
step 2: screening and preprocessing the data set;
and step 3: making a face data part in the data set into a face data subset, obtaining corresponding face emotion attributes according to different feature analysis strategies, and sorting the obtained emotion attributes into a specific emotion data set;
and 4, step 4: processing emotion data and post-lesson test data under different lesson durations, lesson types and teacher types to construct a data set;
and 5: constructing a characteristic project, extracting various characteristic data in a data set according to a specific rule, and performing model training;
step 6: and testing and optimizing the model.
4. A system for feeding back classroom efficiency based on electronic whiteboard and face recognition is characterized by comprising:
a knowledge conversion rate prediction model generation module: establishing different knowledge conversion rate prediction models according to different collected student face information and post-class test data of the number of students, the school time, the male and female proportions of the students and the areas to which the students belong;
a data acquisition module: the system is used for collecting face information of students in the current classroom, teacher names, teacher ages, student numbers, course names, course types and course duration;
an emotion data generation module: calling a face recognition api provided by an online AI platform by using the collected data to obtain facial expression data, and performing feature extraction and analysis on the facial expression data to finally obtain emotion transformation data of each student expression and comprehensive facial data of the whole classroom;
knowledge conversion rate prediction module: after the emotion data is input, other information acquired in data acquisition is integrated, and a data model obtained through training is used for prediction to obtain a knowledge conversion rate prediction result;
classroom efficiency calculation module: calculating the classroom efficiency according to different weights occupied by the knowledge conversion rate and the emotion change data of students and the ratio of the study period to male and female according to the current classroom student number;
a report generation module: and making data reports of the data acquired by the data acquisition module, the emotion data generated by the emotion data generation module, the knowledge conversion rate prediction result obtained by the knowledge conversion rate prediction module and the classroom efficiency calculated by the classroom efficiency calculation module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210790578.6A CN115660129A (en) | 2022-07-05 | 2022-07-05 | Method and system for feeding back classroom efficiency based on electronic whiteboard and face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210790578.6A CN115660129A (en) | 2022-07-05 | 2022-07-05 | Method and system for feeding back classroom efficiency based on electronic whiteboard and face recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115660129A true CN115660129A (en) | 2023-01-31 |
Family
ID=85024294
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210790578.6A Pending CN115660129A (en) | 2022-07-05 | 2022-07-05 | Method and system for feeding back classroom efficiency based on electronic whiteboard and face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115660129A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117391900A (en) * | 2023-11-23 | 2024-01-12 | 重庆第二师范学院 | Learning efficiency detection system and method based on big data analysis |
-
2022
- 2022-07-05 CN CN202210790578.6A patent/CN115660129A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117391900A (en) * | 2023-11-23 | 2024-01-12 | 重庆第二师范学院 | Learning efficiency detection system and method based on big data analysis |
| CN117391900B (en) * | 2023-11-23 | 2024-05-24 | 重庆第二师范学院 | Learning efficiency detection system and method based on big data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109272789A (en) | Learning effect assessment system and appraisal procedure based on data analysis | |
| Falakmasir et al. | Using Educational Data Mining Methods to Study the Impact of Virtual Classroom in E-Learning. | |
| CN109214664B (en) | Emotional behavior comprehensive analysis system based on artificial intelligence | |
| CN112069970B (en) | Classroom teaching event analysis method and device | |
| CN107483397A (en) | A kind of examinee's self-test assessment method based on B/S framework | |
| CN111915458A (en) | On-line experiment teaching system for exploration type and personalized learning | |
| CN112527821A (en) | Student bloom mastery degree evaluation method, system and storage medium | |
| CN115760510B (en) | Teaching method and system based on VR virtual reality | |
| Bussaman et al. | Prediction models of learning strategies and learning achievement for lifelong learning | |
| CN106875770A (en) | A kind of juvenile student innovation ability tests evaluation device | |
| CN115660129A (en) | Method and system for feeding back classroom efficiency based on electronic whiteboard and face recognition | |
| CN1632782A (en) | On-line achievement assessment method and system | |
| CN115062950A (en) | Training management system based on digital intelligent learning | |
| CN116681556A (en) | Intelligent remote teaching cloud platform system and method based on education big data | |
| CN116011856A (en) | Online course quality evaluation system and method based on emotion analysis | |
| CN115205072A (en) | Cognitive diagnosis method for long-period evaluation | |
| Hrich et al. | ARTIFICIAL INTELLIGENCE FOR EDUCATIONAL ASSESSMENT | |
| Ogunkunle et al. | A data mining based optimization of selecting learning material in an intelligent tutoring system for advancing STEM education | |
| CN117556381B (en) | Knowledge level depth mining method and system for cross-disciplinary subjective test questions | |
| CN117094863B (en) | Intelligent learning behavior analysis system based on intelligent learning | |
| Hu et al. | A cognitive diagnostic framework for computer science education based on probability graph model | |
| CN117932044B (en) | Automatic dialogue generation method and system for psychological counseling assistant based on AI | |
| Bai et al. | An In-class Teaching Comprehensive Evaluation Model Based on Statistical Modelling and Ensemble Learning | |
| Bihui | Design and implementation of mathematical MOOC based on BP Neural Network Algorithm | |
| BENABDELLAH et al. | Moroccan Case Study: Comparison and Analysis of Two Prediction Techniques Applied to Grades |
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 |