CN112614034A - Test question recommendation method and device, electronic equipment and readable storage medium - Google Patents
Test question recommendation method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN112614034A CN112614034A CN202110246990.7A CN202110246990A CN112614034A CN 112614034 A CN112614034 A CN 112614034A CN 202110246990 A CN202110246990 A CN 202110246990A CN 112614034 A CN112614034 A CN 112614034A
- Authority
- CN
- China
- Prior art keywords
- test
- difficulty
- priority
- test question
- student
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 568
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000006870 function Effects 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 7
- 239000000126 substance Substances 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 125000004432 carbon atom Chemical group C* 0.000 claims description 4
- 230000003416 augmentation Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 6
- 238000010606 normalization Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- ANRHNWWPFJCPAZ-UHFFFAOYSA-M thionine Chemical class [Cl-].C1=CC(N)=CC2=[S+]C3=CC(N)=CC=C3N=C21 ANRHNWWPFJCPAZ-UHFFFAOYSA-M 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The application provides a test question recommendation method and device, electronic equipment and a readable storage medium. The method comprises the following steps: acquiring at least two alternative test questions; determining the difficulty matching degree of the alternative test questions relative to the students; determining the test question priority of the alternative test questions relative to the students according to the basic information of the alternative test questions and the basic information of the students; and determining recommended test questions according to the test question priority and the difficulty matching degree. By implementing the technical scheme, the recommendation precision of the recommended test questions can be improved.
Description
Technical Field
The present application relates to the field of education, and in particular, to a method and an apparatus for recommending test questions, an electronic device, and a readable storage medium.
Background
Most of the existing tutoring systems generally adopt a recommendation strategy based on simple rules, for example, by counting the answer accuracy of different learning points of students, the number of required practice questions and difficulty rules are artificially defined. This requires specialized experts to evaluate the learning scenarios of different types of learners, to classify them into multiple classes, and to define detailed rules for each class. The method has high requirements on field experts, is limited to manpower, can only classify learners into very limited learning modes in practice, cannot complete recommendation effects which are different from person to person, and has poor test question recommendation precision.
Disclosure of Invention
In order to solve at least one of the above technical problems, the present application provides a test question recommendation method, apparatus, electronic device and readable storage medium.
In a first aspect of the present application, a method for recommending test questions includes:
acquiring at least two alternative test questions;
determining the difficulty matching degree of the alternative test questions relative to the student;
determining the test question priority of the alternative test questions relative to the student according to the basic information of the alternative test questions and the basic information of the student;
and determining recommended test questions according to the test question priority and the difficulty matching degree.
Optionally, the determining the difficulty matching degree of the candidate test questions with respect to the student includes:
acquiring difficulty reference test questions of the students, wherein the difficulty reference test questions are already made test questions of the students;
obtaining the test question difficulty of the alternative test questions and the test question difficulty of the difficulty reference test questions;
acquiring a knowledge point set of the candidate test questions and a knowledge point set of the difficulty reference test questions;
and determining the difficulty matching degree of the candidate test questions and the students according to the test question difficulty of the candidate test questions, the test question difficulty of the difficulty reference test questions, the knowledge point set of the candidate test questions and the knowledge point set of the difficulty reference test questions.
Optionally, determining the difficulty matching degree of the candidate test questions with respect to the student according to the test question difficulty of the candidate test questions, the test question difficulty of the difficulty reference test questions, the knowledge point set of the candidate test questions and the knowledge point set of the difficulty reference test questions comprises:
acquiring class type, grade and knowledge point mastering degree of the student;
according to the class type, the grade and the mastery degree of the knowledge points, acquiring an optimal accuracy range, a bottom line accuracy range and a knowledge point expansion indication from a preset optimal accuracy range tensor, a bottom line accuracy range tensor and a knowledge point expansion indication tensor;
and determining the difficulty matching degree of the candidate test questions and the students according to the optimal correct rate range, the bottom line correct rate range, the knowledge point expansion indication, the test question difficulty of the candidate test questions, the test question difficulty of the difficulty reference test questions, the knowledge point set of the candidate test questions and the knowledge point set of the difficulty reference test questions.
Optionally, the determining the difficulty matching degree of the candidate test questions with respect to the student according to the preferred accuracy range, the baseline accuracy range, the knowledge point extension instruction, the test question difficulty of the candidate test questions, the test question difficulty of the difficulty reference test questions, the knowledge point set of the candidate test questions, and the knowledge point set of the difficulty reference test questions includes:
calculating the difficulty matching degree of the alternative test questions according to a formula I;
the first formula comprises:
Optionally, the basic information of the candidate test questions includes grade, region, examination type and year;
the basic information of the students comprises grades and regions;
determining the priority of the alternative test questions relative to the test questions of the student, comprising:
determining the grade priority, the area priority, the year priority and the examination category priority of the alternative test questions relative to the student according to the basic information of the student and the basic information of the alternative test questions;
determining the priority weights of the grade priority, the area priority, the year priority and the examination category priority of the students according to the basic information of the students and a preset priority matrix;
adjusting the year priority, the region priority, the year priority and the test category priority according to the priority weight;
and determining the test question priority of the alternative test question relative to the student according to the adjusted year priority, the adjusted region priority, the adjusted year priority and the adjusted test category priority.
Optionally, determining the priority of the candidate test questions relative to the test questions of the student includes:
calculating the priority of the test questions according to a formula II;
the second formula includes:
Optionally, the determining recommended test questions according to the test question priorities and the difficulty matching degrees includes:
calculating the comprehensive recommendation degree through a formula III;
the third formula includes:
wherein the content of the first and second substances,
is the comprehensive recommendation degree of the t-th candidate test question relative to the n-th difficulty reference test question of the student u,
whether the t-th candidate test question exceeds the outline or not is shown,
indicating whether the t-th candidate test question is made by the student u,
is a decay function, n is arranged inversely in time;
as the weight of the priority of the test question,
shows the test question priority of the t-th candidate test question relative to the student u,
the weight of the degree of difficulty matching is,
representing the difficulty matching degree of the t-th candidate test question relative to the n-th difficulty reference test question of the student u,
the filtering weight of the candidate test question of the t-th channel relative to the student u;
and determining recommended test questions according to the comprehensive recommendation degree.
Optionally, the mastery degree of the knowledge points of the students is judged again according to the test question answering records of the students.
In a second aspect of the present application, a test question recommendation apparatus includes:
the candidate test question acquisition module is used for acquiring at least two candidate test questions;
the difficulty matching degree determining module is used for determining the difficulty matching degree of the candidate test questions relative to the students;
the test question priority determining module is used for determining the test question priority of the alternative test questions relative to the student according to the basic information of the alternative test questions and the basic information of the student;
and the test question recommending module is used for determining recommended test questions according to the test question priority and the difficulty matching degree.
A third aspect of the present application. An electronic device comprising a memory and a processor, the memory for storing computer instructions, wherein the computer instructions are executable by the processor to implement the method of any of the first aspects of the present application.
In a fourth aspect of the present application, a readable storage medium has stored thereon computer instructions which, when executed by a processor, implement the method of any of the first aspect of the present application.
The technical scheme of the application can achieve the following beneficial technical effects: according to the characteristics of students, the appropriate test questions are recommended to the students, the purpose of recommendation which is different from person to person is achieved, and the recommendation precision of the recommended test questions is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the application and together with the description serve to explain the principles of the application.
Fig. 1 is a schematic flowchart of a test question recommendation method disclosed in an embodiment of the present application;
fig. 2 is a schematic flowchart illustrating a process of determining difficulty matching degrees of candidate test questions with respect to a student according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a process for determining the priority of alternative test questions relative to the test questions of a student according to an embodiment of the present disclosure;
fig. 4 is a block diagram of a test question recommendation apparatus disclosed in an embodiment of the present application;
fig. 5 is a block diagram of an electronic device according to an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of a computer system of a test question recommendation method disclosed in an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are for purposes of illustration only and are not to be construed as limitations of the present application. It should be noted that, for convenience of description, only the portions related to the present application are shown in the drawings.
In addition, the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
The following explains the names appearing in the examples of the present application:
an indicative function: the other name indicates the function, when showing a certain condition and meeting, the value is a; if not, the value is b.
Tensor: similar to matrices, such as three-dimensional tensors, representing a three-dimensional matrix, information can be better generalized and represented.
Referring to fig. 1, an embodiment of the present application discloses a test question recommendation method, including:
s101, obtaining at least two alternative test questions;
s102, determining the difficulty matching degree of the alternative test questions relative to the students;
s103, determining the test question priority of the alternative test questions relative to the students according to the basic information of the alternative test questions and the basic information of the students;
and S104, determining recommended test questions according to the test question priority and the difficulty matching degree.
The method in the embodiment of the application is used for recommending test questions to students; when the candidate test questions are obtained, the test questions with the knowledge points to be learned can be obtained as the candidate test questions according to the knowledge points to be learned of the students.
In the above embodiment, the basic information of the student may include a region, and may further include a grade, the basic information of the candidate test question may include a region, and may further include a grade, a test category, and a year, and the test question priority may include a grade priority, and may further include a region priority, a test category priority, and a year priority.
According to the test question recommending method, the recommended test questions are determined according to the test question priority and the difficulty matching degree, so that the recommended test questions can be provided with conventional recommendation factors such as difficulty and the like, and can also be provided with unconventional massage factors such as the basic information of students and the basic information of the recommended test questions, the proper test questions are recommended to the students according to the characteristics of the students, the purpose of recommendation which is different from person to person is achieved, the recommendation precision of the recommended test questions is improved, the students can practice the test question practice recommended by the method of the embodiment of the application, and the practice effect can be improved.
According to the test question recommendation method of the embodiment, when the recommended test questions are determined according to the test question priority and the difficulty matching degree, the comprehensive matching degree can be determined according to the test question priority and the difficulty matching degree, and the alternative test questions corresponding to the top N large comprehensive matching degrees are selected as the recommended test questions according to the ranking of the comprehensive matching degrees of the same knowledge point.
For example, when the basic information includes a region, the region can be taken into consideration of the recommended test question scheme, so that the recommended test questions are more matched with students, and can be well combined with actual teaching.
In an alternative embodiment, referring to fig. 2, determining the difficulty matching degree of the candidate test questions with respect to the student includes:
s201, acquiring difficulty reference test questions of students, wherein the difficulty reference test questions are already made test questions of the students;
s202, obtaining the test question difficulty of the alternative test questions and the test question difficulty of the difficulty reference test questions;
s203, acquiring a knowledge point set of the alternative test questions and a knowledge point set of the difficulty reference test questions;
and S204, determining the difficulty matching degree of the candidate test questions and the students according to the test question difficulty of the candidate test questions, the test question difficulty of the difficulty reference test questions, the knowledge point set of the candidate test questions and the knowledge point set of the difficulty reference test questions.
In the above embodiment, the difficulty matching degree of the candidate test questions with respect to the student is determined according to the test question difficulty of the candidate test questions, the test question difficulty of the difficulty reference test questions, the knowledge point set of the candidate test questions and the knowledge point set of the difficulty reference test questions; the difficulty relation between the candidate test questions and the difficulty reference test questions can be determined according to the test question difficulty of the candidate test questions and the test question difficulty of the difficulty reference test questions, and the knowledge point relation between the candidate test questions and the difficulty reference test questions can be determined according to the knowledge point set of the candidate test questions and the knowledge point set of the difficulty reference test questions, for example, whether the knowledge points of the candidate test questions have knowledge points which are not available in the difficulty reference test questions or not can be determined. The difficulty matching degree of the students and the alternative test questions determined after the test question difficulty of the alternative test questions, the test question difficulty of the difficulty reference test questions, the knowledge point set of the alternative test questions and the knowledge point set of the difficulty reference test questions are comprehensively considered, the relation between the test question difficulty of the alternative test questions and the test question difficulty of the difficulty reference test questions is considered, the relation between the knowledge point set of the alternative test questions and the knowledge point set of the difficulty reference test questions is also considered, and the difficulty matching degree of the determined alternative test questions and the students is closer to the real situation.
Specifically, determining the difficulty matching degree of the candidate test questions relative to the student according to the test question difficulty of the candidate test questions, the test question difficulty of the difficulty reference test questions, the knowledge point set of the candidate test questions and the knowledge point set of the difficulty reference test questions comprises:
acquiring class type, grade and knowledge point mastering degree of students;
according to the class type, the grade and the mastery degree of the knowledge points, acquiring an optimal accuracy range, a bottom line accuracy range and a knowledge point expansion indication from a preset optimal accuracy range tensor, a bottom line accuracy range tensor and a knowledge point expansion indication tensor;
and determining the difficulty matching degree of the candidate test questions and the students according to the preferred accuracy range, the bottom line accuracy range, the knowledge point expansion indication, the test question difficulty of the candidate test questions, the test question difficulty of the difficulty reference test questions, the knowledge point set of the candidate test questions and the knowledge point set of the difficulty reference test questions.
In the above embodiment, it is preferable that the accuracy range tensor, the bottom line accuracy range tensor, and the knowledge point expansion indication tensor are preset; the preferred accuracy range tensor comprises the corresponding relation between the preferred accuracy range and the class type, the grade and the mastery degree of the knowledge points; the bottom line accuracy range tensor comprises the corresponding relation between the bottom line accuracy range and the class type, the grade and the knowledge point mastering degree, and the knowledge point expansion indication tensor comprises the corresponding relation between the bottom line accuracy range and the class type, the grade and the knowledge point mastering degree; namely: according to the class type, the grade and the mastery degree of the knowledge points, a corresponding optimal accuracy range, a corresponding bottom line accuracy range and a corresponding knowledge point expansion indication can be determined;
whether the difference between the test question difficulty of the candidate test question and the test question difficulty of the difficulty reference test question is in the optimal accuracy range can be judged; whether the difference between the test question difficulty of the candidate test question and the test question difficulty of the difficulty reference test question is within the bottom line accuracy range or not; whether the knowledge point set of the candidate test question has knowledge point expansion relative to the knowledge point set of the difficulty reference test question. And determining the difficulty matching degree of the candidate test questions and the students according to the judgment result and the corresponding preset weight.
In the embodiment, the optimal accuracy range, the bottom line accuracy range and the knowledge point expansion indication can be determined according to the class type, the grade and the knowledge point mastering degree; matching the obtained difficulty matching degree with the characteristics of students, wherein the mastering degree of the knowledge points can be untrained, weak, general and firm, and can also be set in other settings, the test question difficulty of the candidate test questions can be the accuracy of the candidate test questions, and the test question difficulty of the difficulty reference test questions can be the accuracy of the difficulty reference test questions; in this embodiment, the optimal accuracy ranges of students with different knowledge points mastering degrees are different from the baseline accuracy range, so that the difficulty degree matching degree and the real matching degree of the candidate test questions and the students obtained through calculation are closer to each other.
More specifically, determining the difficulty matching degree of the candidate test questions relative to the student according to the preferred accuracy range, the bottom line accuracy range, the knowledge point expansion indication, the test question difficulty of the candidate test questions, the test question difficulty of the difficulty reference test questions, the knowledge point set of the candidate test questions and the knowledge point set of the difficulty reference test questions comprises:
calculating the difficulty matching degree of the alternative test questions according to a formula I;
the first formula comprises:
In an alternative embodiment of the method according to the invention,
the basic information of the alternative test questions comprises grades, regions, examination types and years;
the basic information of the students includes grades and regions;
referring to fig. 3, determining the priority of the alternative test questions relative to the student test questions includes:
s301, determining the grade priority, the area priority, the year priority and the examination type priority of the alternative test questions relative to the students according to the basic information of the students and the basic information of the alternative test questions;
s302, determining the priority weights of the grade priority, the area priority, the year priority and the examination type priority of the students according to the basic information of the students and a preset priority matrix;
s303, adjusting the grade priority, the area priority, the year priority and the test type priority according to the priority weight;
and S304, determining the test question priority of the alternative test questions relative to the students according to the adjusted year priority, area priority, year priority and examination category priority.
In the embodiment of the application, the grade factor, the area factor, the year factor and the examination type factor are comprehensively considered, and the test question priority is determined according to the grade factor, the area factor, the year factor and the examination type factor, so that the matching degree of the alternative test questions and students can be better reflected by the test question priority; the test questions recommended based on the test question priority can better meet the requirements of students, and the exercise effect of the students is improved.
Specifically, the priority of the test questions is calculated according to a formula II;
the second formula includes:
In an optional embodiment, determining recommended test questions according to the test question priority and the difficulty matching degree includes: and determining the comprehensive recommendation degree according to the priority and the difficulty matching degree of the test questions, and selecting the alternative test questions corresponding to the previous N large comprehensive recommendation degrees as recommended test questions according to the sequence of the comprehensive recommendation degrees from large to small.
Specifically, calculating the comprehensive recommendation degree through a formula III;
the third formula includes:
wherein the content of the first and second substances,
is the comprehensive recommendation degree of the t-th candidate test question relative to the n-th difficulty reference test question of the student u,
whether the t-th candidate test question exceeds the outline or not is shown,
indicating whether the t-th candidate test question is made by the student u,
is a decay function, n is arranged inversely in time;
as the weight of the priority of the test question,
shows the test question priority of the t-th candidate test question relative to the student u,
the weight of the degree of difficulty matching is,
representing the difficulty matching degree of the t-th candidate test question relative to the n-th difficulty reference test question of the student u,
the filtering weight of the candidate test question of the t-th channel relative to the student u;
and determining recommended test questions according to the comprehensive recommendation degree.
It will be appreciated that, due to the foregoing
Represents the difficulty matching degree of the t-th candidate test question relative to the n-th difficulty reference test question of the student u, and
the comprehensive recommendation degree of the nth difficulty reference test question of the nth candidate test question relative to the student u is selected, so that the maximum value of the comprehensive recommendation degrees of the nth candidate test question relative to the difficulty reference test question of the student u can be selected as the comprehensive recommendation degree of the nth candidate test question relative to the student u.
In an alternative embodiment, the knowledge point mastery degree of the student is judged again according to the test question answering records of the student. When knowledge points of students are different in mastery degree, corresponding optimal accuracy rate ranges and the like can be changed, so that the difficulty matching degree of the final alternative test questions relative to the students is different, the updating and perfecting of recommendation results are further realized, and the method is convenient to implement and good in effect.
Meanwhile, it can be known that the questions made by the students need to be updated after new test question answering records exist.
For the convenience of understanding, the first school segment of a student is taken as an example for explanation, and the practical application can be extended to other school segments.
Step 1: key factors available for recommending test questions are combed and stored in a corresponding database, and specifically, in the test question recommendation, two core entities are provided: students and test questions.
The introduction of students and test questions are performed separately as follows:
step 1-1: the characteristics of the student (denoted u) are as follows:
grade of year, as
Values are pre-initial upper (15), pre-initial lower (16), primary upper (17), primary lower (18), primary upper second (19), primary lower second (20), primary upper third (21) and primary lower third (22);
class type, is marked as
When the student class type is empty, the value is 1, the class type is cyanine class/school class and when the student class type is off class, the value is 2, the class type is target class and when the student class type is on class, the value is 3;
province, mark as
The value is directly the province where the student is (the missing value is 0);
market, record as
Taking the value as the city where the student is located (the missing value is 0);
degree of knowledge points, record
The method can be divided into classification types, such as four mastery degrees, namely, non-practice (1), weakness (2), general (3) and firmness (4);
difficulty list of over/error test questions, note
，
The value ranges from 0 to 1. Wherein n is the number of the test questions made by the student. It should be noted that, since the untrained knowledge points do not have question data,
the difficulty list only needs to take one element, and the average difficulty of the candidate test questions with the knowledge points can be set specifically;
list of set of knowledge points on which wrong test questions were made/written
，
Is the knowledge point set of the nth topic. Note: since the untrained knowledge points have no question data,
the knowledge point set list only needs to take one element, and the specific value of the element is the current knowledge point.
Step 1-2: the candidate test question (denoted as t) is characterized as follows:
grade of year, as
Values are pre-initial upper (15), pre-initial lower (16), primary upper (17), primary lower (18), primary upper second (19), primary lower second (20), primary upper third (21) and primary lower third (22);
province, mark as
Taking the value as the province where the test question is from (the missing value is temporarily set as-1);
market, record as
Taking the value as the market where the test question comes (the missing value is temporarily set as-1);
year, is recorded as
Taking the value as the year of the source of the test question;
examination classification, note
The value is taken as the type of examination. Wherein, if the question is a real question of the middle entrance examination and the type of the middle entrance examination simulation is 1, other types are 2, and the null value/missing value is 3;
difficulty, note as
The value is between 0 and 1;
set of knowledge points, denoted
And the value is taken as the knowledge point set of the question. For example (internal angles of triangles and, the nature of parallel triangles).
Through the combing of key factors in the personalized recommendation of the test questions, on one hand, the precision of subsequent personalized recommendation can be improved; on the other hand, the interpretability of subsequent recommendation can be ensured, because what key factors play a key role can be tracked back based on the recommendation result, and the user is informed of why the problem is solved, namely, the interpretability of the recommendation is improved.
And grading the mastery conditions of the students according to the answer records of the students. For easy understanding, the knowledge point grasping conditions in the embodiment of the application are divided into 4 levels, namely four levels of firmness, generality, no grasping and no exercise. In practical applications, adjustments and changes can be made based on actual traffic conditions. Wherein if the student does not have any answer record on the knowledge point, the student defaults to the non-exercise state. The knowledge point grasping condition of the student is calculated by various algorithms including a common IRT \ DKT algorithm and the like, and after the specific score of the grasping degree of the student on the knowledge point is calculated, the specific grade of the student can be obtained through a clustering algorithm or thresholds for dividing different stages based on the overall grasping condition distribution of the student on the knowledge point.
Calling candidate test questions with the knowledge points from a database as a candidate test question set according to the knowledge point mastering conditions of the students and the knowledge points required to be linked by the students; and calculating the scores of the candidate test question priorities and the scores of the difficulty matching degrees, and calculating the final score of the comprehensive matching degree. And sequencing the scores of the comprehensive matching degrees from large to small, and acquiring TopN candidate test questions as recommended test questions.
Specifically, the calculation can be performed through the following modules;
the test question priority calculation module is used for calculating the priority of the test questions, wherein the test question priority refers to the recommended priority of a certain candidate test question based on the current basic information of the student compared with the basic information of the candidate test question. A total of 4 conditions, year priority, region priority (including province and city), examination category priority, year priority, are considered. Since the priorities recommended by students in different grades are different, a priority matrix PR is constructed as follows:
wherein the content of the first and second substances,
indicating the priority weight of the ith grade on the jth condition. For example, when
Indicating that the priority weight on the annual priority of the first grade of the primary school is 1 when
The priority weight of the regional priority in the grade of primary school is 1 when
The priority of the test class in the grade I of primary school is 1, when
It means that the priority weight in the annual priority of elementary school is 1.
It should be noted that the grade in this embodiment is divided into half a year, so that when the grade is divided into half a year
In time, the top three is shown.
Take three grades in junior middle school (calculating to predict the first grade) as a specific example, namely
To
These 8 rows. Suppose from
To
The five year segments are identical in priority and
there are differences in this year segment (i.e., first three lower). Next, specific priority weight values are given.
Calculating the test question priority score of the alternative test question t relative to the student u based on the priority matrix and the judgment condition
The method comprises the following steps:
wherein the content of the first and second substances,
shows the test question priority of the t-th candidate test question relative to the student u,
indicating an indicator function of 1 when the condition is satisfied and 0 when the condition is not satisfied, for example,
indicating that when the grade of the test question is equal to the grade of the student,
otherwise, the value is 0;
represents the grade of student u;
representing the grade of the t-th candidate test question;
a priority weight representing the grade of student u;
the province in the area of the t-th candidate test question is shown,
representing a province in the region of student u,
shows the cities in the area of the t-th candidate test question,
representing the city in the region of student u,
a priority weight representing the region of student u,
the examination type of the t-th candidate test question is shown, and when the examination type of the t-th candidate test question belongs to the target type
The number of the carbon atoms is 1,
a priority weight representing the test category of student u,
which indicates the current year of the year in which the year is currently active,
the year of the t-th candidate test question is shown,
indicating the priority weight of the year of student u.
as can be appreciated, the above
Can be set in a normalized form in advance, then
No further normalization step needs to be performed.
The difficulty matching degree score calculating module is mainly used for calculating three tensors constructed according to the following steps:
the tensor for the range of accuracy is preferred,
. Wherein the elements of the tensor are
And the preferred accuracy range of the candidate test questions and the original test questions (namely the difficulty reference test questions in the foregoing) of the ith class in the mastery degree of the kth knowledge point on j year-level sections is shown. For example, when
And then, the difference between the accuracy of the candidate test questions and the accuracy of the original test questions is less than or equal to 5 percent and more than or equal to-5 percent. Note:
it is indicated that the class-type information is missing,
represents cyanine class/commuter class and the following classes,
representing the target class and the above class types; the value range of j refers to the grade of the student; k is within a range of values when
The time indicates that the knowledge points are mastered as not being exercised,
when the film is a weak film, the film is weak,
the time is indicated to be in general,
it is firm when it is used;
the bottom line accuracy range tensor,
. Wherein the elements of the tensor are
And the base line accuracy range of the candidate test questions and the original test questions in the mastery degree of the kth knowledge point of the ith class in j years is shown. For example, when
The difference between the accuracy of the candidate test questions and the accuracy of the original test questions is smaller than or equal to 100 percent and larger than or equal to-5 percent;
the point of knowledge expansion indicates the tensor,
. Wherein the elements of the tensor are
And the display unit is used for displaying the current situation of the ith class according to the current situation of the ith class. For example, when
The time, it shows that the knowledge points do not need to be expanded;when in use
The knowledge points of the pushed test question need to be expanded.
Based on the three tensors, the difficulty matching degree score between the nth question and the test question t of the student u can be obtained
The specific calculation formula is as follows:
To pair
And carrying out normalization, wherein the normalization formula is as follows:
；（7）
as can be appreciated, the above
Can be set in a normalized form in advance, then
No further normalization step needs to be performed.
A comprehensive score calculating module for scoring based on the test question priority
Matching score with test question difficulty
The comprehensive score between the nth topic and the tth topic of the candidate test topic made by the student u can be obtained as follows:
wherein the content of the first and second substances,
is the comprehensive recommendation degree of the t-th candidate test question relative to the n-th difficulty reference test question of the student u,
whether the t-th alternative test question exceeds the basic rule or not is shown
When not exceeding the basic line
，
Indicating whether the t-th candidate test question is made by the student u,
indicating whether the test question is done by the student and is out of date
When not doing so
，
Is a decay function, n is arranged inversely in time;
as the weight of the priority of the test question,
shows the test question priority of the t-th candidate test question relative to the student u,
the weight of the degree of difficulty matching is,
representing the difficulty matching degree of the t-th candidate test question relative to the n-th difficulty reference test question of the student u,
the filtering weight of the candidate test question of the tth track relative to the student u represents whether the candidate test question t needs to be filtered or not for the student u;
the initial period may be set to 0.5.
In order to simplify the Newton attenuation function of the version, the test question sequence is attenuated, and the closer the test question time is, the weaker the attenuation is, so that the recommendation precision is further improved. It should be noted that the order of the test questions made by the student is reversed, i.e. a larger n indicates that the question is farther from the current time. The introduction of the filtering weight not only improves the recommendation precision, but also meets the teaching and teaching research requirements (namely, the super-class test questions cannot be recommended), and further improves the use experience of the user.
In the optional embodiment, the test question priority score and the test question difficulty matching degree score are obtained through comprehensive calculation based on the relevant information (such as the grade, the class type, the knowledge point mastering condition, the question making record and the like) of the student and the relevant information (such as the difficulty, the knowledge point range, the age limit, the area and the like) of the test question, and then the comprehensive score of the candidate question is obtained based on the two scores, so that the comprehensive personalized test question sequencing and recommendation based on the student information are realized. In the step, through the construction of a plurality of tensors, key factors of students and test questions are fully integrated, and the recommendation precision can be remarkably improved. Meanwhile, the key factors can be used as interpretable factors for test question recommendation, such as a certain question is pushed for a certain student, because the difficulty of the question is matched with the ability of the student; for example, a certain question is pushed for a certain student because the question is in accordance with the region and grade of the student, and has high quality. Particularly, compared with the existing recommendation system based on complex models such as neural networks and reinforcement learning, the personalized recommendation scheme designed by the proposal does not need large-scale data training, has low model complexity, and can remarkably improve the topic recommendation efficiency of personalized recommendation. In addition, the scheme has good expandability, and only the tensor needs to be increased or modified.
And finally, the response data of the students can be returned, the related information of the students is updated, the knowledge point mastering condition of the students is judged again, and the recommendation result is updated and perfected. The scheme can be conveniently landed and applied, and has the advantages of low implementation cost, good effect and the like.
In summary, in the technical scheme of the embodiment of the application, key factors of personalized test question recommendation are extracted, including relevant factors of students (such as grade, class type, knowledge point mastering condition, question making record and the like) and relevant factors of test questions (such as difficulty, knowledge point range, year limit, area and the like), and compared with the previous recommendation scheme. When the key factors are combed, conventional information such as difficulty is considered, and factors related to teaching and teaching research such as regions and the like are considered. Because the requirements and difficulties for making questions are different in different regions, the factors are considered in the recommendation scheme, and the factors can be well combined with actual teaching. The combing of the key factors not only improves the recommendation precision, but also well improves the recommendation interpretability. In the actual topic deduction process, the key factors can be tracked reversely to play a dominant role in the recommendation, so that the factors can be output, and the interpretability of the recommendation is improved. According to the technical scheme of the embodiment of the application, based on the recommendation algorithm with the fusion of a plurality of quantities, on one hand, a plurality of key factors can be accurately fused into the final recommendation scoring result, and the recommendation accuracy is obviously improved; on the other hand, the recommendation algorithm can adjust corresponding scoring parameters according to actual service conditions, can be adapted to scenes of different subject sections, and has good interpretability on recommendation results; in addition, compared with the existing test question recommendation scheme, the recommendation scheme greatly reduces the complexity and the calculation amount of the model on the premise of ensuring the precision, improves the recommendation efficiency, and can be better used on the ground and in a large scale.
Referring to fig. 4, a test question recommending apparatus includes:
the candidate test question acquiring module 401 is configured to acquire at least two candidate test questions;
a difficulty matching degree determining module 402, configured to determine a difficulty matching degree of the candidate test question with respect to the student;
the test question priority determining module 403 is configured to determine the test question priority of the candidate test question relative to the student according to the basic information of the candidate test question and the basic information of the student;
and the test question recommending module 404 is configured to determine recommended test questions according to the test question priority and the difficulty matching degree.
Determining the difficulty matching degree of the candidate test questions relative to the student, comprising the following steps:
acquiring difficulty reference test questions of students, wherein the difficulty reference test questions are test questions already made by the students;
obtaining the test question difficulty of the alternative test questions and the test question difficulty of the difficulty reference test questions;
acquiring a knowledge point set of the alternative test questions and a knowledge point set of the difficulty reference test questions;
and determining the difficulty matching degree of the candidate test questions and the students according to the test question difficulty of the candidate test questions, the test question difficulty of the difficulty reference test questions, the knowledge point set of the candidate test questions and the knowledge point set of the difficulty reference test questions.
In one embodiment, determining difficulty matching degrees of the candidate test questions with respect to the student according to test question difficulties of the candidate test questions, test question difficulties of difficulty reference test questions, knowledge point sets of the candidate test questions and knowledge point sets of the difficulty reference test questions comprises:
acquiring class type, grade and knowledge point mastering degree of students;
according to the class type, the grade and the mastery degree of the knowledge points, acquiring an optimal accuracy range, a bottom line accuracy range and a knowledge point expansion indication from a preset optimal accuracy range tensor, a bottom line accuracy range tensor and a knowledge point expansion indication tensor;
and determining the difficulty matching degree of the student according to the difficulty matching degree of the candidate test questions and the student according to the preferred accuracy range, the bottom line accuracy range, the knowledge point expansion indication, the test question difficulty of the candidate test questions, the test question difficulty of the difficulty reference test questions, the knowledge point set of the candidate test questions and the knowledge point set of the difficulty reference test questions.
In one embodiment, determining the difficulty matching degree of the candidate test questions with respect to the student according to the preferred accuracy range, the baseline accuracy range, the knowledge point extension indication, the test question difficulty of the candidate test questions, the test question difficulty of the difficulty reference test questions, the knowledge point set of the candidate test questions and the knowledge point set of the difficulty reference test questions comprises:
calculating the difficulty matching degree of the alternative test questions according to a formula I;
in one embodiment, the basic information of the candidate test questions includes grade, region, examination category and year;
the basic information of the students includes grades and regions;
determining the priority of the alternative test questions relative to the test questions of the student, comprising the following steps:
determining the grade priority, the area priority, the year priority and the examination type priority of the alternative test questions relative to the students according to the basic information of the students and the basic information of the alternative test questions;
determining the priority weights of the grade priority, the area priority, the year priority and the examination type priority of the students according to the basic information of the students and a preset priority matrix;
adjusting the grade priority, the area priority, the year priority and the examination category priority according to the priority weight;
and determining the test question priority of the alternative test questions relative to the students according to the adjusted year priority, area priority, year priority and examination category priority.
In one embodiment, determining the priority of the alternative test questions relative to the student test questions comprises:
calculating the priority of the test questions according to a formula II;
in one embodiment, determining recommended test questions according to the test question priority and the difficulty matching degree includes:
calculating the comprehensive recommendation degree through a formula III;
and determining recommended test questions according to the comprehensive recommendation degree.
In one embodiment, the system further comprises a re-judging module, which is used for re-judging the mastery degree of the knowledge points of the students according to the test question answering records of the students.
The test question recommendation device of the embodiment is a device for implementing any one of the test question recommendation methods in the embodiments, and the technical scheme and the effect of the test question recommendation method in the embodiments can be referred to for the difficulty and the effect of the selectable technology.
Referring to fig. 5, an electronic device 500 includes a processor 501 and a memory 502, where the memory 502 is used to store computer instructions, and the computer instructions are executed by the processor 501 to implement a test question recommendation method according to any one of the embodiments of the present application.
The application also provides a readable storage medium, on which computer instructions are stored, and the computer instructions, when executed by a processor, implement a test question recommendation method in any one of the embodiments of the application.
Fig. 6 is a schematic diagram of a computer system suitable for implementing a test question recommendation method according to an embodiment of the present application.
Referring to fig. 6, the computer system includes a processing unit 601 which can execute various processes in the embodiment shown in the above-described drawings according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage portion 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data necessary for system operation are also stored. The processing unit 601, the ROM602, and the RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary. The processing unit 601 may be implemented as a CPU, a GPU, a TPU, an FPGA, an NPU, or other processing units.
In the description herein, reference to the description of the terms "one embodiment/mode," "some embodiments/modes," "example," "specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment/mode or example is included in at least one embodiment/mode or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to be the same embodiment/mode or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments/modes or examples. Furthermore, the various embodiments/aspects or examples and features of the various embodiments/aspects or examples described in this specification can be combined and combined by one skilled in the art without conflicting therewith.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
It should be understood by those skilled in the art that the above embodiments are only for clarity of explanation and are not intended to limit the scope of the present application. Other variations or modifications will occur to those skilled in the art based on the foregoing disclosure and are still within the scope of the present application.
Claims (11)
1. A test question recommendation method is characterized by comprising the following steps:
acquiring at least two alternative test questions;
determining the difficulty matching degree of the alternative test questions relative to the student;
determining the test question priority of the alternative test questions relative to the student according to the basic information of the alternative test questions and the basic information of the student;
and determining recommended test questions according to the test question priority and the difficulty matching degree.
2. The method for recommending test questions according to claim 1, wherein said determining the difficulty matching degree of said candidate test questions with respect to said student comprises:
acquiring difficulty reference test questions of the students, wherein the difficulty reference test questions are already made test questions of the students;
obtaining the test question difficulty of the alternative test questions and the test question difficulty of the difficulty reference test questions;
acquiring a knowledge point set of the candidate test questions and a knowledge point set of the difficulty reference test questions;
and determining the difficulty matching degree of the candidate test questions and the students according to the test question difficulty of the candidate test questions, the test question difficulty of the difficulty reference test questions, the knowledge point set of the candidate test questions and the knowledge point set of the difficulty reference test questions.
3. The test question recommendation method according to claim 2, wherein determining the difficulty matching degree of the candidate test questions with respect to the student according to the test question difficulty of the candidate test questions, the test question difficulty of the difficulty reference test questions, the knowledge point set of the candidate test questions and the knowledge point set of the difficulty reference test questions comprises:
acquiring class type, grade and knowledge point mastering degree of the student;
according to the class type, the grade and the mastery degree of the knowledge points, acquiring an optimal accuracy range, a bottom line accuracy range and a knowledge point expansion indication from a preset optimal accuracy range tensor, a bottom line accuracy range tensor and a knowledge point expansion indication tensor;
and determining the difficulty matching degree of the candidate test questions and the students according to the optimal correct rate range, the bottom line correct rate range, the knowledge point expansion indication, the test question difficulty of the candidate test questions, the test question difficulty of the difficulty reference test questions, the knowledge point set of the candidate test questions and the knowledge point set of the difficulty reference test questions.
4. The test question recommendation method according to claim 3, wherein determining the difficulty matching degree of the candidate test questions with respect to the student according to the preferred accuracy range, the baseline accuracy range, the knowledge point expansion indication, the test question difficulty of the candidate test questions, the test question difficulty of the difficulty reference test questions, the knowledge point set of the candidate test questions and the knowledge point set of the difficulty reference test questions comprises:
calculating the difficulty matching degree of the alternative test questions according to a formula I;
the first formula comprises:
5. The method of claim 1, wherein the basic information of the candidate test questions comprises a grade, a region, a test category and a year;
the basic information of the students comprises grades and regions;
determining the priority of the alternative test questions relative to the test questions of the student, comprising:
determining the grade priority, the area priority, the year priority and the examination category priority of the alternative test questions relative to the student according to the basic information of the student and the basic information of the alternative test questions;
determining the priority weights of the grade priority, the area priority, the year priority and the examination category priority of the students according to the basic information of the students and a preset priority matrix;
adjusting the year priority, the region priority, the year priority and the test category priority according to the priority weight;
and determining the test question priority of the alternative test question relative to the student according to the adjusted year priority, the adjusted region priority, the adjusted year priority and the adjusted test category priority.
6. The method of claim 5, wherein determining the priority of the candidate test questions relative to the student test questions comprises:
calculating the priority of the test questions according to a formula II;
the second formula includes:
7. The method for recommending test questions according to claim 1, wherein said determining recommended test questions according to said test question priorities and said difficulty matching degrees comprises:
calculating the comprehensive recommendation degree through a formula III;
the third formula includes:
wherein the content of the first and second substances,
is the comprehensive recommendation degree of the t-th candidate test question relative to the n-th difficulty reference test question of the student u,
whether the t-th candidate test question exceeds the outline or not is shown,
indicating whether the t-th candidate test question is made by the student u,
is a decay function, n is arranged inversely in time;
as the weight of the priority of the test question,
shows the test question priority of the t-th candidate test question relative to the student u,
the weight of the degree of difficulty matching is,
representing the difficulty matching degree of the t-th candidate test question relative to the n-th difficulty reference test question of the student u,
the filtering weight of the candidate test question of the t-th channel relative to the student u;
and determining recommended test questions according to the comprehensive recommendation degree.
8. The test question recommendation method according to claim 7, characterized in that the mastery degree of the knowledge points of the students is re-judged according to the test question answering records of the students.
9. A test question recommendation apparatus, comprising:
the candidate test question acquisition module is used for acquiring at least two candidate test questions;
the difficulty matching degree determining module is used for determining the difficulty matching degree of the candidate test questions relative to the students;
the test question priority determining module is used for determining the test question priority of the alternative test questions relative to the student according to the basic information of the alternative test questions and the basic information of the student;
and the test question recommending module is used for determining recommended test questions according to the test question priority and the difficulty matching degree.
10. An electronic device comprising a memory and a processor, the memory for storing computer instructions, wherein the computer instructions are executable by the processor to implement the method of any one of claims 1-8.
11. A readable storage medium having stored thereon computer instructions, characterized in that the computer instructions, when executed by a processor, implement the method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110246990.7A CN112614034A (en) | 2021-03-05 | 2021-03-05 | Test question recommendation method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110246990.7A CN112614034A (en) | 2021-03-05 | 2021-03-05 | Test question recommendation method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112614034A true CN112614034A (en) | 2021-04-06 |
Family
ID=75254387
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110246990.7A Pending CN112614034A (en) | 2021-03-05 | 2021-03-05 | Test question recommendation method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112614034A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113377942A (en) * | 2021-07-12 | 2021-09-10 | 北京乐学帮网络技术有限公司 | Test paper generation method and device, computer equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7733366B2 (en) * | 2002-07-01 | 2010-06-08 | Microsoft Corporation | Computer network-based, interactive, multimedia learning system and process |
| CN104834729A (en) * | 2015-05-14 | 2015-08-12 | 百度在线网络技术（北京）有限公司 | Title recommendation method and title recommendation device |
| CN106227809A (en) * | 2016-07-22 | 2016-12-14 | 广东小天才科技有限公司 | Test question pushing method and device |
| CN110472147A (en) * | 2019-07-29 | 2019-11-19 | 天闻数媒科技（湖南）有限公司 | It is a kind of to provide the method and its system of personalized examination question based on recommended engine |
-
2021
- 2021-03-05 CN CN202110246990.7A patent/CN112614034A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7733366B2 (en) * | 2002-07-01 | 2010-06-08 | Microsoft Corporation | Computer network-based, interactive, multimedia learning system and process |
| CN104834729A (en) * | 2015-05-14 | 2015-08-12 | 百度在线网络技术（北京）有限公司 | Title recommendation method and title recommendation device |
| CN106227809A (en) * | 2016-07-22 | 2016-12-14 | 广东小天才科技有限公司 | Test question pushing method and device |
| CN110472147A (en) * | 2019-07-29 | 2019-11-19 | 天闻数媒科技（湖南）有限公司 | It is a kind of to provide the method and its system of personalized examination question based on recommended engine |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113377942A (en) * | 2021-07-12 | 2021-09-10 | 北京乐学帮网络技术有限公司 | Test paper generation method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107230174B (en) | Online interactive learning system and method based on network | |
| CN111062842A (en) | Method and device for dynamically generating personalized questions | |
| CN112699283B (en) | Test paper generation method and device | |
| CN111090809A (en) | Topic recommendation method and device, computer equipment and storage medium | |
| WO2022170985A1 (en) | Exercise selection method and apparatus, and computer device and storage medium | |
| CN111651677B (en) | Course content recommendation method, apparatus, computer device and storage medium | |
| CN116263782A (en) | Intelligent winding method, system and storage medium based on question bank | |
| CN107256522A (en) | Teaching assessment system based on cloud teaching platform | |
| CN114429212A (en) | Intelligent learning knowledge ability tracking method, electronic device and storage medium | |
| CN113535935B (en) | Method, device, equipment and medium for grouping rolls based on importance degree and priority | |
| CN115544268A (en) | Construction and application method of teaching and employment auxiliary knowledge map | |
| Dorn et al. | Becoming experts: Measuring attitude development in introductory computer science | |
| CN112614034A (en) | Test question recommendation method and device, electronic equipment and readable storage medium | |
| Keng | A comparison of the performance of testlet-based computer adaptive tests and multistage tests | |
| CN112784154B (en) | Online teaching recommendation system with data enhancement | |
| CN117313947A (en) | Learning early warning method based on random forest and tuna group optimization algorithm | |
| Dragoset et al. | Measuring School Performance for Early Elementary Grades in Maryland. | |
| CN111104455A (en) | Multisource and multidimensional school teaching transverse information difference comparison analysis method | |
| CN115713441A (en) | Teaching quality evaluation method and system based on AHP-Fuzzy algorithm and neural network | |
| CN112700356B (en) | Method and system for managing information of training personnel for real-time online education and training | |
| CN115409257A (en) | Score distribution prediction method and system based on condition density estimation model | |
| CN113642880A (en) | Internet-based team training method and system | |
| Perez et al. | Implementation of a test constructor utilizing a calibrated item bank using 3PL-IRT model | |
| Valsamidis et al. | A combined algorithm for LMS usage assessment | |
| JPH08179682A (en) | Score processing means for question forming apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210406 |
|
| RJ01 | Rejection of invention patent application after publication |