Classroom teaching teacher'supply side 'influence assessment system based on data analysis

Abstract

The invention relates to the technical field of data analysis, and discloses a classroom teaching teacher'supply side 'influence evaluation system based on data analysis, which comprises a data acquisition module, a data analysis module, an evaluation module and a result output module. According to the classroom teaching teacher'supply side 'influence assessment system based on data analysis, various reactions of students in a classroom can be objectively and comprehensively captured through multi-dimensional data acquisition and advanced data analysis technologies, objective deviation of manual subjective evaluation is avoided through multi-dimensional and multi-module big data acquisition and analysis, and the assessment efficiency is improved. The classroom teaching influence (effect) evaluation of teachers is more accurate and objective, and the pertinence is strong. Age characteristics, classroom reaction differences and learning content characteristics of students in different classes and different subjects are fully considered, the weight of the evaluation model is dynamically adjusted according to actual classroom investigation and survey data, and it is ensured that the evaluation result better conforms to the real reflection of the actual teaching influence.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a "supply-side" influence evaluation system for classroom teachers based on data analysis. Background Art

[0002] In traditional classroom teaching evaluation, teachers' teaching effectiveness is often evaluated by manual observation, student questionnaires, etc. These methods have shortcomings such as strong subjectivity, limited data volume, and difficulty in quantification. With the advancement of educational informatization, the use of data collection and analysis technology to assist teaching evaluation has become a research hotspot. However, some existing related technical solutions focus on single-dimensional data collection, such as only paying attention to students' classroom performance or teachers' teaching behavior, lacking comprehensive analysis and in-depth mining of multi-dimensional data, and unable to comprehensively and objectively reflect the influence of teachers' classroom teaching. In addition, there is insufficient consideration of the differences in classroom responses of students in different stages and subjects, and a lack of pertinence in evaluation standards and methods, which limits the accuracy and practicality of the evaluation results. Summary of the Invention

[0003] In view of the shortcomings of the above-mentioned existing methods, such as strong subjectivity, limited data volume, and difficulty in quantification, with the advancement of educational informatization, the use of data collection and analysis technology to assist teaching evaluation has become a research hotspot, and some related technical solutions focus on single-dimensional data collection, such as only paying attention to students' classroom performance or teachers' teaching behavior, lacking comprehensive analysis and in-depth mining of multi-dimensional data, and unable to comprehensively and objectively reflect the influence of teachers' classroom teaching. Therefore, the present invention is proposed.

[0004] Therefore, the purpose of the present invention is to provide a "supply-side" influence evaluation system for classroom teaching teachers based on data analysis, which aims to: through multi-dimensional data collection and advanced data analysis technology, be able to objectively and comprehensively capture the various reactions of students in the classroom, avoid the subjective bias of manual evaluation, and make the evaluation of teachers' teaching effectiveness more accurate and reliable, fully consider the age characteristics, classroom reaction differences and learning content characteristics of students in different stages and subjects, dynamically adjust the weights of the evaluation model, ensure that the evaluation results are in line with the actual teaching situation, and provide teachers with more targeted teaching improvement guidance.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: a classroom teaching teacher "supply-side" influence evaluation system based on data analysis, comprising:

[0006] Data acquisition module: used to collect students' facial expressions, body language, and physiological indicators in class. Facial expression data is captured by smart cameras, body language data is monitored by motion sensors, and physiological indicator data is obtained through wearable devices.

[0007] Data analysis module: Uses artificial intelligence algorithms to analyze the collected representational data and identify characteristic information such as students' concentration, participation, and emotional response in class;

[0008] Evaluation module: Based on the characteristic information obtained by the data analysis module, the teacher's classroom teaching influence score is calculated according to a preset evaluation model. The evaluation model comprehensively considers multi-dimensional data such as facial expressions, body language, and physiological indicators. The weight of each dimension of data is dynamically adjusted according to the stage of study and subject to adapt to the characteristics of student reactions in different teaching situations.

[0009] Result output module: The impact scores and corresponding analysis reports obtained by the evaluation module are presented to teachers and school administrators in a visual manner, providing a basis for teaching improvement and decision-making.

[0010] As a preferred solution of the classroom teaching teacher "supply-side" influence evaluation system based on data analysis of the present invention, wherein: the data acquisition module includes a facial expression acquisition submodule, a body language acquisition submodule and a physiological index acquisition submodule;

[0011] Facial Expression Capture Submodule: This module captures students' facial expressions using multiple high-resolution smart cameras installed at the front of the classroom. The cameras are equipped with real-time capture capabilities and light compensation devices, and the collected image data is processed for privacy protection.

[0012] Body language collection submodule: This module uses motion sensors installed on desks, chairs, and students to monitor students' body movements, including raising their hands, lowering their heads, and lying on their desks. The collected data is then processed and transmitted through the data transmission and preprocessing unit.

[0013] Physiological indicator collection submodule: collects physiological indicator data such as heart rate, skin electricity, and body temperature through wearable devices such as smart bracelets and smart watches voluntarily worn by students, and transmits them to the data analysis module after being processed by the data encryption and transmission unit.

[0014] As a preferred solution of the classroom teaching teacher "supply-side" influence evaluation system based on data analysis of the present invention, wherein: the data analysis module includes a facial expression analysis submodule, a body language analysis submodule, a physiological index analysis submodule and a multi-dimensional data fusion submodule;

[0015] Facial expression analysis submodule: pre-processes the collected facial images, extracts features, and classifies emotions to identify students’ emotional states;

[0016] Body language analysis submodule: extracts motion features, recognizes behavioral patterns, and assesses engagement based on motion sensor data;

[0017] Physiological indicator analysis submodule: pre-processes physiological indicator data, maps emotional states, and assesses concentration;

[0018] Multi-dimensional data fusion submodule: aligns and synchronizes data of different dimensions such as facial expressions, body language, and physiological indicators on the time axis, uses feature-level fusion methods to form comprehensive feature vectors, and uses multimodal data analysis algorithms for comprehensive analysis.

[0019] As a preferred solution of the classroom teaching teacher "supply-side" influence evaluation system based on data analysis of the present invention, wherein: the evaluation module includes a weight setting submodule and a multi-dimensional comprehensive evaluation submodule;

[0020] Weighted evaluation submodule: The influence score is calculated using a weighted average method. For primary, middle, and high school students, the initial weights are set to 40% for facial expression data, 30% for body language data, and 30% for physiological indicator data.

[0021] Weight setting submodule: This module can further adjust weights based on the characteristics of different subjects. For science courses, the weight of physiological indicator data is increased by 5% and the weight of facial expression data is correspondingly reduced by 5% to more accurately reflect students' internal reactions during logical thinking and problem-solving. For liberal arts courses, the weight of body language data is increased by 5% and the weight of physiological indicator data is correspondingly reduced by 5% to better capture students' external expressions in discussions and expressions.

[0022] Multi-dimensional comprehensive evaluation sub-module: The weighted average method is used to calculate the influence score of teachers' classroom teaching. The specific formula is influence score = facial expression data score × facial expression weight + body language data score × body language weight + physiological indicator data score × physiological indicator weight.

[0023] As a preferred solution of the classroom teaching teacher "supply-side" influence evaluation system based on data analysis of the present invention, wherein: the result output module includes a score display submodule, a report generation submodule, a visualization display submodule and a data security and privacy protection submodule;

[0024] Score display submodule: provides teachers with a display of their personal influence scores, including different time dimensions such as class, week, and month, as well as class score comparison and subject score ranking;

[0025] Report generation submodule: Generates classroom performance analysis reports, teaching improvement suggestion reports and personalized teaching reports based on the evaluation results;

[0026] Visual display submodule: uses bar charts, line charts, radar charts and other chart formats to display evaluation results, designs an intuitive dashboard interface, and displays the school-wide teaching evaluation status in real time on a large-screen display system;

[0027] Data security and privacy protection sub-module: All data in the evaluation system are encrypted and stored, strict user access rights are set, and data usage compliance is regularly reviewed.

[0028] As a preferred solution of the "supply-side" influence evaluation system of classroom teaching teachers based on data analysis described in the present invention, the intelligent camera in the facial expression acquisition submodule has high resolution and real-time capture functions, which can accurately capture the micro-expression changes on the students' faces, and the installation position and angle of the camera are optimized to ensure coverage of all student seating areas in the classroom, while avoiding the influence of external factors such as light and occlusion on the capture effect.

[0029] As a preferred solution of the data analysis-based classroom teaching teacher "supply-side" influence evaluation system described in the present invention, the artificial intelligence algorithm in the data analysis module includes a deep learning algorithm and a sentiment analysis algorithm. The deep learning algorithm is used to automatically learn and extract features from a large amount of facial expression and body language image data, and the sentiment analysis algorithm is used to associate and map physiological indicator data with the student's emotional state, thereby realizing accurate identification and quantitative evaluation of the student's classroom status.

[0030] Compared with the prior art, the present invention has at least the following beneficial effects:

[0031] 1. This invention can objectively and comprehensively capture students' various reactions in class through multi-dimensional data collection and advanced data analysis technology. Through multi-dimensional and multi-module big data collection and analysis, it avoids the objective deviation of manual subjective evaluation, making the evaluation of teachers' classroom teaching influence (effect) more accurate, objective, and targeted. Taking into full consideration the age characteristics, classroom reaction differences, and learning content characteristics of students in different stages and subjects, the weight of the evaluation model is dynamically adjusted according to the actual classroom survey data to ensure that the evaluation results are more in line with the true reflection of the actual teaching influence, and provide teachers with more targeted teaching and research improvements and guidance for classroom teaching.

[0032] 2. The present invention can provide real-time feedback. The system can process and analyze data in real time, generate evaluation results in a timely manner and feed them back to teachers, so that teachers can adjust teaching strategies in a timely manner during the teaching process and improve the quality and efficiency of classroom teaching.

[0033] 3. This invention not only focuses on students' external performance, but also combines internal data such as physiological indicators to gain in-depth insights into students' learning status and emotional experience, providing strong support for teachers to fully understand teaching effectiveness and optimize teaching methods. At the same time, it provides school administrators with detailed data support and visual reports to help them better make decisions such as teacher teaching evaluation, curriculum optimization, and teaching resource allocation, thereby improving the overall education and teaching level of the school. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0035] Figure 1 This is a schematic diagram of the overall process of the classroom teaching teacher "supply-side" influence evaluation system based on data analysis of the present invention. DETAILED DESCRIPTION

[0036] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0037] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0038] Example

[0039] Reference Figure 1 , which is an embodiment of the present invention, provides a classroom teaching teacher "supply-side" influence evaluation system based on data analysis. This classroom teaching teacher "supply-side" influence evaluation system based on data analysis includes:

[0040] Data acquisition module: used to collect students' facial expressions, body language, and physiological indicators in class. Facial expression data is captured by smart cameras, body language data is monitored by motion sensors, and physiological indicator data is obtained through wearable devices.

[0041] Data analysis module: Uses artificial intelligence algorithms to analyze the collected representational data and identify characteristic information such as students' concentration, participation, and emotional response in class;

[0042] Evaluation module: Based on the characteristic information obtained by the data analysis module, the teacher's classroom teaching influence score is calculated according to a preset evaluation model. The evaluation model comprehensively considers multi-dimensional data such as facial expressions, body language, and physiological indicators. The weight of each dimension of data is dynamically adjusted according to the stage of study and subject to adapt to the characteristics of student reactions in different teaching situations.

[0043] Result output module: The impact scores and corresponding analysis reports obtained by the evaluation module are presented to teachers and school administrators in a visual manner, providing a basis for teaching improvement and decision-making.

[0044] The data acquisition module includes a facial expression acquisition submodule, a body language acquisition submodule and a physiological index acquisition submodule;

[0045] Facial Expression Capture Submodule: This module captures students' facial expressions using multiple high-resolution smart cameras installed at the front of the classroom. The cameras are equipped with real-time capture capabilities and light compensation devices, and the collected image data is processed for privacy protection.

[0046] Body language collection submodule: This module uses motion sensors installed on desks, chairs, and students to monitor students' body movements, including raising their hands, lowering their heads, and lying on their desks. The collected data is then processed and transmitted through the data transmission and preprocessing unit.

[0047] Physiological indicator collection submodule: collects physiological indicator data such as heart rate, skin electricity, and body temperature through wearable devices such as smart bracelets and smart watches voluntarily worn by students, and transmits them to the data analysis module after being processed by the data encryption and transmission unit.

[0048] The data analysis module includes a facial expression analysis submodule, a body language analysis submodule, a physiological index analysis submodule and a multi-dimensional data fusion submodule;

[0049] Facial expression analysis submodule: pre-processes the collected facial images, extracts features, and classifies emotions to identify students’ emotional states;

[0050] Body language analysis submodule: extracts motion features, recognizes behavioral patterns, and assesses engagement based on motion sensor data;

[0051] Physiological indicator analysis submodule: pre-processes physiological indicator data, maps emotional states, and assesses concentration;

[0052] Multi-dimensional data fusion submodule: aligns and synchronizes data of different dimensions such as facial expressions, body language, and physiological indicators on the time axis, uses feature-level fusion methods to form comprehensive feature vectors, and uses multimodal data analysis algorithms for comprehensive analysis.

[0053] The evaluation module includes a weight setting submodule and a multi-dimensional comprehensive evaluation submodule;

[0054] Weighted evaluation submodule: The influence score is calculated using a weighted average method. For primary, middle, and high school students, the initial weights are set to 40% for facial expression data, 30% for body language data, and 30% for physiological indicator data.

[0055] Weight setting submodule: This module can further adjust weights based on the characteristics of different subjects. For science courses, the weight of physiological indicator data is increased by 5% and the weight of facial expression data is correspondingly reduced by 5% to more accurately reflect students' internal reactions during logical thinking and problem-solving. For liberal arts courses, the weight of body language data is increased by 5% and the weight of physiological indicator data is correspondingly reduced by 5% to better capture students' external expressions in discussions and expressions.

[0056] Multi-dimensional comprehensive evaluation sub-module: The weighted average method is used to calculate the influence score of teachers' classroom teaching. The specific formula is influence score = facial expression data score × facial expression weight + body language data score × body language weight + physiological indicator data score × physiological indicator weight.

[0057] The result output module includes a score display submodule, a report generation submodule, a visualization display submodule and a data security and privacy protection submodule;

[0058] Score display submodule: provides teachers with a display of their personal influence scores, including different time dimensions such as class, week, and month, as well as class score comparison and subject score ranking;

[0059] Report generation submodule: Generates classroom performance analysis reports, teaching improvement suggestion reports and personalized teaching reports based on the evaluation results;

[0060] Visual display submodule: uses bar charts, line charts, radar charts and other chart formats to display evaluation results, designs an intuitive dashboard interface, and displays the school-wide teaching evaluation status in real time on a large-screen display system;

[0061] Data security and privacy protection sub-module: All data in the evaluation system are encrypted and stored, strict user access rights are set, and data usage compliance is regularly reviewed.

[0062] Due to differences in age and grade, students have different degrees of "response" to the stimulation of teachers' influence. That is to say, students of different stages and ages show different "stability and insufficiency". The lower the grade, the more "sensitive" they are to the stimulation, and on the contrary, they show more stability (calmness).

[0063] The evaluation criteria for different stages of study are shown in the following table:

[0064]

[0065] The intelligent camera in the facial expression acquisition submodule has high resolution and real-time capture capabilities, which can accurately capture the micro-expression changes on students' faces. The installation position and angle of the camera have been optimized to ensure coverage of all student seating areas in the classroom, while avoiding the influence of external factors such as light and occlusion on the capture effect.

[0066] The artificial intelligence algorithms in the data analysis module include deep learning algorithms and sentiment analysis algorithms. The deep learning algorithm is used to automatically learn and extract features from a large amount of facial expression and body language image data. The sentiment analysis algorithm is used to associate and map physiological indicator data with students' emotional states, thereby achieving accurate identification and quantitative evaluation of students' classroom status.

[0067] Hardware deployment: Data collection equipment such as smart cameras, motion sensors, and wearable devices are deployed in classrooms. Smart cameras are installed at the front of the classroom, covering all student seating areas, to capture students' facial expressions. Motion sensors are installed on desks and chairs or on students to monitor their body movements. Wearable devices such as smart bracelets are voluntarily worn by students to collect physiological indicators such as heart rate and skin conductivity.

[0068] Data collection and preprocessing: During classroom instruction, the data collection module collects students' facial expressions, body language, and physiological indicators in real time and transmits them to the data analysis module. The data analysis module first preprocesses the collected data, including data cleaning, denoising, and normalization, to improve data quality and usability.

[0069] Data analysis and feature extraction: Deep learning algorithms are used to analyze processed facial expression and body language image data, automatically identifying emotional features such as joy, confusion, and boredom in students' expressions, as well as behavioral features such as raising hands, lowering heads, and leaning over desks. Simultaneously, sentiment analysis algorithms are used to correlate physiological indicator data with students' emotional states. For example, an increased heart rate may indicate excitement or tension, while an increased galvanic skin response may reflect a student's level of concentration.

[0070] Teaching influence assessment: Based on the extracted feature information, the influence score of the teacher's classroom teaching is calculated according to a preset evaluation model. The evaluation model comprehensively considers multi-dimensional data such as facial expressions, body language, and physiological indicators. The weight of each dimension of data is dynamically adjusted according to the grade level and subject. For primary, middle and high school students, the initial weight is set to 40% for facial expression data, 30% for body language data, and 30% for physiological indicator data. The influence score calculated by weighted average method can objectively reflect the teacher's teaching effect in the class;

[0071] Result presentation and application: The impact scores and detailed analysis reports obtained from the evaluation are presented to teachers and school administrators in a visual manner through the result output module. Teachers can use the reports to understand their strengths and weaknesses in the teaching process, adjust teaching methods and strategies in a targeted manner, and improve teaching quality. School administrators can use these data to make decisions such as teacher teaching evaluation, curriculum optimization, and teaching resource allocation, thereby promoting the overall improvement of the school's education and teaching level.

[0072] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A classroom teaching teacher "supply side" influence evaluation system based on data analysis, characterized by: include: Data collection module: used to collect students' facial expressions, body language, physiological indicators and other representative data in class; Data analysis module: uses artificial intelligence algorithms to analyze the collected representation data; Evaluation module: Based on the characteristic information obtained by the data analysis module, the influence score of the teacher's classroom teaching is calculated according to the preset evaluation model; Result output module: presents the impact score obtained by the evaluation module and the corresponding analysis report in a visual manner.

2. The data analysis-based classroom teacher "supply-side" influence evaluation system according to claim 1 is characterized by: The data acquisition module includes a facial expression acquisition submodule, a body language acquisition submodule and a physiological index acquisition submodule; Facial expression acquisition submodule: This module captures students' facial expressions using multiple high-resolution smart cameras installed at the front of the classroom. The cameras have real-time capture capabilities and light compensation devices. Body language acquisition submodule: uses motion sensors installed on desks, chairs and students to monitor students' body movements; Physiological indicator collection submodule: collects physiological indicator data such as heart rate, skin electricity, and body temperature through wearable devices such as smart bracelets and smart watches voluntarily worn by students, and transmits them to the data analysis module after being processed by the data encryption and transmission unit.

3. The data analysis-based classroom teaching teacher "supply-side" influence evaluation system according to claim 2 is characterized by: The data analysis module includes a facial expression analysis submodule, a body language analysis submodule, a physiological index analysis submodule and a multi-dimensional data fusion submodule; Facial expression analysis submodule: pre-processes the collected facial images, extracts features, and classifies emotions to identify students’ emotional states; Body language analysis submodule: extracts motion features, recognizes behavioral patterns, and assesses engagement based on motion sensor data; Physiological indicator analysis submodule: pre-processes physiological indicator data, maps emotional states, and assesses concentration; Multi-dimensional data fusion sub-module: aligns and synchronizes data of different dimensions such as facial expressions, body language, and physiological indicators on the timeline.

4. The data analysis-based classroom teaching teacher "supply-side" influence evaluation system according to claim 3 is characterized by: The evaluation module includes a weight setting submodule and a multi-dimensional comprehensive evaluation submodule; Weighted evaluation submodule: The influence score is calculated using a weighted average method. For primary, middle, and high school students, the initial weights are set to 40% for facial expression data, 30% for body language data, and 30% for physiological indicator data. Weight setting submodule: This module can further adjust weights based on the characteristics of different subjects. For science courses, the weight of physiological indicator data is increased by 5% and the weight of facial expression data is correspondingly reduced by 5% to more accurately reflect students' internal reactions during logical thinking and problem-solving. For liberal arts courses, the weight of body language data is increased by 5% and the weight of physiological indicator data is correspondingly reduced by 5% to better capture students' external expressions in discussions and expressions. Multi-dimensional comprehensive evaluation sub-module: The weighted average method is used to calculate the influence score of teachers' classroom teaching. The specific formula is influence score = facial expression data score × facial expression weight + body language data score × body language weight + physiological indicator data score × physiological indicator weight.

5. The data analysis-based classroom teaching teacher "supply-side" influence evaluation system according to claim 4 is characterized by: The result output module includes a score display submodule, a report generation submodule, a visualization display submodule and a data security and privacy protection submodule; Score display submodule: provides teachers with a display of their personal influence scores, including different time dimensions such as class, week, and month, as well as class score comparison and subject score ranking; Report generation submodule: Generates classroom performance analysis reports, teaching improvement suggestion reports and personalized teaching reports based on the evaluation results; Visual display submodule: uses bar charts, line charts, radar charts and other chart formats to display evaluation results, designs an intuitive dashboard interface, and displays the school-wide teaching evaluation status in real time on a large-screen display system; Data security and privacy protection sub-module: All data in the evaluation system are encrypted and stored, strict user access rights are set, and data usage compliance is regularly reviewed.

6. The data analysis-based classroom teaching teacher "supply-side" influence evaluation system according to claim 5 is characterized by: The smart camera in the facial expression acquisition submodule has high resolution and real-time capture capabilities, and can accurately capture micro-expression changes on students' faces.

7. The data analysis-based classroom teaching teacher "supply-side" influence evaluation system according to claim 6 is characterized by: The artificial intelligence algorithms in the data analysis module include deep learning algorithms and sentiment analysis algorithms.

Images