CN113159480A - Learning condition evaluation method and device based on education big data image - Google Patents
Learning condition evaluation method and device based on education big data image Download PDFInfo
- Publication number
- CN113159480A CN113159480A CN202011644862.XA CN202011644862A CN113159480A CN 113159480 A CN113159480 A CN 113159480A CN 202011644862 A CN202011644862 A CN 202011644862A CN 113159480 A CN113159480 A CN 113159480A
- Authority
- CN
- China
- Prior art keywords
- analysis
- education
- class
- score
- analysis model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 46
- 238000004458 analytical method Methods 0.000 claims abstract description 204
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 20
- 238000005096 rolling process Methods 0.000 claims abstract description 15
- 238000012360 testing method Methods 0.000 claims description 34
- 238000009826 distribution Methods 0.000 claims description 23
- 238000007781 pre-processing Methods 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 12
- 238000005211 surface analysis Methods 0.000 claims description 9
- 238000013480 data collection Methods 0.000 claims description 3
- 230000004888 barrier function Effects 0.000 abstract description 4
- 230000010354 integration Effects 0.000 abstract description 3
- 238000011161 development Methods 0.000 abstract description 2
- 238000009412 basement excavation Methods 0.000 abstract 1
- 239000006185 dispersion Substances 0.000 description 18
- 230000000694 effects Effects 0.000 description 8
- 238000001514 detection method Methods 0.000 description 4
- 210000003141 lower extremity Anatomy 0.000 description 4
- 206010017577 Gait disturbance Diseases 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010835 comparative analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06398—Performance of employee with respect to a job function
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Educational Technology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention provides a learning condition evaluation method and device based on education big data images, comprising the following steps: step S1, collecting education basic data; step S2, determining the type of the collected education basic data from the preset types; step S3, inputting the education basic data of the determined type into the analysis model obtained by training to obtain the analysis result output by the analysis model; the analysis model comprises a personal analysis model, a rolling analysis model, a class analysis model, a subject analysis model, a school grade analysis model and a comprehensive report analysis model; step S4, based on the analysis result, evaluating the student learning condition; the method realizes deep analysis and excavation of education basic data, realizes integration of the education basic data, breaks through information data sharing barriers existing in provincial and urban education bureaus, school managers, senior leaders and the like, is convenient for students, teachers, parents and education bureaus to know the required conditions respectively, and realizes benign collaborative development of learning, education and management.
Description
[ technical field ] A method for producing a semiconductor device
The invention relates to a learning condition education technology, in particular to a learning condition evaluation method and device based on education big data images.
[ background of the invention ]
Large data images are models built on a large amount of data. The education big data image is an education model established on the basis of a large amount of basic data in the education field. The educational big data portrait has guiding significance for students, teachers, parents and educational institutions.
However, at present, there are data sharing barriers for information in the provincial and urban education bureau, school chief, senior officer, and the like, and a large amount of education basic data cannot be integrated, and the analysis and mining of the education basic data cannot be mentioned. And the traditional education evaluation mode is single, and the teacher in school is busy in teaching, can only know the examination result of the student, but can not know the reason that the student results cause in all aspects, thereby can not really help the student improve the score to the medicine is given to the case. How to form a scientific, systematic and complete evaluation system, so as to achieve the purpose of realizing the evaluation of the learning situation with higher informatization and automation degrees, which is a problem to be solved urgently at present.
[ summary of the invention ]
The invention provides a learning condition evaluation method and device based on education big data images, which form a scientific, systematic and complete evaluation system, realize the common requirements of students, teachers, parents and education bureau personnel in four directions, comprehensively improve various qualities of the students and realize the collaborative development and improvement of the multiple directions.
In order to achieve the purpose, the technical scheme is as follows:
a learning condition evaluation method based on education big data images comprises the following steps:
step S1, collecting education basic data;
step S2, determining the type of the collected education basic data from the preset types;
step S3, inputting the education basic data of the determined type into the analysis model obtained by training to obtain the analysis result output by the analysis model;
the analysis model comprises a personal analysis model, a rolling analysis model, a class analysis model, a subject analysis model, a school grade analysis model and a comprehensive report analysis model;
and step S4, evaluating the student learning condition based on the analysis result.
Further, the training process of the analysis model in step S3 includes the following steps:
s3.1, collecting education sample data;
s3.2, dividing the education sample data into preset types;
and S3.3, training a preset analysis model according to the divided education sample data.
Further, in step S3.2, the preset types include: pre-class work, current class testing, post-class work, class practice work, unit testing, mid-term testing, and end-of-term testing.
Further, the personal analysis model in the step S3 includes: the general description of the scores of each department of the examinee, the hierarchical analysis of each department of the examination and the tendency of the scores of the examinee;
the score profile attributes of each department of the examinees comprise subjects, original scores, class ranking, school ranking, examinee answer sheets, average score numbers lower than the whole class and score lowest TOP 3;
each department level in the analysis of each department level of the examination is divided into class level statistics and school level statistics, including the comparison of the score of the examinee under a certain subject with the highest score of the whole class or the whole school, and the average score of the whole class or the whole school;
the score trend of the examinees is the comparison of the personal scores with the trends of class average score and school average score.
Further, the rolling surface analysis model in the step S3 includes: the analysis of score overview, quality analysis of the single questions, the scoring condition of the single questions of each class, the answering details of students, knowledge point analysis and examination paper comment is carried out aiming at a certain subject of a certain examination.
The score general profiles of a certain subject in a certain examination comprise statistical average scores, highest scores, lowest scores, standard deviations, difficulty, reliability, discrimination and difficulty proportion (proportion of difficult to distinguish and easy to subject), and the score general profiles can reflect the test paper general profiles of the subject. Standard deviation: the method comprises the steps of representing absolute dispersion degrees among examination scores of all examinees, wherein the larger the value is, the larger the dispersion degree of the scores among individuals is, and conversely, the smaller the value is, the smaller the dispersion degree of the scores among the individuals is; difficulty: the difficulty coefficient of a certain question or subject represents the difficulty degree of the test question, the difficulty coefficient is between 0 and 1, and the larger the value is, the simpler the test question is; reliability: the stability of the test results is between 0 and 1, and the larger the value, the higher the quality of the test paper (more than 0.9 is excellent, 0.7 to 0.9 is good, 0.35 to 0.7 is medium, and less than 0.35 is low); and (3) discrimination: the degree of distinguishing the examination questions on the abilities of the examinees is represented, the larger the value is, the better the effect of distinguishing the examinees with different abilities is, the larger the value of the examination questions is, the value range is from-1.00 to +1.00, and the evaluation standard is as follows: 0.4 or more is preferable, 0.3 to 0.39 is preferable, 0.20 to 0.29 is preferable, and 0.19 or less is not preferable; difficulty ratio: the score proportion of the difficult questions, the medium questions and the simple questions, wherein the score of the small questions is less than 30% as the difficult questions, the score is between 30% and 80% as the medium questions, and the score of the small questions is more than 80% as the easy questions.
The quality analysis attributes of the single question include: the system comprises a question number, a question type, an over-score, an average score, a score rate, a difficulty coefficient, a discrimination degree, a standard deviation, a zero score proportion and an over-score proportion.
The attribute of each class of single-question scoring condition comprises the following steps: question number, question type, total score, and score of each class.
The student answering situation attributes include: question number, question type, correct answer, score, answer (choice questions show the choice probability of each choice).
The knowledge point analysis attributes include: sequence number, knowledge point, score ratio of knowledge point and corresponding question.
The examination paper comment and comment pointer displays question numbers, question types, question stems, class scores, grade scores, full scores, lost scores and answer details for independent questions.
Further, the class analysis model in the step S3 includes: selecting a class of the examination to obtain the score general view, quartile analysis, score subsection analysis, third rate and first grade analysis, grading arrival line analysis, subject examination performance analysis, subject score structure distribution, student answering details and important student information of the class.
The performance profiles for a class include: the highest score, the lowest score, the average score, the standard deviation, the median and the difference coefficient, and the score profile can reflect the examination profile of the students in the examination; standard deviation: the method comprises the steps of representing absolute dispersion degrees among examination scores of all examinees, wherein the larger the value is, the larger the dispersion degree of the scores among individuals is, and conversely, the smaller the value is, the smaller the dispersion degree of the scores among the individuals is; median: the score at the middle position in the scores of the examinees arranged from low to high; coefficient of difference: the ratio of the standard deviation to the average score represents the relative degree of dispersion of different samples, and a larger value represents a larger relative degree of dispersion, whereas a smaller value represents a smaller relative degree of dispersion.
In quartile analysis, the first quartile (Q1): the 25 th% of the test taker's scores in low to high order; third quartile (Q3): the 75% of the test taker's scores in low to high order; quartering distance IQR: the difference between the third quartile and the first quartile; kurtosis: the larger the absolute value of the kurtosis is, the larger the difference degree between the steepness degree of the distribution form and the normal distribution is; skewness: the larger the absolute value of the skewness is, the larger the degree of skewness of the distribution form is; abnormal value: the method is characterized in that the method refers to an individual value in a sample, and the value of the individual value is obviously deviated from the rest observed values of the sample to which the individual value belongs; high and low segmentation: the high segmentation yield is more than or equal to 80 percent, and the low segmentation yield is less than or equal to 20 percent.
The score subsection analysis can reflect the score distribution state of the students in the examination, and allows the evaluation object to set the highest score, the lowest score and the score interval by oneself, so that the people number histogram of each score section can be obtained.
The three-rate one-score analysis can reflect the basic conditions of the academic levels of students of all classes of the examination, including excellent rate, good rate and passing rate, and the numerical values can be set by the evaluation object.
The grading and line-reaching analysis can reflect the grading and line-reaching performance of students of each class of the examination, and allows the evaluation object to set the grading line by itself.
The subject performance analysis quotes the superior-average rate of subjects to reflect the superior-inferior performance of each subject of the class of the examination, the superior-inferior performance is used for evaluating the contribution of the analysis subjects to the class score level, the index value is positive, which is the promotion effect, and the index value is negative, which is the hind leg dragging; subject excess average ratio: the discipline excess average rate (average score of this discipline-average score of the grade discipline) is 100%/average score of the grade discipline.
The subject achievement structure distribution utilizes A, B, C, D, E five levels to reflect the distribution of the achievement structures of various subjects of the current exam class, and allows the evaluation subjects to set the percentage of each level by themselves.
The student answering details can reflect the answering conditions of all the questions of the class-level subject; the key student information analyzes the distribution condition of students in the key ranking section by setting the key ranking section, wherein the distribution condition comprises ten names before the class and ten names after the class.
Further, the discipline analysis reporting model in the step S3 includes: the method comprises the following steps of score overview, score segmentation analysis, four-rate one-minute analysis, grading and line-reaching analysis, critical student group analysis, score structure proportion analysis, key student information and subject balance comparison analysis.
The four-rate one-score analysis can reflect the basic conditions of the academic levels of students of all classes of the examination, including excellent rate, good rate, passing rate and low score, the number of people of four rates of all classes is counted visually by using a histogram or a table, then the comprehensive ranking of all classes is calculated, and the comprehensive ranking calculation method comprises the following steps: and taking the average of the average ranking, the excellent ranking, the good ranking and the passing ranking for ranking.
The critical student group analysis can reflect the number distribution condition of each class in the exam in critical states of different grading lines so as to remind the classes to pay attention in time, and can perform critical student conversion in time, improve school learning rate and allow an evaluation object to set the critical student grading lines by self.
The key student information analyzes the distribution condition of students in the key ranking section by setting the key ranking section, provides four ranking sections and allows the evaluation object to be set by oneself.
The discipline balance comparative analysis is to investigate the contribution of a certain discipline to the comprehensive level of the class discipline based on the actual comprehensive level performance, and carry out comprehensive analysis by combining the overall corresponding situation of the examination, and extract the index of 'discipline excess average rate' which reflects the academic level, so as to evaluate the contribution of the analytical discipline to the school score level, wherein the index value is positive, which is the promotion effect, and is negative, which is the hind leg; subject excess average ratio: the discipline excess average rate (average score of this discipline-average score of the grade discipline) is 100%/average score of the grade discipline.
Further, the calibration analysis report model in the step S3 includes: the method comprises the following steps of score overview, score segmentation analysis, four-rate one-minute analysis, grading and line-reaching analysis, critical student group analysis, score structure proportion analysis, key student information and subject balance comparison analysis.
Further, the comprehensive report analysis model in the step S3 includes: the comprehensive achievement table, the achievement grading table, the ranking grading table, the arrival line table, the class comparison table, the subtotal scoring table, the rolling surface analysis table and the rolling surface analysis comparison table among classes, and the analysis of all the tables can be analyzed from a single subject and a single class and can also be analyzed from a whole subject and a whole class.
Further, before determining the type of the collected education basic data, preprocessing the collected education basic data, wherein the preprocessing includes unifying formats and removing noise and redundant data, is further included in the preset types of step S3.
Further, in the step S4, the evaluating the student learning situation includes evaluating the student personal, the scroll, the class, the subject, the school grade and the comprehensive analysis in six dimensions.
An education evaluation apparatus based on an education big data portrait, comprising:
the data collection module is used for collecting education basic data;
the classification module is used for determining the type of the collected education basic data from preset types;
the model analysis module is used for inputting the education basic data of the determined type into an analysis model obtained through training to obtain an analysis result output by the analysis model, and the analysis model comprises a personal analysis model, a rolling analysis model, a class analysis model, a subject analysis model, a school grade analysis model and a comprehensive report analysis model;
and the evaluation module is used for evaluating the learning situation based on the analysis result.
Further, still include:
and the model training module is used for collecting education sample data, dividing the education sample data into preset types, and training a preset analysis model according to the divided education sample data.
Further, the preset types include pre-class work, on-class test, post-class work, class practice work, unit test, interim test, and end-of-term test.
Further, the model training module further comprises:
and the preprocessing module is used for preprocessing the collected education basic data, wherein the preprocessing comprises uniform format and noise and redundant data removal.
Further, the evaluation module evaluates the student learning conditions by six-dimensional evaluation on student personal, scroll, class, subject, school, and comprehensive analysis.
The invention has the advantages that:
the learning situation evaluation method can deeply analyze and mine the education basic data, realize the integration of the education basic data and break the data sharing barriers of information existing in provincial and urban education bureaus, school leaders, senior leaders and the like.
For students, personalized and intelligent learning guidance for each student is realized.
For teachers, the learning conditions of students can be known in real time, and real-time studying condition analysis reports enable the teachers to quickly and accurately master teaching effects so as to adjust teaching strategies in time.
For parents, the children can see the learning progress and know the learning condition at a glance.
To the personnel of education office, can develop the teaching management work conveniently, clearly manage student's study archives.
[ description of the drawings ]
FIG. 1 is a flow chart of the academic aptitude evaluation method of the present invention;
FIG. 2 is a structural diagram of the evaluation of academic aptitude of the present invention;
fig. 3 is a block diagram of an education evaluation apparatus according to the present invention.
[ detailed description ] embodiments
The present invention will be further described with reference to the following specific examples.
A learning situation evaluation method based on education big data images is shown in figure 1 and comprises the following steps:
step S1, collecting education basic data;
step S2, determining the type of the collected education basic data from the preset types;
step S3, inputting the education basic data of the determined type into the analysis model obtained by training to obtain the analysis result output by the analysis model; the analysis model comprises a personal analysis model, a rolling analysis model, a class analysis model, a subject analysis model, a school grade analysis model and a comprehensive report analysis model;
wherein, (1), the personal analysis model includes: the general description of the scores of each department of the examinee, the hierarchical analysis of each department of the examination and the tendency of the scores of the examinee; the score profile attributes of each department of the examinees comprise subjects, original scores, class ranking, school ranking, examinee answer sheets, average score numbers lower than the whole class and score lowest TOP 3; each department level in the analysis of each department level of the examination is divided into class level statistics and school level statistics, including the comparison of the score of the examinee under a certain subject with the highest score of the whole class or the whole school, and the average score of the whole class or the whole school; the score trend of the examinees is the comparison of the personal scores with the trends of class average score and school average score.
(2) The rolling surface analysis model comprises: the analysis of score overview, quality analysis of the single questions, the scoring condition of the single questions of each class, the answering details of students, knowledge point analysis and examination paper comment is carried out aiming at a certain subject of a certain examination.
The score general profiles of a certain subject in a certain examination comprise statistical average scores, highest scores, lowest scores, standard deviations, difficulty, reliability, discrimination and difficulty proportion (proportion of difficult to distinguish and easy to subject), and the score general profiles can reflect the test paper general profiles of the subject. Standard deviation: the method comprises the steps of representing absolute dispersion degrees among examination scores of all examinees, wherein the larger the value is, the larger the dispersion degree of the scores among individuals is, and conversely, the smaller the value is, the smaller the dispersion degree of the scores among the individuals is; difficulty: the difficulty coefficient of a certain question or subject represents the difficulty degree of the test question, the difficulty coefficient is between 0 and 1, and the larger the value is, the simpler the test question is; reliability: the stability of the test results is between 0 and 1, and the larger the value, the higher the quality of the test paper (more than 0.9 is excellent, 0.7 to 0.9 is good, 0.35 to 0.7 is medium, and less than 0.35 is low); and (3) discrimination: the degree of distinguishing the examination questions on the abilities of the examinees is represented, the larger the value is, the better the effect of distinguishing the examinees with different abilities is, the larger the value of the examination questions is, the value range is from-1.00 to +1.00, and the evaluation standard is as follows: 0.4 or more is preferable, 0.3 to 0.39 is preferable, 0.20 to 0.29 is preferable, and 0.19 or less is not preferable; difficulty ratio: the score proportion of the difficult questions, the medium questions and the simple questions, wherein the score of the small questions is less than 30% as the difficult questions, the score is between 30% and 80% as the medium questions, and the score of the small questions is more than 80% as the easy questions.
The quality analysis attributes of the single question include: the system comprises a question number, a question type, an over-score, an average score, a score rate, a difficulty coefficient, a discrimination degree, a standard deviation, a zero score proportion and an over-score proportion.
The attribute of each class of single-question scoring condition comprises the following steps: question number, question type, total score, and score of each class.
The student answering situation attributes include: question number, question type, correct answer, score, answer (choice questions show the choice probability of each choice).
The knowledge point analysis attributes include: sequence number, knowledge point, score ratio of knowledge point and corresponding question.
The examination paper comment and comment pointer displays question numbers, question types, question stems, class scores, grade scores, full scores, lost scores and answer details for independent questions.
(3) The class analysis model comprises: selecting a class of the examination to obtain the score general view, quartile analysis, score subsection analysis, third rate and first grade analysis, grading arrival line analysis, subject examination performance analysis, subject score structure distribution, student answering details and important student information of the class.
The performance profiles for a class include: the highest score, the lowest score, the average score, the standard deviation, the median and the difference coefficient, and the score profile can reflect the examination profile of the students in the examination; standard deviation: the method comprises the steps of representing absolute dispersion degrees among examination scores of all examinees, wherein the larger the value is, the larger the dispersion degree of the scores among individuals is, and conversely, the smaller the value is, the smaller the dispersion degree of the scores among the individuals is; median: the score at the middle position in the scores of the examinees arranged from low to high; coefficient of difference: the ratio of the standard deviation to the average score represents the relative degree of dispersion of different samples, and a larger value represents a larger relative degree of dispersion, whereas a smaller value represents a smaller relative degree of dispersion.
In quartile analysis, the first quartile (Q1): the 25 th% of the test taker's scores in low to high order; third quartile (Q3): the 75% of the test taker's scores in low to high order; quartering distance IQR: the difference between the third quartile and the first quartile; kurtosis: the larger the absolute value of the kurtosis is, the larger the difference degree between the steepness degree of the distribution form and the normal distribution is; skewness: the larger the absolute value of the skewness is, the larger the degree of skewness of the distribution form is; abnormal value: the method is characterized in that the method refers to an individual value in a sample, and the value of the individual value is obviously deviated from the rest observed values of the sample to which the individual value belongs; high and low segmentation: the high segmentation yield is more than or equal to 80 percent, and the low segmentation yield is less than or equal to 20 percent.
The score subsection analysis can reflect the score distribution state of the students in the examination, and allows the evaluation object to set the highest score, the lowest score and the score interval by oneself, so that the people number histogram of each score section can be obtained.
The three-rate one-score analysis can reflect the basic conditions of the academic levels of students of all classes of the examination, including excellent rate, good rate and passing rate, and the numerical values can be set by the evaluation object.
The grading and line-reaching analysis can reflect the grading and line-reaching performance of students of each class of the examination, and allows the evaluation object to set the grading line by itself.
The subject performance analysis quotes the superior-average rate of subjects to reflect the superior-inferior performance of each subject of the class of the examination, the superior-inferior performance is used for evaluating the contribution of the analysis subjects to the class score level, the index value is positive, which is the promotion effect, and the index value is negative, which is the hind leg dragging; subject excess average ratio: the discipline excess average rate (average score of this discipline-average score of the grade discipline) is 100%/average score of the grade discipline.
The subject achievement structure distribution utilizes A, B, C, D, E five levels to reflect the distribution of the achievement structures of various subjects of the current exam class, and allows the evaluation subjects to set the percentage of each level by themselves.
The student answering details can reflect the answering conditions of all the questions of the class-level subject; the key student information analyzes the distribution condition of students in the key ranking section by setting the key ranking section, wherein the distribution condition comprises ten names before the class and ten names after the class.
(4) The discipline analysis report model comprises the following components: the method comprises the following steps of score overview, score segmentation analysis, four-rate one-minute analysis, grading and line-reaching analysis, critical student group analysis, score structure proportion analysis, key student information and subject balance comparison analysis.
The four-rate one-score analysis can reflect the basic conditions of the academic levels of students of all classes of the examination, including excellent rate, good rate, passing rate and low score, the number of people of four rates of all classes is counted visually by using a histogram or a table, then the comprehensive ranking of all classes is calculated, and the comprehensive ranking calculation method comprises the following steps: and taking the average of the average ranking, the excellent ranking, the good ranking and the passing ranking for ranking.
The critical student group analysis can reflect the number distribution condition of each class in the exam in critical states of different grading lines so as to remind the classes to pay attention in time, and can perform critical student conversion in time, improve school learning rate and allow an evaluation object to set the critical student grading lines by self.
The key student information analyzes the distribution condition of students in the key ranking section by setting the key ranking section, provides four ranking sections and allows the evaluation object to be set by oneself.
The discipline balance comparative analysis is to investigate the contribution of a certain discipline to the comprehensive level of the class discipline based on the actual comprehensive level performance, and carry out comprehensive analysis by combining the overall corresponding situation of the examination, and extract the index of 'discipline excess average rate' which reflects the academic level, so as to evaluate the contribution of the analytical discipline to the school score level, wherein the index value is positive, which is the promotion effect, and is negative, which is the hind leg; subject excess average ratio: the discipline excess average rate (average score of this discipline-average score of the grade discipline) is 100%/average score of the grade discipline.
(5) The calibration analysis report model comprises: the method comprises the following steps of score overview, score segmentation analysis, four-rate one-minute analysis, grading and line-reaching analysis, critical student group analysis, score structure proportion analysis, key student information and subject balance comparison analysis.
(6) The comprehensive report analysis model comprises: the comprehensive achievement table, the achievement grading table, the ranking grading table, the arrival line table, the class comparison table, the subtotal scoring table, the rolling surface analysis table and the rolling surface analysis comparison table among classes, and the analysis of all the tables can be analyzed from a single subject and a single class and can also be analyzed from a whole subject and a whole class.
S3.1, collecting education sample data;
s3.2, dividing the education sample data into preset types, wherein the preset types comprise pre-class work, current class detection, post-class work, class practice work, unit detection, period detection and end-of-term detection;
and S3.3, training a preset analysis model according to the divided education sample data.
In addition, before determining the type of the collected education basic data, preprocessing is further included, wherein the preprocessing includes unifying formats and removing noise and redundant data.
And step S4, evaluating the student learning condition based on the analysis result.
Evaluating student learning conditions includes evaluating student individuals, books, classes, disciplines, school classes and comprehensive analysis in six dimensions.
As shown in fig. 3, the education evaluating apparatus based on the education macro image includes:
the data collection module 1 is used for collecting education basic data;
the classification module 2 is used for determining the type of the collected education basic data from the preset types;
and the preprocessing module 3 is used for preprocessing the collected education basic data, wherein the preprocessing comprises uniform format and noise and redundant data removal.
The model analysis module 4 is used for inputting the education basic data of the determined type into the analysis model obtained by training to obtain the analysis result output by the analysis model, wherein the analysis model comprises a personal analysis model 41, a rolling surface analysis model 42, a class analysis model 43, a subject analysis model 44, a school grade analysis model 45 and a comprehensive report analysis model 46; the model analysis module further comprises a model training module 40, which is used for collecting education sample data, dividing the education sample data into preset types, and training a preset analysis model according to the divided education sample data; the preset types include pre-class work, on-class test, post-class work, class practice work, unit test, interim test, and end-of-term test.
And the evaluation module 5 is used for evaluating the learning situation based on the analysis result. The evaluation module 5 evaluates the student learning conditions by six-dimensional evaluation on the student personal, book face, class, subject, school grade and comprehensive analysis.
The learning situation evaluation method can deeply analyze and mine the education basic data, realize the integration of the education basic data and break the data sharing barriers of information existing in provincial and urban education bureaus, school leaders, senior leaders and the like.
For students, personalized and intelligent learning guidance for each student is realized.
For teachers, the learning conditions of students can be known in real time, and real-time studying condition analysis reports enable the teachers to quickly and accurately master teaching effects so as to adjust teaching strategies in time.
For parents, the children can see the learning progress and know the learning condition at a glance.
To the personnel of education office, can develop the teaching management work conveniently, clearly manage student's study archives.
The above-mentioned embodiments are only preferred embodiments of the present invention, and the scope of the present invention is not limited by these embodiments, except for the cases listed in the specific embodiments; all equivalent variations of the methods and principles of the present invention are intended to be within the scope of the present invention.
Claims (16)
1. A learning condition evaluation method based on education big data images is characterized by comprising the following steps:
step S1, collecting education basic data;
step S2, determining the type of the collected education basic data from the preset types;
step S3, inputting the education basic data of the determined type into the analysis model obtained by training to obtain the analysis result output by the analysis model;
the analysis model comprises a personal analysis model, a rolling analysis model, a class analysis model, a subject analysis model, a school grade analysis model and a comprehensive report analysis model;
and step S4, evaluating the student learning condition based on the analysis result.
2. The method for evaluating learning situation based on education big data image according to claim 1, wherein the training process of the analytical model in step S3 includes the following steps:
s3.1, collecting education sample data;
s3.2, dividing the education sample data into preset types;
and S3.3, training a preset analysis model according to the divided education sample data.
3. The method for evaluating learning situation based on education big data image according to claim 2, wherein in step S3.2, the preset types include: pre-class work, current class testing, post-class work, class practice work, unit testing, mid-term testing, and end-of-term testing.
4. The method for evaluating a learning situation based on an educational big data image according to claim 1, wherein the personal analysis model in the step S3 comprises: the general description of the scores of each department of the examinee, the hierarchical analysis of each department of the examination and the tendency of the scores of the examinee;
the score profile attributes of each department of the examinees comprise subjects, original scores, class ranking, school ranking, examinee answer sheets, average score numbers lower than the whole class and score lowest TOP 3;
each department level in the analysis of each department level of the examination is divided into class level statistics and school level statistics, including the comparison of the score of the examinee under a certain subject with the highest score of the whole class or the whole school, and the average score of the whole class or the whole school;
the score trend of the examinees is the comparison of the personal scores with the trends of class average score and school average score.
5. The method for evaluating a learning situation based on an educational big data image according to claim 1, wherein the scroll analysis model in step S3 comprises: the analysis of score overview, quality analysis of the single questions, the scoring condition of the single questions of each class, the answering details of students, knowledge point analysis and examination paper comment is carried out aiming at a certain subject of a certain examination.
6. The method for evaluating a learning situation based on an educational big data image according to claim 1, wherein the class analysis model in the step S3 comprises: selecting a class of the examination to obtain the score general view, quartile analysis, score subsection analysis, third rate and first grade analysis, grading arrival line analysis, subject examination performance analysis, subject score structure distribution, student answering details and important student information of the class.
7. The method for evaluating a learning situation based on an educational big data portrait according to claim 1, wherein the discipline analysis report model in the step S3 comprises: the method comprises the following steps of score overview, score segmentation analysis, four-rate one-minute analysis, grading and line-reaching analysis, critical student group analysis, score structure proportion analysis, key student information and subject balance comparison analysis.
8. The method for evaluating an educational situation based on an image of big data according to claim 1, wherein the calibration analysis report model in step S3 comprises: the method comprises the following steps of score overview, score segmentation analysis, four-rate one-minute analysis, grading and line-reaching analysis, critical student group analysis, score structure proportion analysis, key student information and subject balance comparison analysis.
9. The method for evaluating a learning situation based on an image of education big data according to claim 1, wherein the comprehensive report analysis model in the step S3 includes: the comprehensive achievement table, the achievement grading table, the ranking grading table, the arrival line table, the class comparison table, the subtotal scoring table, the rolling surface analysis table and the rolling surface analysis comparison table among classes, and the analysis of all the tables can be analyzed from a single subject and a single class and can also be analyzed from a whole subject and a whole class.
10. The method for evaluating an educational situation based on an image of big educational data according to claim 2 or 3, wherein the step S3 further comprises preprocessing the collected educational basic data before determining the type of the collected educational basic data, wherein the preprocessing comprises unifying the format and removing noise and redundant data.
11. The method for evaluating the learning situation based on the education big data image according to the claim 1, wherein in the step S4, the evaluation of the learning situation of the student includes the evaluation of the student' S personal, scroll, class, subject, school grade and comprehensive analysis in six dimensions.
12. An education evaluation apparatus based on an education big data portrait, comprising:
the data collection module is used for collecting education basic data;
the classification module is used for determining the type of the collected education basic data from preset types;
the model analysis module is used for inputting the education basic data of the determined type into an analysis model obtained through training to obtain an analysis result output by the analysis model, and the analysis model comprises a personal analysis model, a rolling analysis model, a class analysis model, a subject analysis model, a school grade analysis model and a comprehensive report analysis model;
and the evaluation module is used for evaluating the learning situation based on the analysis result.
13. An educational evaluation apparatus based on an educational big data portrait according to claim 12, further comprising:
and the model training module is used for collecting education sample data, dividing the education sample data into preset types, and training a preset analysis model according to the divided education sample data.
14. An education evaluation apparatus based on education macro data portrait according to claim 12 or 13, wherein the preset types include pre-class work, current class test, post-class work, class practice work, unit test, period test and end-of-term test.
15. An educational evaluation apparatus based on educational big data portrait according to claim 12, wherein the model training module further comprises:
and the preprocessing module is used for preprocessing the collected education basic data, wherein the preprocessing comprises uniform format and noise and redundant data removal.
16. The apparatus of claim 12, wherein the evaluation module evaluates the student's learning conditions in six dimensions of student personal, scroll, class, subject, school, and general analysis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011644862.XA CN113159480A (en) | 2020-12-31 | 2020-12-31 | Learning condition evaluation method and device based on education big data image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011644862.XA CN113159480A (en) | 2020-12-31 | 2020-12-31 | Learning condition evaluation method and device based on education big data image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113159480A true CN113159480A (en) | 2021-07-23 |
Family
ID=76878340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011644862.XA Pending CN113159480A (en) | 2020-12-31 | 2020-12-31 | Learning condition evaluation method and device based on education big data image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113159480A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114971962A (en) * | 2022-05-17 | 2022-08-30 | 北京十六进制科技有限公司 | Student homework evaluation method and device, electronic device and storage medium |
| CN115081965A (en) * | 2022-08-22 | 2022-09-20 | 山东悦知教育科技有限公司 | Big data analysis system for learning situation and learning situation server |
-
2020
- 2020-12-31 CN CN202011644862.XA patent/CN113159480A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114971962A (en) * | 2022-05-17 | 2022-08-30 | 北京十六进制科技有限公司 | Student homework evaluation method and device, electronic device and storage medium |
| CN115081965A (en) * | 2022-08-22 | 2022-09-20 | 山东悦知教育科技有限公司 | Big data analysis system for learning situation and learning situation server |
| CN115081965B (en) * | 2022-08-22 | 2022-11-25 | 山东悦知教育科技有限公司 | Big data analysis system of condition of learning and condition of learning server |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Garfield et al. | Assessment in statistics education: Issues and challenges | |
| Rosário et al. | An explanatory model of the intention to continue studying among nontraditional university students | |
| Johnson et al. | The predictive validity of the early warning system tool | |
| CN110232343B (en) | Child personalized behavior statistical analysis system and method based on latent variable model | |
| CN113159480A (en) | Learning condition evaluation method and device based on education big data image | |
| Hossler et al. | The role of institutional practices in college student persistence | |
| Getachew | Factors affecting student’s academic performance in Ahuntegen general secondary school, North Wollo Zone, Ethiopia | |
| Crocker | Introduction to measurement theory | |
| Rowe et al. | Constructing and using educational performance indicators | |
| Lawrence et al. | Student personality type versus grading procedures in intermediate accounting courses | |
| Shahmirzadi | Validation of a language center placement test: Differential item functioning | |
| Paraschiva et al. | A study of the evolution of educational efficiency: Romanian case | |
| Sokele et al. | The importance of synchronous online learning for student success in exams | |
| Ferand et al. | The relationship of prior FFA membership on perceived ability to manage an FFA chapter | |
| Jakupec et al. | PISA–Shocks, after shocks and misconceptions | |
| CN117455126B (en) | Ubiquitous practical training teaching and evaluation management system and method | |
| Faleye et al. | Differential item functioning of 2015/2016 Biology multiple Choice items of Osun State joint promotion examination | |
| Lawrence et al. | PERCEPTIONS OF MATHEMATICS AND POSITIONING TOWARDS THE DISCIPLINE–PRE-SERVICE PRIMARY TEACHERS’ATTITUDES IN SERBIA | |
| Gong | Analysis of Scl-90 Survey Results of Chinese University Freshmen in Recent Five Years and Determination of Their Norm | |
| Njoku et al. | Post Unified Tertiary Matriculation Examination as predictor of students’ final degree results | |
| CN114282755A (en) | Student behavior data analysis method | |
| Getachew | Analysis of factors affecting students’ academic performance in Gubalafto Woreda: the case of Ahuntegen general secondary school, North Wollo Zone, Amhara, Ethiopia | |
| Sun | Application of Cluster Analysis in the Management of College Students' Mental Health Education | |
| Fajariah et al. | Analysis of Data Collection and Measurement of Progress in The English Education Curriculum | |
| Bene et al. | Strengths of English Self-Efficacy Beliefs among Arabic-Native-Speaker University Students whose Language of Instruction is English |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210723 |