Education quality evaluation method based on multi-source data fusion and statistical hypothesis testing
By collecting and fusing multi-source data and conducting statistical hypothesis testing, we constructed characteristic values for the evaluation of educational quality throughout the semester. This solved the problem that traditional evaluation methods could not fully reflect online learning attitudes and participation, and enabled accurate evaluation and dynamic tracking of teaching quality.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-28
- Publication Date
- 2026-03-24
AI Technical Summary
Traditional methods of assessing educational quality cannot fully reflect students' learning attitudes and participation in online classes, resulting in low accuracy of assessments, especially in online courses where they cannot truly reflect the quality of teaching.
By collecting multi-source learning data, calculating real-time learning performance and classroom participation performance indicators, and combining them with education quality measurement factors and end-of-term grade data, we can construct a full-semester education quality assessment feature value to achieve dynamic tracking and evaluation of the teaching process.
This improves the accuracy and fairness of education quality assessment, enabling a more comprehensive reflection of students' learning progress, reducing the weight of exam scores in the assessment, and enhancing the precision of teaching quality evaluation.
Smart Images
Figure CN121724481A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of educational assessment technology, specifically to an educational quality assessment method based on multi-source data fusion and statistical hypothesis testing. Background Technology
[0002] Educational quality assessment is a process of comprehensively testing and judging the effectiveness of an education system, institution, or curriculum to measure whether it has achieved its preset educational goals and quality standards. The core significance of conducting educational quality assessment on a curriculum is to ensure that the curriculum accurately aligns with students' needs and educational goals, ensures that the learning content is valuable, matches students' cognition and needs, and avoids "useless teaching" and "ineffective learning." It is a key link connecting the teaching plan with the actual educational effect, providing teachers with teaching guidelines, monitoring the implementation effect of teaching, and promoting the improvement of teaching methods.
[0003] With the development of internet technology, online courses have been widely used in the field of education. Traditional education quality assessment often relies too much on exam scores and classroom performance. This assessment method has certain limitations. Exam scores can only reflect the degree of students' mastery of knowledge at a specific point in time. Especially for online courses, this assessment method cannot fully reflect students' learning attitude, participation and other information when watching online courses, and cannot truly reflect the teaching quality. Summary of the Invention
[0004] To address the technical problem of low accuracy in education quality assessment, the present invention aims to provide an education quality assessment method based on multi-source data fusion and statistical hypothesis testing. The specific technical solution adopted is as follows: In a first aspect, embodiments of the present invention provide an educational quality assessment method based on multi-source data fusion and statistical hypothesis testing, the method comprising: For each course, multi-source learning data is collected from all students who have enrolled in that course. Based on the collected multi-source learning data, calculate each student's real-time learning performance indicators and classroom participation performance indicators for each course. By combining the real-time learning performance indicators and the classroom participation performance indicators, the educational quality measurement factors for each course are determined. Construct a sequence of educational quality measurement factors for the entire semester according to the order of class hours, analyze the dynamic change trend of the educational quality measurement factor sequence, obtain the dynamic change trend characteristic value, and correct the dynamic change trend characteristic value in combination with the final grade data to obtain the course educational quality assessment characteristic value. The overall educational quality of the course throughout the semester is comprehensively evaluated based on the course's educational quality assessment characteristic values.
[0005] In some embodiments, the collection of multi-source learning data for each course, corresponding to all students enrolled in that course, includes: For each course, a pre-set learning management system is used to monitor each student's video viewing behavior data, interaction behavior data, after-class exercise data, and final grade data.
[0006] In some embodiments, calculating the real-time learning performance indicators for each student per course based on the collected multi-source learning data includes: Extract the effective viewing time from the video viewing behavior data; The total number of exercises for each course, the time each student spent completing the exercises, and the accuracy rate of the exercises were determined from the after-class exercise data. By combining the effective viewing time, the time spent completing the after-class exercises, and the accuracy rate of the after-class exercises, an instant learning performance index for each student for each course is calculated.
[0007] In some embodiments, based on collected multi-source learning data, classroom participation performance indicators for each student in each course are calculated, including: For each course, keywords and text fragments are extracted as reference text based on the corresponding teaching content. Using text similarity algorithms in natural language processing, the similarity between each student's interactive behavior data for the course and the reference text is calculated; Based on the preset similarity judgment criteria, the number of interactive behaviors of each student in relation to the course that meet the similarity judgment criteria is counted, and the average similarity between the interactive behaviors and the reference text is calculated. By combining the number of interactive behaviors and the average similarity, a classroom participation performance index for each student in each course is calculated.
[0008] In some embodiments, it also includes: Obtain real-time learning performance metrics for each student for each course; Obtain each student's classroom participation performance metrics for each course; By combining the real-time learning performance indicators and the classroom participation performance indicators, a comprehensive performance characteristic value for each student for each course is determined.
[0009] In some embodiments, determining the educational quality measurement factor for each course by combining the real-time learning performance indicators and the classroom participation performance indicators includes: Determine the overall performance characteristics of each student for each course; Based on the pre-set comprehensive performance characteristic value judgment standard, all students enrolled in each course are divided into those who meet the standard and those who do not meet the standard. Count the total number of students who meet the standard category in each course, and calculate the mean of the comprehensive performance characteristic values of all students who meet the standard category in each course; The educational quality measurement factors for each course are determined by combining the proportion of students who meet the standard category to the total number of students, as well as the average comprehensive performance characteristic value of students who meet the standard category.
[0010] In some embodiments, the step of constructing a sequence of educational quality measurement factors for the entire semester according to the order of class hours, analyzing the dynamic change trend of the educational quality measurement factor sequence, and obtaining dynamic change trend characteristic values includes: Collect educational quality measurement factors for each lesson of the same course taught by the same teacher to the same class throughout the entire semester; According to the time sequence of the course's class schedule throughout the semester, the educational quality measurement factors corresponding to each class are arranged sequentially to construct the full semester educational quality measurement factor sequence for the course. Identify consecutive negative and consecutive positive change periods from the sequence of educational quality measurement factors for the entire semester, determine the number of class hours included in the longest consecutive positive change period, the number of class hours included in the longest consecutive negative change period, and the slope of the change curve of educational quality measurement factors within the longest consecutive positive change period, and calculate the dynamic change trend characteristic value of the course educational quality. Calculate the mean of all education quality measurement factors in the entire semester education quality measurement factor sequence, and use it as the measurement mean; Based on the measured mean, the calculated dynamic trend characteristic values are normalized to obtain the final dynamic trend characteristic values.
[0011] In some embodiments, identifying periods of continuous negative change and periods of continuous positive change from the sequence of educational quality measurement factors for the entire semester includes: Calculate the difference between two adjacent education quality measurement factors in the entire semester education quality measurement factor sequence; Based on the preset difference judgment criteria, the class hours corresponding to all education quality measurement factors in the whole semester education quality measurement factor sequence are divided into class hours with declining quality and class hours with improving quality. Two or more adjacent periods of declining quality are defined as a period of continuous negative change, and the number of periods contained in the longest period of continuous negative change is recorded. Two or more adjacent periods of improved quality are defined as a continuous positive change period, and the number of periods contained in the longest continuous positive change period is recorded.
[0012] In some embodiments, the step of correcting the dynamic trend feature value by combining the final exam results data to obtain the course teaching quality assessment feature value includes: Collect the final grades of all students who have taken the same course; Calculate the average final exam score for all students enrolled in the course based on the final exam score data. Calculate the final exam pass rate for all students who enrolled in the course. By combining the average final exam score and the final exam pass rate, the teaching quality index reflected by the final exam score is determined. The dynamic trend feature value is integrated with the teaching quality index for calculation, and the dynamic trend feature value is corrected to obtain the course education quality assessment feature value.
[0013] In some embodiments, the step of comprehensively evaluating the overall educational quality of the course throughout the semester based on the course's educational quality assessment characteristic values includes: Define and pre-set thresholds for education quality assessment; If the course education quality assessment feature value is greater than or equal to the education quality assessment threshold, then the course education quality corresponding to the course education quality assessment feature value is determined to be high. If the course education quality assessment characteristic value is less than the education quality assessment threshold, then the course education quality corresponding to the course education quality assessment characteristic value is determined to be low.
[0014] In a second aspect, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, it implements the various possible implementations of the first aspect.
[0015] Thirdly, embodiments of the present invention provide a computer program product comprising: computer program code, which, when run on a computer, causes the computer to perform the method described in the first aspect or any possible implementation thereof.
[0016] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the various possible implementations of the first aspect.
[0017] The embodiments of the present invention have at least the following beneficial effects: This invention comprehensively considers students' performance in each class, determines the educational quality measurement factors for each class, and analyzes their dynamic change characteristics. It continuously tracks and evaluates online teaching throughout the semester, accurately capturing quality changes at different stages of the teaching process, more comprehensively reflecting students' learning in the online course, accurately assessing teaching quality, reducing the weight of exam scores in the evaluation, and enhancing the fairness of educational quality assessment. Attached Figure Description
[0018] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0019] Figure 1 This is a flowchart of an educational quality assessment method based on multi-source data fusion and statistical hypothesis testing, provided in one embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of a computer device provided in one embodiment of the present invention. Detailed Implementation
[0020] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the education quality assessment method based on multi-source data fusion and statistical hypothesis testing proposed in this invention.
[0021] In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments may be combined in any suitable form.
[0022] In the description of the embodiments of the present invention, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present invention, "multiple" means two or more.
[0023] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.
[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.
[0025] The embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided by the embodiments of the present invention are also applicable to similar technical problems.
[0026] The following description, in conjunction with the accompanying drawings, details the specific scheme of the educational quality assessment method based on multi-source data fusion and statistical hypothesis testing provided by this invention.
[0027] Example 1: Please see Figure 1 The diagram illustrates a flowchart of an educational quality assessment method based on multi-source data fusion and statistical hypothesis testing, provided by an embodiment of the present invention. The method includes the following steps: S10. For each course, collect multi-source learning data from all students enrolled in that course.
[0028] Specifically, for each course, a pre-set learning management system or online teaching platform is used to monitor and record each student's video viewing behavior data, interaction behavior data, after-class exercise data, and final grade data at the end of the semester in real time. Video viewing behavior data includes the total viewing time of each lesson, the number of pauses, the number of exits, the timestamps of fast-forwarding actions, and the cumulative fast-forwarding time; interaction behavior data covers the number of times students post comments in the course discussion area, the number of times they reply to other students, and the number of bullet comments posted during the lesson; after-class exercise data includes the total number of exercises for each lesson, the time each student spends completing all exercises, and the number of questions each student answers correctly; the final grade data is the final exam score of all students enrolled in the course, and the accuracy and completeness of the data must be ensured during the collection process.
[0029] S11. Based on the collected multi-source learning data, calculate the real-time learning performance indicators and classroom participation performance indicators for each student for each course.
[0030] Specifically, based on the collected multi-source learning data, an immediate learning performance indicator for each student for each course is calculated. First, effective viewing time is extracted from video viewing behavior data. Effective viewing time is the remaining time after deducting accumulated fast-forwarding time from the total viewing time, reflecting the student's level of focus while watching the course. Next, the total number of homework questions for each course, the time each student spends completing homework questions, and the accuracy rate of homework questions are determined from the homework practice data. The accuracy rate is the ratio of the number of correctly answered questions to the total number of questions. Finally, combining the effective viewing time, homework completion time, and homework accuracy rate, an immediate learning performance indicator A is calculated.
[0031] in, Represents the effective viewing time. The total viewing time is f, the time spent completing the homework is d0, the total number of homework questions is d, and the number of questions answered correctly is d. This indicates the accuracy rate of answering the after-class exercises. The longer the effective viewing time, the shorter the time to complete the exercises, and the higher the accuracy rate, the better the student's learning performance in that lesson, and the larger the corresponding value of the immediate learning performance indicator A. It should be noted that this immediate learning performance indicator is only analyzed for students who completed the after-class exercises after watching the course. For students who only watched the course but did not complete the exercises, their immediate learning performance indicator is set to 0.
[0032] Furthermore, based on the collected multi-source learning data, classroom participation performance indicators for each student in each course are calculated. First, for each course, keywords and important text fragments closely related to the course content are extracted according to the course syllabus, courseware content, and teaching focus of each lesson. These are used as reference texts to ensure accurate matching of the core course content. Then, text similarity algorithms in natural language processing, such as the cosine similarity algorithm, are used to calculate the similarity *g* between each student's interactive behavior data for the course and the reference text. Specifically, the similarity *g* ranges from 0 to 1, with a higher value indicating a stronger relevance between the interactive content and the course. Next, according to preset similarity criteria, the number of interactive behaviors for each student that meet the similarity criteria for the course is counted, and the average similarity between these compliant interactive behaviors and the reference text is calculated. Specifically, the preset similarity judgment standard can be 0.7, or it can be adjusted according to actual needs. That is, when g≥0.7, the corresponding interactive behavior meets the similarity judgment standard.
[0033] Specifically, the formula for calculating classroom participation performance indicator B is as follows:
[0034] Where k0 represents the total number of interactive behaviors for each student; k represents the number of interactive behaviors that meet the similarity judgment criteria; This represents the mean similarity between the standard interactive behavior and the reference text. The more relevant a student's comments are, and the greater their relevance to the classroom content, the better their classroom participation, and the higher the corresponding B value. It should be noted that the classroom participation performance index here is only analyzed for students who engage in interactive behavior; for students who do not engage in interactive behavior, their classroom participation performance index is set to 0.
[0035] S12. Combining the real-time learning performance indicators and the classroom participation performance indicators, determine the educational quality measurement factors for each course.
[0036] Specifically, firstly, the calculation method for each student's overall performance characteristic value C for each course is as follows:
[0037] The better the immediate learning performance and the better the classroom participation performance, the larger the overall performance characteristic value C.
[0038] Next, based on the preset comprehensive performance characteristic value judgment standard, all students enrolled in each course are divided into those who meet the standard and those who do not meet the standard. Those who meet the standard indicate that their comprehensive performance in the course is good, while those who do not meet the standard indicate that their comprehensive performance needs to be improved. The specific preset comprehensive performance characteristic value judgment standard can be 0.5, or it can be adjusted according to actual needs. That is, when the comprehensive performance characteristic value C>0.5, it is the category that meets the standard, and when the comprehensive performance characteristic value C≤0.5, it is the category that does not meet the standard.
[0039] Furthermore, the formula for calculating the educational quality measurement factor D for each course is as follows:
[0040] Where b represents the number of students who meet the standard category; b0 represents the total number of all students; The value of D represents the average comprehensive performance characteristic value of students who meet the standard. The higher the percentage of students who meet the standard and the better their classroom performance, the better the overall educational quality of the lesson. The larger the value of D, the better the overall learning effect of the lesson, reflecting high educational quality, attracting students' attention, and stimulating students' learning enthusiasm and initiative. The smaller the value of D, the worse the overall learning effect, the poorer the students' learning enthusiasm and mastery of knowledge points, and the lower the educational quality needs to be.
[0041] S13. Construct a sequence of educational quality measurement factors for the whole semester in chronological order of class hours, analyze the dynamic change trend of the sequence of educational quality measurement factors, obtain the characteristic values of the dynamic change trend, and correct the characteristic values of the dynamic change trend in combination with the final exam score data to obtain the characteristic values for evaluating the educational quality of the course.
[0042] First, collect the educational quality measurement factor D for each class of the same course taught by the same teacher to the same class throughout the semester. Then, arrange the educational quality measurement factor D corresponding to each class in sequence according to the chronological order of the class hour arrangement of the course throughout the semester to construct the sequence of educational quality measurement factors for the whole semester corresponding to the course. Next, calculate the difference c between two adjacent educational quality measurement factors in the sequence. According to the preset difference judgment standard, divide the class hours corresponding to all the educational quality measurement factors in the sequence into class hours with decreasing quality, class hours with stable quality, and class hours with increasing quality. Specifically, the preset difference judgment standard is 0.2. Also, according to actual needs, when c ≤ -0.2, it is a class hour with decreasing quality; when -0.2 < c < 0, it is a class hour with stable quality; when c ≥ 0, it is a class hour with increasing quality.
[0043] Subsequently, define two or more adjacent class hours with decreasing quality as a continuously negatively changing period, record the number of class hours t included in the longest continuously negatively changing period, and define two or more adjacent class hours with stable quality or increasing quality as a continuously positively changing period, and record the number of class hours ; at the same time, determine the slope m of the change curve of the educational quality measurement factor within the longest continuously positively changing period. The larger the slope m, the faster the educational quality improves within this period. Then, in combination with the number of class hours included in the longest continuously positively changing period, the slope m of the change curve of the educational quality measurement factor within the longest continuously positively changing period, and the number of class hours t included in the longest continuously negatively changing period, calculate the characteristic value E of the dynamic change trend of the educational quality of this course through the following formula:
[0044] where, represents the number of class hours included in the longest continuously positively changing period; represents the total number of class hours in this semester; m represents the slope of the change curve of the educational quality measurement factor within the longest continuously positively changing period; t represents the number of class hours included in the longest continuously negatively changing period. It should be noted that if there are no class hours with decreasing quality, .
[0045] Furthermore, determine the final characteristic value of the dynamic change trend according to the magnitudes of all the educational quality measurement factors in the sequence of educational quality measurement factors :
[0046] Where D1 represents the mean and dynamic trend characteristic value of all education quality measurement factors in the entire semester's education quality measurement factor sequence. It can reflect the fluctuations and development trends in the quality of course instruction throughout the semester.
[0047] Furthermore, the educational quality assessment characteristics of this course... It can be represented as:
[0048] Where n1 represents the average final grade of all students who have taken the course; q0 represents the total number of students who have taken the course; and q represents the number of students who have passed the final grade. The final grades represent the teaching quality index. A larger value indicates that the final exam results are objective and the overall teaching effect is good. This is indicated by the use of dynamic trend characteristic values. The teaching quality reflected in the final grades is adjusted and revised to obtain the final educational quality assessment characteristic value for the course. ; The larger the value, the higher the educational quality of the course, the higher the student's learning continuity, the better the course participation, and the steady improvement in educational quality. The smaller the number of hours, the more deficiencies there are in the teaching process and results, indicating that the quality of education needs to be improved and that teaching needs further optimization.
[0049] S14. Based on the course's educational quality assessment characteristic values, conduct a comprehensive assessment of the course's educational quality throughout the semester.
[0050] First, define the preset threshold for education quality assessment. This threshold can be determined based on educational standards, curriculum type, and historical data, and is used to classify education quality levels. Specifically, the preset threshold for education quality assessment can be 0.6, but it can also be adjusted according to actual needs. A score ≥0.6 indicates that the course's educational quality is high, meaning the course maintains stable teaching effectiveness throughout the semester, promotes continuous student participation and progress, and achieves good final grades. If the educational quality assessment characteristic value is lower, the course is considered to have high educational quality. If the value is less than 0.6, the course is considered to have low educational quality, indicating that there may be problems such as unreasonable content design and insufficient interactive guidance in the course, resulting in low student participation and weak knowledge acquisition. It is necessary to optimize the teaching methods and course content in a targeted manner.
[0051] It should be noted that the device provided in the above embodiments is only an example of the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above.
[0052] Figure 2 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. For example, as shown... Figure 2 As shown, the computer device 20 includes: a memory 21, a processor 22, and a computer program 23 stored in the memory 21 and running on the processor 22, wherein when the processor 22 executes the computer program 23, the computer device can execute any of the aforementioned educational quality assessment methods based on multi-source data fusion and statistical hypothesis testing.
[0053] Furthermore, embodiments of the present invention also protect an apparatus that may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to perform the education quality assessment method based on multi-source data fusion and statistical hypothesis testing provided in the embodiments of the present invention.
[0054] In this embodiment of the invention, the device can be divided into functional modules according to the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and is only a logical functional division. In actual implementation, there may be other division methods.
[0055] It should be understood that the apparatus provided in this embodiment of the invention is used to perform the above-described method for evaluating educational quality based on multi-source data fusion and statistical hypothesis testing, and therefore can achieve the same effect as the above-described implementation method.
[0056] When using integrated units, the device may include a processing module and a storage module. When applied to a device, the processing module can be used to control and manage the device's operations. The storage module can be used to support the device in executing program code, etc. The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits as described in this disclosure. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of Digital Signal Processing (DSP) and a microprocessor, etc., and the storage module may be a memory.
[0057] In addition, the device provided in the embodiments of the present invention may specifically be a chip, component or module. The chip may include a connected processor and a memory. The memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute the education quality assessment method based on multi-source data fusion and statistical hypothesis testing provided in the above embodiments.
[0058] This invention also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the aforementioned method steps to implement the education quality assessment method based on multi-source data fusion and statistical hypothesis testing provided in the above embodiments.
[0059] This invention also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to implement the education quality assessment method based on multi-source data fusion and statistical hypothesis testing provided in the above embodiments.
[0060] In this invention, the apparatus, computer-readable storage medium, computer program product, or chip provided in the embodiments are all used to execute the corresponding methods described above. Therefore, the beneficial effects they achieve can be referred to the beneficial effects in the corresponding methods described above, and will not be repeated here. Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by this invention, it should be understood that the disclosed apparatus and method can be implemented in other ways.
[0061] The device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.
[0062] It should also be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.
[0063] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0064] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.
[0065] The above content is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the protection scope of the present invention.
Claims
1. An educational quality assessment method based on multi-source data fusion and statistical hypothesis testing, characterized in that, The method includes the following steps: For each course, multi-source learning data is collected from all students who have enrolled in that course. Based on the collected multi-source learning data, calculate each student's real-time learning performance indicators and classroom participation performance indicators for each course. By combining the real-time learning performance indicators and the classroom participation performance indicators, the educational quality measurement factors for each course are determined. Construct a sequence of educational quality measurement factors for the entire semester according to the order of class hours, analyze the dynamic change trend of the educational quality measurement factor sequence, obtain the dynamic change trend characteristic value, and correct the dynamic change trend characteristic value in combination with the final grade data to obtain the course educational quality assessment characteristic value. The overall educational quality of the course throughout the semester is comprehensively evaluated based on the course's educational quality assessment characteristic values.
2. The method for evaluating educational quality based on multi-source data fusion and statistical hypothesis testing according to claim 1, characterized in that, The process involves collecting multi-source learning data from all students enrolled in each course, including: For each course, a pre-set learning management system is used to monitor each student's video viewing behavior data, interaction behavior data, after-class exercise data, and final grade data.
3. The method for evaluating educational quality based on multi-source data fusion and statistical hypothesis testing according to claim 2, characterized in that, The calculation of real-time learning performance indicators for each student in each course based on the collected multi-source learning data includes: Extract the effective viewing time from the video viewing behavior data; The total number of exercises for each course, the time each student spent completing the exercises, and the accuracy rate of the exercises were determined from the after-class exercise data. By combining the effective viewing time, the time spent completing the after-class exercises, and the accuracy rate of the after-class exercises, an instant learning performance index for each student for each course is calculated.
4. The method for evaluating educational quality based on multi-source data fusion and statistical hypothesis testing according to claim 2, characterized in that, Based on the collected multi-source learning data, classroom participation performance indicators for each student in each course are calculated, including: For each course, keywords and text fragments are extracted as reference text based on the corresponding teaching content. Using text similarity algorithms in natural language processing, the similarity between each student's interactive behavior data for the course and the reference text is calculated; Based on the preset similarity judgment criteria, the number of interactive behaviors of each student in relation to the course that meet the similarity judgment criteria is counted, and the average similarity between the interactive behaviors and the reference text is calculated. By combining the number of interactive behaviors and the average similarity, a classroom participation performance index for each student in each course is calculated.
5. The method for evaluating educational quality based on multi-source data fusion and statistical hypothesis testing according to claim 1, characterized in that, Also includes: Obtain real-time learning performance metrics for each student for each course; Obtain each student's classroom participation performance metrics for each course; By combining the real-time learning performance indicators and the classroom participation performance indicators, a comprehensive performance characteristic value for each student for each course is determined.
6. The method for evaluating educational quality based on multi-source data fusion and statistical hypothesis testing according to claim 5, characterized in that, The method of combining the real-time learning performance indicators and the classroom participation performance indicators to determine the educational quality measurement factors for each course includes: Determine the overall performance characteristics of each student for each course; Based on the pre-set comprehensive performance characteristic value judgment standard, all students enrolled in each course are divided into those who meet the standard and those who do not meet the standard. Count the total number of students who meet the standard category in each course, and calculate the mean of the comprehensive performance characteristic values of all students who meet the standard category in each course; The educational quality measurement factors for each course are determined by combining the proportion of students who meet the standard category to the total number of students, as well as the average comprehensive performance characteristic value of students who meet the standard category.
7. The method for evaluating educational quality based on multi-source data fusion and statistical hypothesis testing according to claim 1, characterized in that, The process involves constructing a sequence of educational quality measurement factors for the entire semester according to the order of class hours, analyzing the dynamic trends of these factors, and obtaining characteristic values of the dynamic trends, including: Collect educational quality measurement factors for each lesson of the same course taught by the same teacher to the same class throughout the entire semester; According to the time sequence of the course's class schedule throughout the semester, the educational quality measurement factors corresponding to each class are arranged sequentially to construct the full semester educational quality measurement factor sequence for the course. Identify consecutive negative and consecutive positive change periods from the sequence of educational quality measurement factors for the entire semester, determine the number of class hours included in the longest consecutive positive change period, the number of class hours included in the longest consecutive negative change period, and the slope of the change curve of educational quality measurement factors within the longest consecutive positive change period, and calculate the dynamic change trend characteristic value of the course educational quality. Calculate the mean of all education quality measurement factors in the entire semester education quality measurement factor sequence, and use it as the measurement mean; Based on the measured mean, the calculated dynamic trend characteristic values are normalized to obtain the final dynamic trend characteristic values.
8. The method for evaluating educational quality based on multi-source data fusion and statistical hypothesis testing according to claim 7, characterized in that, The process of identifying periods of continuous negative change and periods of continuous positive change from the sequence of educational quality measurement factors for the entire semester includes: Calculate the difference between two adjacent education quality measurement factors in the entire semester education quality measurement factor sequence; Based on the preset difference judgment criteria, the class hours corresponding to all education quality measurement factors in the whole semester education quality measurement factor sequence are divided into class hours with declining quality and class hours with improving quality. Two or more adjacent periods of declining quality are defined as a period of continuous negative change, and the number of periods contained in the longest period of continuous negative change is recorded. Two or more adjacent periods of improved quality are defined as a continuous positive change period, and the number of periods contained in the longest continuous positive change period is recorded.
9. The method for evaluating educational quality based on multi-source data fusion and statistical hypothesis testing according to claim 1, characterized in that, The dynamic trend characteristic value is corrected by combining the final exam data to obtain the course teaching quality assessment characteristic value, including: Collect the final grades of all students who have taken the same course; Calculate the average final exam score for all students enrolled in the course based on the final exam score data. Calculate the final exam pass rate for all students who enrolled in the course. By combining the average final exam score and the final exam pass rate, the teaching quality index reflected by the final exam score is determined. The dynamic trend feature value is integrated with the teaching quality index for calculation, and the dynamic trend feature value is corrected to obtain the course education quality assessment feature value.
10. The method for evaluating educational quality based on multi-source data fusion and statistical hypothesis testing according to claim 1, characterized in that, The comprehensive evaluation of the course's overall educational quality throughout the semester, based on the course's educational quality assessment characteristic values, includes: Define and pre-set thresholds for education quality assessment; If the course education quality assessment feature value is greater than or equal to the education quality assessment threshold, then the course education quality corresponding to the course education quality assessment feature value is determined to be high. If the course education quality assessment characteristic value is less than the education quality assessment threshold, then the course education quality corresponding to the course education quality assessment characteristic value is determined to be low.