CN112734212A

CN112734212A - Student homework behavior portrait method and device and electronic equipment

Info

Publication number: CN112734212A
Application number: CN202011642362.2A
Authority: CN
Inventors: 李梦圆; 杨熙; 饶丰
Original assignee: Beijing Yiyi Education Technology Co ltd
Current assignee: Beijing Yiyi Education Technology Co ltd
Priority date: 2020-12-31
Filing date: 2020-12-31
Publication date: 2021-04-30

Abstract

The invention provides a student homework behavior portrait method, a device, electronic equipment and a computer readable storage medium, wherein the method comprises the following steps: converting the acquired feature sample of the student homework behavior portrait into a feature vector; determining the optimal clustering number according to the contour coefficient, and randomly extracting characteristic samples with the optimal clustering number as initial intra-class central points; sequentially extracting each of the rest characteristic samples, dividing the characteristic sample into classes corresponding to the class center points with the Euclidean distance closest to the characteristic sample, and updating the class center points; and obtaining the average value of each classification behavior according to the average value of the achievement indexes in the classification for sequencing and reading. The embodiment of the invention applies the student homework behavior index and the student learning performance index to the portrait portrayal of individual students and student groups, can perform labeling portrayal on the student groups, and is convenient for teachers to perform layered teaching and layered guidance.

Description

Student homework behavior portrait method and device and electronic equipment

Technical Field

The invention relates to the technical field of education, in particular to a student homework behavior imaging method and device, electronic equipment and a computer readable storage medium.

Background

The homework is a very important link in the teaching process, is a key link for connecting the in-class learning and the out-of-class learning of students, and is the most direct and effective mode and means for consolidating the learning effect of the students and tracking the learning state of the students by teachers. Therefore, it is very important for students, parents and all teaching related parties to record the student work behaviors, form the work behavior portrayal of the students, and monitor, early warn and conduct layered teaching on the student group according to the portrayal result. In the existing work data research, the following problems mainly exist: firstly, the operation data is often used as an auxiliary analysis only by a certain submodule of a research topic and is not deep; secondly, a large number of audience groups are not used as an operation platform, namely, data sources are sparse; thirdly, the description indexes of the operation data are simple, the operation data stay in shallow angles such as operation participation, operation completion and operation scores, and the data mining strength is not enough. Based on the above student portrait and clustering research, the research precision is also deficient due to the reasons of the non-systematic indexes and the poor characteristics.

Disclosure of Invention

In order to solve the existing technical problems, embodiments of the present invention provide a method, an apparatus, an electronic device and a computer-readable storage medium for representing a student's homework behavior.

In a first aspect, an embodiment of the present invention provides a method for representing student homework behaviors, including:

converting the acquired student work behavior portrait feature sample into a feature vector in a sample feature space of a feature training clustering model;

determining the optimal clustering number according to the contour coefficient of the student work behavior portrait feature samples, and randomly extracting the student work behavior portrait feature samples with the optimal clustering number as initial intra-class center points;

sequentially extracting feature samples of each rest student homework behavior portrait, dividing the feature samples into classes corresponding to the intra-class central points with the nearest Euclidean distance from the feature samples, and updating the intra-class central points;

and obtaining the average value of each classification behavior according to the average value of the achievement indexes in the classification for sequencing and reading.

In a second aspect, an embodiment of the present invention provides an apparatus for representing a student's homework behavior, including:

the characteristic conversion module is used for converting the acquired student work behavior portrait characteristic samples into characteristic vectors in a sample characteristic space of a characteristic training clustering model;

the characteristic extraction module is used for determining the optimal clustering number according to the profile coefficient of the student operation behavior image characteristic samples, and randomly extracting the student operation behavior image characteristic samples with the optimal clustering number as initial intra-class central points;

the characteristic dividing module is used for sequentially extracting characteristic samples of each rest student homework behavior portrait, dividing the characteristic samples into classes corresponding to the intra-class central points with the nearest Euclidean distance from the characteristic samples, and updating the intra-class central points;

and the classification acquisition module is used for acquiring the average value of each classification behavior according to the average value of the achievement indexes in the classification to perform sequencing and interpretation.

In a third aspect, an embodiment of the present invention provides an electronic device, which includes a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, where the transceiver, the memory, and the processor are connected via the bus, and when the computer program is executed by the processor, the steps in the method for representing the student's homework behavior are implemented.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps in the above method for representing student's homework behavior.

The method, the device, the electronic equipment and the computer readable storage medium provided by the embodiment of the invention can be used for portraying the portrait of the student individual and the student group by establishing the student homework behavior portraits which are divided into two main categories respectively used as student homework behavior indexes and student learning score indexes.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments or the background art of the present invention, the drawings required to be used in the embodiments or the background art of the present invention will be described below.

FIG. 1 is a flow chart of a method for representing the performance of a student's homework according to an embodiment of the present invention;

FIG. 2 is a flow chart of another student assignment behavior representation method provided by an embodiment of the invention;

FIG. 3 is a flow chart of another student assignment behavior representation method provided by an embodiment of the invention;

FIG. 4 is a schematic diagram illustrating an exemplary embodiment of an apparatus for representing a student's homework behavior;

FIG. 5 is a schematic diagram illustrating a specific structure of a feature extraction module in the device for representing student's homework behaviors according to the embodiment of the present invention;

fig. 6 is a schematic structural diagram of an electronic device for representing a student's homework behavior according to an embodiment of the present invention.

Detailed Description

For clarity and conciseness of description of embodiments of the present invention, a brief introduction to the relevant concepts or technologies is first given:

as will be appreciated by one skilled in the art, embodiments of the present invention may be embodied as methods, apparatus, electronic devices, and computer-readable storage media. Thus, embodiments of the invention may be embodied in the form of: entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), a combination of hardware and software. Furthermore, in some embodiments, embodiments of the invention may also be embodied in the form of a computer program product in one or more computer-readable storage media having computer program code embodied in the medium.

The computer-readable storage media described above may take any combination of one or more computer-readable storage media. The computer-readable storage medium includes: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the computer-readable storage medium include: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only Memory (ROM), an erasable programmable read-only Memory (EPROM), a Flash Memory, an optical fiber, a compact disc read-only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any combination thereof. In embodiments of the invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, device, or apparatus.

The computer program code embodied on the computer readable storage medium may be transmitted using any appropriate medium, including: wireless, wire, fiber optic cable, Radio Frequency (RF), or any suitable combination thereof.

Computer program code for carrying out operations for embodiments of the present invention may be written in one or more programming languages, including an object oriented programming language such as: java, Smalltalk, C + +, and also include conventional procedural programming languages, such as: c or a similar programming language. The computer program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be over any of a variety of networks, including: a Local Area Network (LAN) or a Wide Area Network (WAN), which may be connected to the user's computer, may be connected to an external computer.

Embodiments of the present invention are described below with reference to flowchart illustrations and/or block diagrams of methods, apparatus, electronic devices, and computer-readable storage media according to embodiments of the invention.

It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions. These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.

These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing apparatus to function in a particular manner. Thus, the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.

The embodiments of the present invention will be described below with reference to the drawings.

FIG. 1 is a flowchart illustrating a method for representing a student's homework behavior according to an embodiment of the present invention. On the data source acquisition end, behavior information such as questions, corrections, report checking and the like of students on the operation platform is recorded mainly through an APP (application) embedded point technology.

As shown in fig. 1, the method includes:

s101, burying points on a homework platform, and tracking and recording student homework and model examination information;

when a student executes homework operation on the homework platform, if a buried point is arranged below the corresponding interface area, a series of behavior data of the student is recorded and is recorded into the database. The types of data that may be recorded include the point in time of the open/commit, the type of the problem, the length of the problem, etc.

And S102, collecting and storing original data in a classified mode.

The data obtained by the buried points are stored in a teacher end, a student end, a family end and a model examination end. The teacher end mainly stores teacher's personal information and its job layout information. The teacher personal information mainly comprises: information such as school, subject, grade and class; the job arrangement information includes: job type, job publishing time, job submitting ending time, question information, question number, whether to check the job, whether to urge completion, whether to urge correction and the like.

The student end stores the personal information of students and the homework behavior information of students. The student personal information comprises: school, grade, class, age, etc. Student's homework behavior information is mainly including with the topic as key point: (1) basic information of the job, such as job subjects, job release and closing time, job forms, number of questions and the like; (2) basic information of the subject, such as teaching materials, units, knowledge points, types, difficulty, standards and the like corresponding to the subject; (3) recording answering conditions, such as operation starting and submitting time, answering time of each question, completion conditions, scores, correct times and results of wrong questions and the like; (4) and (4) checking the behavior data of the error report, and recording the information such as the time and the times of checking the error report.

The parental terminal stores the information related to the parents and the students and the homework information arranged by the parents for the students, such as the information related to the parents of the students, the time for the parents to arrange the homework, the information of the subjects for arranging the homework, and the like.

The model examination end stores student personal information, examination information and student answering information, and also takes the subject as a key point, and the method comprises the following steps: (1) examination basic information such as examination subjects, opening and ending time, grades and the like; (2) basic information of the subject, such as knowledge points, difficulty, standards and the like; (3) and recording the answering condition, such as answering time, completion condition, achievement and the like.

FIG. 2 is a flow chart of another student assignment behavior representation method according to an embodiment of the present invention. First, a student's homework behavior portrait system is established, and then the characteristic index of student's homework behavior portrait is preset in the portrait system. The preset characteristic index of the student work behavior portrait is not necessarily the final portrait characteristic index, and the generated student work behavior portrait has various uses through subsequent missing value analysis and significance test.

As shown in fig. 2, the method includes:

step S201, a student homework behavior portrait system is constructed, and students are preset as behavior portrait characteristic indexes;

in the step, student homework behavior image characteristic indexes are constructed according to the collected original data, meanwhile, the indexes are divided into 6 types on the basis of literature research, and the details can refer to table 1.

The preliminarily constructed characteristic indexes of the student homework behavior portrait are not final results, and the grouped characteristic indexes of the student homework behavior portrait need to be subjected to significance test to screen out indexes meeting requirements. For example, people generally have a concern about whether an index can distinguish different performance populations, and therefore, the significance test is to group sample populations and then test whether an index has significant differences in performance among the different groups. Teachers are often concerned about the performance, grade and subject of students. Therefore, the index needs to be subjected to the three-layer inspection, and the detailed grouping and inspection steps can refer to S202 and S203.

The main dimensions, corresponding analysis sub-dimensions and related operation platform index marks of the student operation behavior portrait are shown in table 1, table 1 only shows part of operation platform indexes, and the specifically used platform indexes can be modified or added according to different requirements.

TABLE 1

As shown in table 1, the work platform index is calculated as follows:

1. number of times of use of work platform

(1) Definition of

The number of times of using each homework of students on the platform.

(2) Computing method

The number of times that the student has homework records on the platform is summed up in subject.

2. Mean value of total operating duration

(1) Definition of

In a homework, the total homework duration represents the length of time in minutes from the opening of the homework to the submission of the homework by the student.

(2) Computing method

Let T_iIs the total duration of the ith job, O_iOpen time (Open), C for the ith job_iThe Commit time (Commit, in the case of multiple submissions, whichever is the last submission) of the ith job is:

T_i＝C_i-O_i(conversion of Unit unity into minutes)

The students are designed to complete n times of homework, and the average time length of the total homework of the students is

Then there is

(unit is minute)

The index is calculated in disciplines.

3. Standard deviation of total operating duration

(1) Definition of

The standard deviation characterizes the degree of dispersion of an index around the mean value by the distance of each index value from the mean value of the index. The larger the standard deviation is, the more dispersed the index distribution is, namely the index performance is unstable; the smaller the standard deviation is, the more concentrated the index distribution is, namely the overall performance is more regular and stable.

(2) Computing method

Let the standard deviation of the total working time length be ST and the average value of the total working time length of the students be

The single-time operation duration of the student is T_iAnd if the student completes n homework, the following steps are performed:

4. maximum and minimum total operation duration

(1) Definition of

And according to disciplines, the maximum value and the minimum value in the total work time of the students.

(2) Computing method

T_max＝max(T_i)

T_min＝min(T_i) Wherein i is 1, 2

5. Mean of length of time to submit jobs ahead of time

(1) Definition of

The advance submission job time refers to the difference between the time when the student actually submits the job and the time when the teacher requests to submit the job, and the unit is minutes. When the teacher arranges the homework, the completion time range can be set to 1 day or more than 1 day, so that the students can complete the homework 1 day or more than 1 day in advance.

(2) Computing method

Is provided with AC_i(Actual Commit) is the time that the student actually submitted the ith assignment, RC_i(Required Commit) is the Commit time, PC, Required by the ith job teacher_i(previouslly Commit) is the time that student's ith assignment was submitted in advance, then:

PC_i＝RC_i-AC_i

if the value is changed to negative, the student delays submitting the homework.

Is provided with

Mean value of homework submitted by students in advance, when n is homework done by students, then

The index is calculated in disciplines.

6. Number of operations completed, number of operations not completed, and operation completion rate

(1) Definition of

The number of the completion of the homework is the number of the homework which is submitted and recorded on the platform by the student.

The number of unfinished homework is the number of homework which is recorded by students on the platform but not submitted.

Operation completion rate is the number of operation completions/total number of operations

(2) Computing method

The calculation mode is defined above, and the index is calculated in disciplines.

7. Mean and standard deviation of effective question-making duration

(1) Definition of

The effective question making duration refers to the time actually spent on making a question by a student in one-time homework, and the effective question making time of a single-time homework of the student is obtained by adding the answering time (duration) of each question in the homework. When students use the platform to do questions, the following three situations can appear:

(a) there is a network request between the topic and the topic switch, resulting in latency.

(b) The students quit midway when doing the questions, and the time for solving the questions is paused until the students enter again to continue the statistics.

(c) In some homework, after the student finishes submitting one question, the student can select whether to enter the next question (instead of automatically jumping to the next question by the system). Under the three conditions, the effective exercise time of the students is unequal to the total work time of the students.

(2) Computing method

Let the effective question-making duration of a single student's homework be E_i(effective), the students complete n homework totally, the average value of the effective exercise duration of the single homework of the students is

Then there are:

the index is calculated according to disciplines

The standard deviation is obtained based on the mean result, and the calculation mode can be calculated by referring to the standard deviation of the other indexes, which is not described herein.

8. Overall operating efficiency

(1) Definition of

The work efficiency refers to the proportion of time actually put into the exercise in the work process of the students, and the work efficiency can be used for depicting the concentration degree of the students.

(2) Computing method

Let the work efficiency of a single student's homework be WE_i(Work Efficiency) the effective test time of the student in the homework is E_i(Efficient Work Time), total job Time is T_i(Total Work Time), then

WE_i＝E_i/T_i

The students are designed to complete n times of homework in total, and the average homework efficiency is

Then:

the index is calculated in disciplines.

9. Location of student work efficiency among whole students

(1) Definition of

The index can be understood as an evaluation index of the work efficiency, which is the ratio of the work efficiency of a certain student to the overall work efficiency of the student. When the index is more than or equal to 1, the operation efficiency of the famous student is not inferior to the whole; when the index is less than 1, the result shows that the efficiency of the student is inferior to the overall efficiency. A larger index indicates a better performance of the student in the population.

(2) Computing method

Let us say that for the general student, n is completed altogether^T(n times for Total clients) with an average job efficiency of

(Work Efficiency) in the same way as the calculation of "Work Efficiency", and the average Work Efficiency of a certain student is

The student has the working efficiency evaluation index of

Then

And

all are subject to disciplinary calculations.

10. Maximum and minimum of effective question-making duration

(1) Definition of

And according to disciplines, the students can effectively make the maximum value and the minimum value of the question time in all the homework.

(2) Computing method

The calculation method can be referred to above, but omitted here.

11. Effective question making time mean value of questions with different difficulties

(1) Definition of

On the platform, aiming at the data analysis, the Chinese has 0-5 difficulty levels, and the mathematics and English have 1-5 difficulty levels. According to analysis, the data condition with the language difficulty of 0 shows that the abnormality exists, so that three subjects take subjects with the difficulty of 1-5 for analysis.

(2) Computing method

If the question with the question difficulty of i is set, the students do n questions together, and the question making time of each question is DT_i(Time for Difficulty) the average Time to problem for a topic of Difficulty i is

Then there are:

12. mean value of different difficulty subject scores

Reference may be made to "effective time mean of questions of different difficulty".

13. Location of different difficulty topic scores in a population

Reference may be made to "location of overall work efficiency among the students as a whole".

14. Mean value and standard deviation of difficulty coefficient of student completing homework

(1) Definition of

The mean value of the difficulty coefficient of the student homework refers to the mean value of the difficulty of all homework subjects done by students, the standard deviation defines the same principle, and the index is calculated according to subjects.

(2) Computing method

The students are designed to complete n questions together, and the difficulty coefficient of each question is D_iThe mean value of difficulty coefficients of student's homework is

Then there are:

the standard deviation calculation is the same.

15. Mean and standard deviation of student assignment scores

(1) Definition of

The student scores the mean and standard deviation of each discipline assignment.

(2) Computing method

Let the student work n homeworks, each homework has a score of S_i(Score), the Score has been converted to a percentile Score, the student assignment Score averages

Then there are:

the operation standard deviation calculation mode is the same.

16. Frequency of week of job report viewing

(1) Definition of

Students see the job reports on average, weekly, over a specified period.

In this statistic, the number of weeks elapsed was calculated as 20 weeks, spanning 3-7 months (5 months total).

This index does not distinguish disciplines, as job report views in the raw data do not distinguish disciplines.

(2) Computing method

If the number of times that the student views the report in the statistical period (20 weeks) is CR (checking report), and the frequency of the job report viewing Week is CR _ Week, there are:

CR_Week＝CR/20

17. correction rate of wrong questions

(1) Definition of

The wrong question correction rate refers to the probability that students correct the questions wrongly made by themselves. The index does not distinguish between disciplines because the original data does not distinguish between disciplines.

(2) Computing method

The correction rate of wrong questions is the number of corrected wrong questions/total number of wrong questions

18. Correction rate of wrong questions correction

(1) Definition of

In the corrected subjects, correct subject proportion is corrected, and the index also does not distinguish subjects.

(2) Computing method

The correct rate of correction of wrong questions is the number of wrong questions/total number of wrong questions

19. Mean and standard deviation of single job submission intervals

(1) Definition of

The single job submission interval refers to the average and standard deviation of the time interval between jobs and jobs after the jobs are sorted by start time if the student completes several jobs within one day.

(2) Computing method

Setting the time interval of student's homework as T_iIn the counting period, n student work intervals are counted, and the average value of the student work submission intervals is

Then:

the indexes do not distinguish disciplines, the standard deviation definition and the calculation mode are slight, and other indexes can be referred.

The raw data and preset indexes are processed and analyzed following the following criteria: (1) removing indexes with deletion values of more than 75%; (2) removing student data which have examination score data and have corresponding preset index deletion rate of more than 80%; (3) filling missing values in the residual student data by adopting an average number or a median according to actual conditions; (4) analyzing the correlation among the indexes, and rejecting the indexes which have high correlation with other indexes and low correlation with the achievement; (5) when clustering analysis is carried out, data standardization processing is carried out on each index, and the index is converted into a Z value, so that each index is dimensionless, and the deviation caused by large index distribution difference in the clustering analysis process is reduced.

Step S202, grouping the characteristic indexes of the student homework behavior portrait on different dimensions;

in the step, according to the actual situation requirement, the characteristic indexes of the student homework behavior portrait are grouped according to the student score, the student grade and the subject (the grouping can be based on multiple dimensions). For students, parents, teachers and other relevant teaching benefits, student scores are the first indicators of concern for tracking learning conditions. For the education researchers, the operation behavior portrait characteristic index is the primary attention index, and grouping results of different types can meet the requirements of different groups.

Step S203, performing differentiation evaluation on the grouped student homework behavior portrait characteristic indexes;

the purpose of carrying out differentiation evaluation on the student homework behavior portrait characteristic indexes is to verify the significance of the student homework behavior portrait characteristic indexes on score grouping, and the method specifically comprises the following steps:

(1) according to different requirements, students are grouped according to the scores of a plurality of tests, such as high grouping, medium grouping and low grouping, or A-level group, B-level group … …, and the like.

(2) For a student's homework behavior profile feature index, a variance test (such as ANOVA variance test) is adopted to verify the significance of the difference between different groups.

First, for a student's homework behavior profile feature index, assuming that it has no significance for a certain group (e.g., score), the following statistical assumptions are formed:

the original assumption is H0, μ a ═ μ B ═ μ N

Mu i represents the average value of the student work behavior image characteristic index in the ith group, and when the student work behavior image characteristic index is assumed to have no significance to the group, the average values of the student work behavior image characteristic indexes in the groups are theoretically equal.

Let us assume H1 ≠ μ A ≠ μ B ≠ μ N

In the alternative hypothesis, the average values of the student work behavior image characteristic indexes in each group are not equal, that is, the student work behavior image characteristic indexes have significance for the groups.

Secondly, calculating the Mean Square Error (MSE) in the group of the student homework behavior profile characteristic index, namely the mean square error of the student homework behavior profile characteristic index in each group, and the mean square error (MSB) between the groups, namely the mean square error of each group relative to the whole, wherein the calculation formula is as follows:

(

represents the variance in the i-th group, k represents the number of groups)

(where. mu. represents the average value of the whole index)

Is provided with

If the F index can significantly distinguish different groups of people, the Mean Square Error (MSE) in a group should be as small as possible (the similarity between the same group is large), and the mean square error (MSB) between groups should be as large as possible (the difference between different groups is large), then the F index should be larger. At this time, the F index follows the F distribution in statistics. A preset significance level a (i.e. a preset probability) which means "if we make the decision to reject the original hypothesis, we can accept that this decision is the upper limit of the probability of error". In the F distribution, according to the preset probability α, a corresponding value F' can be obtained, and the calculation formula is as follows:

where x denotes the F value, where n1 is the number of samples-group number, n2 is the group number-1, and F (x, n1, n2) is the associated probability value. The formula can be used to scale both the probability values (p and α) and the F values.

At this time, there are two ways to determine whether to reject the original hypothesis:

(a) if F' < F, which indicates that F is greater than our preset value, we have reason to reject the original hypothesis, and the probability of making a mistake in making this decision is less than α, i.e., within our acceptance range.

(b) The p-value in the F distribution is calculated from F, and when the p-value is small enough, e.g., less than 0.001, it indicates that we have reason to reject the original hypothesis, and the probability of making a mistake in making this decision is less than 0.001. The original assumption is rejected, namely the assumption that the index has no significant difference among different components is rejected, namely the index is considered to have significance.

After the analysis of the significant difference is completed, the final student homework behavior portrait can be obtained. The inquiry of student's homework behavior portrait is on the basis that the differentiation aassessment was screened out and is showing the index, according to teacher's different demands, inquires student's homework condition, specifically includes:

(1) and inquiring the detailed list. The system can inquire the detail of each index of each individual student in the homework, can definitely know the performance of each behavior dimension of the student, and accurately positions the learning state of the student. For example, if a student wants to know the work efficiency of the student in a specific period, detailed data of indexes such as the effective question making time, the total work time and the work efficiency can be inquired from the image, and the average input and concentration degree of the student on the work in the period can be specifically known. For another example, by inquiring the wrong question correction rate of the student, it can be known whether the student has positive backstepping in the time period.

(2) The query is reported. The condition of a certain index under different groups (score, grade, class, school, etc.) can be inquired and visualized. For example, for the work efficiency index, the performance conditions of the work efficiency index in different score groups or different grades can be inquired, so that a demander can conveniently know the group difference among different groups, particularly find out some special groups, such as students with higher work efficiency but poor scores, or students with lower work efficiency but better scores, can give certain academic guidance for the former and trigger certain behavior habit early warning for the latter.

(3) And (6) performing score inquiry. The score is one of the most concerned indexes of the interested persons in teaching, and the average level and the ranking position of the score of the student on the examination of each subject can be inquired through the portrait, so that the learning result of the student can be directly positioned.

Fig. 3 is a flowchart illustrating another method for representing the activities of student assignments according to an embodiment of the present invention, as shown in fig. 3, the method includes:

step S301, converting the acquired student work behavior portrait feature sample into a feature vector in a sample feature space of a feature training clustering model;

in this step, the characteristics of the student work behavior portraits (i.e. the dimension indexes in table 1) generated finally are regarded as the model characteristics in the characteristic training clustering model, and the purpose of classifying the student groups by using the student behavior portraits is finally achieved.

Step S302, in order to reduce the characteristic model deviation caused by inconsistent characteristic dimensions, the model characteristic is subjected to standardization/Z value processing;

at this time, a sample (i.e., a student) is converted into "a feature a processed by a certain student | a processed by a certain student |, and at this time, the sample is a vector (sample point) in the sample feature space.

Determining the optimal clustering number by adopting a contour coefficient method, and specifically operating as follows:

the outline coefficient of a characteristic sample of a student homework behavior portrait is as follows:

where a is the average distance of the sample from other samples of the same class, and b is the average distance of the sample from all samples in the nearest class. And solving the contour coefficients of all the samples, then solving the average value to obtain the overall contour coefficient of the samples, traversing and solving the contour coefficients under different types (k), making a contour coefficient distribution curve, and finding out the k value which enables the contour coefficient to be maximum as the final classification number.

And after the optimal classification number k is obtained, randomly extracting k samples as initial intra-class central points. And for the rest student homework behavior portrait feature samples, extracting one feature sample every time, and dividing the feature sample into categories corresponding to the intra-category central points separated from the feature sample by the nearest Euclidean distance. At the same time, for this class, the center point within its class is updated (taking the mean of the feature vectors within its class). And so on until all feature samples belong to the corresponding category.

Step S303, obtaining the average value of each classification behavior according to the average value of the achievement indexes in the classification, and sequencing and reading;

and after classification is finished, calculating the average value of the achievement indexes in each class, calculating the average value of each behavior index in each class, sequencing according to the calculation result, and reading the meaning of each classification.

Excellent development students, excellent performance and high overall performance of learning behavior indexes.

The general development students have average scores and have high learning behavior index performance.

Early warning position class student, the score is relatively poor, and learning behavior index performance is relatively poor.

The tail positions of students are poor in performance and learning behavior index performance.

The above classification results can be used in each scene of step S304.

Step S304, outputting a multi-dimensional report based on the clustering result of the student homework behavior;

the services provided based on the existing clustering results are:

(1) a learning feedback service. And providing the clustering crowd to which the student belongs, the interpretation description of the clustering crowd and the characteristic analysis of the clustering crowd to the teaching interest correlators. In the embodiment of the invention, student clustering groups are divided into four types: excellent development students, general development students, early warning position students and caudal position students. Excellent development students have high learning performance and good learning habits; the general development students have high learning score and good learning habits; early warning position students with low learning score and low learning habit; the tail positions of students are similar, and the learning score and the learning habit are low. According to the clustering population, the teacher can better comprehensively evaluate the conditions of the students.

(2) An educational policy suggestion service. And providing education strategy suggestions of layered education for students of different clustering groups. In the background, detailed index interpretation of each class of students is given for teachers to automatically specify relevant education strategies. For example, early warning position students need to pay special attention to low-level indicators in their homework behaviors to prevent their scores from further declining. Meanwhile, individual students can be analyzed independently. For example, students who are not high in performance but who are classified into excellent development classes because of their good practice can be instructed on the learning method. Finally, comprehensive evaluation can be carried out on the effectiveness of the education strategy of the teacher in the last stage. For example, after the upper stage adopts the supervising strategy, whether the performance of the students at the stage is obviously improved or not is judged.

(3) A personalized job recommendation service. By integrating the student homework behavior portrait and the student clustering result, individual recommendation can be realized for the student homework, such as topic type, homework amount, question making amount, key attention knowledge points and the like, and more accurate training on the student homework habit can be performed. For example, for a student with excellent development or a student with a high difficulty score rate in the image feature index, a problem with high difficulty challenge, such as a problem with a historical difficulty average of 4 or more, is recommended. And for students with lower 'homework completion rate' index, some questions with lower difficulty and stronger interest can be recommended to promote the students to complete homework better.

Step S305, generating a comprehensive report according to the requirements of each party.

And integrating the information in the step S304, and generating a comprehensive report for each party to refer according to the requirements of each party such as students, teachers and the like.

In summary, the method for portraying the homework behaviors of the students in the embodiments of fig. 1 to 3 is to create the homework behavior portraits, the portraits are divided into two categories, namely the homework behavior indexes and the student learning performance indexes, the two categories can be used for portraying the portraits of the individual students and the student groups, and based on the clustering results of the student groups made by the two categories, the portraits can be labeled for the student groups, thereby facilitating the implementation of layered teaching and layered guidance by teachers.

The student homework behavior index comprises the following five categories: the system can participate, insist, concentrate on, challenge academic and regulate self, describe the homework behavior of students from a more scientific and comprehensive angle, and provide information decision support for teachers.

Wherein, the 'participation' refers to the condition that students participate in the homework activity, including the use frequency of the homework platform, the communication discussion condition, the early and delayed submission condition, the feedback to the teacher comment and the like. The 'firm holding' refers to the regularity of the student homework conditions, and comprises a homework concentrated time period rule, a single homework time interval, a homework subject sequence, a homework completion rate and the like. "concentration" refers to the input level of the student, including the work efficiency, the effective question-making time, the single question-answering time interval, etc. The academic challenge is used for depicting the performance of students in dealing with difficulty, and comprises scores of questions with different difficulties, time and completion proportion, answering results of different types of questions and the like. The self-regulation is used for describing the thinking resistance of students, including wrong question correction rate, correct question making correction rate, homework report viewing frequency and the like.

Meanwhile, the significance of the image index dimension on group distinguishing is verified in a statistical sense by grouping the scores, grades and subjects of students and adopting technical means such as variance test and the like. Based on the method, student group portrait modeling is carried out, and student groups are clustered into four classes, so that groups such as teachers and parents can comprehensively evaluate individual performances of students and group performances of students from the aspects of student homework behaviors, student learning scores and the like, and supervision, early warning and guidance on the learning conditions of the students are realized. Meanwhile, the student portrait indexes are dynamic indexes, and the index updating period can be selected according to actual requirements to continuously track the dynamic development of students.

The method for representing the student's homework behavior according to the embodiment of the present invention is described in detail with reference to fig. 1 to 3, and the device for representing the student's homework behavior according to the embodiment of the present invention is described in detail with reference to fig. 4 to 5.

FIG. 4 is a schematic structural diagram of an exemplary apparatus for representing the activities of students according to an embodiment of the present invention. As shown in fig. 4, the student's work behavior image device comprises:

the characteristic conversion module 10 is used for converting the acquired student work behavior portrait characteristic samples into characteristic vectors in a sample characteristic space of a characteristic training clustering model;

the feature extraction module 20 is used for determining the optimal clustering number according to the contour coefficient of the feature samples of the student work behavior images, and randomly extracting the feature samples of the student work behavior images with the optimal clustering number as initial intra-class central points;

the feature dividing module 30 is configured to sequentially extract feature samples of each of the rest student homework behavior image, divide the feature samples into categories corresponding to intra-class central points having a closest euclidean distance from the feature samples, and update the intra-class central points;

and the classification acquisition module 40 is configured to acquire an average value of each classification behavior according to the average value of the achievement indexes in the category, and perform ranking and interpretation.

In the feature extraction module, the contour coefficient S of the feature sample includes:

wherein, a represents the average distance between the student work behavior image characteristic sample and other student work behavior image characteristic samples, and b represents the average distance between the student work behavior image characteristic sample and all student work behavior image characteristic samples in the nearest category.

In the embodiment of the present invention, optionally, as shown in fig. 5, the feature extraction module 20 specifically includes:

the coefficient calculation submodule 21 is used for calculating the contour coefficients of all the student work behavior portrait characteristic samples, and obtaining the integral contour coefficient of the student work behavior portrait characteristic samples by taking the arithmetic mean value of the obtained results;

the coefficient traversal submodule 22 is used for performing traversal calculation on the contour coefficients in different categories to obtain a contour coefficient distribution curve;

and the number determining submodule 23 is used for determining the optimal clustering number according to the profile coefficient distribution curve.

Optionally, in an embodiment of the present invention, the student homework behavior representation apparatus further includes a model building module, where the model building module includes:

the index presetting submodule is used for presetting the characteristic index of the student work behavior portrait according to the constructed student work behavior portrait system;

the characteristic grouping submodule is used for grouping the characteristic indexes of the student homework behavior portrait;

and the characteristic differentiation submodule is used for carrying out differentiation processing on the characteristic indexes of the grouped student homework behavior portrait.

In an embodiment of the present invention, the feature differentiation sub-module includes:

the score grouping unit is used for grouping the scores of the multiple examinations of the students according to the requirements;

and the checking and verifying unit is used for checking the student work behavior portrait characteristic indexes of the students by using variance and verifying the significance of the differences of the student work behavior portrait characteristic indexes among different groups.

Therefore, the student work behavior portrait device of the embodiment of the invention establishes the student work behavior portrait, the portrait is divided into two main categories which are respectively student work behavior indexes and student learning performance indexes, the two main categories can be used for portrait portrayal of individual students and student groups, and based on the clustering result of the student groups made by the two main categories, the student groups can be labeled portrayed, thereby facilitating the teacher to carry out layered teaching and layered guidance.

It should be understood that in the embodiment of the present invention, "B corresponding to a" means that B is associated with a, and determining B according to a does not mean determining B only according to a, but may also determine B according to a and/or other information.

In addition, an embodiment of the present invention further provides an electronic device, which includes a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the transceiver, the memory, and the processor are connected via the bus, respectively, and when the computer program is executed by the processor, the processes of the student homework behavior sketch method embodiment are implemented, and the same technical effects can be achieved, and are not described herein again to avoid repetition.

Specifically, referring to fig. 6, the embodiment of the present invention further provides an electronic device, which includes a bus 71, a processor 72, a transceiver 73, a bus interface 74, a memory 75, and a user interface 76.

In an embodiment of the present invention, the electronic device further includes: a computer program stored on the memory 75 and executable on the processor 72, the computer program when executed by the processor 72 performing the steps of:

determining the optimal clustering number according to the contour coefficient of the student work behavior portrait feature samples, and randomly extracting the student work behavior portrait feature samples with the optimal clustering number as initial intra-class central points;

The contour coefficient S of the feature sample includes:

Optionally, the computer program when executed by the processor 72 may further implement the steps of:

the step of determining the optimal clustering number according to the profile coefficient of the student homework behavior portrait feature sample specifically comprises the following steps:

calculating the contour coefficients of all the student work behavior portrait characteristic samples, and taking the arithmetic mean value of the obtained results to obtain the overall contour coefficient of the student work behavior portrait characteristic samples;

traversing and calculating the contour coefficients under different categories to obtain a contour coefficient distribution curve;

and determining the optimal clustering number according to the profile coefficient distribution curve.

The construction process of the feature training clustering model comprises the following steps:

presetting student work behavior portrait characteristic indexes according to the constructed student work behavior portrait system;

grouping the characteristic indexes of the student homework behavior portrait;

and performing differentiation processing on the grouped student homework behavior portrait characteristic indexes.

The specific steps of carrying out differentiation processing on the grouped student homework behavior portrait characteristic indexes comprise:

grouping the multiple examination scores of the students according to the requirements;

and verifying the significance of the difference of the characteristic indexes of the student work behavior portrait among different groups by adopting variance inspection on the characteristic indexes of the student work behavior portrait of the students.

The specific steps for verifying the significance of the difference of the characteristic indexes of the student homework behavior portrait between different groups include:

supposing that the characteristic index of the student homework behavior portrait has no significance to a certain group, forming a statistical hypothesis;

calculating the mean square error MSE of each group of the student homework behavior portrait characteristic indexes and the mean square error MSB of each group relative to the whole, and obtaining F (MSB)/MSE;

and determining the significance of the characteristic index of the student homework behavior portrait according to the F index.

A transceiver 73 for receiving and transmitting data under the control of the processor 72.

In FIG. 6, a bus architecture (represented by bus 71), bus 71 may include any number of interconnected buses and bridges, bus 71 connecting various circuits including one or more processors, represented by processor 72, and memory, represented by memory 75.

Bus 71 represents one or more of any of several types of bus structures, including a memory bus, and memory controller, a peripheral bus, an Accelerated Graphics Port (AGP), a processor, or a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include: an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an Enhanced ISA (EISA) bus, a Video Electronics Standards Association (VESA), a Peripheral Component Interconnect (PCI) bus.

The processor 72 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method embodiments may be performed by integrated logic circuits in hardware or instructions in software in a processor. The processor described above includes: general purpose processors, Central Processing Units (CPUs), Network Processors (NPs), Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs), Complex Programmable Logic Devices (CPLDs), Programmable Logic Arrays (PLAs), Micro Control Units (MCUs) or other Programmable Logic devices, discrete gates, transistor Logic devices, discrete hardware components. The various methods, steps and logic block diagrams disclosed in the embodiments of the present invention may be implemented or performed. For example, the processor may be a single core processor or a multi-core processor, which may be integrated on a single chip or located on multiple different chips.

The processor 72 may be a microprocessor or any conventional processor. The steps of the method disclosed in connection with the embodiments of the present invention may be directly performed by a hardware decoding processor, or may be performed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), a register, and other readable storage media known in the art. The readable storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the method in combination with the hardware.

The bus 71 may also connect various other circuits such as peripherals, voltage regulators, or power management circuits to one another, and a bus interface 74 provides an interface between the bus 71 and the transceiver 73, as is well known in the art. Therefore, the embodiments of the present invention will not be further described.

The transceiver 73 may be one element or a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other devices over a transmission medium. For example: the transceiver 73 receives external data from other devices, and the transceiver 73 is used to transmit data processed by the processor 72 to other devices. Depending on the nature of the computer system, a user interface 76 may also be provided, such as: touch screen, physical keyboard, display, mouse, speaker, microphone, trackball, joystick, stylus.

It should be appreciated that in embodiments of the present invention, the memory 75 may further include memory remotely located from the processor 72, which may be connected to a server over a network. One or more portions of the above-described networks may be an ad hoc network (ad hoc network), an intranet (intranet), an extranet (extranet), a Virtual Private Network (VPN), a Local Area Network (LAN), a Wireless Local Area Network (WLAN), a Wide Area Network (WAN), a Wireless Wide Area Network (WWAN), a Metropolitan Area Network (MAN), the Internet (Internet), a Public Switched Telephone Network (PSTN), a plain old telephone service network (POTS), a cellular telephone network, a wireless fidelity (Wi-Fi) network, and combinations of two or more of the above. For example, the cellular phone network and the wireless network may be a global system for Mobile Communications (GSM) system, a Code Division Multiple Access (CDMA) system, a Worldwide Interoperability for Microwave Access (WiMAX) system, a General Packet Radio Service (GPRS) system, a Wideband Code Division Multiple Access (WCDMA) system, a Long Term Evolution (LTE) system, an LTE Frequency Division Duplex (FDD) system, an LTE Time Division Duplex (TDD) system, an advanced long term evolution (LTE-a) system, a Universal Mobile Telecommunications (UMTS) system, an enhanced Mobile Broadband (eMBB) system, a mass Machine Type Communication (massive Machine Type Communication, mtc) system, an Ultra Reliable Low Latency Communication (Ultra Low Latency Communication, rluclc) system, or the like.

It will be appreciated that memory 75 in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. Wherein the nonvolatile memory includes: Read-Only Memory (ROM), Programmable ROM (PROM), Erasable PROM (EPROM), Electrically Erasable PROM (EEPROM), or Flash Memory.

The volatile memory includes: random Access Memory (RAM), which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as: static random access memory (Static RAM, SRAM), Dynamic random access memory (Dynamic RAM, DRAM), Synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), Double Data Rate Synchronous Dynamic random access memory (Double Data Rate SDRAM, DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct memory bus RAM (DRRAM). The memory 75 of the electronic device described in the embodiments of the present invention includes, but is not limited to, the above and any other suitable types of memory.

In an embodiment of the present invention, memory 75 stores the following elements of operating system 751 and application programs 752: an executable module, a data structure, or a subset thereof, or an expanded set thereof.

Specifically, the operating system 751 comprises various system programs, such as: a framework layer, a core library layer, a driver layer, etc. for implementing various basic services and processing hardware-based tasks. Applications 752 include various applications such as: media Player (Media Player), Browser (Browser), for implementing various application services. A program implementing the method of an embodiment of the present invention may be included in the application 752. The application programs 752 include: applets, objects, components, logic, data structures, and other computer system executable instructions that perform particular tasks or implement particular abstract data types.

In addition, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements each process of the above-mentioned student homework behavior imaging method embodiment, and can achieve the same technical effect, and is not described herein again to avoid repetition.

In particular, the computer program may, when executed by a processor, implement the steps of:

sequentially extracting feature samples of each rest student homework behavior portrait, dividing the feature samples into classes corresponding to class inner center points with Euclidean distances from the feature samples, and updating the class inner center points;

The contour coefficient S of the feature sample comprises:

Optionally, the computer program when executed by the processor may further implement the steps of:

presetting a characteristic index of the student homework behavior portrait according to the constructed student homework behavior portrait system;

grouping the characteristic indexes of the student homework behavior portrait;

The differentiation processing of the grouped student homework behavior portrait characteristic indexes specifically comprises the following steps:

The computer-readable storage medium includes: permanent and non-permanent, removable and non-removable media, are tangible devices that can retain and store instructions for use by an instruction execution apparatus. The computer-readable storage medium includes: electronic memory devices, magnetic memory devices, optical memory devices, electromagnetic memory devices, semiconductor memory devices, and any suitable combination of the foregoing. The computer readable storage medium includes: phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), non-volatile random access memory (NVRAM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic tape cartridge storage, magnetic tape disk storage or other magnetic storage devices, memory sticks, mechanical coding devices (e.g., punched cards or raised structures in a groove having instructions recorded thereon), or any other non-transmission medium useful for storing information that may be accessed by a computing device. As defined in embodiments of the present invention, the computer-readable storage medium does not include transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses traveling through a fiber optic cable), or electrical signals transmitted through a wire.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed in the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating the interchangeability of hardware and software. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer program instructions. The computer program instructions include: assembly instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, integrated circuit configuration data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as: smalltalk, C + + and procedural programming languages, such as: c or a similar programming language.

When the computer program instructions are loaded and executed on a computer, which may be a computer, a special purpose computer, a network of computers, or other editable apparatus, all or a portion of the procedures or functions described herein may be performed, or portions thereof, performed. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, such as: the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, twisted pair, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave) link. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device including one or more available media integrated servers, data centers, and the like. The usable medium may be a magnetic medium (e.g., floppy disk, magnetic tape), an optical medium (e.g., optical disk), or a semiconductor medium (e.g., Solid State Drive (SSD)), among others. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present embodiments.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing embodiments of the method of the present invention, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus, electronic device and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is merely a logical functional division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electrical, mechanical or other form of connection.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to solve the problem to be solved by the embodiment of the invention.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention may be implemented in a form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (including a personal computer, a server, a data center, or other network devices) to perform all or part of the steps of the methods of the embodiments of the present invention. And the storage medium includes various media that can store the program code as listed in the foregoing.

The above description is only a specific implementation of the embodiments of the present invention, but the scope of the embodiments of the present invention is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the embodiments of the present invention, and all such changes or substitutions should be covered by the scope of the embodiments of the present invention. Therefore, the protection scope of the embodiments of the present invention shall be subject to the protection scope of the claims.

Claims

1. A student homework behavior portrait method is characterized by comprising the following steps:

determining the optimal clustering number according to the contour coefficient of the student work behavior sketch feature samples, and randomly extracting the student work behavior sketch feature samples with the optimal clustering number as initial in-class center points;

2. The method of claim 1, wherein the profile coefficients S of the feature samples comprise:

3. The method according to claim 1 or 2, wherein the determining the optimal number of clusters according to the contour coefficients of the student work behavior image feature samples specifically comprises:

4. The method of claim 1, wherein the constructing of the feature training clustering model comprises:

grouping the student homework behavior portrait characteristic indexes;

and performing differentiation processing on the grouped characteristic indexes of the student homework behavior portrait.

5. The method according to claim 4, wherein the differentiating the grouped student work activity image characteristic indicators specifically comprises:

and verifying the significance of the difference of the characteristic indexes of the student homework behavior portrait among different groups by adopting variance inspection on the characteristic indexes of the student homework behavior portrait of the students.

6. The method of claim 5, wherein verifying the significance of differences between different groups of the student assignment behavior profile characteristic indicators specifically comprises:

assuming that the characteristic indexes of the student homework behavior portrait have no significance to a certain group, forming a statistical hypothesis;

7. An image device for student's homework behavior, comprising:

the feature extraction module is used for determining the optimal clustering number according to the contour coefficient of the student work behavior portrait feature samples, and randomly extracting the student work behavior portrait feature samples with the optimal clustering number as initial intra-class central points;

the characteristic dividing module is used for sequentially extracting characteristic samples of each rest student homework behavior portrait, dividing the characteristic samples into classes corresponding to the class-in central points with the nearest Euclidean distance away from the characteristic samples, and updating the class-in central points;

8. The apparatus of claim 7, wherein the feature extraction module specifically comprises:

the coefficient calculation submodule is used for calculating the contour coefficients of all the student work behavior portrait characteristic samples and taking the arithmetic mean value of the obtained results to obtain the overall contour coefficient of the student work behavior portrait characteristic samples;

the coefficient traversal submodule is used for performing traversal calculation on the contour coefficients under different categories to obtain a contour coefficient distribution curve;

and the number determining submodule is used for determining the optimal clustering number according to the profile coefficient distribution curve.

9. An electronic device comprising a bus, a transceiver, a memory, a processor and a computer program stored on the memory and executable on the processor, the transceiver, the memory and the processor being connected via the bus, wherein the computer program when executed by the processor implements the steps of the student assignment behavior representation method as claimed in any one of claims 1 to 6.

10. A computer-readable storage medium, on which a computer program is stored, the computer program, when being executed by a processor, implementing the steps of the student work activity representation method according to any one of claims 1 to 6.