Course goal achievement degree analysis and evaluation method based on artificial intelligence

Abstract

The invention discloses a course goal achievement degree analysis and evaluation method based on artificial intelligence, and relates to the technical field of course evaluation, and the method comprises the steps: obtaining the performance score of a student in each stage based on a stage goal, and obtaining the examination score of the student during course examination based on the course goal; performing mean value calculation on the performance scores of the same student to obtain a performance mean value; carrying out discreteness analysis on the expression mean value to obtain a discrete coefficient; filtering the students based on the discrete coefficient to obtain a screened student list; based on the screened student list, inputting the performance scores and the examination scores of the students on the list into a built-in evaluation model to obtain course achievement degree data; evaluating and analyzing the course achievement degree data to obtain an evaluation report; and outputting the performance score, the examination score, the course achievement data and the evaluation report of the student based on a built-in course goal achievement report output format. The method has the effect of improving the accuracy of the evaluation result.

Description

Technical Field

[0001] The present application relates to the technical field of course evaluation, and in particular to an artificial intelligence-based course goal achievement analysis and evaluation method. Background Art

[0002] Course objectives refer to the expected results in terms of knowledge, skills and attitudes that students should achieve after completing their studies in a course. The analysis and evaluation of course goal achievement is to evaluate whether students have achieved the predetermined learning objectives and learning outcomes during the course learning process, thereby reflecting the students' learning situation and improving the teaching quality.

[0003] In related technologies, teachers determine graduation requirements based on professional training programs, and determine course objectives based on graduation requirements. Corresponding assessment methods are set based on course objectives, such as regular performance scores and test scores. By determining the weights of each assessment method, the scores of each assessment method are weighted and calculated to obtain the average, thereby obtaining the corresponding course objective achievement degree.

[0004] Regarding the above-mentioned related technologies, the weights of students' academic performance at different stages of the course objectives are simply calculated, and then the weighted calculation results are averaged, which makes the evaluation results inaccurate and unable to reflect the students' actual learning situation. There is room for improvement. Summary of the invention

[0005] In order to improve the accuracy of the evaluation results, this application provides an artificial intelligence-based course goal achievement analysis and evaluation method.

[0006] In the first aspect, the present application provides a course goal achievement analysis and evaluation method based on artificial intelligence, which adopts the following technical solutions:

[0007] A course goal achievement analysis and evaluation method based on artificial intelligence, comprising:

[0008] Get the teacher's course objectives and the corresponding course stage objectives in the blockchain;

[0009] Obtain students' performance scores at each stage based on stage goals, and obtain students' test scores during course assessments based on course goals;

[0010] The performance scores of the same student at each stage were averaged to obtain the performance mean;

[0011] Conduct a dispersion analysis on the performance mean of each student to determine the dispersion degree of the performance mean of each student relative to the performance score of the entire student group, and record it as the dispersion coefficient;

[0012] Filter students based on the dispersion coefficient to obtain a list of screened students;

[0013] Acquire the actual test questions actually taken by the students, and make knowledge point judgments and logical thinking judgments on the actual test questions based on the evaluation model, so as to determine the knowledge point data involved in each question in the actual test questions, the application thinking marks of the corresponding knowledge points, and the thinking weighting coefficients under the corresponding application thinking marks; the application thinking marks of the knowledge points include forward thinking marks and reverse thinking marks; the thinking weighting coefficients include forward thinking weighting coefficients and reverse thinking weighting coefficients;

[0014] Obtain the students' answer questions, and make knowledge point judgments and logical thinking judgments on the answer questions according to the test scores of the students in the screened student list, and make positive thinking weighting and / or reverse thinking weighting on the students' test scores according to the applied thinking marks to determine the students' course achievement of the course, and output the course achievement data;

[0015] Evaluate and analyze the course achievement data and obtain an evaluation report;

[0016] Output student performance scores, test scores, course achievement data and evaluation reports based on the built-in course goal achievement report output format.

[0017] Preferably, obtaining test question data in a training set and standard answer data corresponding to the test question data;

[0018] Based on the application thinking of knowledge points, the test data is divided into positive test questions and reverse test questions; positive test questions are the direct application of knowledge points, and reverse test questions are the reverse application of knowledge points;

[0019] Perform text language understanding on the test data to obtain understanding data;

[0020] Extract knowledge points from the standard answer data to obtain knowledge point data;

[0021] Based on the applied thinking of knowledge points, the positive test questions and their corresponding understanding data and knowledge point data are logically constructed into the evaluation model to obtain positive thinking marks;

[0022] Based on the applied thinking of knowledge points, the reverse test questions and their corresponding understanding data and knowledge point data are used to construct the evaluation model through logical thinking to obtain the reverse thinking mark;

[0023] A test set is obtained, and the test question data in the test set and the standard answer data corresponding to the test question data are input into the evaluation model. The evaluation model performs text language understanding and logical thinking judgment on the test question data in the test set, obtains the knowledge points involved in each test question data and the application thinking of the corresponding knowledge points, and records them as the first knowledge point data and the first logical thinking data;

[0024] The evaluation model extracts knowledge points and makes logical thinking judgments on the standard answer data in the test set to obtain second knowledge point data and second logical thinking data;

[0025] Compare the first knowledge point data with the second knowledge point data, and compare the first logical thinking data with the second logical thinking data, so as to screen out test question data in the test set that satisfies the conditions that the first knowledge point data is the same as the second knowledge point data and the first logical thinking data is the same as the second logical thinking data, and record the test question data as the test question data to be analyzed;

[0026] According to logical thinking, the question scores of the test data to be analyzed under the same logical thinking and the same knowledge point are counted, and the ratio of positive thinking marks to reverse thinking marks in the same test data to be analyzed is obtained, and recorded as the mean value of thinking proportion;

[0027] Based on the mean value of thinking proportion, the scores of knowledge points under different applied thinking marks are weighted to obtain a thinking weighting coefficient; the thinking weighting coefficient includes a positive thinking weighting coefficient and a reverse thinking weighting coefficient.

[0028] Preferably, the student's answer questions are obtained and the test scores are matched with the answer questions to determine the student's score for each question in the answer questions, and the student's score for each question is recorded as question score data;

[0029] The students' question score data are counted and screened to screen out questions that have not received full marks among the student group, and the questions are recorded as questions to be evaluated;

[0030] The evaluation model extracts knowledge points and makes logical thinking judgments on the questions to be evaluated, so as to determine the knowledge point data involved in the corresponding questions and the application thinking marks of the corresponding knowledge points;

[0031] Generate an answer to the question based on the knowledge point data obtained by judgment and the application thinking mark of the corresponding knowledge point to obtain a simulated answer;

[0032] Obtaining the actual test questions and the standard answer data of the corresponding actual test questions, and scoring the simulated answers based on the scoring mechanism of the standard answer data of the actual test questions to obtain a basic score;

[0033] Based on the questions to be evaluated, the student's question score data is compared with the basic score to determine the comparison relationship, and the student's score data is weighted according to the comparison relationship to obtain weighted score data;

[0034] Calculate the ratio of the score data of each knowledge point data in the question to be evaluated to the weighted score data to obtain the corresponding ratio data;

[0035] Statistically calculate the ratio data of the knowledge point data involved in each stage goal to obtain the stage achievement data of the corresponding stage goal;

[0036] Based on the sum of the scores of the knowledge points involved in the goals of each stage in the actual test questions taken by students, determine the importance ratio of the goals of each stage and obtain the importance data;

[0037] Based on the stage achievement data of each stage goal and the importance data of the corresponding stage goal, the course achievement data is calculated.

[0038] Preferably, the basic score and the question score of the question to be evaluated are subtracted to obtain the lost score value;

[0039] Calculate the ratio of the lost points to the score of the assessment question to get the difficulty coefficient;

[0040] Based on the questions to be evaluated, the student's question score data is compared with the basic score. If the student's question score data is greater than or equal to the basic score, it indicates that the student has mastered the logical thinking obtained by the evaluation model analysis, and the student's question score data is judged based on the scoring mechanism of the standard answer data and the basic score, and the knowledge point data of the middle score of the student's question score data, the application thinking mark of the corresponding knowledge point data and the score value of the corresponding knowledge point data are determined;

[0041] Based on the scoring mechanism of the standard answer data and the basic score, the knowledge point data involved in the student question score data is divided to obtain a first knowledge point group consistent with the basic score and a second knowledge point group inconsistent with the basic score;

[0042] Matching the thinking weighting coefficient of the knowledge point data according to the judged knowledge point data and the applied thinking mark of the corresponding knowledge point data;

[0043] Performing score weighted calculation on the knowledge points in the first knowledge point group, if the thinking weighted coefficient of the knowledge point data is a positive thinking weighted coefficient, performing weighted calculation on the positive thinking weighted coefficient and the score value of the knowledge point to obtain a first score value of the knowledge point data;

[0044] If the thinking weighting coefficient of the knowledge point data is a reverse thinking weighting coefficient, the reverse thinking weighting coefficient and the score value of the knowledge point are weighted and calculated to obtain a first score value of the knowledge point data;

[0045] Performing a weighted score calculation on the knowledge points in the second knowledge point group based on the thinking weight coefficient and the difficulty coefficient of the knowledge point data to obtain a second score value, and taking the sum of the first score value and the second score value as the weighted score data of the student;

[0046] If the student's question score data is less than the basic score, the thinking weighting coefficient and the score value of each knowledge point data in the student's question score data are weighted and calculated to obtain the student's weighted score data.

[0047] Preferably, the number of knowledge points of the question to be evaluated is determined. If the number of knowledge points is 1, the thinking weighting coefficient and difficulty coefficient corresponding to the knowledge point are used as the question weighting coefficient of the knowledge point on the question.

[0048] If the number of knowledge points is greater than 1, the involved knowledge point data are sorted according to the standard answer to obtain a knowledge point sequence;

[0049] The thinking weighting coefficient of the corresponding knowledge point is read according to the knowledge point data involved in the question to be evaluated, and the thinking weighting coefficient of the knowledge point is superimposed according to the knowledge point sequence to obtain the superposition coefficient of the corresponding knowledge point in the question, and the superposition coefficient and the difficulty coefficient are used as the question weighting coefficient of the corresponding knowledge point in the question.

[0050] Preferably, data judgment is performed on the course achievement data to determine whether the course achievement meets the teaching requirements;

[0051] If it is judged that the teaching requirements are met, the course teaching is excellent;

[0052] If the teaching needs are not met, the scores of the knowledge points corresponding to the goals of each stage of each student will be counted according to the screening student list to obtain the score data of the corresponding stage goals;

[0053] According to the screening student list, the score data of different students with the same stage goal are counted to obtain the stage change curve;

[0054] Compare the phase change curves of each phase goal with each other to determine the phase goal that causes the course achievement data to be lower than the teaching requirements, and mark this phase goal as an obstacle stage;

[0055] Conducting teaching correlation judgment between multiple obstacle stages to determine the influence relationship between the multiple obstacle stages; the influence relationship includes an influence stage and an influenced stage;

[0056] The phase change curves of the influencing phase and the affected phase are compared with each other to determine whether the phase change curve of the influencing phase is similar to the phase change curve of the affected phase;

[0057] If there are similarities, the impact stage is analyzed to determine the causes of the obstacles in the impact stage;

[0058] If there is no similarity, the influencing stage and the affected stage are analyzed separately to determine the corresponding obstacle causes;

[0059] The corresponding obstacle suggestions are matched based on the obstacle causes, and the obstacle causes and the corresponding obstacle suggestions are output to obtain an evaluation report.

[0060] Preferably, the stage goals are determined based on the impact stage, and the corresponding performance scores are matched according to the stage goals;

[0061] Based on the screening student list, the performance scores of students in the target stage are counted to obtain the performance change curve of the corresponding stage;

[0062] comparing the performance change curve with the stage change curve to determine the similarity between the performance change curve and the stage change curve;

[0063] If the performance change curve is similar to the stage change curve, it means that the student's usual performance has an impact on the test score, and a discreteness analysis is performed on the performance change curve to determine the discreteness of the performance change curve;

[0064] If the dispersion of the performance change curve is greater than or equal to the built-in first performance standard value, the cause of the obstacle is determined to be a teaching obstacle;

[0065] If the dispersion of the performance change curve is less than the second performance standard value, the cause of the obstacle is determined to be a learning attitude obstacle;

[0066] If the dispersion of the performance change curve is between the first performance standard value and the second performance standard value, the cause of the disorder is determined to be a learning disability;

[0067] If the performance change curve is not similar to the stage change curve, it means that the student's usual performance has no impact on the test scores, and the cause of the obstacle is determined to be the mismatch between the test difficulty and the teaching difficulty.

[0068] Preferably, if the obstacle is caused by a teaching obstacle, a suggestion for modifying the teaching plan is output;

[0069] If the obstacle is caused by learning attitude obstacle, output supervision suggestions;

[0070] If the obstacle is due to learning ability obstacle, the student's question score data is compared with the basic score of the corresponding question to determine the student's learning ability, and the students are divided according to their learning ability to obtain the student ability category, and modification suggestions are made to the teaching plan according to the student ability category;

[0071] If the obstacle is caused by the mismatch between the exam difficulty and the teaching difficulty, then suggestions for modifying the exam question type are output.

[0072] In summary, the present application includes at least one of the following beneficial technical effects:

[0073] 1. By using blockchain technology, the teacher's course objectives and the stage objectives of the corresponding courses, as well as the students' performance scores at each stage and the final test scores of the course are stored to ensure data security, thereby reducing the possibility of data deviation. Students are screened by the average performance of each student in the course to reduce the impact of cheating on the course goal completion evaluation, thereby improving the fairness of the course goal completion evaluation results. The performance scores and test scores of students in the screened student list are evaluated for course goal completion through the built-in evaluation model, thereby improving the accuracy of the course goal completion evaluation results. At the same time, the evaluation results of the course goal completion evaluation results are analyzed by obstacles to obtain the corresponding evaluation report, so that relevant staff can adjust the teaching plan according to the evaluation report, thereby improving students' learning outcomes;

[0074] 2. By using the difficulty of applying the same knowledge point under different thinking, the thinking weighting coefficient of the knowledge point is determined. By using the difficulty of the knowledge point in the actual test questions, the difficulty coefficient of the knowledge point in the question is determined. The student's score in the actual test questions is weighted by the thinking weighting coefficient and the difficulty coefficient, so that the final weighted score value can better reflect the student's application of the knowledge point, thereby improving the accuracy of the evaluation results of the completion of the course objectives;

[0075] 3. By using the stage change curve of each stage goal to reflect the students' scores, we can determine the stage goals that cause the course goals to not meet the teaching needs. Then, by analyzing the screened stage goals, we can further determine the reasons for the poor student scores, so that relevant personnel can make corresponding adjustments based on the evaluation report, thereby improving students' learning outcomes. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 This is a flowchart of the steps of the course goal achievement analysis and evaluation method based on artificial intelligence in this embodiment. DETAILED DESCRIPTION

[0077] The following is combined with Figure 1 This application is described in further detail.

[0078] The embodiment of the present application discloses a course goal achievement analysis and evaluation method based on artificial intelligence.

[0079] Example: Figure 1 As shown, the present invention provides an artificial intelligence-based course goal achievement analysis and evaluation method, comprising:

[0080] S100, obtaining the teacher's course objectives and the corresponding course stage objectives in the blockchain;

[0081] S200, obtaining the performance scores of students at each stage based on the stage goals, and obtaining the test scores of students during course assessment based on the course goals; wherein the performance scores refer to the performance of students during daily teaching, and the test scores refer to the scores of students after the knowledge points are taught or at the mid-term and final exams.

[0082] S300, average the performance scores of the same student at each stage to obtain the performance mean;

[0083] S400, conduct a dispersion analysis on the performance mean of each student to determine the dispersion degree of the performance mean of each student relative to the performance score of the entire student group, and record it as the dispersion coefficient;

[0084] S500, filtering students based on the dispersion coefficient to obtain a screened student list;

[0085] S600, obtaining actual test questions actually taken by students, and performing knowledge point judgment and logical thinking judgment on the actual test questions based on the evaluation model, so as to determine the knowledge point data involved in each question in the actual test questions, the application thinking mark of the corresponding knowledge point, and the thinking weighting coefficient under the corresponding application thinking mark; the application thinking mark of the knowledge point includes a positive thinking mark and a reverse thinking mark; the thinking weighting coefficient includes a positive thinking weighting coefficient and a reverse thinking weighting coefficient;

[0086] S700, obtaining the students' answer questions, and performing knowledge point judgment and logical thinking judgment on the answer questions according to the test scores of the students in the screened student list, and performing positive thinking weighting and / or reverse thinking weighting on the students' test scores according to the applied thinking marks to determine the students' course achievement of the course, and outputting the course achievement data;

[0087] S800, evaluates and analyzes the course achievement data to obtain an evaluation report;

[0088] S900 outputs students' performance scores, test scores, course achievement data and evaluation reports based on the built-in course goal achievement report output format.

[0089] In this embodiment, the teacher's course objectives and the stage objectives under the corresponding course, as well as the students' performance scores at each stage and the final test scores of the course are stored by means of blockchain technology to ensure data security, thereby reducing the possibility of data deviation. Students are screened by the average performance of each student in the course to reduce the impact of cheating on the course goal completion evaluation, thereby improving the fairness of the course goal completion evaluation results. The course goal completion evaluation is performed on the performance scores and test scores of students in the screened student list through the built-in evaluation model, thereby improving the accuracy of the course goal completion evaluation results. At the same time, the evaluation results of the course goal completion evaluation results are subjected to obstacle analysis to obtain the corresponding evaluation report, so that relevant staff can adjust the teaching plan according to the evaluation report, thereby improving students' learning outcomes.

[0090] For example, the course goal is to achieve XX learning outcomes for course A, and course A includes knowledge a, b, c, and d. The course goal is divided according to the knowledge points to obtain multiple stage goals, such as stage goal 1 to learn knowledge points a and b, stage goal 2 to learn knowledge point c, and stage goal 3 to learn knowledge point d. The performance score of the student in stage goal 1 is x1, the performance score in stage goal 2 is x2, and the performance score in stage goal 3 is x3. The performance mean obtained by mean calculation is x. By performing discrete analysis on the performance mean x of multiple students, for example, if the score interval (y1, y2) contains 90% of the students' scores, the students who are not within this interval are filtered, thereby ensuring that the filtered students can more accurately reflect the completion of the course goal. By analyzing and calculating the performance scores and test scores of these students, the course achievement degree of course A is obtained, and then the course achievement degree is evaluated and analyzed to determine the quality of the course achievement degree, and then a corresponding evaluation report is generated according to the quality of the course achievement degree for reference and adjustment by relevant personnel to improve the teaching quality.

[0091] In step S600, the evaluation model includes the following steps:

[0092] S601, obtaining test question data in a training set and standard answer data corresponding to the test question data;

[0093] S602, divide the test data based on the application thinking of knowledge points to obtain forward test questions and reverse test questions; wherein the forward test questions are direct applications of knowledge points, and the reverse test questions are reverse applications of knowledge points; for example, the knowledge point is a formula or theorem A, that is, according to condition a, result b can be obtained. The forward test question gives condition a in the question content and asks to solve result b. The reverse test question gives result b in the question content and asks to infer condition a.

[0094] S603, performing text language understanding on the test question data to obtain understanding data;

[0095] S604, extracting knowledge points from the standard answer data to obtain knowledge point data;

[0096] S605, constructing an evaluation model based on the application thinking of knowledge points by logically thinking the positive test questions and their corresponding understanding data and knowledge point data, and obtaining a positive thinking mark;

[0097] S606, based on the applied thinking of the knowledge point, the reverse test question and its corresponding understanding data and knowledge point data are logically constructed for the evaluation model to obtain a reverse thinking mark; wherein the positive thinking mark can be represented by 1, and the reverse thinking mark can be represented by 0. Among them, positive thinking and reverse thinking are only used to represent the application method of the knowledge point, for example, positive thinking is a way of thinking that derives the result according to the condition in the question, and reverse thinking is a way of thinking that derives the condition according to the result in the question.

[0098] S607, obtaining a test set, and inputting the test question data in the test set and the standard answer data corresponding to the test question data into the evaluation model, the evaluation model performs text language understanding and logical thinking judgment on the test question data in the test set, obtains the knowledge points involved in each test question data and the application thinking of the corresponding knowledge points, and records them as the first knowledge point data and the first logical thinking data;

[0099] S608, the evaluation model extracts knowledge points and performs logical thinking judgment on the standard answer data in the test set to obtain second knowledge point data and second logical thinking data;

[0100] S609, compare the first knowledge point data with the second knowledge point data, and compare the first logical thinking data with the second logical thinking data, so as to screen out the test question data in the test set that satisfies the first knowledge point data and the second knowledge point data are the same and the first logical thinking data and the second logical thinking data are the same, and record the test question data as the test question data to be analyzed; when the first knowledge point data and the second knowledge point data are the same, and the first logical thinking data and the second logical thinking data are the same, it indicates that the evaluation model can correctly identify the question, so the first knowledge point data, the second knowledge point data, the first logical thinking data, and the second logical thinking data are compared with each other to screen the test question data, so as to further ensure that the judged thinking weighting coefficient is more authoritative.

[0101] S6010, performing question score statistics for the same logical thinking and the same knowledge point on the test data to be analyzed according to logical thinking, obtaining a ratio of positive thinking marks to reverse thinking marks in the same test data to be analyzed, and recording it as a mean value of thinking ratio;

[0102] S6011, based on the average of the proportion of thinking, the scores of the knowledge points under different applied thinking marks are weighted to obtain the thinking weighting coefficient; the thinking weighting coefficient includes the forward thinking weighting coefficient and the reverse thinking weighting coefficient. By calculating the ratio of the scores of the questions of forward thinking and reverse thinking, it can not only reflect the teacher's requirements for students' mastery of the knowledge point in the teaching, but also reflect the difficulty of flexibly mobilizing the applied thinking on the knowledge point, thereby making the judged thinking weighting coefficient more accurate and authoritative.

[0103] In this embodiment, the test data is divided by the application thinking of the knowledge points, so that the evaluation model can be trained on the corresponding knowledge points through different application thinking, so that the evaluation model can judge the knowledge points involved and the application thinking of the corresponding knowledge points according to the question text of the test data. Because different application thinking of the same knowledge point can indirectly reflect the students' mastery of the knowledge point, and the difficulty of students' mastery of the positive application of the knowledge point is lower than the difficulty of mastering the reverse application of the knowledge point, the test set is analyzed and judged by the trained evaluation model to determine the first knowledge point data and the first logical thinking data involved in the test questions in the test set, and the first knowledge point data and the first logical thinking data are compared with the second knowledge point data and the second logical thinking data, so as to screen out the test questions to be analyzed that are correctly identified by the evaluation model, and then the scores of the questions with the same logical thinking and the same knowledge point for the test questions to be analyzed are counted, so as to determine the proportion of thinking marked by positive logical thinking and reverse thinking in the test questions, and then determine the thinking weighting coefficients of the positive thinking mark and the reverse thinking mark, so that when the course goal achievement is calculated according to the students' performance scores and test scores, the calculation results are more accurate.

[0104] The evaluation model is trained in logical thinking through the test data in the training set and the standard answer data of the corresponding test data, so that the evaluation model can judge the knowledge points involved in the question and the application thinking of the corresponding knowledge points based on the question information of the test data; and then the weights of the positive thinking marks and the reverse thinking marks are judged according to the test data in the test set and the standard answer data of the corresponding test data, so as to clarify the feedback effect of the positive thinking marks and the reverse thinking marks on the students' learning situation, thereby making the judgment result more accurate when judging the degree of achievement of the course objectives based on the students' performance scores and test scores.

[0105] In step S700, the student's answer questions are obtained, and the knowledge point judgment and logical thinking judgment are performed on the answer questions according to the test scores of the students in the screened student list, and the positive thinking weighting and / or reverse thinking weighting are performed on the student's test scores according to the applied thinking mark to determine the student's course achievement of the course, and the course achievement data is output, including the following steps:

[0106] S710, obtaining the students' answered test questions and matching the test scores with the answered test questions to determine the students' scores for each question in the answered test questions, and recording the students' scores for each question as question score data; wherein the answered test questions are actual test questions after the students answer them.

[0107] S720, collecting and filtering the students' question score data to filter out questions that have not received full marks among the student group, and recording the questions as questions to be evaluated;

[0108] S730, the evaluation model extracts knowledge points and performs logical thinking judgment on the evaluation question to determine the knowledge point data involved in the corresponding question and the application thinking mark of the corresponding knowledge point;

[0109] S740, generating an answer to the question based on the knowledge point data obtained by judgment and the application thinking mark of the corresponding knowledge point to obtain a simulated answer;

[0110] S750, obtaining actual test questions actually taken by students and standard answer data corresponding to the actual test questions, scoring the simulated answers based on the scoring mechanism of the standard answer data of the actual test questions, and obtaining a basic score; wherein the actual test questions are original test questions before the students answer them.

[0111] S760, based on the question to be evaluated, comparing the student's question score data with the basic score to determine a comparison relationship, and weighting the student's score data according to the comparison relationship to obtain weighted score data;

[0112] S770, calculating the ratio of the score data of each knowledge point data in the question to be evaluated to the weighted score data to obtain corresponding ratio data;

[0113] S780, statistically calculating the ratio data of the knowledge point data involved in each stage goal to obtain stage achievement data of the corresponding stage goal;

[0114] S790, determining the importance ratio of each stage goal based on the scores of the knowledge point data involved in each stage goal in the actual test questions actually tested by the students, and obtaining importance data;

[0115] S7100, based on the sum of the scores of the knowledge points involved in the goals of each stage in the actual test questions actually taken by the students, determine the importance ratio of the goals of each stage and obtain the importance data. For example, the course goal includes two stage goals. Stage goal 1 includes knowledge point a and knowledge point b, and stage goal 2 includes knowledge point c. Among them, the ratio data of knowledge point a is 0.8, the ratio data of knowledge point b is 1, and the ratio data of knowledge point c is 0.8. Then the stage achievement degree of stage goal 1 is (0.8+1)÷2=0.9, and the stage achievement degree of stage goal 2 is 0.8. At the same time, the importance of each stage goal is determined according to the score proportion of the knowledge points corresponding to each stage goal in the actual test questions. For example, the full score of the actual test questions is 100, knowledge point 1 accounts for 40 points, knowledge point 2 accounts for 30 points, and knowledge point 3 accounts for 30 points. Then stage goal 1 accounts for 0.7, and stage goal 2 accounts for 0.3. That is, the achievement of the course goal is 0.9*0.7+0.8*0.3=0.87, that is, the course achievement degree is 0.87.

[0116] In this embodiment, the student's answer situation is obtained to determine the student's score for each question in the actual test. The student's score for each question is judged to screen out the questions that need to be evaluated, so as to reduce the amount of data that the system needs to analyze and improve the analysis efficiency. The evaluation questions are judged based on knowledge points and logical thinking, and the answers are simulated and generated based on the knowledge point data and applied thinking obtained by the judgment. The standard answer is compared with the simulated answer to determine the score under system thinking, and then the student's score on the question is weighted according to the score of system thinking, so that the weighted score value can more intuitively reflect the student's mastery of the knowledge point, and then the achievement of the course objectives is determined based on the mastery, so that the judgment result is more accurate and reliable.

[0117] By obtaining the students' answers, we can determine the scores of each question in the actual test. When every student answers a question correctly, it means that the students have mastered all the knowledge points corresponding to the question, so no re-evaluation is required and the score is full. On the contrary, when there is always at least one student who does not answer a question correctly, it means that the students have not mastered the knowledge points corresponding to the question, so re-evaluation is required. When the evaluation model judges the knowledge points and logical thinking of the questions, the result of the judgment is the student's first reaction to the question. Therefore, the simulated answers generated by the evaluation model can reflect the students' inertial thinking to a certain extent, and then use the results of inertial thinking as a basic reference to judge the students' test situation to improve the accuracy of the judgment.

[0118] In step S760, based on the question to be evaluated, the student's question score data is compared with the basic score to determine the comparison relationship, and the student's score data is weighted according to the comparison relationship to obtain weighted score data, including the following steps:

[0119] S761, calculating the difference between the basic score and the question score of the question to be evaluated to obtain the loss score;

[0120] S762, the lost score is calculated by ratio with the question score of the evaluation question to obtain the difficulty coefficient; by using the basic score to determine the difficulty coefficient of the question, the determination result is more referenceable, authoritative and unique.

[0121] S763, based on the question to be evaluated, comparing the question score data of the student with the basic score, if the question score data of the student is greater than or equal to the basic score, it indicates that the student has mastered the logical thinking obtained by the evaluation model analysis, and judging the question score data of the student based on the scoring mechanism of the standard answer data and the basic score, determining the knowledge point data of the middle score of the student's question score data, the application thinking mark of the corresponding knowledge point data and the score value of the corresponding knowledge point data;

[0122] S764, dividing the knowledge point data involved in the student question score data based on the scoring mechanism of the standard answer data and the basic score to obtain a first knowledge point group consistent with the basic score and a second knowledge point group inconsistent with the basic score;

[0123] S765, matching the thinking weighting coefficient of the knowledge point data according to the judged knowledge point data and the applied thinking mark of the corresponding knowledge point data;

[0124] S766, performing score weighted calculation on the knowledge points in the first knowledge point group, and if the thinking weighted coefficient of the knowledge point data is a positive thinking weighted coefficient, performing weighted calculation on the positive thinking weighted coefficient and the score value of the knowledge point to obtain a first score value of the knowledge point data;

[0125] S767, if the thinking weighting coefficient of the knowledge point data is a reverse thinking weighting coefficient, weighted calculation is performed on the reverse thinking weighting coefficient and the score value of the knowledge point to obtain a first score value of the knowledge point data;

[0126] S768, performing score weighted calculation on the knowledge points in the second knowledge point group based on the thinking weighted coefficient and the difficulty coefficient of the knowledge point data to obtain a second score value, and taking the sum of the first score value and the second score value as the weighted score data of the student;

[0127] S769, if the student's question score data is less than the basic score, the thinking weighting coefficient and the score value of each knowledge point data in the student's question score data are weighted and calculated to obtain the student's weighted score data.

[0128] In this embodiment, when weighting the students' scores, the basic score obtained by the evaluation model and the question score of the question to be evaluated are subjected to difference calculation and ratio calculation, so as to determine the difficulty coefficient of the knowledge point in the question, thereby making it possible to take into account not only the thinking difficulty but also the difficulty coefficient of the question itself when weighting the students' scores, so that the weighted score value can better reflect the students' mastery of the knowledge point and improve the accuracy of the evaluation of the achievement of course objectives.

[0129] For example, if the score of positive thinking is 80 and the score of reverse thinking is 20, the score of positive thinking shall prevail, and the weight of positive logic shall be 1 and the weight of reverse logic shall be 1.25 [1+20 / 80=1+0.25=1.25]. When the full score of the question is 10 and the basic score is 8, the difficulty coefficient of the question is 1.2 calculated by the ratio. If the student scores 4 points, the final score of the student is 4*1=4 points when the problem-solving thinking is positive thinking, that is, the score of the student under this thinking is 0.4. If the problem-solving thinking is reverse thinking, the final score of the student is 4*1.25=5 points, that is, the score of the student under this thinking is 0.5. If the student scores 9, it means that the student's mastery of the knowledge points exceeds the mastery of the machine, so when the problem-solving thinking is positive thinking, the final score of the student is 8*1+1*1.2*1=9.2 points, that is, the score of the student under this thinking is 0.92. Under reverse thinking, the student's final score is 8*1.25+1*1.2*1.25=11.5, that is, the student's score under this thinking is 1.

[0130] In step S760, based on the question to be evaluated, the student's question score data is compared with the basic score to determine the comparison relationship, and the student's score data is weighted according to the comparison relationship to obtain weighted score data, which also includes the following steps:

[0131] S760a, judging the number of knowledge points of the question to be evaluated, if the number of knowledge points is 1, taking the thinking weighting coefficient and difficulty coefficient corresponding to the knowledge point as the question weighting coefficient of the knowledge point on the question;

[0132] S760b, if the number of knowledge points is greater than 1, sorting the involved knowledge point data according to the standard answer to obtain a knowledge point sequence;

[0133] S760c, read the thinking weighting coefficient of the corresponding knowledge point according to the knowledge point data involved in the question to be evaluated, and superimpose the thinking weighting coefficients of the knowledge points according to the knowledge point sequence to obtain the superposition coefficient of the corresponding knowledge point in the question, and use the superposition coefficient and difficulty coefficient as the question weighting coefficient of the corresponding knowledge point in the question.

[0134] In this embodiment, the basic score is calculated by comparing it with the score of the standard answer to determine whether there is an inertial thinking trap in the question, and then the difficulty of the question is determined. The complexity of the question is further determined by judging the number of knowledge points in the question to be evaluated. When the question contains only one knowledge point, it indicates that the question is only a test of the logical thinking of a single knowledge point. Therefore, the score of the question is weighted according to the corresponding thinking weighting coefficient and the difficulty coefficient of the question to ensure that the obtained score value is more referenceable. When the question contains multiple knowledge points, it indicates that the question is a flexible application of the multiple knowledge points, so the complexity of the question increases. Therefore, when judging the score of the question, not only the application of a single knowledge point but also the joint application of multiple knowledge points should be considered. Therefore, the weighting coefficients of knowledge point thinking are superimposed to make the final score value more referenceable, thereby improving the accuracy of the judgment on the completion of the course objectives.

[0135] For example, the question contains two knowledge points, namely knowledge point a and knowledge point b, and the corresponding arrangement order is: knowledge point a→knowledge point b. If the thinking weighting coefficient of knowledge point a is 2, and the thinking weighting coefficient of knowledge point b is 2, then in this question, the thinking weighting coefficient of knowledge point b is 2×2=4.

[0136] In step S800, the course achievement data is evaluated and analyzed to obtain an evaluation report, including the following steps:

[0137] S810, performing data judgment on the course achievement data to determine whether the course achievement meets the teaching requirements; wherein the teaching requirements are the school's requirements for the teacher's course achievement.

[0138] S820: If it is judged that the teaching requirements are met, the course teaching is excellent;

[0139] S830, if the teaching requirements are not met, the scores of the knowledge points corresponding to the goals of each stage of each student are counted according to the screened student list to obtain the score data of the corresponding stage goal;

[0140] S840, statistically analyzing the score data of different students with the same stage goal according to the screened student list to obtain a stage change curve;

[0141] S850, comparing the stage change curves of the various stage goals with each other to determine the stage goal that causes the course achievement data to be lower than the teaching requirement, and marking the stage goal as an obstacle stage;

[0142] S860, judging the teaching relevance between the multiple obstacle stages to determine the influence relationship between the multiple obstacle stages; the influence relationship includes an influence stage and an influenced stage;

[0143] S870, comparing the phase change curves of the influencing phase and the phase change curves of the affected phase to determine whether the phase change curve of the influencing phase is similar to the phase change curve of the affected phase;

[0144] S880, if there is similarity, the impact stage is analyzed to determine the cause of the obstacle in the impact stage;

[0145] S890, if there is no similarity, the influencing stage and the affected stage are analyzed separately to determine the corresponding obstacle causes;

[0146] S8100, matching corresponding obstacle suggestions based on the obstacle cause, and outputting the obstacle cause and the corresponding obstacle suggestion to obtain an evaluation report.

[0147] In this embodiment, after the achievement of the course objectives of the corresponding course is determined based on the students' performance scores and test scores, the teaching requirements are judged on the achievement of the course objectives to determine whether the achievement of the course objectives meets the teaching requirements. If the teaching requirements are met, the teaching situation is judged to be excellent. Conversely, if the teaching requirements are not met, it is judged that there are problems with the teaching situation. Therefore, it is necessary to judge the problems existing in the teaching process. By statistically analyzing the scores of different students under the same stage objectives, a stage change curve is obtained. Then, by comparing the stage change curves of each stage objective with each other, the stage objectives whose scores are generally lower than other stage objectives are screened out, and the stage objectives are analyzed and judged to further determine the cause of the obstacle.

[0148] The course achievement data is judged according to the teaching requirements to evaluate the course goal achievement. When it is judged that the course goal achievement does not meet the teaching requirements, the stage change curve of each stage goal is used to reflect the student's score, and then the stage goal that caused the course goal completion to not meet the teaching needs is determined. Then, by analyzing the screened stage goals, the reasons for the poor student scores are further determined, so that relevant personnel can make corresponding adjustments based on the evaluation report, thereby improving students' learning outcomes.

[0149] In step S880, the impact stage is analyzed to determine the cause of the obstacle affecting the stage, including the following steps:

[0150] S881, determine the stage goal based on the impact stage, and match the corresponding performance results according to the stage goal;

[0151] S882, statistically analyzing the performance scores of students at the target stage based on the screened student list to obtain a performance change curve for the corresponding stage;

[0152] S883, comparing the performance change curve with the stage change curve to determine the similarity between the performance change curve and the stage change curve;

[0153] S884, if the performance change curve is similar to the stage change curve, it indicates that the student's usual performance has an impact on the test score, and a discreteness analysis is performed on the performance change curve to determine the discreteness of the performance change curve;

[0154] S885, if the discreteness of the performance change curve is greater than or equal to the built-in first performance standard value, then the obstacle cause is determined to be a teaching obstacle;

[0155] S886, if the dispersion of the performance change curve is less than the second performance standard value, then the cause of the obstacle is determined to be a learning attitude obstacle;

[0156] S887, if the discreteness of the performance change curve is between the first performance standard value and the second performance standard value, the cause of the disorder is determined to be a learning disability;

[0157] S888, if the performance change curve is not similar to the stage change curve, it indicates that the student's usual performance has no impact on the test scores, and the cause of the obstacle is determined to be the mismatch between the test difficulty and the teaching difficulty.

[0158] In this embodiment, when it is determined that the students' scores at a certain stage are not good, the performance scores of the students at that stage are counted, and the performance change curve is used to reflect the students' learning status at that stage. By comparing the performance change curve with the stage change curve, it is determined whether the students' poor scores at that stage are caused by the students' learning status. When it is determined to be caused by the students' learning status, the performance change curve is re-analyzed to determine the reasons for the students' poor performance at that stage, so as to further clarify the causes of the obstacles, so that relevant staff can make corresponding adjustments based on the clear causes of the obstacles, thereby improving the students' learning effects.

[0159] For example, when the performance change curve is similar to the stage change curve, it indicates that the learning outcome of the stage is related to the student's learning status at that stage. Therefore, the performance change curve is judged to determine the cause of the student's poor learning status. When the discreteness of the performance change curve is greater than or equal to the first performance standard value, it indicates that the student status of the general students is not good, which in turn indicates that the teacher cannot make the students keep up with the teacher's pace in the teaching of the knowledge points of this stage, which leads to poor performance results in normal times. When the discreteness of the performance change curve is less than the second performance standard value, it indicates that some students in the student group perform poorly and some students perform well, which in turn indicates that the students' learning attitude has changed, which leads to poor learning effect on the knowledge point and poor test scores. When the discreteness of the performance change curve is between the first performance standard value and the second performance standard value, it indicates that the difficulty of the knowledge points at this stage has increased, which in turn causes some students' learning ability to fail to keep up with the teacher's progress, which in turn leads to poor performance.

[0160] In step S8100, the corresponding obstacle suggestion is matched based on the obstacle cause, and the obstacle cause and the corresponding obstacle suggestion are output to obtain an evaluation report, including the following steps:

[0161] S8101, if the obstacle is a teaching obstacle, output teaching lesson plan modification suggestions;

[0162] S8102, if the obstacle is caused by learning attitude obstacle, then output supervision suggestions;

[0163] S8103, if the obstacle is a learning ability obstacle, the student's question score data is calculated by ratio with the basic score of the corresponding question to determine the student's learning ability, and the students are divided according to their learning ability to obtain the student's ability category, and modification suggestions are made to the teaching plan according to the student's ability category;

[0164] S8104: If the obstacle is that the difficulty of the test does not match the difficulty of the teaching, then a suggestion for modifying the test question type is output.

[0165] In this embodiment, different obstacle suggestions are output according to different obstacle causes to improve students' learning outcomes. When the obstacle causes are teaching obstacles, learning attitude obstacles, and the difficulty of the examination does not match the difficulty of the teaching, revision suggestions are output to the teacher to modify the teaching syllabus. When the obstacle cause is a learning ability obstacle, the students' learning abilities are divided through the performance change curve to obtain student ability categories with different learning abilities, so that teachers can carry out targeted teaching on the teaching syllabus according to the student ability categories, thereby improving students' learning outcomes.

[0166] For example, we teach students in accordance with their aptitude, make targeted corrections to the assessment methods of students according to their learning abilities, and adopt different teaching methods to meet the needs of multiple students with different learning abilities.

[0167] Compared with the existing course goal achievement analysis and evaluation method based on artificial intelligence, the present invention improves the accuracy of the evaluation results.

[0168] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A course goal achievement analysis and evaluation method based on artificial intelligence, characterized in that: include: Get the teacher's course objectives and the corresponding course stage objectives in the blockchain; Obtain students' performance scores at each stage based on stage goals, and obtain students' test scores during course assessments based on course goals; The performance scores of the same student at each stage were averaged to obtain the performance mean; Conduct a dispersion analysis on the performance mean of each student to determine the dispersion degree of the performance mean of each student relative to the performance score of the entire student group, and record it as the dispersion coefficient; Filter students based on the dispersion coefficient to obtain a list of screened students; Acquire the actual test questions actually taken by the students, and make knowledge point judgments and logical thinking judgments on the actual test questions based on the evaluation model, so as to determine the knowledge point data involved in each question in the actual test questions, the application thinking marks of the corresponding knowledge points, and the thinking weighting coefficients under the corresponding application thinking marks; the application thinking marks of the knowledge points include forward thinking marks and reverse thinking marks; the thinking weighting coefficients include forward thinking weighting coefficients and reverse thinking weighting coefficients; Obtain the students' answer questions, and make knowledge point judgments and logical thinking judgments on the answer questions according to the test scores of the students in the screened student list, and make positive thinking weighting and / or reverse thinking weighting on the students' test scores according to the applied thinking marks to determine the students' course achievement of the course, and output the course achievement data; Evaluate and analyze the course achievement data and obtain an evaluation report; Output student performance scores, test scores, course achievement data and evaluation reports based on the built-in course goal achievement report output format.

2. The method for analyzing and evaluating the achievement of course objectives based on artificial intelligence according to claim 1, characterized in that: The evaluation model is specifically: Obtain the test data in the training set and the standard answer data corresponding to the test data; Based on the application thinking of knowledge points, the test data is divided into positive test questions and reverse test questions; positive test questions are the direct application of knowledge points, and reverse test questions are the reverse application of knowledge points; Perform text language understanding on the test data to obtain understanding data; Extract knowledge points from the standard answer data to obtain knowledge point data; Based on the applied thinking of knowledge points, the positive test questions and their corresponding understanding data and knowledge point data are logically constructed into the evaluation model to obtain positive thinking marks; Based on the applied thinking of knowledge points, the reverse test questions and their corresponding understanding data and knowledge point data are used to construct the evaluation model through logical thinking to obtain the reverse thinking mark; A test set is obtained, and the test question data in the test set and the standard answer data corresponding to the test question data are input into the evaluation model. The evaluation model performs text language understanding and logical thinking judgment on the test question data in the test set, obtains the knowledge points involved in each test question data and the application thinking of the corresponding knowledge points, and records them as the first knowledge point data and the first logical thinking data; The evaluation model extracts knowledge points and makes logical thinking judgments on the standard answer data in the test set to obtain second knowledge point data and second logical thinking data; Compare the first knowledge point data with the second knowledge point data, and compare the first logical thinking data with the second logical thinking data, so as to screen out test question data in the test set that satisfies the conditions that the first knowledge point data is the same as the second knowledge point data and the first logical thinking data is the same as the second logical thinking data, and record the test question data as the test question data to be analyzed; According to logical thinking, the question scores of the test data to be analyzed under the same logical thinking and the same knowledge point are counted, and the ratio of positive thinking marks to reverse thinking marks in the same test data to be analyzed is obtained, and recorded as the mean value of thinking proportion; Based on the mean value of thinking proportion, the scores of knowledge points under different applied thinking marks are weighted to obtain a thinking weighting coefficient; the thinking weighting coefficient includes a positive thinking weighting coefficient and a reverse thinking weighting coefficient.

3. The method for analyzing and evaluating the achievement of course objectives based on artificial intelligence according to claim 2, characterized in that: The student's answer questions are obtained, and the knowledge point judgment and logical thinking judgment are performed on the answer questions according to the test scores of the students in the screened student list, and the positive thinking weighting and / or reverse thinking weighting are performed on the student's test scores according to the applied thinking mark to determine the student's course achievement of the course, and the course achievement data is output, specifically: Obtaining the students' answered test questions and matching the test scores with the answered test questions to determine the students' scores for each question in the answered test questions, and recording the students' scores for each question as question score data; The students' question score data are counted and screened to screen out questions that have not received full marks among the student group, and the questions are recorded as questions to be evaluated; The evaluation model extracts knowledge points and makes logical thinking judgments on the questions to be evaluated, so as to determine the knowledge point data involved in the corresponding questions and the application thinking marks of the corresponding knowledge points; Generate an answer to the question based on the knowledge point data obtained by judgment and the application thinking mark of the corresponding knowledge point to obtain a simulated answer; Obtaining the actual test questions and the standard answer data of the corresponding actual test questions, and scoring the simulated answers based on the scoring mechanism of the standard answer data of the actual test questions to obtain a basic score; Based on the questions to be evaluated, the student's question score data is compared with the basic score to determine the comparison relationship, and the student's score data is weighted according to the comparison relationship to obtain weighted score data; Calculate the ratio of the score data of each knowledge point data in the question to be evaluated to the weighted score data to obtain the corresponding ratio data; Statistically calculate the ratio data of the knowledge point data involved in each stage goal to obtain the stage achievement data of the corresponding stage goal; Based on the sum of the scores of the knowledge points involved in the goals of each stage in the actual test questions taken by students, determine the importance ratio of the goals of each stage and obtain the importance data; Based on the stage achievement data of each stage goal and the importance data of the corresponding stage goal, the course achievement data is calculated.

4. The method for analyzing and evaluating the achievement of course objectives based on artificial intelligence according to claim 3 is characterized by: Based on the topic to be evaluated, the student's topic score data is compared with the basic score to determine the comparison relationship, and the student's score data is weighted according to the comparison relationship to obtain weighted score data, specifically: Calculate the difference between the basic score and the score of the question to be evaluated to get the loss value; Calculate the ratio of the lost points to the score of the assessment question to get the difficulty coefficient; Based on the questions to be evaluated, the student's question score data is compared with the basic score. If the student's question score data is greater than or equal to the basic score, it indicates that the student has mastered the logical thinking obtained by the evaluation model analysis, and the student's question score data is judged based on the scoring mechanism of the standard answer data and the basic score, and the knowledge point data of the middle score of the student's question score data, the application thinking mark of the corresponding knowledge point data and the score value of the corresponding knowledge point data are determined; Based on the scoring mechanism of the standard answer data and the basic score, the knowledge point data involved in the student question score data is divided to obtain a first knowledge point group consistent with the basic score and a second knowledge point group inconsistent with the basic score; Matching the thinking weighting coefficient of the knowledge point data according to the judged knowledge point data and the applied thinking mark of the corresponding knowledge point data; Performing score weighted calculation on the knowledge points in the first knowledge point group, if the thinking weighted coefficient of the knowledge point data is a positive thinking weighted coefficient, performing weighted calculation on the positive thinking weighted coefficient and the score value of the knowledge point to obtain a first score value of the knowledge point data; If the thinking weighting coefficient of the knowledge point data is a reverse thinking weighting coefficient, the reverse thinking weighting coefficient and the score value of the knowledge point are weighted and calculated to obtain a first score value of the knowledge point data; Performing a weighted score calculation on the knowledge points in the second knowledge point group based on the thinking weight coefficient and the difficulty coefficient of the knowledge point data to obtain a second score value, and taking the sum of the first score value and the second score value as the weighted score data of the student; If the student's question score data is less than the basic score, the thinking weighting coefficient and the score value of each knowledge point data in the student's question score data are weighted and calculated to obtain the student's weighted score data.

5. The method for analyzing and evaluating the achievement of course objectives based on artificial intelligence according to claim 4 is characterized by: The method further includes comparing the student's question score data with the basic score based on the question to be evaluated to determine the comparison relationship, and weighting the student's score data according to the comparison relationship to obtain weighted score data. The number of knowledge points of the question to be evaluated is determined. If the number of knowledge points is 1, the thinking weighting coefficient and difficulty coefficient corresponding to the knowledge point are used as the question weighting coefficient of the knowledge point on the question; If the number of knowledge points is greater than 1, the involved knowledge point data are sorted according to the standard answer to obtain a knowledge point sequence; The thinking weighting coefficient of the corresponding knowledge point is read according to the knowledge point data involved in the question to be evaluated, and the thinking weighting coefficient of the knowledge point is superimposed according to the knowledge point sequence to obtain the superposition coefficient of the corresponding knowledge point in the question, and the superposition coefficient and the difficulty coefficient are used as the question weighting coefficient of the corresponding knowledge point in the question.

6. The method for analyzing and evaluating the achievement of course objectives based on artificial intelligence according to claim 1, characterized in that: The course achievement data is evaluated and analyzed to obtain an evaluation report, specifically: Conduct data judgment on course achievement data to determine whether the course achievement meets the teaching requirements; If it is judged that the teaching requirements are met, the course teaching is excellent; If the teaching needs are not met, the scores of the knowledge points corresponding to the goals of each stage of each student will be counted according to the screening student list to obtain the score data of the corresponding stage goals; According to the screening student list, the score data of different students with the same stage goal are counted to obtain the stage change curve; Compare the phase change curves of each phase goal with each other to determine the phase goal that causes the course achievement data to be lower than the teaching requirements, and mark this phase goal as an obstacle stage; Conducting teaching correlation judgment between multiple obstacle stages to determine the influence relationship between the multiple obstacle stages; the influence relationship includes an influence stage and an influenced stage; The phase change curves of the influencing phase and the affected phase are compared with each other to determine whether the phase change curve of the influencing phase is similar to the phase change curve of the affected phase; If there are similarities, the impact stage is analyzed to determine the causes of the obstacles in the impact stage; If there is no similarity, the influencing stage and the affected stage are analyzed separately to determine the corresponding obstacle causes; The corresponding obstacle suggestions are matched based on the obstacle causes, and the obstacle causes and the corresponding obstacle suggestions are output to obtain an evaluation report.

7. The method for analyzing and evaluating the achievement of course objectives based on artificial intelligence according to claim 6 is characterized by: The impact stage is analyzed to determine the causes of obstacles in the impact stage, specifically: Determine the stage goals based on the impact stage, and match the corresponding performance results according to the stage goals; Based on the screening student list, the performance scores of students in the target stage are counted to obtain the performance change curve of the corresponding stage; comparing the performance change curve with the stage change curve to determine the similarity between the performance change curve and the stage change curve; If the performance change curve is similar to the stage change curve, it means that the student's usual performance has an impact on the test score, and a discreteness analysis is performed on the performance change curve to determine the discreteness of the performance change curve; If the dispersion of the performance change curve is greater than or equal to the built-in first performance standard value, the cause of the obstacle is determined to be a teaching obstacle; If the dispersion of the performance change curve is less than the second performance standard value, the cause of the obstacle is determined to be a learning attitude obstacle; If the dispersion of the performance change curve is between the first performance standard value and the second performance standard value, the cause of the disorder is determined to be a learning disability; If the performance change curve is not similar to the stage change curve, it means that the student's usual performance has no impact on the test scores, and the cause of the obstacle is determined to be the mismatch between the test difficulty and the teaching difficulty.

8. The method for analyzing and evaluating the achievement of course objectives based on artificial intelligence according to claim 7 is characterized by: The obstacle suggestions are matched based on the obstacle causes, and the obstacle causes and the corresponding obstacle suggestions are output to obtain an evaluation report, specifically: If the obstacle is caused by a teaching obstacle, then output suggestions for modifying the teaching plan; If the obstacle is caused by learning attitude disorder, output supervision suggestions; If the obstacle is due to learning ability obstacle, the student's question score data is compared with the basic score of the corresponding question to determine the student's learning ability, and the students are divided according to their learning ability to obtain the student ability category, and modification suggestions are made to the teaching plan according to the student ability category; If the obstacle is caused by the mismatch between the exam difficulty and the teaching difficulty, then suggestions for modifying the exam question type are output.

Images