A teaching evaluation method and system

Abstract

The present invention provides a teaching evaluation method and system, which obtains student electroencephalogram (EEG) signals of multiple time segments within a time period to be evaluated; removes electrooculogram (EOG) artifacts from the obtained student EEG signals, extracts β-band EEG signals and calculates sample entropy, and obtains attention concentration according to the sample entropy; obtains a functional relationship between a ranking increment and a basic ranking according to the percentiles of two adjacent grades of the student; obtains the influence of the basic ranking on the ranking increment according to the student's basic ranking and the functional relationship; obtains the ranking increment after removing the basic influence by combining the ranking increment; and performs weighted summation on the ranking increment and the attention concentration after removing the basic influence to obtain a final evaluation result.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a teaching evaluation method and system. Background Art

[0002] The statements in this section merely provide background art related to the present invention and do not necessarily constitute prior art.

[0003] Value-added evaluation breaks the traditional evaluation method that uses students' absolute scores as indicators, and pays more attention to students' growth and progress, so it has been widely recognized and paid attention to. At present, value-added evaluation mostly uses test scores to calculate value-added, but test scores are affected by the difficulty of test questions and test subjects. Therefore, the value-added of scores cannot reflect the real progress of students, and it is also impossible to directly compare and evaluate teachers of different subjects. At the same time, although the use of value-added can eliminate the impact of differences in students' foundation to a certain extent, and pay more attention to the effectiveness of schools and teachers for the educated, value-added cannot completely eliminate the impact of differences in students' foundation. Generally speaking, students with different foundations have different potential for value-added. Due to the ceiling effect, the higher the students' grades, the more difficult it is to obtain value-added. The value-added of classes and schools is also affected by the foundation of students in the class and school. Therefore, directly using value-added for evaluation is also unfair to teachers and schools with relatively better students.

[0004] On the other hand, value-added evaluation constructs evaluation indicators based on academic progress, which belongs to the category of process evaluation. It cannot reflect the state of classroom teaching, nor can it conduct real-time evaluation. The evaluation factors are relatively single, and it does not combine factors such as changes in EEG signals during course teaching, so it is impossible to achieve a more comprehensive and objective teaching evaluation. Summary of the invention

[0005] In order to address the deficiencies of the prior art, the present invention provides a teaching evaluation method and system, which utilizes regression analysis to determine the quantitative relationship between students' added value and foundation, thereby eliminating the influence of students' foundation on the value-added evaluation, and combines students' concentration to achieve a more comprehensive and objective teaching evaluation.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] A first aspect of the present invention provides a teaching evaluation method.

[0008] A teaching evaluation method, comprising the following process:

[0009] Obtaining the students' EEG signals for multiple time segments within the time period to be evaluated;

[0010] Remove the eye artifacts from the students' EEG signals, extract the β-band EEG signals and calculate the sample entropy, and then get the degree of attention concentration based on the sample entropy.

[0011] The functional relationship between the ranking increment and the basic ranking is obtained based on the percentiles of the student's two adjacent grades.

[0012] According to the basic ranking of the students and the functional relationship, the influence of the basic ranking on the ranking increment is obtained;

[0013] Combine the ranking value-added to get the ranking value-added after removing the basic influence;

[0014] The final evaluation result is obtained by taking a weighted sum of the ranking increase and attention concentration after removing the basic influence.

[0015] Further, the removal of electrooculographic artifacts includes:

[0016] Perform empirical mode decomposition to obtain multiple eigenmode components;

[0017] Perform blind source separation on the obtained intrinsic mode components to obtain the EEG component source signal and the eyeball component source signal;

[0018] The obtained EEG component source signals are transformed into pure EEG signals extracted from a single eigenmode component by fast independent component analysis inverse transformation;

[0019] All the pure EEG signals obtained are added together to obtain the EEG signal with eye artifacts removed.

[0020] Going a step further, empirical mode decomposition, including:

[0021] After analog-to-digital conversion, the EEG signal is decomposed into multiple intrinsic mode components by overall empirical mode decomposition. The intrinsic mode components meet the following conditions: the number of signal extreme points is equal to the number of zero points or the difference is 1; the local mean of the upper envelope defined by the maximum value of the signal and the lower envelope defined by the minimum value is 0.

[0022] Furthermore, the rank increment is the difference between the student’s previous grade ranking percentile and the student’s current grade ranking percentile.

[0023] Furthermore, the ranking percentile is the student's grade ranking divided by the total number of students in the grade or the total number of students in the class.

[0024] A second aspect of the present invention provides a teaching evaluation method.

[0025] A teaching evaluation method, comprising the following process:

[0026] Obtaining the students' EEG signals for multiple time segments within the time period to be evaluated;

[0027] Remove the eye artifacts from the students' EEG signals, extract the β-band EEG signals and calculate the sample entropy, and then get the degree of attention concentration based on the sample entropy.

[0028] The functional relationship between the grade increment and the basic grade is obtained based on the standardized values ​​of two consecutive grades of the student;

[0029] According to the basic scores of students and the functional relationship, the influence of the basic scores on the added value of scores is obtained;

[0030] Combine the performance value-added to get the performance value-added after removing the basic influence;

[0031] The weighted sum of the performance value-added and attention concentration after removing the basic influence is taken to obtain the final evaluation result.

[0032] A third aspect of the present invention provides a teaching evaluation system.

[0033] A teaching evaluation system, comprising:

[0034] The data acquisition module is configured to: acquire the student's EEG signals of multiple time segments within the time period to be evaluated;

[0035] The attention concentration calculation module is configured to: remove eye artifacts from the acquired student EEG signals, extract the β-band EEG signals and calculate the sample entropy, and obtain the attention concentration according to the sample entropy;

[0036] The function relationship determination module is configured to: obtain the function relationship between the ranking increment and the basic ranking according to the percentiles of two adjacent grade rankings of the student;

[0037] The basic ranking influence obtaining module is configured to: obtain the influence of the basic ranking on the ranking appreciation according to the student's basic ranking and the functional relationship;

[0038] The basic ranking influence removal module is configured to: combine the ranking increment to obtain the ranking increment after removing the basic influence;

[0039] The evaluation result generation module is configured to perform weighted summation of the ranking increment and attention concentration after removing the basic influence to obtain the final evaluation result.

[0040] A fourth aspect of the present invention provides a teaching evaluation system.

[0041] A teaching evaluation system, comprising:

[0042] The data acquisition module is configured to: acquire the student's EEG signals of multiple time segments within the time period to be evaluated;

[0043] The attention concentration calculation module is configured to: remove eye artifacts from the acquired student EEG signals, extract the β-band EEG signals and calculate the sample entropy, and obtain the attention concentration according to the sample entropy;

[0044] The function relationship determination module is configured to: obtain the function relationship between the grade increment and the basic grade according to two adjacent grade standardization values ​​of the student;

[0045] The basic score influence obtaining module is configured to: obtain the influence of the basic score on the score appreciation according to the student's basic score and the functional relationship;

[0046] The basic score influence removal module is configured to: combine the score value-added to obtain the score value-added after removing the basic influence;

[0047] The evaluation result generation module is configured to perform weighted summation of the performance increment and attention concentration after removing the basic influence to obtain the final evaluation result.

[0048] A fifth aspect of the present invention provides a method for evaluating teacher teaching, comprising the following steps:

[0049] Obtaining the students' EEG signals for multiple time segments within the time period to be evaluated;

[0050] Remove the electrooculogram artifacts from the obtained student EEG signals, extract the β-band EEG signals and calculate the sample entropy, and obtain the concentration of attention based on the sample entropy. According to the concentration of each student, the average concentration of attention of all students in the teacher's class is obtained;

[0051] The functional relationship between the ranking increment and the basic ranking is obtained based on the percentiles of the student's two adjacent grades.

[0052] According to the basic ranking of the students and the functional relationship, the influence of the basic ranking on the ranking increment is obtained;

[0053] Combine the ranking value-added to get the ranking value-added after removing the basic influence, and according to the ranking value-added of each student, get the average ranking value-added of all students in the teacher's class;

[0054] The weighted sum of the average value of all students’ ranking increments and the average value of their concentration is taken to obtain the final evaluation result.

[0055] The sixth aspect of the present invention provides a method for evaluating teacher teaching, comprising the following steps:

[0056] Obtaining the students' EEG signals for multiple time segments within the time period to be evaluated;

[0057] Remove the electrooculogram artifacts from the obtained student EEG signals, extract the β-band EEG signals and calculate the sample entropy, and obtain the concentration of attention based on the sample entropy. According to the concentration of each student, the average concentration of attention of all students in the teacher's class is obtained;

[0058] The functional relationship between the grade increment and the basic grade is obtained based on the standardized values ​​of two consecutive grades of the student;

[0059] According to the basic scores of students and the functional relationship, the influence of the basic scores on the added value of scores is obtained;

[0060] Combine the grade value-added to get the grade value-added after removing the influence of the foundation. According to the grade value-added of each student, get the average grade value-added of all students in the teacher's class.

[0061] The weighted sum of the average value-added of all students' grades and the average value of their concentration is used to obtain the final evaluation result.

[0062] A seventh aspect of the present invention provides a teacher teaching evaluation system, comprising:

[0063] The data acquisition module is configured to: acquire the student's EEG signals of multiple time segments within the time period to be evaluated;

[0064] The attention concentration calculation module is configured to: remove eye artifacts from the acquired student EEG signals, extract the β-band EEG signals and calculate the sample entropy, obtain the attention concentration according to the sample entropy, and obtain the average attention concentration of all students in the teacher's class according to the attention concentration of each student;

[0065] The function relationship determination module is configured to: obtain the function relationship between the ranking increment and the basic ranking according to the percentiles of two adjacent grade rankings of the student;

[0066] The basic ranking influence obtaining module is configured to: obtain the influence of the basic ranking on the ranking appreciation according to the student's basic ranking and the functional relationship;

[0067] The basic ranking influence removal module is configured to: combine the ranking increments to obtain the ranking increments after removing the basic influences, and obtain the average ranking increments of all students in the teacher's class according to the ranking increments of each student;

[0068] The evaluation result generation module is configured to perform weighted summation on the average value of the ranking increments and the average value of the concentration of all students to obtain the final evaluation result.

[0069] An eighth aspect of the present invention provides a teacher teaching evaluation system, comprising:

[0070] The data acquisition module is configured to: acquire the student's EEG signals of multiple time segments within the time period to be evaluated;

[0071] The attention concentration calculation module is configured to: remove eye artifacts from the acquired student EEG signals, extract the β-band EEG signals and calculate the sample entropy, obtain the attention concentration according to the sample entropy, and obtain the average attention concentration of all students in the teacher's class according to the attention concentration of each student;

[0072] The function relationship determination module is configured to: obtain the function relationship between the grade increment and the basic grade according to two adjacent grade standardization values ​​of the student;

[0073] The basic score influence obtaining module is configured to: obtain the influence of the basic score on the score appreciation according to the student's basic score and the functional relationship;

[0074] The basic grade impact removal module is configured to: combine the grade value-added to obtain the grade value-added after removing the basic impact, and obtain the average of the grade value-added of all students in the teacher's class according to the grade value-added of each student;

[0075] The evaluation result generation module is configured to perform weighted summation on the average value of the added value of all students' grades and the average value of their concentration to obtain the final evaluation result.

[0076] A ninth aspect of the present invention provides a school teaching evaluation method, comprising the following process:

[0077] Obtaining the students' EEG signals for multiple time segments within the time period to be evaluated;

[0078] Remove the electrooculogram artifacts from the obtained student EEG signals, extract the β-band EEG signals and calculate the sample entropy, and obtain the concentration of attention based on the sample entropy. According to the concentration of each student, the average concentration of all students in the school is obtained;

[0079] The functional relationship between the ranking increment and the basic ranking is obtained based on the percentiles of the student's two adjacent grades.

[0080] According to the basic ranking of the students and the functional relationship, the influence of the basic ranking on the ranking increment is obtained;

[0081] Combine the ranking value-added to get the ranking value-added after removing the basic influence, and according to the ranking value-added of each student, get the average ranking value-added of all students in the school;

[0082] The weighted sum of the average value of all students’ ranking increments and the average value of their concentration is taken to obtain the final evaluation result.

[0083] The tenth aspect of the present invention provides a school teaching evaluation method, comprising the following process:

[0084] Obtaining the students' EEG signals for multiple time segments within the time period to be evaluated;

[0085] Remove the electrooculogram artifacts from the obtained student EEG signals, extract the β-band EEG signals and calculate the sample entropy, and obtain the concentration of attention based on the sample entropy. According to the concentration of each student, the average concentration of all students in the school is obtained;

[0086] The functional relationship between the grade increment and the basic grade is obtained based on the standardized values ​​of two consecutive grades of the student;

[0087] According to the basic scores of students and the functional relationship, the influence of the basic scores on the added value of scores is obtained;

[0088] Combine the grade value-added to get the grade value-added after removing the influence of the foundation. According to the grade value-added of each student, get the average value-added of all students in the school.

[0089] The weighted sum of the average value-added of all students' grades and the average value of their concentration is used to obtain the final evaluation result.

[0090] The eleventh aspect of the present invention provides a school teaching evaluation system, comprising:

[0091] The data acquisition module is configured to: acquire the student's EEG signals of multiple time segments within the time period to be evaluated;

[0092] The attention concentration calculation module is configured to: remove eye artifacts from the acquired student EEG signals, extract the β-band EEG signals and calculate the sample entropy, obtain the attention concentration according to the sample entropy, and obtain the average attention concentration of all students in the school according to the attention concentration of each student;

[0093] The function relationship determination module is configured to: obtain the function relationship between the ranking increment and the basic ranking according to the percentiles of two adjacent grade rankings of the student;

[0094] The basic ranking influence obtaining module is configured to: obtain the influence of the basic ranking on the ranking appreciation according to the student's basic ranking and the functional relationship;

[0095] The basic ranking influence removal module is configured to: combine the ranking increments to obtain the ranking increments after removing the basic influence, and obtain the average ranking increments of all students in the school according to the ranking increments of each student;

[0096] The evaluation result generation module is configured to perform weighted summation on the average value of the ranking increments and the average value of the concentration of all students to obtain the final evaluation result.

[0097] A twelfth aspect of the present invention provides a school teaching evaluation system, comprising:

[0098] The data acquisition module is configured to: acquire the student's EEG signals of multiple time segments within the time period to be evaluated;

[0099] The attention concentration calculation module is configured to: remove eye artifacts from the acquired student EEG signals, extract the β-band EEG signals and calculate the sample entropy, obtain the attention concentration according to the sample entropy, and obtain the average attention concentration of all students in the school according to the attention concentration of each student;

[0100] The function relationship determination module is configured to: obtain the function relationship between the grade increment and the basic grade according to two adjacent grade standardization values ​​of the student;

[0101] The basic score influence obtaining module is configured to: obtain the influence of the basic score on the score appreciation according to the student's basic score and the functional relationship;

[0102] The basic grade impact removal module is configured to: combine the grade value-added to obtain the grade value-added after removing the basic impact, and obtain the average of the grade value-added of all students in the school according to the grade value-added of each student;

[0103] The evaluation result generation module is configured to perform weighted summation on the average value of the added value of all students' grades and the average value of their concentration to obtain the final evaluation result.

[0104] Compared with the prior art, the present invention has the following beneficial effects:

[0105] 1. The teaching evaluation method and system described in the present invention use regression analysis to determine the quantitative relationship between the ranking increment and the basic ranking, eliminating the influence of students' foundation, and combining students' concentration to achieve more accurate and objective teaching evaluation.

[0106] 2. The teaching evaluation method and system described in the present invention use rankings for value-added calculation, which is compatible with the new college entrance examination grade points, while eliminating the influence of the difficulty of the test paper and the test subjects.

[0107] 3. The teaching evaluation method and system described in the present invention obtains the percentile of the ranking by dividing the ranking by the total number of students, thereby eliminating the influence of the number of students taking the course on the value-added evaluation.

[0108] 4. The teaching evaluation method and system of the present invention utilizes regression analysis to quantify the impact of student foundation on value-added, thereby eliminating the impact of student foundation on value-added evaluation, obtaining the net value-added of students and the effectiveness of teachers and schools, and realizing scientific, reasonable and objective teaching evaluation.

[0109] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0110] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0111] Figure 1 This is a flow chart of the student teaching evaluation method provided in Example 1 of the present invention.

[0112] Figure 2 This is a value-added scatter plot provided in Example 1 of the present invention.

[0113] Figure 3 This is a fitting effect diagram provided in Example 1 of the present invention.

[0114] Figure 4 This is a schematic diagram of the percentile increment of ranking provided in Example 1 of the present invention.

[0115] Figure 5 A flowchart of a teacher teaching evaluation method provided in Example 3 of the present invention.

[0116] Figure 6 This is a flow chart of the school teaching evaluation method provided in Example 5 of the present invention. DETAILED DESCRIPTION

[0117] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0118] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0119] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0120] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0121] Embodiment 1:

[0122] like Figure 1 As shown, Embodiment 1 of the present invention provides a teaching evaluation method, comprising the following process:

[0123] Obtaining the students' EEG signals for multiple time segments within the time period to be evaluated;

[0124] Remove the eye artifacts from the students' EEG signals, extract the β-band EEG signals and calculate the sample entropy, and then get the degree of attention concentration based on the sample entropy.

[0125] The functional relationship between the ranking increment and the basic ranking is obtained based on the percentiles of the student's two adjacent grades.

[0126] According to the basic ranking of the students and the functional relationship, the influence of the basic ranking on the ranking increment is obtained;

[0127] Combine the ranking value-added to get the ranking value-added after removing the basic influence;

[0128] The final evaluation result is obtained by taking a weighted sum of the ranking increase and attention concentration after removing the basic influence.

[0129] In this embodiment, the weight of each factor can be set manually, or each factor can account for 50%. Those skilled in the art can make a choice according to specific working conditions, which will not be described in detail here.

[0130] Remove electrooculogram artifacts, including:

[0131] Perform empirical mode decomposition to obtain multiple eigenmode components;

[0132] Perform blind source separation on the obtained intrinsic mode components to obtain the EEG component source signal and the eyeball component source signal;

[0133] The obtained EEG component source signals are transformed into pure EEG signals extracted from a single eigenmode component by fast independent component analysis inverse transformation;

[0134] All the pure EEG signals obtained are added together to obtain the EEG signal with eye artifacts removed.

[0135] Empirical Mode Decomposition, including:

[0136] After analog-to-digital conversion, the EEG signal is decomposed into multiple intrinsic mode components by overall empirical mode decomposition. The intrinsic mode components meet the following conditions: the number of signal extreme points is equal to the number of zero points or the difference is 1; the local mean of the upper envelope defined by the maximum value of the signal and the lower envelope defined by the minimum value is 0.

[0137] Calculating sample entropy includes the following steps:

[0138] A sliding time window is added to the EEG signal, and the sample entropy of the EEG signal is calculated with a sliding time window of 1s, i.e. 512 points. The window moves 64 sampling points each time, and the sample entropy of the EEG signal in the next 1s time window is calculated until the sample entropy of the EEG signal in the last 1s time window of the signal within one minute is calculated, thereby obtaining the time series of the sample entropy of the EEG signal in this section of sample data. This group of sample entropy sequences is superimposed and averaged to obtain the sample entropy of the signal within 1 minute.

[0139] The attention concentration is obtained according to the sample entropy, including the following process:

[0140] The concentration of attention in different time periods is calibrated by calculating the value of beta wave sample entropy in different time periods. The quantification process quantifies the value of sample entropy into five levels: label1, label2, label3, label4, and label5 according to (0-0.5], (0.5-1.0], (1.0-1.5], (1.5-2.0], and greater than 2.0, representing low value, lower value, normal level, high value, and higher value, respectively, and the concentration degree gradually increases.

[0141] The ranking increase after removing the basic influence includes the following process:

[0142] S1: Get the ranking of all students in a grade in a certain subject. If the rankings are the same, take the average. For example, if two students are tied for 7th place, then the rankings of both students are 7.5.

[0143] S2: The ranking divided by the total number of students in the grade is called the ranking percentile. The percentages of the two rankings of student i are denoted as x i and x′ i .x i It is called the basic ranking percentile, referred to as the basic ranking, and the difference between the two ranking percentiles is y i =x i -x′ i It is called the percentile value of student i’s rank, or simply the rank value.

[0144] S3: The ranking increment is objectively affected by the basic ranking, and the ranking increment (x i ,y i ) is the sample data, and the regression analysis method is used to obtain the functional relationship between the ranking increase and the basic ranking y=f(x), where x represents the basic ranking and y represents the ranking increase.

[0145] S4: Suppose a student’s basic ranking is x*, and the corresponding ranking increment is y*, then the impact of the basic ranking on the ranking increment is f(x*).

[0146] S5: Let z*=y*-f(x*), then z* is the adjusted value added of the original ranking y* minus the influence of the basic ranking f(x*).

[0147] S6: Use z* to conduct periodic evaluation of students.

[0148] Here is a specific example:

[0149] (1) A total of 1948 students from the entire grade of a certain school took the Chinese language test twice. The student's test ranking divided by 1948 is called the student's ranking percentile. The concept of ranking percentile eliminates the impact of the number of test takers in a subject.

[0150] (2) Let the percentile of student i’s first exam be x i , i = 1, 2, ..., 1948, called the basic ranking percentile, referred to as the basic ranking. After a period of teaching, the ranking percentile of student i in the second exam becomes x′ i , i = 1, 2, ..., 1984. The increment of the two percentile rankings is denoted by y i =x i -x′ i , i = 1, 2,…, 1984, which is called ranking appreciation.

[0151] (3) Due to the large number of tied rankings, there are 50 different x i The same value of x i The corresponding value added is averaged and still recorded as y i ,(x i ,y i ), the scatter plot of i=1,2,…,50 is attached Figure 2 .

[0152] (4) From the attachment Figure 1 It can be seen that the value added of students ranked in the first half is generally negative, and the value added of students ranked in the second half is generally positive. In addition to the relatively stable data at both ends, as the basic ranking increases, the value added of the ranking also increases.

[0153] (5) Establish a polynomial regression to quantitatively analyze the relationship between the ranking increment and the basic ranking. Suppose the functional relationship between the ranking increment and the basic ranking is y = f(x) = a5x 5 +a4x 4 +a3x 3 +a2x 2 +a1x+a0, where x represents the basic ranking and y represents the ranking increase.

[0154] (6) With (x i ,y i), i = 1, 2, ..., 50 as samples, find the values ​​of a5, a4, a3, a2, a1, a0, and then get the function relationship: f(x) = -1.6912 × 10 -12 x 5 +8.0147×10 -9 x 4 -1.392×10 -5 x 3 +0.0108x 2 -2.8597x-267.0079, the fitting effect is attached Figure 3 Middle curve.

[0155] (7) Assume that a student's ranking in the first exam is 400, and in the second exam it is 600, which means that the ranking has dropped by 200 places. His basic ranking percentile is 0.2016, and the ranking percentile increment is -0.1008. Although the student has dropped to a certain extent, according to the relationship between the ranking increment and the basic ranking, the average ranking percentile increment of students with a basic ranking percentile of 0.2016 is y = f(x) = -0.1980, that is, the ranking has dropped by 0.1980 × 1984 = 392.8 places. Figure 4 It can be seen that the ranking increase of this student (the * in the figure corresponds to the data) is above the curve, so this student should still be evaluated positively. After adjustment, the ranking percentile increase of this student is:

[0156] z=-0.1008-f(x)=0.0972

[0157] (8) The same method can be used to calculate the adjusted value-added scores for the remaining students, and a value-added evaluation can be performed based on the adjusted value-added scores.

[0158] It is understandable that in some other embodiments, the video data of students in the time period to be evaluated is obtained, and the head-up time T of each student in the current course in the first video image information is extracted by the video image analysis module. 抬 , Head down time T 低 , Speech time T 讲 , Lecture time T 听 , the number of blinks N, and the head-up time T 抬 , Head down time T 低 , Speech time T 讲 , Lecture time T 听 , the blinking times N are used to obtain each student's head-up rate A, communication rate B and blinking rate C;

[0159] The head-up rate A is used to indicate the proportion of time that the student raises his head to listen to the class during the whole course, A = T 抬 / T 低 ;

[0160] The communication rate B is used to indicate the proportion of the time that the student spends communicating in the entire course, B = T 讲 / T 听 ;

[0161] Blink rate C is used to indicate the frequency of the student's blinking in the entire class, C = N / T 抬 .

[0162] Students are rated based on:

[0163] Score=a|(AA 基 ) / A 基 |+b|(BB 基 ) / B 基 |+c|(CC 基 ) / C 基 |;

[0164] Among them, a is the weight of head-up rate, b is the weight of communication rate, c is the weight of blink rate, A 基 , B 基 and C 基 They are the head-up rate benchmark, the communication rate benchmark and the blink rate benchmark.

[0165] The above scores are weightedly summed with the ranking increase and attention concentration after removing the basic influence to obtain the final evaluation result.

[0166] Embodiment 2:

[0167] Embodiment 2 of the present invention provides a teaching evaluation system, including:

[0168] The data acquisition module is configured to: acquire the student's EEG signals of multiple time segments within the time period to be evaluated;

[0169] The attention concentration calculation module is configured to: remove eye artifacts from the acquired student EEG signals, extract the β-band EEG signals and calculate the sample entropy, and obtain the attention concentration according to the sample entropy;

[0170] The function relationship determination module is configured to: obtain the function relationship between the ranking increment and the basic ranking according to the percentiles of two adjacent grade rankings of the student;

[0171] The basic ranking influence obtaining module is configured to: obtain the influence of the basic ranking on the ranking appreciation according to the student's basic ranking and the functional relationship;

[0172] The basic ranking influence removal module is configured to: combine the ranking increment to obtain the ranking increment after removing the basic influence;

[0173] The evaluation result generation module is configured to perform weighted summation of the ranking increment and attention concentration after removing the basic influence to obtain the final evaluation result.

[0174] The working method of the system is the same as the student teaching evaluation method provided in Example 1, and will not be repeated here.

[0175] Embodiment 3:

[0176] Embodiment 3 of the present invention provides a method for evaluating teacher teaching, comprising the following steps:

[0177] Obtaining the students' EEG signals for multiple time segments within the time period to be evaluated;

[0178] Remove the electrooculogram artifacts from the obtained student EEG signals, extract the β-band EEG signals and calculate the sample entropy, and obtain the concentration of attention based on the sample entropy. According to the concentration of each student, the average concentration of attention of all students in the teacher's class is obtained;

[0179] The functional relationship between the ranking increment and the basic ranking is obtained based on the percentiles of the student's two adjacent grades.

[0180] According to the basic ranking of the students and the functional relationship, the influence of the basic ranking on the ranking increment is obtained;

[0181] Combine the ranking value-added to get the ranking value-added after removing the basic influence, and according to the ranking value-added of each student, get the average ranking value-added of all students in the teacher's class;

[0182] The weighted sum of the average value of all students’ ranking increments and the average value of their concentration is taken to obtain the final evaluation result.

[0183] Get the average value of the ranking increment of all students in the teacher's class, including the following process:

[0184] S1: Ranking the scores of all students in a certain subject in the school, using the rankings of the two previous exams to obtain the basic rankings and corresponding ranking increments of all students in the grade, using the data of all students in the grade as a sample, using regression analysis to obtain the functional relationship between ranking increments and basic rankings y=f(x), which reflects the impact of basic rankings on ranking increments across the school.

[0185] S2: Assume that there are m students in a class, and the basic rankings and corresponding ranking increments of the students in the class are (x i ,y i )i=1,2,…,m. Use the original ranking of student i to increase the value y i Subtract the effect of student i's basic ranking f(x i ), the adjusted ranking value of student i is zi =y i -f(x i ), i=1,2,…,m.

[0186] S3: Note Then Z represents the average of the adjusted ranking increases of all students in the class. It eliminates the influence of the class students' foundation, reflects the effectiveness of the teachers, and uses Z to evaluate the teaching quality of the teachers.

[0187] The following is a specific example, including:

[0188] (1) In Example 1, 1984 students are distributed in 33 classes. There are large differences between students in different classes. Appendix 1 selects 10 classes and displays the data of the average ranking of students. For the convenience of data display, the ranking and its increment are not divided by the number of students in the grade.

[0189]

[0190] (2) From the table above, we can see that the students in classes 1-4 have a good foundation and their average class rankings are high, among which the original average ranking increment of classes 2-4 is negative. The students in classes 5-10 have a poor foundation and their average class rankings are low, among which the original average ranking increment of classes 5, 7 and 10 is positive. Since the increment of the ranking of the students in a class is affected by the basic ranking of the students in the class, it is difficult for the classes with high average rankings to obtain positive increments. It is unreasonable to directly use the original average increment of the class to evaluate the teachers.

[0191] (3) Calculate the adjusted ranking increment of each student in the class using Example 1, and then recalculate the class average increment using the adjusted ranking increment. Take Class 2 as an example. Class 2 has 55 students, and the basic ranking and the corresponding ranking increment are (x i ,y i )i=1,2,…,55, the adjusted ranking value of student i is z i =y i -f(x i ), i=1,2,…,55. remember Then Z represents the average of the adjusted ranking increases of all students in the class. It eliminates the influence of the students' foundation in the class and reflects the effectiveness of the teacher.

[0192] (4) Calculate the adjusted average value added of each class using step 3 for all 33 classes in the school, and then use the adjusted average value added to evaluate the teaching quality of the class teachers.

[0193] (5) The table above lists the correspondence between the original average value added of 10 classes and the adjusted average value added of the classes. Take Class 2 and Class 10 as examples. Class 2 has 55 students, the average ranking of the students is 579, the students have a good foundation, and the average value added of the class ranking is -1; Class 10 has 55 students, the average ranking of the students is 1720, the students have a poor foundation, and the average value added of the class ranking is 37. Obviously, it is unreasonable to directly use the original average value added of the class to evaluate the teachers. The adjusted average value added of the class eliminates the influence of the students' foundation, and it is more scientific and reasonable to evaluate the teaching quality of the teachers.

[0194] Embodiment 4:

[0195] Embodiment 4 of the present invention provides a teacher teaching evaluation system, including:

[0196] The data acquisition module is configured to: acquire the student's EEG signals of multiple time segments within the time period to be evaluated;

[0197] The attention concentration calculation module is configured to: remove eye artifacts from the acquired student EEG signals, extract the β-band EEG signals and calculate the sample entropy, obtain the attention concentration according to the sample entropy, and obtain the average attention concentration of all students in the teacher's class according to the attention concentration of each student;

[0198] The function relationship determination module is configured to: obtain the function relationship between the ranking increment and the basic ranking according to the percentiles of two adjacent grade rankings of the student;

[0199] The basic ranking influence obtaining module is configured to: obtain the influence of the basic ranking on the ranking appreciation according to the student's basic ranking and the functional relationship;

[0200] The basic ranking influence removal module is configured to: combine the ranking increments to obtain the ranking increments after removing the basic influences, and obtain the average ranking increments of all students in the teacher's class according to the ranking increments of each student;

[0201] The evaluation result generation module is configured to perform weighted summation on the average value of the ranking increments and the average value of the concentration of all students to obtain the final evaluation result.

[0202] The working method of the system is the same as the student teaching evaluation method provided in Example 3, and will not be repeated here.

[0203] Embodiment 5:

[0204] Embodiment 5 of the present invention provides a school teaching evaluation method, comprising the following process:

[0205] Obtaining the students' EEG signals for multiple time segments within the time period to be evaluated;

[0206] Remove the electrooculogram artifacts from the obtained student EEG signals, extract the β-band EEG signals and calculate the sample entropy, and obtain the concentration of attention based on the sample entropy. According to the concentration of each student, the average concentration of all students in the school is obtained;

[0207] The functional relationship between the ranking increment and the basic ranking is obtained based on the percentiles of the student's two adjacent grades.

[0208] According to the basic ranking of the students and the functional relationship, the influence of the basic ranking on the ranking increment is obtained;

[0209] Combine the ranking value-added to get the ranking value-added after removing the basic influence, and according to the ranking value-added of each student, get the average ranking value-added of all students in the school;

[0210] The weighted sum of the average value of all students’ ranking increments and the average value of their concentration is taken to obtain the final evaluation result.

[0211] Get the average value of the ranking increment of all students in the school, including the following process:

[0212] S1: All students of the schools to be evaluated in a certain region are ranked, and the basic ranking and corresponding ranking increment of the regional students are obtained by using the rankings of the two previous and subsequent examinations. The data of all students in the region are used as samples, and the functional relationship between the ranking increment and the basic ranking y=g(x) is obtained by regression analysis. This function reflects the impact of the basic ranking on the ranking increment within the region.

[0213] S2: Suppose a school has a total of n students, and their basic ranking percentiles and corresponding ranking percentile increments are (x i ,y i )i=1,2,…,n. Then the adjusted percentile value of student i’s ranking after removing the influence of the basic ranking is z i =y i -g(x i ), i=1,2,…,n.

[0214] S3: Note Q represents the average value of the adjusted percentile rank of all students in the school. It eliminates the influence of the school's student base and reflects the effectiveness of the school. Q is used to evaluate the school's teaching quality.

[0215] Embodiment 6:

[0216] Embodiment 6 of the present invention provides a school teaching evaluation system, including:

[0217] The data acquisition module is configured to: acquire the student's EEG signals of multiple time segments within the time period to be evaluated;

[0218] The attention concentration calculation module is configured to: remove eye artifacts from the acquired student EEG signals, extract the β-band EEG signals and calculate the sample entropy, obtain the attention concentration according to the sample entropy, and obtain the average attention concentration of all students in the school according to the attention concentration of each student;

[0219] The function relationship determination module is configured to: obtain the function relationship between the ranking increment and the basic ranking according to the percentiles of two adjacent grade rankings of the student;

[0220] The basic ranking influence obtaining module is configured to: obtain the influence of the basic ranking on the ranking appreciation according to the student's basic ranking and the functional relationship;

[0221] The basic ranking influence removal module is configured to: combine the ranking increments to obtain the ranking increments after removing the basic influence, and obtain the average ranking increments of all students in the school according to the ranking increments of each student;

[0222] The evaluation result generation module is configured to perform weighted summation on the average value of the ranking increments and the average value of the concentration of all students to obtain the final evaluation result.

[0223] The working method of the system is the same as the student teaching evaluation method provided in Example 5, and will not be repeated here.

[0224] Embodiment 7:

[0225] Embodiment 7 of the present invention provides a teaching evaluation method, comprising the following process:

[0226] Obtaining the students' EEG signals for multiple time segments within the time period to be evaluated;

[0227] Remove the eye artifacts from the students' EEG signals, extract the β-band EEG signals and calculate the sample entropy, and then get the degree of attention concentration based on the sample entropy.

[0228] The functional relationship between the grade increment and the basic grade is obtained based on the standardized values ​​of two consecutive grades of the student;

[0229] According to the basic scores of students and the functional relationship, the influence of the basic scores on the added value of scores is obtained;

[0230] Combine the performance value-added to get the performance value-added after removing the basic influence;

[0231] The weighted sum of the performance value-added and attention concentration after removing the basic influence is taken to obtain the final evaluation result.

[0232] The standardized score value described in this embodiment can be a grade point converted from the product of all students, or a point converted from the highest score, or a normalized numerical score. Technical personnel in this field can make a choice based on specific working conditions, which will not be elaborated here.

[0233] Embodiment 8:

[0234] Embodiment 8 of the present invention provides a teaching evaluation system, including:

[0235] The data acquisition module is configured to: acquire the student's EEG signals of multiple time segments within the time period to be evaluated;

[0236] The attention concentration calculation module is configured to: remove eye artifacts from the acquired student EEG signals, extract the β-band EEG signals and calculate the sample entropy, and obtain the attention concentration according to the sample entropy;

[0237] The function relationship determination module is configured to: obtain the function relationship between the grade increment and the basic grade according to two adjacent grade standardization values ​​of the student;

[0238] The basic score influence obtaining module is configured to: obtain the influence of the basic score on the score appreciation according to the student's basic score and the functional relationship;

[0239] The basic score influence removal module is configured to: combine the score value-added to obtain the score value-added after removing the basic influence;

[0240] The evaluation result generation module is configured to perform weighted summation of the performance increment and attention concentration after removing the basic influence to obtain the final evaluation result.

[0241] Embodiment 9:

[0242] Embodiment 9 of the present invention provides a method for evaluating teacher teaching, comprising the following process:

[0243] Obtaining the students' EEG signals for multiple time segments within the time period to be evaluated;

[0244] Remove the electrooculogram artifacts from the obtained student EEG signals, extract the β-band EEG signals and calculate the sample entropy, and obtain the concentration of attention based on the sample entropy. According to the concentration of each student, the average concentration of attention of all students in the teacher's class is obtained;

[0245] The functional relationship between the grade increment and the basic grade is obtained based on the standardized values ​​of two consecutive grades of the student;

[0246] According to the basic scores of students and the functional relationship, the influence of the basic scores on the added value of scores is obtained;

[0247] Combine the grade value-added to get the grade value-added after removing the influence of the foundation. According to the grade value-added of each student, get the average grade value-added of all students in the teacher's class.

[0248] The weighted sum of the average value-added of all students' grades and the average value of their concentration is used to obtain the final evaluation result.

[0249] Embodiment 10:

[0250] Embodiment 10 of the present invention provides a teacher teaching evaluation system, including:

[0251] The data acquisition module is configured to: acquire the student's EEG signals of multiple time segments within the time period to be evaluated;

[0252] The attention concentration calculation module is configured to: remove eye artifacts from the acquired student EEG signals, extract the β-band EEG signals and calculate the sample entropy, obtain the attention concentration according to the sample entropy, and obtain the average attention concentration of all students in the teacher's class according to the attention concentration of each student;

[0253] The function relationship determination module is configured to: obtain the function relationship between the grade increment and the basic grade according to two adjacent grade standardization values ​​of the student;

[0254] The basic score influence obtaining module is configured to: obtain the influence of the basic score on the score appreciation according to the student's basic score and the functional relationship;

[0255] The basic grade impact removal module is configured to: combine the grade value-added to obtain the grade value-added after removing the basic impact, and obtain the average of the grade value-added of all students in the teacher's class according to the grade value-added of each student;

[0256] The evaluation result generation module is configured to perform weighted summation on the average value of the added value of all students' grades and the average value of their concentration to obtain the final evaluation result.

[0257] Embodiment 11:

[0258] Embodiment 11 of the present invention provides a school teaching evaluation method, comprising the following process:

[0259] Obtaining the students' EEG signals for multiple time segments within the time period to be evaluated;

[0260] Remove the electrooculogram artifacts from the obtained student EEG signals, extract the β-band EEG signals and calculate the sample entropy, and obtain the concentration of attention based on the sample entropy. According to the concentration of each student, the average concentration of all students in the school is obtained;

[0261] The functional relationship between the grade increment and the basic grade is obtained based on the standardized values ​​of two consecutive grades of the student;

[0262] According to the basic scores of students and the functional relationship, the influence of the basic scores on the added value of scores is obtained;

[0263] Combine the grade value-added to get the grade value-added after removing the influence of the foundation. According to the grade value-added of each student, get the average value-added of all students in the school.

[0264] The weighted sum of the average value-added of all students' grades and the average value of their concentration is used to obtain the final evaluation result.

[0265] Embodiment 12:

[0266] Embodiment 12 of the present invention provides a school teaching evaluation system, including:

[0267] The data acquisition module is configured to: acquire the student's EEG signals of multiple time segments within the time period to be evaluated;

[0268] The attention concentration calculation module is configured to: remove eye artifacts from the acquired student EEG signals, extract the β-band EEG signals and calculate the sample entropy, obtain the attention concentration according to the sample entropy, and obtain the average attention concentration of all students in the school according to the attention concentration of each student;

[0269] The function relationship determination module is configured to: obtain the function relationship between the grade increment and the basic grade according to two adjacent grade standardization values ​​of the student;

[0270] The basic score influence obtaining module is configured to: obtain the influence of the basic score on the score appreciation according to the student's basic score and the functional relationship;

[0271] The basic grade impact removal module is configured to: combine the grade value-added to obtain the grade value-added after removing the basic impact, and obtain the average of the grade value-added of all students in the school according to the grade value-added of each student;

[0272] The evaluation result generation module is configured to perform weighted summation on the average value of the added value of all students' grades and the average value of their concentration to obtain the final evaluation result.

[0273] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0274] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0275] 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.

[0276] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0277] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0278] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A teaching evaluation method, characterized in that: The process includes: Obtaining the students' EEG signals for multiple time segments within the time period to be evaluated; Remove the eye artifacts from the students' EEG signals, extract the β-band EEG signals and calculate the sample entropy, and then get the degree of attention concentration based on the sample entropy. The functional relationship between the ranking increment and the basic ranking is obtained based on the percentiles of the student's two adjacent grades. According to the basic ranking of the students and the functional relationship, the influence of the basic ranking on the ranking increment is obtained; Combine the ranking value-added to get the ranking value-added after removing the basic influence; The final evaluation result is obtained by weighted summing the ranking increment and attention concentration after removing the basic influence. or, The process includes: Obtaining the students' EEG signals for multiple time segments within the time period to be evaluated; Remove the eye artifacts from the students' EEG signals, extract the β-band EEG signals and calculate the sample entropy, and then get the degree of attention concentration based on the sample entropy. The functional relationship between the grade increment and the basic grade is obtained based on the standardized values ​​of two consecutive grades of the student; According to the basic scores of students and the functional relationship, the influence of the basic scores on the added value of scores is obtained; Combine the performance value-added to get the performance value-added after removing the basic influence; The weighted sum of the performance value-added and attention concentration after removing the basic influence is performed to obtain the final evaluation result; Remove electrooculogram artifacts, including: Perform empirical mode decomposition to obtain multiple eigenmode components; Perform blind source separation on the obtained intrinsic mode components to obtain the EEG component source signal and the eyeball component source signal; The obtained EEG component source signals are transformed into pure EEG signals extracted from a single eigenmode component by fast independent component analysis inverse transformation; All the pure EEG signals obtained are added together to obtain the EEG signal with eye artifacts removed.

2. The teaching evaluation method according to claim 1, characterized in that: Empirical Mode Decomposition, including: After analog-to-digital conversion, the EEG signal is decomposed into multiple intrinsic mode components by overall empirical mode decomposition. The intrinsic mode components meet the following conditions: the number of signal extreme points is equal to the number of zero points or the difference is 1; the local mean of the upper envelope defined by the maximum value of the signal and the lower envelope defined by the minimum value is 0.

3. The teaching evaluation method according to claim 1, characterized in that: The rank increment is the difference between the percentile of the student’s previous grade ranking and the percentile of the student’s current grade ranking; or, The percentile ranking is the student's grade ranking divided by the total number of students in the grade or class.

4. A teaching evaluation system, characterized in that: include: The data acquisition module is configured to: acquire the student's EEG signals of multiple time segments within the time period to be evaluated; The attention concentration calculation module is configured to: remove eye artifacts from the acquired student EEG signals, extract the β-band EEG signals and calculate the sample entropy, and obtain the attention concentration according to the sample entropy; The function relationship determination module is configured to: obtain the function relationship between the ranking increment and the basic ranking according to the percentiles of two adjacent grade rankings of the student; The basic ranking influence obtaining module is configured to: obtain the influence of the basic ranking on the ranking appreciation according to the student's basic ranking and the functional relationship; The basic ranking influence removal module is configured to: combine the ranking increment to obtain the ranking increment after removing the basic influence; The evaluation result generation module is configured to: perform weighted summation of the ranking increment and the attention concentration after removing the basic influence to obtain the final evaluation result; or, include: The data acquisition module is configured to: acquire the student's EEG signals of multiple time segments within the time period to be evaluated; The attention concentration calculation module is configured to: remove eye artifacts from the acquired student EEG signals, extract the β-band EEG signals and calculate the sample entropy, and obtain the attention concentration according to the sample entropy; The function relationship determination module is configured to: obtain the function relationship between the grade increment and the basic grade according to two adjacent grade standardization values ​​of the student; The basic score influence obtaining module is configured to: obtain the influence of the basic score on the score appreciation according to the student's basic score and the functional relationship; The basic score influence removal module is configured to: combine the score value-added to obtain the score value-added after removing the basic influence; The evaluation result generation module is configured to: perform weighted summation of the performance increment and the attention concentration after removing the basic influence to obtain the final evaluation result; Remove electrooculogram artifacts, including: Perform empirical mode decomposition to obtain multiple eigenmode components; Perform blind source separation on the obtained intrinsic mode components to obtain the EEG component source signal and the eyeball component source signal; The obtained EEG component source signals are transformed into pure EEG signals extracted from a single eigenmode component by fast independent component analysis inverse transformation; All the pure EEG signals obtained are added together to obtain the EEG signal with eye artifacts removed.

5. A method for evaluating teacher teaching, characterized in that: The process includes: Obtaining the students' EEG signals for multiple time segments within the time period to be evaluated; Remove the electrooculogram artifacts from the obtained student EEG signals, extract the β-band EEG signals and calculate the sample entropy, and obtain the concentration of attention based on the sample entropy. According to the concentration of each student, the average concentration of attention of all students in the teacher's class is obtained; The functional relationship between the ranking increment and the basic ranking is obtained based on the percentiles of the student's two adjacent grades. According to the basic ranking of the students and the functional relationship, the influence of the basic ranking on the ranking increment is obtained; Combine the ranking value-added to get the ranking value-added after removing the basic influence, and according to the ranking value-added of each student, get the average ranking value-added of all students in the teacher's class; The weighted sum of the average value of all students' ranking increments and the average value of their concentration is used to obtain the final evaluation result. or, The process includes: Obtaining the students' EEG signals for multiple time segments within the time period to be evaluated; Remove the electrooculogram artifacts from the obtained student EEG signals, extract the β-band EEG signals and calculate the sample entropy, and obtain the concentration of attention based on the sample entropy. According to the concentration of each student, the average concentration of attention of all students in the teacher's class is obtained; The functional relationship between the grade increment and the basic grade is obtained based on the standardized values ​​of two consecutive grades of the student; According to the basic scores of students and the functional relationship, the influence of the basic scores on the added value of scores is obtained; Combine the grade value-added to get the grade value-added after removing the influence of the foundation. According to the grade value-added of each student, get the average grade value-added of all students in the teacher's class. The weighted sum of the average value of all students' grade increments and the average value of their concentration is used to obtain the final evaluation result. Remove electrooculogram artifacts, including: Perform empirical mode decomposition to obtain multiple eigenmode components; Perform blind source separation on the obtained intrinsic mode components to obtain the EEG component source signal and the eyeball component source signal; The obtained EEG component source signals are transformed into pure EEG signals extracted from a single eigenmode component by fast independent component analysis inverse transformation; All the pure EEG signals obtained are added together to obtain the EEG signal with eye artifacts removed.

6. A teacher teaching evaluation system, characterized by: include: The data acquisition module is configured to: acquire the student's EEG signals of multiple time segments within the time period to be evaluated; The attention concentration calculation module is configured to: remove eye artifacts from the acquired student EEG signals, extract the β-band EEG signals and calculate the sample entropy, obtain the attention concentration according to the sample entropy, and obtain the average attention concentration of all students in the teacher's class according to the attention concentration of each student; The function relationship determination module is configured to: obtain the function relationship between the ranking increment and the basic ranking according to the percentiles of two adjacent grade rankings of the student; The basic ranking influence obtaining module is configured to: obtain the influence of the basic ranking on the ranking appreciation according to the student's basic ranking and the functional relationship; The basic ranking influence removal module is configured to: combine the ranking increments to obtain the ranking increments after removing the basic influences, and obtain the average ranking increments of all students in the teacher's class according to the ranking increments of each student; The evaluation result generation module is configured to: perform weighted summation on the average of the ranking increments and the average of the concentration of all students to obtain the final evaluation result; or, include: The data acquisition module is configured to: acquire the student's EEG signals of multiple time segments within the time period to be evaluated; The attention concentration calculation module is configured to: remove eye artifacts from the acquired student EEG signals, extract the β-band EEG signals and calculate the sample entropy, obtain the attention concentration according to the sample entropy, and obtain the average attention concentration of all students in the teacher's class according to the attention concentration of each student; The function relationship determination module is configured to: obtain the function relationship between the grade increment and the basic grade according to two adjacent grade standardization values ​​of the student; The basic score influence obtaining module is configured to: obtain the influence of the basic score on the score appreciation according to the student's basic score and the functional relationship; The basic grade impact removal module is configured to: combine the grade value-added to obtain the grade value-added after removing the basic impact, and obtain the average of the grade value-added of all students in the teacher's class according to the grade value-added of each student; The evaluation result generation module is configured to: perform weighted summation on the average value of the added value of all students' grades and the average value of their concentration to obtain a final evaluation result; Remove electrooculogram artifacts, including: Perform empirical mode decomposition to obtain multiple eigenmode components; Perform blind source separation on the obtained intrinsic mode components to obtain the EEG component source signal and the eyeball component source signal; The obtained EEG component source signals are transformed into pure EEG signals extracted from a single eigenmode component by fast independent component analysis inverse transformation; All the pure EEG signals obtained are added together to obtain the EEG signal with eye artifacts removed.

7. A school teaching evaluation method, characterized in that: The process includes: Obtaining the students' EEG signals for multiple time segments within the time period to be evaluated; Remove the electrooculogram artifacts from the obtained student EEG signals, extract the β-band EEG signals and calculate the sample entropy, and obtain the concentration of attention based on the sample entropy. According to the concentration of each student, the average concentration of all students in the school is obtained; The functional relationship between the ranking increment and the basic ranking is obtained based on the percentiles of the student's two adjacent grades. According to the basic ranking of the students and the functional relationship, the influence of the basic ranking on the ranking increment is obtained; Combine the ranking value-added to get the ranking value-added after removing the basic influence, and according to the ranking value-added of each student, get the average ranking value-added of all students in the school; The weighted sum of the average value of all students' ranking increments and the average value of their concentration is used to obtain the final evaluation result. or, The process includes: Obtaining the students' EEG signals for multiple time segments within the time period to be evaluated; Remove the electrooculogram artifacts from the obtained student EEG signals, extract the β-band EEG signals and calculate the sample entropy, and obtain the concentration of attention based on the sample entropy. According to the concentration of each student, the average concentration of all students in the school is obtained; The functional relationship between the grade increment and the basic grade is obtained based on the standardized values ​​of two consecutive grades of the student; According to the basic scores of students and the functional relationship, the influence of the basic scores on the added value of scores is obtained; Combine the grade value-added to get the grade value-added after removing the influence of the foundation. According to the grade value-added of each student, get the average value-added of all students in the school. The weighted sum of the average value of all students' grade increments and the average value of their concentration is used to obtain the final evaluation result. Remove electrooculogram artifacts, including: Perform empirical mode decomposition to obtain multiple eigenmode components; Perform blind source separation on the obtained intrinsic mode components to obtain the EEG component source signal and the eyeball component source signal; The obtained EEG component source signals are transformed into pure EEG signals extracted from a single eigenmode component by fast independent component analysis inverse transformation; All the pure EEG signals obtained are added together to obtain the EEG signal with eye artifacts removed.

8. A school teaching evaluation system, characterized by: include: The data acquisition module is configured to: acquire the student's EEG signals of multiple time segments within the time period to be evaluated; The attention concentration calculation module is configured to: remove eye artifacts from the acquired student EEG signals, extract the β-band EEG signals and calculate the sample entropy, obtain the attention concentration according to the sample entropy, and obtain the average attention concentration of all students in the school according to the attention concentration of each student; The function relationship determination module is configured to: obtain the function relationship between the ranking increment and the basic ranking according to the percentiles of two adjacent grade rankings of the student; The basic ranking influence obtaining module is configured to: obtain the influence of the basic ranking on the ranking appreciation according to the student's basic ranking and the functional relationship; The basic ranking influence removal module is configured to: combine the ranking increments to obtain the ranking increments after removing the basic influence, and obtain the average ranking increments of all students in the school according to the ranking increments of each student; The evaluation result generation module is configured to: perform weighted summation on the average of the ranking increments and the average of the concentration of all students to obtain the final evaluation result; or, include: The data acquisition module is configured to: acquire the student's EEG signals of multiple time segments within the time period to be evaluated; The attention concentration calculation module is configured to: remove eye artifacts from the acquired student EEG signals, extract the β-band EEG signals and calculate the sample entropy, obtain the attention concentration according to the sample entropy, and obtain the average attention concentration of all students in the school according to the attention concentration of each student; The function relationship determination module is configured to: obtain the function relationship between the grade increment and the basic grade according to two adjacent grade standardization values ​​of the student; The basic score influence obtaining module is configured to: obtain the influence of the basic score on the score appreciation according to the student's basic score and the functional relationship; The basic grade impact removal module is configured to: combine the grade value-added to obtain the grade value-added after removing the basic impact, and obtain the average of the grade value-added of all students in the school according to the grade value-added of each student; The evaluation result generation module is configured to: perform weighted summation on the average value of the added value of all students' grades and the average value of their concentration to obtain a final evaluation result; Remove electrooculogram artifacts, including: Perform empirical mode decomposition to obtain multiple eigenmode components; Perform blind source separation on the obtained intrinsic mode components to obtain the EEG component source signal and the eyeball component source signal; The obtained EEG component source signals are transformed into pure EEG signals extracted from a single eigenmode component by fast independent component analysis inverse transformation; All the pure EEG signals obtained are added together to obtain the EEG signal with eye artifacts removed.

Images