A question bank iteration method, system, device and medium based on students' answers

Abstract

The present invention proposes a question bank iteration method, system, device and medium based on students' answers. By presetting the number of centroids for each question in the question bank according to the question type, obtaining the answer sheets of all students for a certain question, dividing the students into different student groups according to the grade and major information of the students, and at the same time placing the answer sheets of the same student group in the same answer set, calculating the distance between each answer set and the standard answer, and thereby determining the difficulty level of the question for different students, adding a corresponding difficulty level label to the question, and when the user filters questions, filtering according to the difficulty level label. The present invention calculates the difficulty of the questions in real time according to the students' answer sheets, is more accurate in identifying the difficulty of the questions, and then filters the questions in detail according to the difficulty level labels of the questions. The user uses the filtered questions for the exam, greatly reducing the volatility of the difficulty level of the test paper and making the entire exam system more intelligent.

Description

Technical Field

[0001] The present invention relates to the technical field of educational evaluation, and particularly to a question bank iteration method, system, device and medium based on students' answers. Background Art

[0002] In an examination system, it is often necessary to select some questions from a question bank to form an examination paper for students to take an exam. When facing different examination scenarios, it is necessary to set the difficulty level of the examination paper by replacing questions of different difficulties. The questions in the question bank usually only include several settings such as the question stem, options, answers, and difficulty level. Among them, the difficulty level is often set by the subjective judgment of the question setter. However, the students taking the questions may not perceive the difficulty level of the questions in the same way as the question setter, which results in a mismatch between the difficulty level of the questions set in the question bank and the difficulty level felt by the students.

[0003] When using the questions in the question bank to form an examination paper, the difficulty level of the entire examination paper will either be extremely high or extremely low, and it is very difficult to control the fluctuation degree of the difficulty level of the examination paper. Moreover, with the change of the time span, the difficulty level of the questions will also be different. In such a design, the design of the difficulty level of the questions needs to be planned.

[0004] Therefore, there is currently no generally applicable method to solve the problem that the difficulty level of the questions in the question bank cannot be dynamically set according to the students' answer situations. Summary of the Invention

[0005] In view of this, the present invention proposes a question bank iteration method based on students' answers to solve the problem that the difficulty level of the questions in the question bank cannot be dynamically set according to the students' answer situations.

[0006] The technical solution of the present invention is implemented as follows:

[0007] In the first aspect of the present invention, a question bank iteration method based on students' answers is disclosed, and the method includes:

[0008] S1. For each question in the question bank, preset the number of centroids according to the question type, and continue to execute step S2;

[0009] S2. For a certain question, obtain the answer sheets of all students, and at the same time obtain the grade and major information of the students. The students with the same grade and major are regarded as a student group, and the answer sheets of each student group are placed in the same answer set to obtain multiple answer sets of the question corresponding to the student groups, and continue to execute step S3;

[0010] S3. For all answer sets corresponding to the said question, calculate the centroid of each answer set, obtain the distance between each answer set and the standard answer based on the centroid, and continue to execute step S4;

[0011] S4. Set the difficulty level of the said question for different student groups according to the said distance, and add the difficulty level combined with the grade and major as a difficulty level label to the said question, and continue to execute step S5;

[0012] S5. When the user filters questions in the question bank, push questions that meet the user's needs according to the said difficulty level label.

[0013] Through the above method, the present invention calculates the difficulty level of questions for different student groups in real time according to the answering situation of students to a certain question, combined with student information, and realizes dynamic marking of question difficulty.

[0014] On the basis of the above technical solutions, preferably, step S1 specifically includes:

[0015] For single-choice questions, use the algorithm based on Euclidean distance to set the number of centroids to 1; for multiple-choice questions, use the algorithm based on Euclidean distance to set the number of centroids to n according to the number n of correct options in its options.

[0016] Through the above method, the present invention sets different calculation requirements for different questions.

[0017] On the basis of the above technical solutions, preferably, step S2 specifically includes:

[0018] For single-choice questions, the answer set is Grade&Profession = {C 1 , C 2 , …, C m}, where C i is the answering answer of the i-th student, and m is the total number of students;

[0019] For multiple-choice questions, the answer set is Grade&Profession =

[0020] {(C 11 , C 12 ), (C 21 , C 22 , C 23 ), …, (C m1 , C m2 )}, where C ij is the j-th answering answer of the i-th student.

[0021] On the basis of the above technical solutions, preferably, step S3 specifically includes:

[0022] Use an algorithm based on the Euclidean distance to calculate the centroid of all answer sets corresponding to a certain question. For a single-choice question, the centroid of a corresponding answer set is x; for a multiple-choice question, the centroid of a corresponding answer set is y = {y 1 , y 2 , …, y n}.

[0023] Based on the above technical solutions, preferably, obtaining the distance between each answer set and the standard answer according to the centroid specifically includes:

[0024] For a single-choice question, the centroid of a corresponding answer set is x, then the distance between this answer set and the standard answer of the corresponding question is x; for a multiple-choice question, the centroid of a corresponding answer set is y = {y 1 , y 2 , …, y n}, then the distance between this answer set and the standard answer of the corresponding question is

[0025]

[0026] Based on the above technical solutions, preferably, step S4 specifically includes:

[0027] Set the difficulty level according to the distance. For those with a distance not exceeding the first threshold, for the student group corresponding to this answer set, the difficulty level of this question is low difficulty; for those with a distance exceeding the first threshold but not exceeding the second threshold, for the student group corresponding to this answer set, the difficulty level of this question is medium difficulty; for those with a distance exceeding the second threshold, for the student group corresponding to this answer set, the difficulty level of this question is high difficulty;

[0028] Combine the grade and major of the student group and the corresponding difficulty, and add a difficulty label to this question, expressed as: Grade&Profession: difficulty level.

[0029] Through the above method, the present invention calculates the distance between the answer of each student group and the standard answer, so as to obtain the difficulty level of this question for different student groups; every time this question is newly answered, steps S1 to S4 are repeatedly executed, and the dynamic calculation of the difficulty of this question is realized.

[0030] Based on the above technical solutions, preferably, step S5 specifically includes:

[0031] When a user filters questions in the question bank, the user can arbitrarily set one or more options among the grade, major, and difficulty options. According to the user's needs and in combination with the difficulty level labels of each question in the question bank, questions that meet the user's needs are provided to the user. When the user uses the filtered questions for an exam, the volatility of the difficulty level of the test paper will be greatly reduced, and the entire exam system will become more intelligent.

[0032] Through the above method, the present invention more accurately pushes questions that meet the user's needs according to the difficulty labels of the questions; when the difficulty level of a certain question for a certain student group is updated, the corresponding difficulty level label is automatically updated accordingly.

[0033] In a second aspect of the present invention, a question bank iteration system based on students' answers is disclosed. The system includes:

[0034] A label module: used to set an initial difficulty label for each question in the question bank, and set difficulty level labels corresponding to different combinations of grades and majors for the questions after difficulty calculation;

[0035] An information acquisition module: used to obtain the answer sheets of all students for a certain question, regard students with the same grade and major as a student group, place the answer sheets of each student group in the same answer set, and obtain the answer sets of multiple student groups corresponding to the question;

[0036] A difficulty calculation module: used to calculate the distance between all answer sets of a certain question and the standard answer, and set the difficulty level labels of the question for different student groups according to the distance;

[0037] A screening module: used to push questions that meet the user's needs according to the difficulty level labels when the user filters questions in the question bank.

[0038] In a third aspect of the present invention, an electronic device is disclosed. The device includes: at least one processor, at least one memory, a communication interface, and a bus; wherein, the processor, the memory, and the communication interface complete communication with each other through the bus; the memory stores a program for a question bank iteration method based on students' answers, and the program for a question bank iteration method based on students' answers is configured to implement a question bank iteration method based on students' answers as described in the first aspect of the present invention.

[0039] In a fourth aspect of the present invention, a computer-readable storage medium is disclosed. The storage medium stores a program for a question bank iteration method based on students' answers, and when the program for a question bank iteration method based on students' answers is executed, it implements a question bank iteration method based on students' answers as described in the first aspect of the present invention.

[0040] A method for iterating question banks based on students' answers according to the present invention has the following beneficial effects compared with the prior art:

[0041] (1) By calculating the difficulty levels of questions for different student groups in real time according to students' answers to a certain question and combining student information, the difficulty of questions can be dynamically marked.

[0042] (2) Add detailed difficulty level labels to questions and classify them in detail to achieve accurate push according to user needs. When users use the selected questions for exams, the volatility of the difficulty level of the test papers will be greatly reduced, and the entire exam system will become more intelligent. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0044] Figure 1 It is a flowchart of a method for iterating question banks based on students' answers according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0046] Embodiment

[0047] The working process of a method for iterating question banks based on students' answers according to the present invention is shown in Figure 1 , and the processing steps are described as follows:

[0048] First step, for each question in the question bank, preset the number of centroids according to the question type. Go to the second step.

[0049] It should be understood that on the basis of the above solution, for single-choice questions, the number of centroids is set to 1 using an algorithm based on the Euclidean distance; for multiple-choice questions, the number of centroids is set to n using an algorithm based on the Euclidean distance according to the number n of correct options in its options.

[0050] For example, if it is a single-choice question with five question options and the standard answer is the second one, using an algorithm based on Euclidean distance, such as the K-means algorithm, set the number of centroids for this question to 1; if it is a multiple-choice question with five question options and the standard answer is the second and fourth ones, use an algorithm based on Euclidean distance to set the number of centroids for this question to 2.

[0051] In the second step, for a certain question, obtain the answer sheets of all students, and at the same time obtain the grade and major information of the students. Group the students with the same grade and major as a student group, and place the answer sheets of each student group in the same answer set to obtain the answer sets of multiple student groups corresponding to the question. Proceed to the third step.

[0052] It should be understood that, based on the above solution, for a single-choice question, the answer set is Grade&Profession={C 1 ,C 2 ,…,C m}, where C i is the answer of the i-th student, and m is the total number of students;

[0053] For a multiple-choice question, the answer set is Grade&Profession=

[0054] {(C 11 ,C 12 ),(C 21 ,C 22 ,C 23 ),…,(C m1 ,C m2 )}, where C ij is the j-th option of the i-th student.

[0055] For example, for a certain multiple-choice question, the answer set of sophomores majoring in communication is: Sophomore&Communication={(A,B),(A,B,D),…,(B,D)}.

[0056] In the third step, for all the answer sets corresponding to the question, calculate the centroid of each answer set, and obtain the distance between each answer set and the standard answer based on the centroid. Proceed to the fourth step.

[0057] It should be understood that, based on the above solution, using an algorithm based on Euclidean distance, such as the K-means algorithm, calculate the centroid of all the answer sets corresponding to a certain question. For a single-choice question, the centroid of a corresponding answer set is x; for a multiple-choice question, the centroid of a corresponding answer set is y={y 1 ,y 2 ,…,y n}.

[0058] It should be understood that on the basis of the above solution, for a single-choice question, if the centroid of a corresponding answer set is x, then the distance between this answer set and the standard answer of the corresponding question is x; for a multiple-choice question, if the centroid of a corresponding answer set is y = {y 1 , y 2 , …, y n}, then the distance between this answer set and the standard answer of the corresponding question is

[0059] For example, for a certain single-choice question, the centroid of the answer set of a student group is 2.1, then the distance between this answer set and the standard answer set is 2.1; for a certain multiple-choice question, the centroids of the answer set of a student group are 2.2 and 3.5, then the distance between this answer set and the standard answer set is 2.85.

[0060] Fourth step, set the difficulty level of the question for different student groups according to the said distance, and add the difficulty level combined with the grade and major as a difficulty level label to the question. Proceed to the fifth step.

[0061] It should be understood that on the basis of the above solution, set the difficulty level according to the said distance. If the set distance does not exceed the first threshold, for the student group corresponding to this answer set, the difficulty level of this question is low difficulty; if the set distance exceeds the first threshold but does not exceed the second threshold, for the student group corresponding to this answer set, the difficulty level of this question is medium difficulty; if the set distance exceeds the second threshold, for the student group corresponding to this answer set, the difficulty level of this question is high difficulty;

[0062] Combine the grade and major of the said student group and the corresponding difficulty, and add a difficulty label to this question, expressed as: Grade&Profession: difficulty level.

[0063] It should be understood that on the basis of the above solution, the questions can be divided into more types of difficulty levels according to the setting of distance points, such as setting a difficulty level every 0.1.

[0064] It should be understood that on the basis of the above solution, whenever this question is newly answered, repeat the first step to the fourth step, and the dynamic calculation of the difficulty of this question can be realized; at the same time, when the difficulty level of this question for a certain student group is updated, the corresponding difficulty level label is also automatically updated accordingly.

[0065] Fifth step, when the user filters questions in the question bank, push the questions that meet the user's needs according to the said difficulty level label.

[0066] It should be understood that, based on the above solution, when a user filters questions in the question bank, the user can arbitrarily set one or more options among the grade, major, and difficulty options. According to the user's needs, combined with the difficulty level tags of each question in the question bank, questions that meet the user's needs are provided for the user.

[0067] The present invention calculates the difficulty of questions in real time according to the answering situations of students, and the recognition difficulty of questions will be more accurate. In continuous iteration, the quality of questions in the question bank is greatly improved. Then, according to the difficulty level tags of the questions, detailed screening is carried out on the questions. When the user uses the screened questions for the exam, the volatility of the difficulty level of the test paper will be greatly reduced, and the entire exam system will also be made more intelligent.

[0068] The present invention also discloses a question bank iteration system based on students' answers. The system includes:

[0069] Label module: used to set an initial difficulty label for each question in the question bank, and set a difficulty level label corresponding to different combinations of grades and majors for the questions after difficulty calculation;

[0070] Information acquisition module: used to obtain the answering answers of all students for a certain question, regard students with the same grade and major as a student group, place the answering answers of each student group in the same answer set, and obtain the answer sets of multiple student groups corresponding to the question;

[0071] Difficulty calculation module: used to calculate the distance between all answer sets of a certain question and the standard answer, and set the difficulty level label of the question for different student groups according to the distance;

[0072] Screening module: used to push questions that meet the user's needs according to the difficulty level labels when the user filters questions in the question bank.

[0073] The present invention also discloses an electronic device. The device includes: at least one processor, at least one memory, a communication interface, and a bus; wherein, the processor, the memory, and the communication interface complete communication with each other through the bus; the memory stores a program of a question bank iteration method based on students' answers, and the program of the question bank iteration method based on students' answers is configured to implement a question bank iteration method based on students' answers as described in the embodiments of the present invention.

[0074] The present invention also discloses a computer-readable storage medium. A program of a question bank iteration method based on students' answers is stored on the storage medium, and when the program of the question bank iteration method based on students' answers is executed, it implements a question bank iteration method based on students' answers as described in the embodiments of the present invention.

[0075] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A question bank iteration method based on students' answers, characterized in that, the question bank iteration method based on students' answers includes the following steps: S1. For each question in the question bank, preset the number of centroids according to the question type, and continue to execute step S2; S2. For a certain question, obtain the answer sheets of all students, and at the same time obtain the grade and major information of the students. Students with the same grade and major are regarded as a student group. The answer sheets of each student group are placed in the same answer set, and multiple answer sets corresponding to the question are obtained, and then continue to execute step S3; S3. For all answer sets corresponding to the question, calculate the centroid of each answer set, and obtain the distance between each answer set and the standard answer according to the centroid, and then continue to execute step S4; S4. Set the difficulty level of the question for different student groups according to the distance, and add the difficulty level combined with the grade and major as a difficulty level label to the question, and then continue to execute step S5; S5. When a user filters questions in the question bank, push questions that meet the user's needs according to the difficulty level label.

2. The question bank iteration method based on students' answers according to claim 1, characterized in that, step S1 specifically includes: For single-choice questions, use an algorithm based on Euclidean distance to set the number of centroids to 1; for multiple-choice questions, use an algorithm based on Euclidean distance to set the number of centroids to n according to the number n of correct options in its options.

3. The question bank iteration method based on students' answers according to claim 2, characterized in that, step S2 specifically includes: For multiple-choice questions, the answer set is Grade&Profession={C 1 ,C 2 ,…,C m}, where C i is the answer given by the i-th student, and m is the total number of students; For multiple-choice questions, the answer set is Grade&Profession= {(C 11 , C 12 ), (C 21 , C 22 , C 23 ), …, (C m1 , C m2 )}, where C ij is the j-th answer of the i-th student.

4. The question bank iteration method based on students' answers according to claim 3, characterized in that, step S3 specifically includes: Calculate the centroid of all answer sets corresponding to a certain question using an algorithm based on the Euclidean distance. For a single-choice question, the centroid of a corresponding answer set is x; for a multiple-choice question, the centroid of a corresponding answer set is y = {y 1 , y 2 , …, y n}.

5. The question bank iteration method based on students' answers according to claim 4, characterized in that, obtaining the distance between each answer set and the standard answer according to the centroid specifically includes: For a single-choice question, if the centroid of a corresponding answer set is x, then the distance between this answer set and the standard answer of the corresponding question is x; for a multiple-choice question, the centroid of a corresponding answer set is y = {y 1 , y 2 , …, y n}, then the distance between this answer set and the standard answer of the corresponding question is 6. The question bank iteration method based on students' answers according to claim 5, characterized in that, step S4 specifically includes: Set the difficulty level according to the distance. If the distance does not exceed the first threshold, for the student group corresponding to this answer set, the difficulty level of this question is low difficulty; if the distance exceeds the first threshold but does not exceed the second threshold, for the student group corresponding to this answer set, the difficulty level of this question is medium difficulty; if the distance exceeds the second threshold, for the student group corresponding to this answer set, the difficulty level of this question is high difficulty; Combine the grade and major of the student group and the corresponding difficulty, and add a difficulty label to this question, expressed as: Grade&Profession: difficulty level.

7. The question bank iteration method based on students' answers according to claim 5, characterized in that, step S5 specifically includes: When the user filters questions in the question bank, the user can arbitrarily set one or more options among the grade, major, and difficulty options. According to the user's needs and in combination with the difficulty level labels of each question in the question bank, questions that meet the user's needs are provided for the user.

8. A question bank iteration system based on students' answers, Characterized in that, The system includes: Label module: used to set an initial difficulty label for each question in the question bank, and set difficulty level labels corresponding to different combinations of grades and majors for the questions after difficulty calculation; Information acquisition module: used to obtain the answer sheets of all students for a certain question, regard students with the same grade and major as a student group, place the answer sheets of each student group in the same answer set, and obtain the answer sets of multiple student groups corresponding to the question; Difficulty calculation module: used to calculate the distance between all answer sets of a certain question and the standard answer, and set the difficulty level labels of the question for different student groups according to the distance; Filtering module: used to push questions that meet the user's needs according to the difficulty level labels when the user filters questions in the question bank.

9. An electronic device, Characterized in that, It includes at least one processor, at least one memory, a communication interface, and a bus; wherein, the processor, the memory, and the communication interface complete communication with each other through the bus; the memory stores a program for a question bank iteration method based on students' answers, and the program for a question bank iteration method based on students' answers is configured to implement a question bank iteration method according to any one of claims 1 to 7.

10. A computer-readable storage medium, Characterized in that, The storage medium stores a program for a question bank iteration method based on students' answers, and when the program for a question bank iteration method based on students' answers is executed, it implements a question bank iteration method according to any one of claims 1 to 7.

Images