Young teacher competition and review system

Abstract

The invention discloses a young teacher competition and review system, and relates to the technical field of teacher review, a teaching log analysis module is used for receiving teaching log files, scoring teaching log analysis results, outputting teaching log scoring data, collecting classroom state images of students, and outputting the classroom state images of the students; the teaching log scoring data and the student expression analysis result correspond to each other according to the first timestamp and the second timestamp, a comprehensive review set is output, the comprehensive review set is analyzed, and a comprehensive analysis result is output. The system achieves objective and accurate evaluation of the teaching effect, combines subjective data captured by a student expression analysis module, comprehensively reflects the teaching effect and classroom atmosphere of a teacher, avoids the unfairness of the overall scoring of traditional students through a personalized evaluation mode, improves the scientificity and fairness of the evaluation of the teacher, and improves the teaching efficiency. And guidance is provided for professional development of teachers.

Description

Technical Field

[0001] The present invention relates to the technical field of teacher evaluation, and in particular to a young teacher competition and evaluation system. Background Art

[0002] With the continuous advancement of educational technology and the advent of the big data era, educational evaluation methods are shifting from traditional qualitative evaluation to quantitative evaluation. Against this background, the young teacher competition and review system came into being, aiming to objectively and comprehensively evaluate teachers' teaching effectiveness through scientific and technological means.

[0003] At present, a Chinese invention patent with application number CN202311501244.3 discloses a comprehensive evaluation method for the teaching quality of college teachers, and its steps include: constructing a college classroom teaching quality index system, and obtaining the data of the college classroom teaching quality index system through machine vision; standardizing the data of the college classroom teaching quality index system, and obtaining the distance between two evidences based on the standardized data; using the Shapley value method to calculate the distance contribution value of each piece of evidence to the evidence fusion combination; forward processing the indicator by using the standard deviation form, and obtaining the indicator weight in combination with the contribution value; obtaining the comprehensive probability of each indicator and sorting them, and verifying the sorting results through trust function and likelihood function, so as to obtain the comprehensive evaluation results of classroom teaching quality.

[0004] The above technology makes it difficult to quantify objective data such as teachers' teaching logs and combine them with subjective data of students' classroom status for comprehensive scoring, and it is difficult to avoid the unfairness caused by general overall student scores. Summary of the invention

[0005] The technical problem solved by the present invention is that it is difficult for the above technology to quantify objective data such as teachers' teaching logs and to make comprehensive scores based on subjective data of students' classroom status, and it is difficult to avoid unfairness caused by general overall student scores.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] A young teacher competition and review system, including a teaching log analysis module, a student expression analysis module and a comprehensive scoring report module;

[0008] The teaching log analysis module is used to receive a teaching log file, the teaching log file contains a corresponding first timestamp, use natural language processing technology to analyze the teaching log file, output the teaching log analysis result, formulate a teaching log scoring rule, score the teaching log analysis result according to the teaching log scoring result, and output teaching log scoring data, the teaching log scoring data contains the corresponding first timestamp;

[0009] The student expression analysis module is used to collect a student classroom status image, the student classroom status image includes a corresponding second timestamp, use a convolutional neural network to recognize the student classroom status image, output a student expression analysis result, the student expression analysis result includes a corresponding second timestamp, correspond the teaching log scoring data and the student expression analysis result according to the first timestamp and the second timestamp, and output a comprehensive review set;

[0010] The comprehensive scoring report module is used to analyze the comprehensive review set, output the comprehensive analysis results, and combine the comprehensive analysis results, teaching log scoring data and student expression analysis results into a comprehensive scoring report.

[0011] Preferably, the teaching log analysis module includes a log receiving unit, a language processing unit, a rule formulation unit and a teaching scoring unit;

[0012] The log receiving unit is used to receive a teaching log file, the teaching log file includes a corresponding timestamp, and stores the teaching log file in a database.

[0013] Preferably, the language processing unit is used to analyze the teaching log file using natural language processing technology, and the analysis logic is:

[0014] The teaching log files are cleaned, including removing stop words and punctuation marks, performing statistical segmentation on the cleaned teaching log files, extracting key information from the segmented teaching log files, and outputting the extracted key information as teaching log analysis results, wherein the key information includes data on the proportion of completed course chapters, data on the number of completed assignments, data on the extent of improvement in student performance, data on the utilization rate of teaching equipment, and data on the consumption of teaching materials.

[0015] Preferably, the rule-making unit is used to make a teaching log scoring rule, and the teaching log scoring rule is:

[0016] The data on the proportion of completed course chapters, the number of completed assignments, the data on the extent of student achievement improvement, the data on the utilization rate of teaching equipment, and the data on the consumption of teaching materials are weighted as follows:

[0017] Data weight of student achievement improvement: 0.4;

[0018] Data weight of the number of completed jobs: 0.2;

[0019] Teaching equipment utilization data weight: 0.2;

[0020] Data weight of the proportion of completed course chapters: 0.1;

[0021] Teaching material consumption data weight: 0.1;

[0022] Substitute the data on the proportion of completed course chapters, the number of completed assignments, the extent of student performance improvement, the utilization rate of teaching equipment, and the consumption of teaching materials into the teaching log scoring rules to calculate the weighted total data.

[0023] Preferably, the teaching scoring unit is used to input the teaching log analysis results into the teaching log scoring rules, calculate the weighted sum data, and output it as teaching log scoring data, wherein the teaching log scoring data includes the corresponding first timestamp.

[0024] Preferably, the student expression analysis module includes an image acquisition unit, an expression recognition unit and a data matching unit;

[0025] The image acquisition unit is used to acquire a student classroom status image, wherein the student classroom status image includes a corresponding second timestamp, and the student classroom status image is stored in a database.

[0026] Preferably, the expression recognition unit is used to load a pre-trained convolutional neural network model, input the student's classroom status image into the convolutional neural network model, identify expression categories, the expression categories include happy, focused, tired and satisfied, obtain the corresponding number of expression categories, and output them as happy expression quantity data, focused expression quantity data, tired expression quantity data and satisfied expression quantity data, and merge the happy expression quantity data, focused expression quantity data, tired expression quantity data and satisfied expression quantity data and output them as a student expression analysis result, which includes a corresponding second timestamp.

[0027] Preferably, the data matching unit is used to match the teaching log scoring data and the student expression analysis results according to the first timestamp and the second timestamp, and output a comprehensive review set, which is the teaching log scoring data and the corresponding student expression analysis results.

[0028] Preferably, the comprehensive score reporting module includes a data analysis unit and a report generation unit;

[0029] The data analysis unit is used to analyze the comprehensive review set:

[0030] The weight distribution is performed on the happy expression quantity data, the focused expression quantity data, the tired expression quantity data and the satisfied expression quantity data, and the weight distribution is:

[0031] Data weight of the number of happy expressions: 0.2;

[0032] Focus on the number of expressions data weight: 0.4;

[0033] Tiredness expression quantity data weight: 0.1;

[0034] Data weight of number of satisfied expressions: 0.3;

[0035] Calculate the weighted sum of the number of happy expressions, the number of focused expressions, the number of tired expressions, and the number of satisfied expressions, and output it as student response data;

[0036] Calculate the sum of the student response data and the teaching log score data, and output it as the first teacher score data;

[0037] If the number of tired expressions is greater than the number of focused expressions, the first teacher's rating data is reduced by 5 and output as the second teacher's rating data;

[0038] If the number of focused expressions is greater than the sum of the number of happy expressions, the number of tired expressions, and the number of satisfied expressions, then add 5 to the first teacher's rating data and output it as the second teacher's rating data;

[0039] If the number of tired expression data is greater than the number of focused expression data and the number of focused expression data is greater than the sum of the number of happy expression data, the number of tired expression data and the number of satisfied expression data, the first teacher rating data is directly output as the second teacher rating data;

[0040] Analysis of the second teacher's rating data:

[0041] If the second teacher's rating data is greater than the teacher rating threshold, the teacher is judged as an excellent teacher;

[0042] If the second teacher's rating data is within the teacher rating threshold, the teacher is judged as an average teacher;

[0043] If the second teacher's rating data is less than the teacher rating threshold, the teacher is determined to be a teacher to be improved;

[0044] Excellent teachers, average teachers and teachers to be improved are combined and output as comprehensive analysis results.

[0045] Preferably, the report generating unit is used to combine the comprehensive analysis results, teaching log scoring data and student expression analysis results into a comprehensive scoring report.

[0046] Beneficial effects of the present invention: The present invention formulates scoring rules by quantifying the teacher's teaching log data, thereby achieving an objective and accurate evaluation of the teaching effect. At the same time, combined with the subjective data captured by the student expression analysis module, it comprehensively reflects the teacher's teaching effect and classroom atmosphere. The personalized evaluation method avoids the unfairness of the traditional student overall scoring, improves the scientificity and fairness of the teacher evaluation, and provides guidance for the professional development of teachers. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A basic flow chart of a young teacher competition and review system provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0049] Example, see Figure 1 , provides a young teacher competition and review system, including a teaching log analysis module, a student expression analysis module and a comprehensive scoring report module.

[0050] The teaching log analysis module is used to receive a teaching log file, which contains a corresponding first timestamp, analyze the teaching log file using natural language processing technology, output the teaching log analysis results, formulate teaching log scoring rules, score the teaching log analysis results according to the teaching log scoring results, and output teaching log scoring data, which contains the corresponding first timestamp.

[0051] The student expression analysis module is used to collect student classroom status images, which include a corresponding second timestamp. A convolutional neural network is used to identify the student classroom status images, and student expression analysis results are output. The student expression analysis results include a corresponding second timestamp. The teaching log scoring data and the student expression analysis results are matched according to the first timestamp and the second timestamp, and a comprehensive review set is output.

[0052] The comprehensive scoring report module is used to analyze the comprehensive review set, output the comprehensive analysis results, and combine the comprehensive analysis results, teaching log scoring data and student expression analysis results into a comprehensive scoring report.

[0053] The teaching log analysis module includes a log receiving unit, a language processing unit, a rule-making unit and a teaching scoring unit.

[0054] The log receiving unit is used to receive the teaching log file, which contains a corresponding time stamp, and store the teaching log file in a database.

[0055] The log receiving unit is the entrance to the teaching log analysis module. It is responsible for receiving the teaching log files submitted by teachers and storing them in the database. The effect of the log receiving unit is mainly reflected in two aspects: one is to ensure the integrity and accuracy of the teaching log files to avoid loss or damage during transmission; the other is to provide a reliable data basis for subsequent log analysis.

[0056] The language processing unit is used to analyze the teaching log file using natural language processing technology, and the analysis logic is:

[0057] The teaching log files are cleaned, including removing stop words and punctuation marks, performing statistical segmentation on the cleaned teaching log files, extracting key information from the segmented teaching log files, and outputting the extracted key information as teaching log analysis results, wherein the key information includes data on the proportion of completed course chapters, data on the number of completed assignments, data on the extent of improvement in student performance, data on the utilization rate of teaching equipment, and data on the consumption of teaching materials.

[0058] The language processing unit uses natural language processing technology to conduct in-depth analysis of teaching log files. First, the teaching log files are cleaned to remove stop words and punctuation marks, and then word segmentation and key information extraction are performed. The language processing unit can accurately identify and extract key information in the teaching logs, providing strong data support for subsequent teaching scoring.

[0059] The rule formulation unit is used to formulate teaching log scoring rules, and the teaching log scoring rules are:

[0060] The data on the proportion of completed course chapters, the number of completed assignments, the data on the extent of student achievement improvement, the data on the utilization rate of teaching equipment, and the data on the consumption of teaching materials are weighted as follows:

[0061] Data weight of student performance improvement: 0.4.

[0062] Data weight of number of completed jobs: 0.2.

[0063] Teaching equipment utilization data weight: 0.2.

[0064] Data weight of proportion of completed course chapters: 0.1.

[0065] Teaching material consumption data weight: 0.1.

[0066] Substitute the data on the proportion of completed course chapters, the number of completed assignments, the extent of student performance improvement, the utilization rate of teaching equipment, and the consumption of teaching materials into the teaching log scoring rules to calculate the weighted total data.

[0067] The rule-making unit is responsible for formulating the teaching log scoring rules, that is, determining the weight distribution of each key information. The rule-making unit can set the weights scientifically and reasonably to ensure that the teaching scores can comprehensively and objectively reflect the teaching effectiveness of teachers. By comprehensively considering the importance of different key information, the rule-making unit provides a reliable basis for teaching scores.

[0068] The teaching scoring unit is used to input the teaching log analysis results into the teaching log scoring rules, calculate the weighted sum data, and output the teaching log scoring data, which includes the corresponding first timestamp.

[0069] The teaching scoring unit is the core part of the teaching log analysis module. It calculates the teaching log scoring data based on the key information extracted by the language processing unit and the weight distribution set by the rule-making unit. The teaching scoring unit can accurately and quickly generate teaching log scoring data, providing strong support for the evaluation of teachers' teaching effectiveness. At the same time, the timestamp information contained in the teaching scoring data can also facilitate subsequent data analysis and research.

[0070] The teaching log analysis module conducts in-depth analysis of the teaching log files submitted by teachers in a systematic and automated manner, and generates teaching log scoring data based on the analysis results. This not only improves the efficiency of teaching evaluation, but also ensures the objectivity and accuracy of the evaluation. By comprehensively considering multiple key information in the teaching log, it can fully reflect the teaching effectiveness and efforts of teachers.

[0071] The student expression analysis module includes an image acquisition unit, an expression recognition unit and a data matching unit.

[0072] The image acquisition unit is used to acquire a student classroom status image, wherein the student classroom status image includes a corresponding second timestamp, and the student classroom status image is stored in a database.

[0073] As the starting point of the student expression analysis module, the image acquisition unit is responsible for capturing and recording images of students' classroom status. The effect of the image acquisition unit is mainly reflected in two aspects: one is to ensure the clarity and integrity of the image for subsequent expression recognition; the other is to ensure that the image is associated with the corresponding teaching moment through timestamp information, which facilitates subsequent data matching. Through the image acquisition unit, teachers can intuitively review students' classroom performance and provide materials for subsequent analysis.

[0074] The expression recognition unit is used to load a pre-trained convolutional neural network model, input the student's classroom status image into the convolutional neural network model, identify expression categories, which include happy, focused, tired and satisfied, obtain the corresponding number of expression categories, and output them as happy expression quantity data, focused expression quantity data, tired expression quantity data and satisfied expression quantity data, and merge the happy expression quantity data, focused expression quantity data, tired expression quantity data and satisfied expression quantity data and output them as student expression analysis results, which include the corresponding second timestamp.

[0075] The expression recognition unit uses a pre-trained convolutional neural network model to classify and count the expressions of students in classroom status images. The expression recognition unit can accurately identify expression categories such as happiness, concentration, fatigue and satisfaction, and calculate the number of each type of expression. It not only improves the objectivity of teaching evaluation, but also provides teachers with quantitative data on students' emotional state. Through the expression recognition unit, teachers can quickly understand students' emotional changes in class and provide a basis for adjusting teaching strategies.

[0076] The data matching unit is used to match the teaching log scoring data and the student expression analysis results according to the first timestamp and the second timestamp, and output a comprehensive review set, which is the teaching log scoring data and the corresponding student expression analysis results.

[0077] The data matching unit is responsible for aligning the timestamps of the teaching log scoring data and the student expression analysis results to generate a comprehensive review set. The data matching unit realizes the integration of objective teaching data and subjective emotional data, providing a more comprehensive and detailed evaluation perspective for the review.

[0078] The student expression analysis module can achieve an objective and accurate analysis of students' emotional reactions by intelligently processing students' classroom status images. It not only improves the refinement of teaching evaluation, but also provides teachers with intuitive data on students' emotional feedback, which helps teachers to adjust teaching strategies in a timely manner and improve teaching effectiveness. Overall, the student expression analysis module plays an important auxiliary role in educational evaluation.

[0079] The comprehensive scoring report module includes a data analysis unit and a report generation unit.

[0080] The data analysis unit is used to analyze the comprehensive review set:

[0081] The weight distribution is performed on the happy expression quantity data, the focused expression quantity data, the tired expression quantity data and the satisfied expression quantity data, and the weight distribution is:

[0082] Data weight of the number of happy expressions: 0.2.

[0083] Data weight of number of focused expressions: 0.4.

[0084] Data weight of number of tired expressions: 0.1.

[0085] Data weight of number of satisfied expressions: 0.3.

[0086] Calculate the weighted sum of the number of happy expressions, the number of focused expressions, the number of tired expressions, and the number of satisfied expressions, and output it as student response data.

[0087] Calculate the sum of student response data and teaching log score data, and output it as the first teacher score data.

[0088] If the number of tired expression data is greater than the number of focused expression data, the first teacher's scoring data will be reduced by 5 and output as the second teacher's scoring data.

[0089] If the number of focused expressions is greater than the sum of the number of happy expressions, the number of tired expressions and the number of satisfied expressions, then the first teacher's rating data is increased by 5 and output as the second teacher's rating data.

[0090] If the condition that the number of tired expression data is greater than the number of focused expression data and the number of focused expression data is greater than the sum of the number of happy expression data, the number of tired expression data and the number of satisfied expression data is not satisfied, the first teacher rating data is directly output as the second teacher rating data.

[0091] Analysis of the second teacher's rating data:

[0092] If the second teacher's rating data is greater than the teacher rating threshold, the teacher is judged to be an excellent teacher.

[0093] If the second teacher rating data is within the teacher rating threshold, the teacher is judged to be an average teacher.

[0094] If the second teacher rating data is less than the teacher rating threshold, the teacher is judged to be in need of improvement.

[0095] Excellent teachers, average teachers and teachers to be improved are combined and output as comprehensive analysis results.

[0096] The data analysis unit first calculates the student response data according to the preset weight distribution, and further calculates the first teacher's scoring data based on the teaching log scoring data. On this basis, the first teacher's scoring data is adjusted according to specific rules to obtain the second teacher's scoring data. Finally, the teacher's level is determined by analyzing the second teacher's scoring data, and the comprehensive analysis results are output, which not only ensures the objectivity and accuracy of the scoring, but also provides teachers with targeted improvement suggestions.

[0097] The report generation unit is used to combine the comprehensive analysis results, teaching log scoring data and student expression analysis results into a comprehensive scoring report.

[0098] The report generation unit displays the teacher's performance in the teaching process and the students' emotional feedback in a clear and intuitive way. It not only provides teachers with a comprehensive basis for self-evaluation, but also provides schools and educational institutions with a scientific reference for teacher evaluation. Through the report generation unit, teachers can clearly see their own strengths and weaknesses, and then develop personalized improvement plans to continuously improve their teaching level.

[0099] The comprehensive scoring report module is a comprehensive evaluation tool that integrates data analysis and report generation. It aims to provide teachers with a comprehensive and objective scoring report through comprehensive analysis of teaching log scoring data and student expression analysis results. It not only improves the accuracy and efficiency of teaching evaluation, but also provides schools and educational institutions with a scientific teacher evaluation system. Through the comprehensive scoring report module, teachers can clearly understand their teaching performance, and then adjust teaching strategies and improve teaching quality.

[0100] The present invention quantifies objective data such as teachers' teaching logs. By formulating scoring rules, key information such as the proportion of completed course chapters, the number of completed assignments, and the extent of student achievement improvement are converted into comparable scoring data. This not only makes the evaluation of teaching effectiveness more objective and accurate, but also avoids the subjective bias that may exist in traditional evaluation methods. Through the student expression analysis module, students' instant reactions in class can be captured. These expression data, as a supplement to subjective data, can more comprehensively reflect the teacher's teaching effectiveness and classroom atmosphere. At the same time, student reaction data are calculated based on the weight distribution of expression data, further enhancing the scientificity and accuracy of the scoring. Traditional teacher evaluation often relies on students' overall scores, but this method is easily affected by various factors such as students' individual differences and evaluation attitudes, resulting in unfair evaluation results. The present invention realizes personalized evaluation of each teacher by combining teaching logs and student expression analysis, avoiding the unfair phenomenon that may be caused by the general overall student score. The present invention comprehensively considers the objective teaching data of teachers and the subjective response data of students, and obtains the comprehensive score and judgment result of each teacher through analysis and calculation of the comprehensive score report module. This evaluation method is not only more scientific and comprehensive, but also can provide targeted guidance and suggestions for teachers' professional development.

[0101] It should be understood by those skilled in the art that the embodiments of the present invention can be provided as methods, systems or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0102] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. 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 young teacher competition and review system, characterized in that: It includes teaching log analysis module, student expression analysis module and comprehensive scoring report module; The teaching log analysis module is used to receive a teaching log file, the teaching log file contains a corresponding first timestamp, use natural language processing technology to analyze the teaching log file, output the teaching log analysis result, formulate a teaching log scoring rule, score the teaching log analysis result according to the teaching log scoring result, and output teaching log scoring data, the teaching log scoring data contains the corresponding first timestamp; The student expression analysis module is used to collect a student classroom status image, the student classroom status image includes a corresponding second timestamp, use a convolutional neural network to recognize the student classroom status image, output a student expression analysis result, the student expression analysis result includes a corresponding second timestamp, correspond the teaching log scoring data and the student expression analysis result according to the first timestamp and the second timestamp, and output a comprehensive review set; The comprehensive scoring report module is used to analyze the comprehensive review set, output the comprehensive analysis results, and combine the comprehensive analysis results, teaching log scoring data and student expression analysis results into a comprehensive scoring report.

2. A young teacher competition and review system as claimed in claim 1, characterized in that: The teaching log analysis module includes a log receiving unit, a language processing unit, a rule formulation unit and a teaching scoring unit; The log receiving unit is used to receive a teaching log file, the teaching log file includes a corresponding timestamp, and stores the teaching log file in a database.

3. A young teacher competition and review system as claimed in claim 2, characterized in that: The language processing unit is used to analyze the teaching log file using natural language processing technology, and the analysis logic is: The teaching log files are cleaned, including removing stop words and punctuation marks, performing statistical segmentation on the cleaned teaching log files, extracting key information from the segmented teaching log files, and outputting the extracted key information as teaching log analysis results, wherein the key information includes data on the proportion of completed course chapters, data on the number of completed assignments, data on the extent of improvement in student performance, data on the utilization rate of teaching equipment, and data on the consumption of teaching materials.

4. A young teacher competition and review system as claimed in claim 3, characterized in that: The rule-making unit is used to make a teaching log scoring rule, and the teaching log scoring rule is: The data on the proportion of completed course chapters, the number of completed assignments, the data on the extent of student achievement improvement, the data on the utilization rate of teaching equipment, and the data on the consumption of teaching materials are weighted, and the weight distribution is as follows: Data weight of student achievement improvement: 0.4; Data weight of the number of completed jobs: 0.2; Teaching equipment utilization data weight: 0.2; Data weight of the proportion of completed course chapters: 0.1; Teaching material consumption data weight: 0.1; Substitute the data on the proportion of completed course chapters, the number of completed assignments, the extent of student performance improvement, the utilization rate of teaching equipment, and the consumption of teaching materials into the teaching log scoring rules to calculate the weighted total data.

5. A young teacher competition and review system as claimed in claim 4, characterized in that: The teaching scoring unit is used to input the teaching log analysis results into the teaching log scoring rules, calculate the weighted sum data, and output the teaching log scoring data, which contains the corresponding first timestamp.

6. A young teacher competition and review system as claimed in claim 5, characterized in that: The student expression analysis module includes an image acquisition unit, an expression recognition unit and a data matching unit; The image acquisition unit is used to acquire a student classroom status image, wherein the student classroom status image includes a corresponding second timestamp, and the student classroom status image is stored in a database.

7. A young teacher competition and review system as claimed in claim 6, characterized in that: The expression recognition unit is used to load a pre-trained convolutional neural network model, input the student's classroom status image into the convolutional neural network model, identify expression categories, which include happy, focused, tired and satisfied, obtain the corresponding number of expression categories, and output them as happy expression quantity data, focused expression quantity data, tired expression quantity data and satisfied expression quantity data, and merge the happy expression quantity data, focused expression quantity data, tired expression quantity data and satisfied expression quantity data and output them as a student expression analysis result, which includes a corresponding second timestamp.

8. A young teacher competition and review system as claimed in claim 7, characterized in that: The data matching unit is used to match the teaching log scoring data and the student expression analysis results according to the first timestamp and the second timestamp, and output a comprehensive review set, which is the teaching log scoring data and the corresponding student expression analysis results.

9. A young teacher competition and review system as claimed in claim 8, characterized in that: The comprehensive score report module includes a data analysis unit and a report generation unit; The data analysis unit is used to analyze the comprehensive review set: The weight distribution is performed on the happy expression quantity data, the focused expression quantity data, the tired expression quantity data and the satisfied expression quantity data, and the weight distribution is: Data weight of the number of happy expressions: 0.2; Focus on the number of expressions data weight: 0.4; Tiredness expression quantity data weight: 0.1; Data weight of number of satisfied expressions: 0.3; Calculate the weighted sum of the number of happy expressions, the number of focused expressions, the number of tired expressions, and the number of satisfied expressions, and output it as student response data; Calculate the sum of the student response data and the teaching log score data, and output it as the first teacher score data; If the number of tired expressions is greater than the number of focused expressions, the first teacher's rating data is reduced by 5 and output as the second teacher's rating data; If the number of focused expressions is greater than the sum of the number of happy expressions, the number of tired expressions, and the number of satisfied expressions, then the first teacher's rating data is increased by 5 and output as the second teacher's rating data; If the number of tired expression data is greater than the number of focused expression data and the number of focused expression data is greater than the sum of the number of happy expression data, the number of tired expression data and the number of satisfied expression data, the first teacher rating data is directly output as the second teacher rating data; Analysis of the second teacher's rating data: If the second teacher's rating data is greater than the teacher rating threshold, the teacher is judged as an excellent teacher; If the second teacher's rating data is within the teacher rating threshold, the teacher is judged as an average teacher; If the second teacher's rating data is less than the teacher rating threshold, the teacher is determined to be a teacher to be improved; Excellent teachers, average teachers and teachers to be improved are combined and output as comprehensive analysis results.

10. A young teacher competition and review system as claimed in claim 9, characterized in that: The report generating unit is used to combine the comprehensive analysis results, the teaching log scoring data and the student expression analysis results into a comprehensive scoring report.

Images