CN110704503A

CN110704503A - Question setting method and device and server

Info

Publication number: CN110704503A
Application number: CN201910889540.2A
Authority: CN
Inventors: 徐涛; 吴峰; 郭伟
Original assignee: Shanghai Yidianshikong Network Co Ltd
Current assignee: Shanghai Yidianshikong Network Co Ltd
Priority date: 2019-09-19
Filing date: 2019-09-19
Publication date: 2020-01-17

Abstract

The application discloses a question setting method and device and a server. The method comprises the steps of dividing statistical data of historical exercise of making questions of a user to obtain different types of test questions according to test question knowledge points and the made test questions; extracting a first type of test questions according to the different types of test question division results, and judging answering results of the first type of test questions; if the answer result is correct, judging the mastering degree of the test question knowledge points through the prediction values; if the answer result is incorrect, continue to extract the second type of test question with the lowest relevance to the wrong answer test question. The application solves the technical problem that the effect of the question setting method is not good. By the method and the device, the test question making efficiency is improved, and the test question exercise time is shortened on the premise of ensuring the accuracy. Meanwhile, big data statistical analysis is combined, and the mastering degree of the knowledge points can be accurately predicted. In addition, the method is suitable for the application of the subject of the driving test subject I.

Description

Question setting method and device and server

Technical Field

The application relates to the field of big data, in particular to a question setting method and device and a server.

Background

The practice of setting questions is usually based on the knowledge points and according to the test question sequence, and the practice of setting questions which are very familiar to the trainee is repeated, which wastes a lot of time.

The inventor finds that if all the topics are made in sequence, the time is long for the user, and the degree of mastering of the knowledge points by the user cannot be predicted. Further, the process of setting questions cannot be optimized, thereby reducing the time for exercise of the questions.

Aiming at the problem of poor effect of the problem solving method in the related technology, no effective solution is provided at present.

Disclosure of Invention

The present application mainly aims to provide a question setting method, a question setting device and a server to solve the problem.

To achieve the above object, according to one aspect of the present application, a method for setting up questions is provided for driving test subjects.

The method of proposing a topic according to the application comprises: dividing the statistical data of the user history exercise according to the test question knowledge points and the test questions already done to obtain different types of test questions; extracting a first type of test questions according to the different types of test question division results, and judging answering results of the first type of test questions; if the answer result is correct, judging the mastering degree of the test question knowledge points through the prediction values; if the answer result is incorrect, continue to extract the second type of test question with the lowest relevance to the wrong answer test question.

Further, if the answer result is correct, after judging the mastery degree of the test question knowledge points by the prediction score, the method further comprises the following steps:

if the prediction score is not smaller than the threshold value, judging that the test question knowledge points are mastered;

and if the prediction score is larger than the threshold value, judging that the test question knowledge points are not mastered.

Further, if the answer result is incorrect, the step of continuously extracting the second type of test questions with the lowest relevance to the wrong answer test questions comprises the following steps:

if the answer result is incorrect, continue to extract the second type of test questions with the lowest relevance to the wrong answer test questions,

wherein, the relevance of the test question Q1 and the test question Q2 in the test questions is the number of people who answer the pair of test questions Q1 and Q2/(the number of people who answer the pair of test questions Q1 is the number of people who answer the pair of test questions Q2);

and determining the test question with the lowest relevance to the wrong test question according to the relevance between the test question Q1 and the test question Q2 and the historical data.

Further, if the answer result is correct, judging the mastering degree of the test question knowledge points through the prediction scores comprises the following steps:

the predicted score (sum of relevance of the answer pair test question and each test question which is not completed at the knowledge point/number of test questions which are not completed at the knowledge point) is 100.

Further, according to the test question knowledge points and the test questions already done, obtaining different types of test questions by dividing the statistical data of the user history question-making practice includes:

obtaining different categories of test questions according to the test question knowledge points and the test questions already made,

the first type of test questions are the types which are easier to select and have higher answer accuracy;

the second type of test question is a type which is easier to select and has a higher answer error rate.

Further, if the answer result is incorrect, after continuing to extract the second type of test question with the lowest relevance to the wrong answer test question, the method further comprises the following steps:

if the answer result is incorrect, continue to extract the third type of test question with the lowest relevance to the wrong answer test question,

To achieve the above object, according to another aspect of the present application, a problem setting device for setting a problem of a driving test subject is provided.

The title device according to this application includes: the test question dividing module is used for dividing the statistical data of the historical test question exercise of the user according to the test question knowledge points and the test questions already made to obtain different types of test questions; the judging module is used for extracting a first type of test questions according to the different types of test question dividing results and judging answering results of the first type of test questions; the score prediction module is used for predicting scores to judge the mastering degree of the test question knowledge points when the answering result is correct; and the extraction module is used for continuously extracting the second type of test questions with the lowest correlation degree with the wrong answer test questions when the answer result is incorrect.

Further, the device also comprises a knowledge point grasping module used for

Further, the apparatus further comprises: and the score prediction module is used for calculating a prediction score (the sum of the relevance of the answer pair test question and each test question which is not completed at the knowledge point/the number of the test questions which are not completed at the knowledge point) × 100.

Further, the test question dividing module is used for dividing test questions

In the method, the device and the server for providing the test questions, a mode of dividing the statistical data of the historical exercise for providing the test questions by the user according to the test question knowledge points and the test questions already made is adopted, a first type of test questions are extracted according to the dividing results of the different types of test questions, the answering results of the first type of test questions are judged, and the mastering degree of the test question knowledge points is judged according to the prediction values if the answering results are correct; if the answer result is incorrect, the purpose of continuously extracting the second type of test questions with the lowest relevance to the wrong answer test questions is achieved, so that the step of optimizing the questions is achieved, the time for the user to practice the test questions can be shortened, the technical effect of reviewing efficiency of corresponding subjects is improved, and the technical problem that the effect of the question-seeking method is poor is solved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:

FIG. 1 is a schematic flow chart of a method of presenting a topic in accordance with a first embodiment of the application;

FIG. 2 is a schematic flow chart of a method of presenting a topic in accordance with a second embodiment of the application;

FIG. 3 is a schematic flow chart of a method of presenting a topic in accordance with a third embodiment of the application;

FIG. 4 is a schematic diagram of a topical device according to a first embodiment of the present application;

FIG. 5 is a schematic diagram of a topical device according to a second embodiment of the present application;

fig. 6 is a schematic diagram of an implementation principle according to the present application.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

In this application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings. These terms are used primarily to better describe the present application and its embodiments, and are not used to limit the indicated devices, elements or components to a particular orientation or to be constructed and operated in a particular orientation.

Moreover, some of the above terms may be used to indicate other meanings besides the orientation or positional relationship, for example, the term "on" may also be used to indicate some kind of attachment or connection relationship in some cases. The specific meaning of these terms in this application will be understood by those of ordinary skill in the art as appropriate.

Furthermore, the terms "mounted," "disposed," "provided," "connected," and "sleeved" are to be construed broadly. For example, it may be a fixed connection, a removable connection, or a unitary construction; can be a mechanical connection, or an electrical connection; may be directly connected, or indirectly connected through intervening media, or may be in internal communication between two devices, elements or components. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.

It should be noted that 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 embodiments with reference to the attached drawings.

The terms used in this application are to be interpreted as follows:

mysql is an open source relational database management system (RDBMS) that uses the most common database management language, Structured Query Language (SQL), for database management.

Sql is a database query and programming language for accessing data and querying, updating and managing.

And a rand () random number generation function.

The short name of App english Application is also the meaning of Application, and generally refers to a third-party Application program of the smart phone.

Correlation degree: a quantity representing the degree of linear correlation between variables.

As shown in fig. 1, the method includes steps S102 to S108 as follows:

step S102, dividing the statistical data of the user history exercise according to the test question knowledge points and the test questions already done to obtain different types of test questions;

and according to the test question knowledge points and the test questions already made, counting and dividing the statistical data of the user history question-making exercises to obtain different types of test questions at a server or a client.

Specifically, a data table is arranged in the Mysql database to store statistical data of historical exercise of doing questions of the user, and A, B, C types of different test questions and the like are divided according to the data table and by combining compilation of sql language.

Step S104, extracting a first type of test questions according to the different types of test question division results, and judging answer results of the first type of test questions;

and extracting the first type of test questions according to the different types of test question division results at a server or a client, and judging answer results of the first type of test questions. And carrying out the next operation according to the answer result of the first type of test questions.

Step S106, if the answer result is correct, judging the mastering degree of the test question knowledge points through the prediction values;

and if the answer result of the first type of test question is judged to be correct at the server or the client, judging the mastering degree of the test question knowledge point according to the affiliated prediction score.

Step S108, if the answer result is incorrect, continuing to extract the second type of test questions with the lowest relevance degree with the wrong answer test questions.

And if the answer result of the first type of test question is judged to be incorrect at the server or the client, continuously extracting a second type of test question with the lowest correlation degree with the wrong answer test question. That is, the correlation degree between the extracted second type of test questions and the second type of test questions is relatively large.

From the above description, it can be seen that the following technical effects are achieved by the present application:

in the embodiment of the application, a mode of dividing the statistical data of the historical exercise of taking questions by users according to the knowledge points of the test questions and the test questions already made is adopted, a first type of test questions are extracted according to the dividing results of the different types of test questions, the answering results of the first type of test questions are judged, and the mastering degree of the knowledge points of the test questions is judged according to the prediction scores if the answering results are correct; if the answer result is incorrect, the purpose of continuously extracting the second type of test questions with the lowest relevance to the wrong answer test questions is achieved, so that the step of optimizing the questions is achieved, the time for the user to practice the test questions can be shortened, the technical effect of reviewing efficiency of corresponding subjects is improved, and the technical problem that the effect of the question-seeking method is poor is solved.

According to the embodiment of the present application, as shown in fig. 2, if the answer result is correct, after judging the mastery degree of the test question knowledge points by the prediction score, the method further includes:

step S202, if the prediction score is not less than the threshold value, judging that the test question knowledge points are mastered;

and step S204, if the prediction score is larger than the threshold value, judging that the test question knowledge points are not mastered.

Specifically, if the type of test question is answered correctly, the prediction score judges the mastery degree of the knowledge point. The higher the score is, the more questions are answered, and if the predicted score > is 90, the knowledge point is mastered; if <90 indicates that the knowledge point has not been mastered.

According to the embodiment of the present application, as a preference in the embodiment, as shown in fig. 3, if the answer result is incorrect, the step of continuously extracting the second type of test questions having the lowest correlation with the wrong answer test questions comprises:

step S302, if the answer result is incorrect, continue to extract the second type of test questions with the lowest correlation degree with the wrong answer test questions,

and S304, determining the test question with the lowest relevance to the wrong test question according to the relevance between the test question Q1 and the test question Q2 and the historical data.

Specifically, the test questions of the type are answered incorrectly, and the test questions with the lowest relevance to the incorrectly answered test questions are continuously extracted. The degree of correlation between the test question Q1 and the test question Q2 is calculated as follows:

q1 and Q2 are related by Q1 and Q2 people who are simultaneously in the same pair (Q1 people who are Q2 people)

According to the above formula and historical data, the test question with the lowest relevance to the wrong test question can be found out for further question setting.

According to the embodiment of the present application, as a preferable preference in the embodiment, if the answer result is correct, the judging the mastery degree of the test question knowledge point by the prediction score includes:

Specifically, the score (sum of the relevance of the test question in the answer pair and each test question whose knowledge point is not completed/number of test questions whose knowledge point is not completed) × 100, higher score indicates more questions in the answer pair, if the predicted score > -90 indicates that the knowledge point is mastered, and if <90 indicates that the knowledge point is not mastered. If the knowledge point is not mastered, the practice is continued according to the C-type test questions and the B-type test questions which are extracted again until the knowledge point is mastered.

According to the embodiment of the present application, as a preferred option in the embodiment, the obtaining of different types of test questions by dividing the statistical data of the user history exercise for doing test questions according to the test question knowledge points and the test questions already done comprises: obtaining different categories of test questions according to the test question knowledge points and the made test questions, wherein the first type of test questions is the type which is easier to select when the answer accuracy is higher; the second type of test question is a type which is easier to select and has a higher answer error rate.

Preferably, if the answer result is incorrect, after continuing to extract the second type of test question with the lowest relevance to the wrong answer test question, the method further comprises: if the answer result is incorrect, the third type of test question with the lowest relevance to the wrong answer test question is continuously extracted.

The relevance between the test question Q1 and the test question Q2 in the test questions is equal to the number of people who answer the pair of test questions Q1 and Q2 at the same time/(the number of people who answer the pair of test questions Q1 is equal to the number of people who answer the pair of test questions Q2).

Specifically, the higher the answer accuracy rate of the class a (first class of test questions) is, the more easily the type a test questions are selected, and the higher the answer error rate of the class C test (second class of test questions) is, the more easily the type C test (second class of test questions) is selected. By using the classification method, the difficult test questions are represented by the class A, the difficult test questions are represented by the class B (third class test questions), and the difficult test questions are represented by the class C.

It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.

According to an embodiment of the present application, there is also provided a question apparatus for implementing the question presenting method, as shown in fig. 4, the apparatus including: the test question dividing module 10 is used for dividing the statistical data of the historical test question exercise of the user according to the test question knowledge points and the test questions already done to obtain different types of test questions; the judging module 20 is used for extracting a first type of test questions according to the different types of test question dividing results and judging answering results of the first type of test questions; the score prediction module 30 is used for predicting scores to judge the mastering degree of the test question knowledge points when the answering result is correct; and the extraction module 40 is used for continuously extracting the second type of test questions with the lowest correlation degree with the wrong answer test questions when the answer result is incorrect.

In the test question dividing module 10 of the embodiment of the present application, the server or the client may count and divide the statistical data of the user history question exercise to obtain different types of test questions according to the test question knowledge points and the made test questions.

In the determination module 20 of the embodiment of the present application, the server or the client extracts the first type of test questions according to the result of dividing the different types of test questions, and determines the answer result of the first type of test questions. And carrying out the next operation according to the answer result of the first type of test questions.

In the score prediction module 30 of the embodiment of the present application, if the server or the client determines that the answer result to the answer result of the first type of test question is correct, the mastery degree of the test question knowledge point is determined according to the prediction score.

In the extraction module 40 of the embodiment of the present application, if it is determined that the answer result to the answer result of the first type of test question is incorrect, the second type of test question with the lowest correlation to the wrong answer test question is continuously extracted. That is, the correlation degree between the extracted second type of test questions and the second type of test questions is relatively large.

According to the embodiment of the present application, as shown in fig. 5, as a preferable option in the embodiment, the method further includes a knowledge point grasping module 50, configured to determine that the test question knowledge point is grasped if the prediction score is not less than the threshold; and if the prediction score is larger than the threshold value, judging that the test question knowledge points are not mastered.

According to the embodiment of the present application, as shown in fig. 5, as a preferable aspect in the embodiment, the method further includes: and the score prediction module 60 is configured to calculate a prediction score (the sum of the relevance of the answer pair test question and each test question that is not completed at the knowledge point/the number of test questions that are not completed at the knowledge point) × 100.

According to the embodiment of the present application, as a preferred option in the embodiment, the test question dividing module is configured to divide the test questions into the test questions

In particular, the amount of the solvent to be used,

and if the test questions of the type are answered incorrectly, continuously extracting the test questions with the lowest relevance to the wrong test questions. The degree of correlation between the test question Q1 and the test question Q2 is calculated as follows:

According to the above formula and historical data, the test question with the lowest relevance to the wrong test question can be found out for further question setting. .

The implementation principle of the present application is shown in fig. 6, and specifically includes the following implementation manners:

the subject-exercise question setting method in the existing driving license application program is to set questions according to the sequence of the examination questions according to the knowledge points, and to repeatedly set questions which are very familiar to the trainees, a lot of time is wasted. The method for optimizing the question setting flow by utilizing big data helps the student to reduce the time for exercise of making questions and improve the examination passing rate. The driving license subject I test question consists of a plurality of knowledge points, the test question exercise is carried out by one knowledge point, and the following description is carried out by taking the driving license subject I as an example:

step one, a table kaojiazhao _ query _ answer _ rate in the mysql database stores the statistical data of the user history exercise, including fields of query _ id (test question id), knowledge _ id (knowledge point id), right _ rate (right answer rate), wrung _ rate (answer error rate), and max _ rate (maximum of right _ rate and wrung _ rate). The classification of the A, B, C type test questions was done according to this table using the following sql:

a type: SELECT FROM Kaojiazhao _ QUESTION _ ANSWER _ RATE WHERE knowledgeid $ { knowledgeid } and QUESTION _ id not in $ { except _ QUESTIONS } ORDER BY (succ _ RATE + RAND () 0.2-0.1) DESC limit 1

B type: SELECT FROM Kaojiazhao _ QUESTION _ ANSWER _ RATE WHERE knowledgeid $ { knowledgeid } and QUESTION _ id not $ { except _ QUESTIONS } ORDER BY ((1-max _ RATE) + RAND () 0.6-0.3) DESC limit 1

Class C: SELECT FROM Kaojiazhao _ QUESTION _ ANSWER _ RATE WHERE knowledgeable _ id $ { knowledgeable _ id } and QUESTION _ id not in $ { exclusion _ queries } ORDER BY (wrung _ rate + RAND () 0.2-0.1) DESC limit 1

The test questions in different categories can be obtained by introducing two parameter values of a knowledge point $ { knowledge _ id }, and the already-made test questions $ { except _ queries }. The higher the answer accuracy of the type A test questions is, the more easily the type A test questions are selected, and the higher the answer error rate of the type C test questions is, the more easily the type C test questions are selected. By using the classification method, the difficult test questions are represented by the class A, the difficult test questions are represented by the class B, and the difficult test questions are represented by the class C.

And 2, selecting the A-type test questions according to the method in the step 1, and if the answer is right jump step 4, the answer is wrong jump step 3.

And 3, continuously extracting the test question with the lowest correlation degree with the wrong answer test question when the type of test question is wrong. The degree of correlation between the test question Q1 and the test question Q2 is calculated as follows:

According to the above formula and historical data, the test question with the lowest relevance to the wrong test question can be found out for further question setting. If the answer is wrong, continuing the step 3, and switching the answer pair to the step 4. .

And 4, judging the mastering degree of the knowledge point by predicting the score, wherein the test question of the type is answered correctly. The predictive score method is as follows:

score (sum of relevance of answer to test question and each test question unfinished in the knowledge point/number of test questions unfinished in the knowledge point) 100

Higher score indicates more questions to be answered, if the predicted score > is 90, the knowledge point is mastered, step 6 is skipped, and if <90, the knowledge point is not mastered, step 5 is skipped.

And 5, continuing to extract C-type and B-type test questions in sequence according to the previous 2-4 steps until the knowledge point is mastered.

And 6, the knowledge point is mastered, and the next knowledge point is switched to.

It will be apparent to those skilled in the art that the modules or steps of the present application described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present application is not limited to any specific combination of hardware and software.

The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for setting up questions for driving test subjects, comprising:

dividing the statistical data of the user history exercise according to the test question knowledge points and the test questions already done to obtain different types of test questions;

extracting a first type of test questions according to the different types of test question division results, and judging answering results of the first type of test questions;

if the answer result is correct, judging the mastering degree of the test question knowledge points through the prediction values;

if the answer result is incorrect, continue to extract the second type of test question with the lowest relevance to the wrong answer test question.

2. The method of claim 1, wherein if the answer result is correct, after determining the mastery degree of the test question knowledge points by the predictive score, further comprising:

3. The method of claim 1, wherein if the answer result is incorrect, the step of continuously extracting the second type of test questions with the lowest correlation degree with the wrong answer test questions comprises:

4. The method of claim 1, wherein if the answer result is correct, the determining the mastery degree of the knowledge points of the test questions by the predictive score comprises:

5. The method of claim 1, wherein the step of dividing the statistical data of the user history exercise for questions according to the knowledge points of the questions and the questions already done to obtain different types of questions comprises:

6. The method of claim 1, wherein if the answer result is incorrect, after continuing to extract the second type of test question with the lowest relevance to the wrong answer test question, further comprising:

7. A question setting apparatus for setting questions for driving test subjects, comprising:

the test question dividing module is used for dividing the statistical data of the historical test question exercise of the user according to the test question knowledge points and the test questions already made to obtain different types of test questions;

the judging module is used for extracting a first type of test questions according to the different types of test question dividing results and judging answering results of the first type of test questions;

the score prediction module is used for predicting scores to judge the mastering degree of the test question knowledge points when the answering result is correct;

and the extraction module is used for continuously extracting the second type of test questions with the lowest correlation degree with the wrong answer test questions when the answer result is incorrect.

8. The device for questions of claim 7, further comprising a knowledge point grasping module for grasping knowledge points

9. The device for questions of claim 7, further comprising: and the score prediction module is used for calculating a prediction score (the sum of the relevance of the answer pair test question and each test question which is not completed at the knowledge point/the number of the test questions which are not completed at the knowledge point) × 100.

10. The apparatus for presenting questions of claim 7, wherein said test question partitioning module is for partitioning said test questions