CN111191928A - Admire class course quality evaluation method based on machine learning - Google Patents
Admire class course quality evaluation method based on machine learning Download PDFInfo
- Publication number
- CN111191928A CN111191928A CN201911392521.5A CN201911392521A CN111191928A CN 111191928 A CN111191928 A CN 111191928A CN 201911392521 A CN201911392521 A CN 201911392521A CN 111191928 A CN111191928 A CN 111191928A
- Authority
- CN
- China
- Prior art keywords
- course
- value
- evaluation
- data record
- quality evaluation
- 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.)
- Granted
Links
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
- G06Q10/06395—Quality analysis or management
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention relates to a method for evaluating the quality of a admiring course based on machine learning, which comprises the steps of abstracting and abstracting the characteristic parameters of the course on an admiring course platform, constructing a quality evaluation system based on a strategy network, dynamically analyzing the registration number and the number of learning participants and evaluation participants of the course through the quality evaluation system, generating a course standard value serving as an evaluation standard of the course standard degree, weighting the average evaluation of the course by using the course standard value to obtain the final quality score of the course serving as the quality evaluation standard of the admiring course, thereby reflecting the real quality of the course and enabling the course to be evaluated more reasonably.
Description
Technical Field
The invention relates to a mullet course quality evaluation method based on machine learning, and belongs to the technical field of internet information.
Background
The admiration Course, i.e. M00C, is a short name for large-scale on-line Open Course (Massive on-line Open Course), and has been developed vigorously in china as an important supplement to traditional classroom teaching in recent years, and admiration courses are opened in great numbers in colleges and universities. In order to ensure the curriculum quality, each admire platform provides the learner with the function of evaluating and grading each curriculum, so that the learner can conveniently feed back the curriculum quality, and the relevant person of the admire platform can judge the quality of each curriculum through the average grading of the curriculum.
In addition, the admire class platform uses big data technology and machine learning technology to improve the course quality, and intelligent classification and recommendation are carried out to admire class course to the action such as frequently visiting and the brush volume of platform user is monitored, prevents that the quality evaluation of the course on the platform is influenced to improper user operation.
With the increase of the number of courses and the improvement of a network countermeasure technology, the existing course evaluation technology uses course grading to evaluate the quality of the courses, the situation that irregular operation of some course lecturers affects the evaluation of the quality of the courses and the influence of highly anthropomorphic machine operation on the quality of the courses cannot be avoided, so that the situation that the grade of one course is very high and the actual quality is very poor occurs, and the actual quality of the courses cannot be reflected by the existing course evaluation technology.
Disclosure of Invention
The invention aims to solve the technical problem of providing a admire course quality evaluation method based on machine learning, and a brand-new design method is adopted, so that more real course quality reflection can be obtained.
The invention adopts the following technical scheme for solving the technical problems: the invention designs a curriculum admiring quality evaluation method based on machine learning, which is used for realizing the quality evaluation of each curriculum on a target admiring platform based on the grading of a learning user on the curriculum on the target admiring platform, and comprises a quality evaluation system obtaining method and a quality evaluation method, wherein the quality evaluation system obtaining method comprises the following steps A to F:
step A, according to the data format of the name of a course, a teacher giving lessons, the time of the course, the number of people reporting and participating in learning, the number of people evaluating and average grading, counting the current time of the course on a target admiring course platform to obtain data records of each course to form a sample base, and then entering the step B;
b, aiming at each course data record in the sample library, firstly deleting the course data record of which the number of the registered learning participants is 0 and the course data record of which the class is not opened in a preset time range from the current time to the historical time direction; then merging a plurality of course data records with the same course name, which are set by the same teacher, wherein the course time is the latest course time, the number of the registered learning persons and the number of the evaluation persons are respectively added, and the average scores are added and then the average is calculated; updating the sample library, selecting the course data records with the preset proportional quantity in the sample library as the data records of each to-be-processed course, and entering the step C;
step C, aiming at each to-be-processed course data record, taking the ratio of the number of the evaluated persons to the number of the persons who report to participate in learning as the evaluation proportion corresponding to the to-be-processed course data record according to the ratio
Obtaining a grouping number M, and then entering a step D; wherein G represents the number of the to-be-processed course data records, G represents the number of the preset to-be-processed course data record grouping units,
represents an upward rounding function;
d, sorting the evaluation proportions respectively corresponding to the curriculum data records to be processed from small to large, grouping the unit number g and the grouping number M of the preset curriculum data records to be processed according to the evaluation proportions, then respectively obtaining the average value of the evaluation proportions in each group, respectively obtaining the numerical value of the middle position according to the average value of the evaluation proportions respectively corresponding to each group in sequence, finally further calculating the average value according to the numerical value of the middle position and the average value of the evaluation proportions corresponding to all the curriculum data records to be processed to be used as a curriculum standard contrast value, and then entering the step E;
step E, obtaining the average absolute deviation of the evaluation proportion and the relative course standard contrast value corresponding to each to-be-processed course data record, dividing the average absolute deviation by two to obtain a course standard granularity value, and then entering the step F;
step F, dividing a 0-1 closed interval into two sections by the course specification contrast value, respectively forming interval spans by the positions of the course specification contrast value in the 0-1 closed interval towards two sides according to the decreasing proportion of the course specification granularity value at the 0 side direction and the increasing proportion of the course specification granularity value at the 1 side direction, respectively dividing the two sections into sequential intervals, wherein the number of the divided intervals of each section is the same, and the division intervals are sequentially numbered from 1 to 1 from the positions of the course specification contrast value towards the two sides respectively, so that the quality evaluation system corresponding to the target mullet platform is obtained by dividing the 0-1 closed interval;
periodically executing the following steps I to III based on the acquisition of the quality evaluation system to realize a quality evaluation method for acquiring the quality evaluation of each course;
step I, obtaining evaluation proportions respectively corresponding to all course data records on a target admiring course platform by adopting the methods in the steps A to C, and then entering the step II;
and II, aiming at each course data record respectively, according to the following formula:
obtaining a course standard value score corresponding to a course data record, wherein a represents an evaluation proportion corresponding to the course data record, b represents a number of a corresponding division part of the evaluation proportion corresponding to the course data record in the 0-1 closed interval, c represents a boundary value of the evaluation proportion corresponding to the course data record in the corresponding division part of the 0-1 closed interval and on one side of a comparison value of the corresponding course standard, d represents an interval span of the evaluation proportion corresponding to the course data record in the corresponding division part of the 0-1 closed interval, and e represents the division interval number in a single segment of the 0-1 closed interval; then entering step III;
and III, respectively aiming at each course data record, taking the product of the course specification value corresponding to the course data record and the average score thereof as the quality score corresponding to the course data record, and realizing the quality evaluation of the course.
As a preferred technical scheme of the invention: the quality evaluation method also comprises a step IV, and after the step III is executed, the step IV is executed;
step IV, judging whether the times of executing the processes from the step I to the step III in the current period reach a preset time threshold value, if so, entering the step V, otherwise, waiting for a preset time length, and then returning to the step I;
and V, respectively aiming at each course data record, obtaining the average value of each quality score corresponding to the course data record in the period, updating the average value as the quality score corresponding to the course data record, and realizing the quality evaluation of the course.
As a preferred technical scheme of the invention: the step F comprises the following steps F1 to F8;
step F1, placing the course specification contrast value in a closed interval from 0 to 1, dividing the closed interval from 0 to 1 into two sections, initializing that n is 1, wherein the interval span at the 0 side and the interval span at the 1 side are both the course specification granularity values, and the initial division value at the 0 side and the initial division value at the 1 side are both the course specification contrast values, and then entering step F2;
step F2., dividing a divided region from the 0 side initial division value to the 0 side direction by the 0 side region span, and defining the number of the divided region as n; meanwhile, dividing a divided region from the 1-side initial division value to the 1-side direction by the 1-side region span, and defining the number of the divided region as n; then proceed to step F3;
step F3. defines an update p of the boundary value corresponding to the 0-side direction between the divisional areas numbered n in the 0-side direction and q of the boundary value corresponding to the 1-side direction between the divisional areas numbered n in the 1-side direction, and proceeds to step F4;
step F4., determining whether p is not equal to 0 and q is not equal to 1, if yes, entering step F5; otherwise go to step F6;
step F5. updates the 0-side starting partition value to p, the 1-side starting partition value to q, performs update by adding 1 to the value of n, performs update by dividing the value of the 0-side span by 2, performs update by multiplying the value of the 1-side span by 2, and then returns to step F2;
step F6., if p is equal to 0 and q is equal to 1, then the acquisition of the quality evaluation system corresponding to the target mullet platform is completed;
if p is equal to 0 and q is not equal to 1, go to step F7;
if p is not equal to 0 and q is equal to 1, go to step F8;
step F7., dividing the part which is not divided into the divided areas in the 1-side direction and the divided areas which are numbered n in the 1-side direction, and finishing the acquisition of the quality evaluation system corresponding to the target mule course platform;
and F8., dividing the rest parts which are not divided into the divided areas in the 0 side direction into the divided areas numbered n in the 0 side direction, and finishing the acquisition of the quality evaluation system corresponding to the target mule class platform.
As a preferred technical scheme of the invention: in the step C, after obtaining the evaluation proportion corresponding to each to-be-processed course data record, performing root-of-square operation on each evaluation proportion according to a preset number of secondary parties and the evaluation proportion, and updating the evaluation proportion by using the obtained result; and updating the evaluation proportion corresponding to each to-be-processed course data record.
As a preferred technical scheme of the invention: in the step C, respectively aiming at each evaluation proportion, carrying out open root calculation aiming at the evaluation proportion, and updating the evaluation proportion by using the obtained result; and updating the evaluation proportion corresponding to each to-be-processed course data record.
As a preferred technical scheme of the invention: what is needed isIn the step D, after obtaining the average value of the evaluation ratio corresponding to each group, if M is odd, then based on the sorting, selecting the first group
The average value of the evaluation ratios is used as the numerical value of the middle position; if M is even, then select [ M/2 ] th based on the ranking]Mean value of evaluation ratio to [ M/2+1 ]]The average value between the individual evaluation scale average values was taken as the value of the middle position.
Compared with the prior art, the admire course quality evaluation method based on machine learning has the following technical effects by adopting the technical scheme:
the invention designs a admiring course quality evaluation method based on machine learning, firstly, abstractly abstracting and abstracting the course characteristic parameters on an admiring course platform, constructing a quality evaluation system based on a strategy network, then, dynamically analyzing the number of people who register and participate in learning and the number of people who evaluate the course through the quality evaluation system, generating a course standard value serving as an evaluation standard of the course standard degree, and finally, weighting the average evaluation of the course by using the course standard value to obtain the final quality score of the course serving as the quality evaluation standard of the admiring course, thereby embodying the real quality of the course and enabling the course to be more reasonably evaluated.
Drawings
FIG. 1 is a flow chart of the method for evaluating the quality of a mullet course based on machine learning according to the present invention.
Detailed Description
The following description will explain embodiments of the present invention in further detail with reference to the accompanying drawings.
The invention designs a curriculum admiring quality evaluation method based on machine learning, which is used for realizing the quality evaluation of each curriculum on a target admiring platform based on the grading of a learning user on the curriculum on the target admiring platform.
Step A, according to the data format of the course name, the teacher giving lessons, the course time, the number of the attendance participants, the number of the evaluation participants and the average score, counting the current time of the course on the target admiring course platform to obtain the data records of each course to form a sample base, and then entering the step B.
B, aiming at each course data record in the sample library, firstly deleting the course data record of which the number of the registered learning participants is 0 and the course data record of which the class is not opened in a preset time range from the current time to the historical time direction; then merging a plurality of course data records with the same course name, which are set by the same teacher, wherein the course time is the latest course time, the number of the registered learning persons and the number of the evaluation persons are respectively added, and the average scores are added and then the average is calculated; and updating the sample library, selecting the course data records with the preset proportional quantity in the sample library as the data records of each to-be-processed course, and entering the step C.
Step C, respectively aiming at each to-be-processed course data record, taking the ratio of the number of the evaluated persons to the number of the persons who report to participate in learning as an evaluation proportion corresponding to the to-be-processed course data record, then respectively aiming at each evaluation proportion, carrying out root-opening operation according to a preset secondary number and the evaluation proportion, updating the evaluation proportion by using the obtained result, and designing the root-opening operation according to the evaluation proportion in practical application; updating the evaluation proportion corresponding to each to-be-processed course data record; last press
Obtaining the number M of the groups, and entering the step D; wherein G represents the number of the to-be-processed course data records, G represents the number of the preset to-be-processed course data record grouping units,
representing an ceiling function.
D, sorting the evaluation proportions respectively corresponding to the curriculum data records to be processed from small to large, presetting the unit number g and the group number M of the group of the curriculum data records to be processed, sequentially grouping the evaluation proportions, respectively obtaining the average value of the evaluation proportions in each group, respectively obtaining the average value of the evaluation proportions corresponding to each group in sequence, obtaining the numerical value of the middle position, finally further calculating the average value of the numerical value of the middle position and the average value of the evaluation proportions corresponding to all the curriculum data records to be processed to be used as a curriculum standard comparison value, and then entering the step E.
In the step D, an operation of obtaining the numerical value of the intermediate position with respect to the average value of the evaluation ratios respectively corresponding to the sequential groups is performed, and in practical application, if M is an odd number, the first evaluation ratio is selected based on the ranking
The average value of the evaluation ratios is used as the numerical value of the middle position; if M is even, then select [ M/2 ] th based on the ranking]Mean value of evaluation ratio to [ M/2+1 ]]The average value between the individual evaluation scale average values was taken as the value of the middle position.
And E, obtaining the average absolute deviation of the evaluation proportion and the relative course specification contrast value corresponding to each to-be-processed course data record, dividing the average absolute deviation by two to obtain a course specification granularity value, and then entering the step F.
And F, dividing the 0-1 closed interval into two sections by the course specification contrast value, respectively forming interval spans by the positions of the course specification contrast value in the 0-1 closed interval towards two sides according to the decreasing proportion of the course specification granularity value at the 0 side direction and the increasing proportion of the course specification granularity value at the 1 side direction, respectively dividing the two sections into sequential intervals, wherein the number of the divided intervals of each section is the same, and the division intervals of the divided intervals are sequentially numbered from 1 to 1 from the positions of the course specification contrast value towards the two sides respectively, so that the quality evaluation system corresponding to the target mule course platform is obtained by dividing the 0-1 closed interval.
In practical applications, the step F specifically executes the following steps F1 to F8.
Step F1, the course specification contrast value is set in a closed interval from 0 to 1, the closed interval from 0 to 1 is divided into two segments, n is initialized to 1, the interval span on the 0 side and the interval span on the 1 side are both the course specification granularity values, and the starting division value on the 0 side and the starting division value on the 1 side are both the course specification contrast values, and then the step F2 is performed.
Step F2., dividing a divided region from the 0 side initial division value to the 0 side direction by the 0 side region span, and defining the number of the divided region as n; meanwhile, dividing a divided region from the 1-side initial division value to the 1-side direction by the 1-side region span, and defining the number of the divided region as n; then proceed to step F3.
Step F3. defines an update p of the boundary value corresponding to the 0-side direction between the divisional areas numbered n in the 0-side direction and q of the boundary value corresponding to the 1-side direction between the divisional areas numbered n in the 1-side direction, and proceeds to step F4.
Step F4., determining whether p is not equal to 0 and q is not equal to 1, if yes, entering step F5; otherwise, go to step F6.
Step F5. updates the 0-side starting partition value to p, the 1-side starting partition value to q, updates the value of n by adding 1, updates the value of 0-side span by dividing by 2, updates the value of 1-side span by multiplying 2, and returns to step F2.
Step F6., if p is equal to 0 and q is equal to 1, then the acquisition of the quality evaluation system corresponding to the target mullet platform is completed;
if p is equal to 0 and q is not equal to 1, go to step F7;
if p is not equal to 0 and q is equal to 1, go to step F8.
Step F7., dividing the part which is not divided into the divided areas in the 1 side direction and the divided area which is numbered n in the 1 side direction, and finishing the obtaining of the quality evaluation system corresponding to the target mule class platform.
And F8., dividing the rest parts which are not divided into the divided areas in the 0 side direction into the divided areas numbered n in the 0 side direction, and finishing the acquisition of the quality evaluation system corresponding to the target mule class platform.
Based on the acquisition of the quality evaluation system, the following steps I to III are periodically executed to realize a quality evaluation method for acquiring the quality evaluation of each course.
And step I, obtaining the evaluation proportion corresponding to each course data record on the target admiring course platform by adopting the method from the step A to the step C, and then entering the step II.
And II, aiming at each course data record respectively, according to the following formula:
obtaining a course standard value score corresponding to a course data record, wherein a represents an evaluation proportion corresponding to the course data record, b represents a number of a corresponding division part of the evaluation proportion corresponding to the course data record in the 0-1 closed interval, c represents a boundary value of the evaluation proportion corresponding to the course data record in the corresponding division part of the 0-1 closed interval and on one side of a comparison value of the corresponding course standard, d represents an interval span of the evaluation proportion corresponding to the course data record in the corresponding division part of the 0-1 closed interval, and e represents the division interval number in a single segment of the 0-1 closed interval; then step III is entered.
And step III, regarding each course data record, taking the product of the course standard value corresponding to the course data record and the average score of the course standard value as the quality score corresponding to the course data record, and entering the step IV.
And IV, judging whether the times of executing the processes from the step I to the step III in the current period reach a preset time threshold value, if so, entering the step V, otherwise, waiting for a preset time length, and then returning to the step I. In practical applications, the preset number threshold is designed to be 3 times.
And V, respectively aiming at each course data record, obtaining the average value of each quality score corresponding to the course data record in the period, updating the average value as the quality score corresponding to the course data record, and realizing the quality evaluation of the course.
In practical application, the evaluation emotion and the evaluation keyword corresponding to each course can be used as analysis factors, and after the quality score of each course is obtained, the evaluation emotion and the evaluation keyword are added with measurement, so that a more multidimensional objective evaluation process is realized.
According to the method for evaluating the quality of the curriculum admiring based on machine learning, firstly, a quality evaluation system based on a strategy network is constructed by abstracting and refining the curriculum characteristic parameters on a curriculum admiring platform, then the number of people participating in learning and the number of people evaluating the curriculum by registering are dynamically analyzed through the quality evaluation system to generate a curriculum standard value serving as an evaluation standard of curriculum standard degree, and finally the average evaluation of the curriculum is weighted by using the curriculum standard value to obtain the final quality score of the curriculum serving as the quality evaluation standard of the curriculum admiring platform, so that the real quality of the curriculum is reflected, and the curriculum is more reasonably evaluated.
The embodiments of the present invention have been described in detail with reference to the drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (6)
1. A admire class course quality evaluation method based on machine learning, admire class platform to admire class grade of course on the goal based on learning user, realize admire class platform to goal each quality evaluation of course, characterized by that, including quality evaluation system acquisition method and quality evaluation method, wherein, quality evaluation system acquisition method includes the following step A to step F:
step A, according to the data format of the name of a course, a teacher giving lessons, the time of the course, the number of people reporting and participating in learning, the number of people evaluating and average grading, counting the current time of the course on a target admiring course platform to obtain data records of each course to form a sample base, and then entering the step B;
b, aiming at each course data record in the sample library, firstly deleting the course data record of which the number of the registered learning participants is 0 and the course data record of which the class is not opened in a preset time range from the current time to the historical time direction; then merging a plurality of course data records with the same course name, which are set by the same teacher, wherein the course time is the latest course time, the number of the registered learning persons and the number of the evaluation persons are respectively added, and the average scores are added and then the average is calculated; updating the sample library, selecting the course data records with the preset proportional quantity in the sample library as the data records of each to-be-processed course, and entering the step C;
step C, aiming at each to-be-processed course data record, taking the ratio of the number of the evaluated persons to the number of the persons who report to participate in learning as the evaluation proportion corresponding to the to-be-processed course data record according to the ratio
Obtaining a grouping number M, and then entering a step D; wherein G represents the number of the to-be-processed course data records, G represents the number of the preset to-be-processed course data record grouping units,
represents an upward rounding function;
d, sorting the evaluation proportions respectively corresponding to the curriculum data records to be processed from small to large, grouping the unit number g and the grouping number M of the preset curriculum data records to be processed according to the evaluation proportions, then respectively obtaining the average value of the evaluation proportions in each group, respectively obtaining the numerical value of the middle position according to the average value of the evaluation proportions respectively corresponding to each group in sequence, finally further calculating the average value according to the numerical value of the middle position and the average value of the evaluation proportions corresponding to all the curriculum data records to be processed to be used as a curriculum standard contrast value, and then entering the step E;
step E, obtaining the average absolute deviation of the evaluation proportion and the relative course standard contrast value corresponding to each to-be-processed course data record, dividing the average absolute deviation by two to obtain a course standard granularity value, and then entering the step F;
step F, dividing a 0-1 closed interval into two sections by the course specification contrast value, respectively forming interval spans by the positions of the course specification contrast value in the 0-1 closed interval towards two sides according to the decreasing proportion of the course specification granularity value at the 0 side direction and the increasing proportion of the course specification granularity value at the 1 side direction, respectively dividing the two sections into sequential intervals, wherein the number of the divided intervals of each section is the same, and the division intervals are sequentially numbered from 1 to 1 from the positions of the course specification contrast value towards the two sides respectively, so that the quality evaluation system corresponding to the target mullet platform is obtained by dividing the 0-1 closed interval;
periodically executing the following steps I to III based on the acquisition of the quality evaluation system to realize a quality evaluation method for acquiring the quality evaluation of each course;
step I, obtaining evaluation proportions respectively corresponding to all course data records on a target admiring course platform by adopting the methods in the steps A to C, and then entering the step II;
and II, aiming at each course data record respectively, according to the following formula:
obtaining a course standard value score corresponding to a course data record, wherein a represents an evaluation proportion corresponding to the course data record, b represents a number of a corresponding division part of the evaluation proportion corresponding to the course data record in the 0-1 closed interval, c represents a boundary value of the evaluation proportion corresponding to the course data record in the corresponding division part of the 0-1 closed interval and on one side of a comparison value of the corresponding course standard, d represents an interval span of the evaluation proportion corresponding to the course data record in the corresponding division part of the 0-1 closed interval, and e represents the division interval number in a single segment of the 0-1 closed interval; then entering step III;
and III, respectively aiming at each course data record, taking the product of the course specification value corresponding to the course data record and the average score thereof as the quality score corresponding to the course data record, and realizing the quality evaluation of the course.
2. The machine learning-based mule course quality evaluation method as claimed in claim 1, wherein: the quality evaluation method also comprises a step IV, and after the step III is executed, the step IV is executed;
step IV, judging whether the times of executing the processes from the step I to the step III in the current period reach a preset time threshold value, if so, entering the step V, otherwise, waiting for a preset time length, and then returning to the step I;
and V, respectively aiming at each course data record, obtaining the average value of each quality score corresponding to the course data record in the period, updating the average value as the quality score corresponding to the course data record, and realizing the quality evaluation of the course.
3. The machine learning-based mule course quality evaluation method as claimed in claim 1, wherein: the step F comprises the following steps F1 to F8;
step F1, placing the course specification contrast value in a closed interval from 0 to 1, dividing the closed interval from 0 to 1 into two sections, initializing that n is 1, wherein the interval span at the 0 side and the interval span at the 1 side are both the course specification granularity values, and the initial division value at the 0 side and the initial division value at the 1 side are both the course specification contrast values, and then entering step F2;
step F2., dividing a divided region from the 0 side initial division value to the 0 side direction by the 0 side region span, and defining the number of the divided region as n; meanwhile, dividing a divided region from the 1-side initial division value to the 1-side direction by the 1-side region span, and defining the number of the divided region as n; then proceed to step F3;
step F3. defines an update p of the boundary value corresponding to the 0-side direction between the divisional areas numbered n in the 0-side direction and q of the boundary value corresponding to the 1-side direction between the divisional areas numbered n in the 1-side direction, and proceeds to step F4;
step F4., determining whether p is not equal to 0 and q is not equal to 1, if yes, entering step F5; otherwise go to step F6;
step F5. updates the 0-side starting partition value to p, the 1-side starting partition value to q, performs update by adding 1 to the value of n, performs update by dividing the value of the 0-side span by 2, performs update by multiplying the value of the 1-side span by 2, and then returns to step F2;
step F6., if p is equal to 0 and q is equal to 1, then the acquisition of the quality evaluation system corresponding to the target mullet platform is completed;
if p is equal to 0 and q is not equal to 1, go to step F7;
if p is not equal to 0 and q is equal to 1, go to step F8;
step F7., dividing the part which is not divided into the divided areas in the 1-side direction and the divided areas which are numbered n in the 1-side direction, and finishing the acquisition of the quality evaluation system corresponding to the target mule course platform;
and F8., dividing the rest parts which are not divided into the divided areas in the 0 side direction into the divided areas numbered n in the 0 side direction, and finishing the acquisition of the quality evaluation system corresponding to the target mule class platform.
4. The machine learning-based mule course quality evaluation method as claimed in claim 1, wherein: in the step C, after obtaining the evaluation proportion corresponding to each to-be-processed course data record, performing root-of-square operation on each evaluation proportion according to a preset number of secondary parties and the evaluation proportion, and updating the evaluation proportion by using the obtained result; and updating the evaluation proportion corresponding to each to-be-processed course data record.
5. The machine learning-based mule course quality evaluation method as claimed in claim 4, wherein: in the step C, respectively aiming at each evaluation proportion, carrying out open root calculation aiming at the evaluation proportion, and updating the evaluation proportion by using the obtained result; and updating the evaluation proportion corresponding to each to-be-processed course data record.
6. The machine learning-based mule course quality evaluation method as claimed in claim 1, wherein: in the step D, after obtaining the average value of the evaluation proportion corresponding to each group, if M is an odd number, selecting the first group based on sorting
The average value of the evaluation ratios is used as the numerical value of the middle position; if M is even, then select [ M/2 ] th based on the ranking]Mean value of evaluation ratio to [ M/2+1 ]]The average value between the individual evaluation scale average values was taken as the value of the middle position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911392521.5A CN111191928B (en) | 2019-12-30 | 2019-12-30 | Admire class course quality evaluation method based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911392521.5A CN111191928B (en) | 2019-12-30 | 2019-12-30 | Admire class course quality evaluation method based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111191928A true CN111191928A (en) | 2020-05-22 |
| CN111191928B CN111191928B (en) | 2023-04-07 |
Family
ID=70705947
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911392521.5A Active CN111191928B (en) | 2019-12-30 | 2019-12-30 | Admire class course quality evaluation method based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111191928B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080138788A1 (en) * | 2006-09-06 | 2008-06-12 | Curtis Dell Allen | Adaptive and individual learning with feedback for online courses |
| US20090061408A1 (en) * | 2007-08-28 | 2009-03-05 | Micro-Star Int'l Co., Ltd. | Device and method for evaluating learning |
| US20140199674A1 (en) * | 2013-01-16 | 2014-07-17 | Empowered Schools, Inc. | Combined Curriculum And Grade Book Manager With Integrated Student/Teacher Evaluation Functions Based On Adopted Standards |
| CN109255028A (en) * | 2018-08-28 | 2019-01-22 | 西安交通大学 | Quality of instruction integrated evaluating method based on teaching evaluation data reliability |
| CN109523201A (en) * | 2019-01-22 | 2019-03-26 | 湖南财政经济学院 | One kind efficiently admiring class method for evaluating quality based on big data era |
| CN110009234A (en) * | 2019-04-09 | 2019-07-12 | 湖南生物机电职业技术学院 | Class evaluation method is admired in a kind of think of political affairs based on big data |
| CN110334810A (en) * | 2019-07-10 | 2019-10-15 | 福州大学 | MOOC corpse course recognition methods based on machine learning |
-
2019
- 2019-12-30 CN CN201911392521.5A patent/CN111191928B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080138788A1 (en) * | 2006-09-06 | 2008-06-12 | Curtis Dell Allen | Adaptive and individual learning with feedback for online courses |
| US20090061408A1 (en) * | 2007-08-28 | 2009-03-05 | Micro-Star Int'l Co., Ltd. | Device and method for evaluating learning |
| US20140199674A1 (en) * | 2013-01-16 | 2014-07-17 | Empowered Schools, Inc. | Combined Curriculum And Grade Book Manager With Integrated Student/Teacher Evaluation Functions Based On Adopted Standards |
| CN109255028A (en) * | 2018-08-28 | 2019-01-22 | 西安交通大学 | Quality of instruction integrated evaluating method based on teaching evaluation data reliability |
| CN109523201A (en) * | 2019-01-22 | 2019-03-26 | 湖南财政经济学院 | One kind efficiently admiring class method for evaluating quality based on big data era |
| CN110009234A (en) * | 2019-04-09 | 2019-07-12 | 湖南生物机电职业技术学院 | Class evaluation method is admired in a kind of think of political affairs based on big data |
| CN110334810A (en) * | 2019-07-10 | 2019-10-15 | 福州大学 | MOOC corpse course recognition methods based on machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111191928B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110378818B (en) | Personalized exercise recommendation method, system and medium based on difficulty | |
| CN107590247B (en) | Intelligent volume organizing method based on group knowledge diagnosis | |
| CN108182489A (en) | Method is recommended in a kind of individualized learning based on on-line study behavioural analysis | |
| CN109858797A (en) | The various dimensions information analysis of the students method of knowledge based network exact on-line education system | |
| US20060099561A1 (en) | Automated assessment development and associated methods | |
| CN107680018A (en) | A kind of college entrance will based on big data and artificial intelligence makes a report on system and method | |
| CN109840595A (en) | A kind of knowledge method for tracing based on group study behavior feature | |
| CN109615264A (en) | A kind of student towards on-line study actively spends the system of determination | |
| He et al. | A study on prediction of customer churn in fixed communication network based on data mining | |
| CN111311997B (en) | Interaction method based on network education resources | |
| CN111191928B (en) | Admire class course quality evaluation method based on machine learning | |
| CN115952299A (en) | Intelligent simulation examination recommendation system and method | |
| Binh et al. | Student ability estimation based on IRT | |
| CN108921434A (en) | A method of user capability prediction is completed by human-computer interaction | |
| CN115660129A (en) | Method and system for feeding back classroom efficiency based on electronic whiteboard and face recognition | |
| Gu et al. | Cluster analysis on the teaching evaluation data from college students | |
| Monterola et al. | Characterizing the effect of seating arrangement on classroom learning using neural networks | |
| CN111985793A (en) | Online student evaluation and education method | |
| Sanmorino et al. | Building Research Productivity Framework in Higher Education Institution | |
| Chang | Design and Application of Evaluation Method for Civics Classroom Based on CRITIC Fuzzy Algorithm | |
| Liu | Satisfaction evaluation method of composite teaching model from the perspective of MOOC concept | |
| Li | An evaluation of college students' involvement in English learning behaviour based on fuzzy comprehensive evaluation | |
| Zhao | Evaluation research on the effectiveness of practical teaching of ideological and political courses in higher vocational colleges under micro-culture | |
| Bai et al. | An In-class Teaching Comprehensive Evaluation Model Based on Statistical Modelling and Ensemble Learning | |
| Zhiyi et al. | Construction of a model for college students' innovation and entrepreneurship quality based on artificial intelligence technology |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |