Course multi-dimensional achievement degree evaluation method and system based on process evaluation management

Abstract

The invention relates to the technical field of student course evaluation, and relates to a course multi-dimensional achievement degree evaluation method and system based on process evaluation management, and the method comprises the steps: collecting a plurality of process learning indexes of students; performing standard normalization processing on each process learning index to obtain a process learning score; performing weighted summation on the process learning scores to obtain a formative score; obtaining scores of a plurality of questions of the student in the assessment, wherein each question is configured with the category label; obtaining association strength between each knowledge point and each question; determining a mastering score of each knowledge point of the student; performing weighted summation on the mastering scores of all the knowledge points to obtain an end score; obtaining a plurality of data sets; calculating a target evaluation score; and outputting the formative score, the end score and the target score. According to the invention, comprehensive evaluation is carried out from multiple dimensions, so that the student effect can be reflected more comprehensively.

Description

Technical Field

[0001] The present invention relates to the technical field of student course evaluation, and more specifically, to a multi-dimensional course achievement evaluation method and system based on process evaluation management. Background Art

[0002] As global education reforms deepen, modern educational philosophies are gradually shifting from traditional knowledge-transferring approaches to cultivating students' comprehensive competencies. Educational goals are no longer limited to memorization; they emphasize the development of diverse abilities, including knowledge application, practical application, innovative thinking, and learning attitudes. Against this backdrop, a series of educational policy adjustments, including the core competency framework advocated by international education organizations and revisions to program structures and curriculum standards, have emphasized a focus on students' learning processes and holistic development.

[0003] Traditional student assessment and evaluation methods, often based primarily on final exam scores, present numerous drawbacks. For one thing, it fails to fully reflect a student's level of effort, knowledge acquisition, and ability development throughout the entire learning process. Furthermore, it can easily lead to students becoming less motivated to study during the regular semester and focusing on cramming at the end of the semester, hindering the development of their overall quality and independent learning abilities.

[0004] In the context of the continuous updating of educational concepts, the emphasis on student-centeredness and ability training, there is an urgent need for a method and system that can comprehensively, objectively and dynamically evaluate students' learning processes and outcomes. The Chinese invention patent application document with publication number CN118469393A discloses a teaching management method and system, including: obtaining a course data set, constructing a teaching management data table, calculating teaching objective parameters, determining the teaching quality information of the target course, generating a visual teaching page, and triggering the response action of the visual teaching page to calculate the achievement of different course goals. The Chinese invention patent application document with publication number CN115375166A discloses a higher education student ability achievement evaluation system based on quantitative calculation, and the teacher end includes: a course achievement evaluation mechanism unit, a course achievement quantitative calculation unit, which normalizes the course requirement indicators and ignores courses with little relevance to graduation requirements, so that students have a clearer understanding of themselves.

[0005] Existing course assessment methods rely heavily on final exams, reducing a semester's learning outcomes to a single test score. This results in a lack of process-based and comprehensive evaluation of student knowledge. Final exams often fail to cover all the key points from the entire semester. Students may achieve high scores due to a cramming session on key content, but their understanding and mastery of other knowledge modules may not be solid. Summary of the Invention

[0006] In order to solve the above-mentioned technical problem that it is difficult to judge the degree of students' knowledge mastery based on the results of only one assessment, the present invention provides solutions in the following aspects.

[0007] In a first aspect, a multi-dimensional achievement evaluation method for a course based on process evaluation management is characterized by comprising: collecting multiple process learning indicators of students; performing standard normalization processing on each process learning indicator to obtain a process learning score; performing weighted summation on each process learning score to obtain a formative score; obtaining scores of multiple questions in the assessment of students; obtaining the strength of association between each knowledge point and each question; determining the mastery score of each knowledge point of the students, wherein the calculation of the first i Knowledge point mastery score The formula is: , For the j Title and i The strength of the association between knowledge points, For the j The score of the question, n is the number of all questions; performing weighted summation on the mastery scores of all knowledge points to obtain a summative score; performing weighted summation on the formative score and the summative score to obtain a multi-dimensional score.

[0008] Preferably, obtaining the correlation strength between each knowledge point and each question includes: obtaining the initial correlation strength between each knowledge point and each question; obtaining the historical scores of all questions in the assessment of multiple students; comparing the initial correlation strength between each knowledge point and each question to obtain the correlation strength between the knowledge point and the question, wherein the correlation strength between the first knowledge point and the question is obtained. i Knowledge point and j The initial correlation strength between the The correction formula is: ,in For the k The first student in the assessment j The historical scores of the questions, norm () is the standard normalization function.

[0009] Preferably, i The formula for standard normalization of process learning indicators is: ,in For students i The value of the process learning indicator, For the preset i The maximum value corresponding to the learning indicator of each process.

[0010] Preferably, collecting multiple process learning indicators of students includes collecting students' online learning time, class attendance rate and number of times they participate in discussions.

[0011] Preferably, the formula for weighted summation of the mastery scores of all knowledge points is: ,in For the i Knowledge point mastery score The preset size of the weight, m is the number of all knowledge points, B Score the summativeness.

[0012] Preferably, weighted summing of the process learning scores and the scores of the questions of the process learning indicators in each target data set includes: obtaining the importance weight preset for each target data set; and calculating the target evaluation score: .

[0013] in For the r The importance weight of the target dataset, For the r The target dataset t The weight of the score of each question, For the r The target dataset t Process learning scores for process learning indicators, T r For the r The number of questions in the target dataset, X r For the r The number of process learning indicators in the target dataset, R is the number of all target data sets, C is the target evaluation score, Learning metric weights for a process of preset size, The weight of the topic is the preset size.

[0014] Optimally, process learning indicator weights The value is 0.4, the topic weight The value of is 0.6.

[0015] Preferably, a multi-dimensional course achievement evaluation method based on process evaluation management further includes: visualizing the students' mastery scores of each knowledge point to obtain a first heat map of the students, and outputting the first heat map.

[0016] Preferably, a multi-dimensional achievement evaluation method for a course based on process evaluation management further includes: visualizing the process learning scores corresponding to each process learning indicator of the student to obtain a second heat map of the student, and outputting the second heat map.

[0017] In the second aspect, a course multidimensional achievement evaluation system based on process evaluation management includes a processor and a memory, the memory stores a computer program, and the processor executes the computer program to implement a course multidimensional achievement evaluation method based on process evaluation management as described in any one of the above invention contents.

[0018] The beneficial effects of the present invention are: This invention uses comprehensive evaluation from multiple dimensions to more comprehensively and scientifically reflect students' learning process and outcomes. The multi-dimensional evaluation scores obtained by the indicator system and weight setting can accurately judge students' course learning status and then formulate appropriate learning plans for students. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an illustrative and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 is a flowchart schematically illustrating the steps of a method for evaluating multidimensional achievement of a course based on process evaluation management according to an embodiment of the present invention; Figure 2 is a first heat map schematically illustrating an embodiment of the present invention; Figure 3 It is a structural block diagram schematically showing a course multi-dimensional achievement evaluation system based on process evaluation management according to this embodiment. DETAILED DESCRIPTION

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0021] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0022] Figure 1 The present invention is a flowchart schematically illustrating a method for evaluating the multidimensional achievement of a course based on process evaluation management according to an embodiment of the present invention.

[0023] like Figure 1 As shown, a method for evaluating the multidimensional achievement of a course based on process evaluation management includes steps S1 to S6.

[0024] Step S1: Collect multiple process learning indicators of students.

[0025] Each process learning indicator is assigned a preset category label, of which there are multiple types. In one embodiment, the multiple category labels include: literacy development labels, ability development labels, and value development labels. The category labels for process learning indicators are determined by experts.

[0026] In one embodiment, collecting a plurality of process learning indicators of students includes collecting students' online learning time, class attendance rate, and number of times they participate in discussions.

[0027] It's important to note that process learning indicators reflect students' engagement and involvement in the learning process. Online learning time refers to the amount of time students spend learning online on a platform or learning management system. Class attendance refers to students' participation in face-to-face or virtual classes. Discussion participation refers to students' involvement in class discussions or online forums. High attendance indicates that students attend classes on time and actively participate in learning activities, a key indicator of academic success.

[0028] Step S2: Perform standard normalization processing on each process learning indicator to obtain a process learning score.

[0029] In one embodiment, i The formula for standard normalization of process learning indicators is: ,in For students i The value of the process learning indicator, For the preset i The maximum value corresponding to the learning indicator of each process.

[0030] It's important to note that each process learning indicator has a preset maximum value. For example, the maximum online learning time is the total number of class hours, the maximum class attendance rate is 100%, and the maximum number of discussion participation is the maximum number of discussions specified in the course. After normalization, the scores of all process learning indicators are placed on the same scale (usually between 0 and 1). These scores are then combined using a weighted average to produce a student's overall learning score (the formative assessment calculated later).

[0031] Furthermore, the present invention also includes: visualizing the process learning scores corresponding to each process learning indicator of the student to obtain a second heat map of the student, and outputting the second heat map. The heat map is used to present the student's performance in each learning link, and the depth of color is used to represent the level of the score. Teachers can quickly identify which students perform poorly in certain links and which links have higher scores, and then conduct a comprehensive evaluation of the student's learning based on the multi-dimensional evaluation score. In other embodiments, the process learning scores corresponding to each process learning indicator of the student are reflected through a network graph, radar chart, scatter plot or box plot.

[0032] Network diagrams are suitable for displaying the relationships between students' various learning process indicators. For example, they can show the mutual influence between different learning indicators or the performance patterns of students in different tasks. Each node can represent a student or a learning indicator, and the connections between nodes represent their correlations. Network diagrams are suitable for displaying the relationships between students' various learning process indicators. For example, they can show the mutual influence between different learning indicators or the performance patterns of students in different tasks. Each node can represent a student or a learning indicator, and the connections between nodes represent their correlations. Scatter plots are used to display the relationship between two variables. In student learning data, scatter plots can be used to display the correlation between certain learning process indicators, such as student study time and grades, learning engagement, and ratings. Boxplots are used to display data distribution, deviation, outliers, etc. In the scenario of student learning process ratings, boxplots can be used to analyze the score distribution of each learning indicator, such as the median, quartiles, and the presence of outliers.

[0033] It should be noted that visualizing the process learning scores corresponding to each process learning indicator of the students can more intuitively show the differences in students' performance in the learning dimensions corresponding to each process learning indicator. A heatmap is a data image that displays data distribution through color depth, and is often used to represent data in matrix form. In the present invention, a heatmap displays students' scores on different learning process indicators through color gradients. Before generating a heatmap, the data needs to be preprocessed to ensure that the process learning scores have been standardized and are within a unified scale. The preprocessing process includes steps such as data denoising. The scores of students in each learning link will be filled in the matrix of the heatmap according to their standardized values, and the depth or brightness of the color will be mapped according to the level of the score.

[0034] Step S3: Perform weighted summation on the process learning scores to obtain the formative score.

[0035] In one embodiment, the formula for weighted summation of learning scores of each process is: ,in For the p The process learns the weight of the score, A For the summative score, For the p The weight of each process learning score is preset.

[0036] Step S4: Obtain the student's scores for multiple questions in the assessment; obtain the strength of association between each knowledge point and each question; and determine the student's mastery score for each knowledge point.

[0037] Each question is assigned a category label, which is the same as the category label of the process learning indicator.

[0038] Among them, calculate the i Knowledge point mastery score The formula is: , For the j Title and i The strength of the association between knowledge points, For the j The score of the question, n is the number of all questions.

[0039] In one embodiment, obtaining the association strength between each knowledge point and each question includes: obtaining the initial association strength between each knowledge point and each question; obtaining the historical scores of all questions in the assessment of multiple students; comparing the initial association strength between each knowledge point and each question to obtain the association strength between the knowledge point and the question, wherein the association strength between the first knowledge point and the question is obtained. i Knowledge point and j The initial correlation strength between the The correction formula is:

[0040] .

[0041] in For the k The first student in the assessment j The historical scores of the questions, norm () is the standard normalization function.

[0042] It should be noted that this invention uses students' historical score data to weight the initial correlation strength between knowledge points and questions. Since students' high scores are primarily due to their mastery of the corresponding knowledge points, if students generally score high on a particular question (indicating a strong correlation between the question and the knowledge point), the correlation strength between the question and the corresponding knowledge point will be strengthened; otherwise, the correlation strength will be weakened.

[0043] Furthermore, knowledge points are typically specific learning content in the course syllabus, including concepts, principles, techniques, and methods. Questions are specific assessment content, including multiple-choice questions, fill-in-the-blank questions, and short-answer questions. In one embodiment, determining the initial correlation strength between each knowledge point and each question includes steps S401 to S403.

[0044] Step S401: Construct a relationship matrix between knowledge points and questions. Each question involves multiple knowledge points, so it is necessary to determine the initial degree of association between each question and each knowledge point. The strength of this association is determined by the following method: invite senior teachers and education experts in the course field to conduct a review and judge the strength of the association between each knowledge point and the question. For each question, experts can evaluate the importance and relevance of the question in examining a specific knowledge point. Weight allocation: The strength of the association between each knowledge point and the question can be represented by a number (usually between 0 and 1). For example, if a multiple-choice question completely examines a certain knowledge point, the strength of the association can be set to 1; if it partially involves the knowledge point, it can be set to a smaller value, such as 0.5 or 0.3. The specific value is determined by the expert.

[0045] Step S402: Using the Analytic Hierarchy Process (AHP), experts assess the initial correlation strength between each knowledge point and the question. For example, for a multiple-choice question, experts need to determine whether it covers multiple knowledge points and assess the weight of each knowledge point. For example, multiple-choice question A (regarding basic formula application) primarily tests knowledge point X (formula memorization), with a correlation strength of 0.8; multiple-choice question A also touches on knowledge point Y (formula application), but the relationship is weaker, with a correlation strength of 0.2; multiple-choice question B (regarding formula derivation) primarily tests knowledge point X (formula derivation), with a correlation strength of 1.

[0046] Step S403: Through expert judgment, comprehensively evaluate each question's contribution to each knowledge point. During this process, the question's direct impact on the knowledge point should be considered. For example, if a question directly tests a certain knowledge point, it will have a higher score weight and a greater correlation strength. In this way, an initial correlation strength matrix for each question and each knowledge point is obtained.

[0047] Step S404: After obtaining the preliminary correlation matrix, it is necessary to make reasonable adjustments to ensure that the weights and ratios between each knowledge point and each question are reasonable. For example, if certain knowledge points appear frequently in multiple questions, their weights can be adjusted appropriately to make the final evaluation system more fair and accurate.

[0048] Furthermore, the present invention includes: visualizing the student's mastery scores for each knowledge point to obtain a first heat map of the student, and outputting the first heat map. In one embodiment, the student's mastery scores for each knowledge point are visualized using data visualization tools and libraries (e.g., Matplotlib or Seaborn in Python) to obtain the first heat map, and the process learning scores corresponding to each process learning indicator are visualized to obtain a second heat map.

[0049] like Figure 2 As shown in the figure, the first heat map includes the mastery scores corresponding to 20 knowledge points. Among them, the knowledge points with high mastery scores correspond to the darker part of the heat map (that is, the grayscale value is larger). Based on this, teachers can more intuitively observe the students' mastery of knowledge points, and then determine the students' learning situation in combination with multi-dimensional evaluation scores.

[0050] Step S5: Perform weighted summation based on the mastery scores of all knowledge points to obtain a final score.

[0051] In one embodiment, the formula for weighted summation of the mastery scores of all knowledge points is: ,in For the i Knowledge point mastery score The preset size of the weight, m is the number of all knowledge points, B Score the summativeness.

[0052] Step S6: Obtain multiple data sets, and select a preset number of data sets from the multiple data sets according to the teacher's needs, and record them as target data sets; perform weighted summation on the process learning scores and question scores of the process learning indicators in each target data set to obtain the target evaluation score.

[0053] Among them, r The dataset includes r The process of learning metrics and topics for class labels.

[0054] In one embodiment, weighted summing of the process learning scores and the scores of the questions of the process learning indicators in each target data set includes: obtaining the importance weight preset for each target data set; and calculating the target evaluation score: .

[0055] in For the r The importance weight of the target dataset, For the r The target dataset t The weight of the score of each question, For the r The target dataset t Process learning scores for process learning indicators, T r For the r The number of questions in the target dataset, X r For the r The number of process learning indicators in the target dataset, R is the number of all target data sets, C is the target evaluation score, Learning metric weights for a process of preset size, is the preset weight of the question. Among them, the process learning indicator weight The value is 0.4, the topic weight The value of is 0.6.

[0056] It should be noted that the present invention selects the desired target dataset from all datasets based on the teacher's needs, and further selects the process learning indicators and question scores for evaluating student literacy. The labels of the process learning indicators and questions in each dataset are the same.

[0057] For example, if the number of all data sets is 3, namely, a data set consisting of process learning indicators and questions with the label "literacy development", a data set consisting of process learning indicators and questions with the label "ability development", and a data set consisting of process learning indicators and questions with the label "value development", and the teacher expects to obtain evaluation scores based on both literacy development and value development, then the data sets corresponding to the literacy development label and the value development label are selected as the target data sets, only for calculating the target evaluation score.

[0058] Step S7: Output the formative score, summative score and target score.

[0059] It should be noted that teachers obtain the formative scores, summative scores and target scores to achieve multi-dimensional evaluation.

[0060] Figure 3 It is a structural block diagram schematically showing a course multi-dimensional achievement evaluation system based on process evaluation management according to this embodiment.

[0061] The present invention also provides a course multi-dimensional achievement evaluation system based on process evaluation management. Figure 3 As shown, the system includes a processor and a memory, and the memory stores computer program instructions. When the computer program instructions are executed by the processor, a multidimensional achievement evaluation method of a course based on process evaluation management according to the first aspect of the present invention is implemented.

[0062] The system also includes other components well known to those skilled in the art, such as a communication interface, and the configuration and functions of which are known in the art, so they will not be described in detail here.

[0063] In the description of this specification, "multiple" and "several" mean at least two, such as two, three or more, etc., unless otherwise clearly defined.

[0064] In the present invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, the computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application, module, or both. Any such computer storage medium can be part of, accessible to, or connectable to a device. Any application or module described in the present invention can be implemented using computer-readable / executable instructions that can be stored or otherwise maintained by such a computer-readable medium.

[0065] While several embodiments of the present invention have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous modifications, variations, and alternatives will occur to those skilled in the art without departing from the concept and spirit of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in practicing the present invention.

Claims

1. A multi-dimensional course achievement evaluation method based on process evaluation management, characterized by: include: Collecting multiple process learning indicators of students, wherein each process learning indicator is configured with a preset category label, and the category labels are multiple; Perform standard normalization on each process learning indicator to obtain the process learning score; The weighted sum of each process learning score is used to obtain the formative score; Obtain the scores of the students for multiple questions in the assessment, wherein each question is configured with the category label; obtain the correlation strength between each knowledge point and each question; determine the mastery score of each knowledge point of the students, wherein the first i Knowledge point mastery score The formula is: , For the j Title and i The strength of the association between knowledge points, For the j The score of the question, n is the number of all questions; The mastery scores of all knowledge points are weighted and summed to obtain the final score; A plurality of data sets are obtained, wherein the xth data set includes process learning indicators and questions configured with xth category labels; a preset number of data sets are screened from the plurality of data sets according to the teacher's needs and recorded as target data sets; a weighted summation of the process learning scores of the process learning indicators and the scores of the questions in each target data set is performed to obtain a target evaluation score; The formative scores, summative scores and target scores are output.

2. A multi-dimensional course achievement evaluation method based on process evaluation management according to claim 1, characterized in that: Obtaining the strength of the association between each knowledge point and each question includes: Obtain the preset initial correlation strength between each knowledge point and each question; Get the historical scores of all questions in the assessment for multiple students; The initial correlation strength between each knowledge point and each question is used to obtain the correlation strength between the knowledge point and the question. i Knowledge point and j The initial correlation strength between the The correction formula is: ； in For the k The first student in the assessment j The historical scores of the questions, norm () is the standard normalization function.

3. The multi-dimensional achievement evaluation method of a course based on process evaluation management according to claim 1 is characterized in that: For the first i The formula for standard normalization of process learning indicators is: ,in For students i The value of the process learning indicator, For the preset i The maximum value corresponding to the learning indicator of each process.

4. A multi-dimensional course achievement evaluation method based on process evaluation management according to claim 3, characterized in that: Collecting multiple process learning indicators of students includes: collecting students' online learning time, class attendance rate and number of times they participate in discussions.

5. The multi-dimensional achievement evaluation method of a course based on process evaluation management according to claim 1 is characterized in that: The formula for weighted summation based on the mastery scores of all knowledge points is: ,in For the i Knowledge point mastery score The preset size of the weight, m is the number of all knowledge points, B Score the summativeness.

6. The multi-dimensional achievement evaluation method of a course based on process evaluation management according to claim 1 is characterized in that: The weighted summation of the process learning scores and the scores of the questions of the process learning indicators in each target data set includes: Obtain the preset importance weights of each target data set; Calculate the target evaluation score: ,in For the r The importance weight of the target dataset, For the r The target dataset t The weight of the score of each question, For the r The target dataset t Process learning scores for process learning indicators, T r For the r The number of questions in the target dataset, X r For the r The number of process learning indicators in the target dataset, R is the number of all target data sets, C is the target evaluation score, Learning metric weights for a process of preset size, The weight of the topic is the preset size.

7. A multi-dimensional course achievement evaluation method based on process evaluation management according to claim 6, characterized in that: Process learning indicator weight The value is 0.4, the topic weight The value of is 0.

6.

8. The multi-dimensional achievement evaluation method of a course based on process evaluation management according to claim 1 is characterized in that: Also includes: The mastery scores of the students' knowledge points are visualized to obtain a first heat map of the students, and the first heat map is output.

9. The multi-dimensional achievement evaluation method of a course based on process evaluation management according to claim 1 is characterized in that: Also includes: The process learning scores corresponding to the process learning indicators of the students are visualized to obtain a second heat map of the students, and the second heat map is output.

10. A course multi-dimensional achievement evaluation system based on process evaluation management, comprising a processor and a memory, wherein the memory stores a computer program, characterized in that: The processor executes the computer program to implement a multi-dimensional achievement evaluation method for a course based on process evaluation management as described in any one of claims 1 to 9.

Images