A training error correction method and device for online education

Abstract

The present invention relates to a training error correction method and device for online education, the method comprising the following steps: real-time collection of student answer text information, judging whether the answer information in the answer text information is correct, and summarizing the answer text information with wrong answer information into a wrong question bank; statistics of the knowledge points in the wrong question bank, and calculating the weight of each knowledge point; extracting questions from the cloud question bank according to the knowledge point weight, and sorting them according to the knowledge point weight to generate a wrong question test paper. The present invention can collect the same questions, similar questions, and similar question errors of students in online education, analyze the learning situation of students for each knowledge point; by combining the learning situation of students with the important situation of the actual chapter knowledge points, the students are given enhanced learning guidance, so as to help the students master all the knowledge points in the chapter and improve their academic performance.

Description

Technical Field

[0001] The present invention relates to the technical field of online education, and in particular to a training and error correction method and device for online education. Background Art

[0002] As the name suggests, online education is a teaching method that uses the Internet as a medium. Through the Internet, students and teachers can carry out teaching activities even if they are thousands of miles apart. In addition, with the help of online courseware, students can also study anytime and anywhere, truly breaking the limitations of time and space. For busy working people with irregular study time, online distance education is the most convenient way of learning.

[0003] During the learning process, students usually need to answer test questions to master the courses they have learned. When students answer test questions, a large number of wrong questions will be generated. Correcting wrong questions is the most important part of the learning course for students.

[0004] At present, most error correction methods in education use technology based on content filtering. Content-based technology mainly relies on keyword matching to directly determine whether the students' answers to test questions are correct. It then searches for incorrect test questions based on keywords and continues to push similar questions to students, thereby achieving error correction and training for students.

[0005] However, when judging the students' answers to test questions, different test questions have different answers. When answering, students often get the correct answer but the incorrect process. Relying only on keywords for error checking cannot accurately judge the correctness of the students' answers. When correcting students' wrong questions, only similar wrong questions are pushed to the students. It is impossible to accurately judge the students' mastery of knowledge points, and it is impossible to improve the students' weak knowledge points. Training, which greatly dampens the students' enthusiasm for learning, cannot achieve a good error correction effect. Summary of the invention

[0006] In order to overcome the above-mentioned technical defects in the prior art, the present invention provides a method and device for error correction in online education, which can effectively solve the problems in the background technology.

[0007] In order to solve the above technical problems, the technical solutions provided by the present invention are as follows:

[0008] The embodiment of the present invention discloses a training and error correction method for online education, the method comprising the following steps:

[0009] Collect students' answer text information in real time, determine whether the answer information in the answer text information is correct, and summarize the answer text information with incorrect answer information into the wrong question database;

[0010] Count the knowledge points in the wrong question bank and calculate the weight of each knowledge point;

[0011] Questions are extracted from the cloud question bank according to the weight of knowledge points, and sorted according to the weight of knowledge points to generate wrong question test papers.

[0012] In any of the above schemes, it is preferred to collect the students' answer text information, which includes answer title information and answer answer information. The answer title information is divided into analytical questions and non-analytical questions. When students answer questions, the attributes of answers to different question types are not the same. For non-analytical questions, the answer information is generally expressed as a direct result answer, and for analytical questions, the answer information is generally expressed as a process-result answer.

[0013] In any of the above schemes, it is preferred that the student's answer information result value is compared with the standard answer result value in the cloud question bank. If correct, the answer question information is classified; if incorrect, the answer text information is summarized in the wrong question bank.

[0014] In any of the above schemes, it is preferred that the question information is classified. If it is a non-analytic question, the student's answer is judged to be correct. If it is an analytic question, the student's answer process is analyzed.

[0015] In any of the above schemes, it is preferred that if the analysis and answering process is correct, the student's answer is judged to be correct; if the analysis and answering result is wrong, the answer text information is summarized in the wrong question database.

[0016] In any of the above schemes, it is preferred that during the teaching process, the course is usually divided into multiple chapters and a knowledge point system is established for teaching. The knowledge system is a collection of knowledge points. In the learning process of students, knowledge points can well reflect the students' mastery of knowledge. Knowledge points exist in a certain structure, and there are hierarchical relationships, predecessor relationships and association relationships between each knowledge point. The hierarchical relationship means that a knowledge point can contain several sub-knowledge points, and the relationship between knowledge points can form a tree structure; for example, the root node of the tree can be set to be the course content, its child nodes are the chapter content, and further down are the composite knowledge points, which can be subdivided into several basic knowledge points; it can be seen from the knowledge point hierarchical relationship tree diagram that each node represents a knowledge point, and there is a horizontal brother relationship and a vertical parent-child relationship between nodes. In this hierarchical structure tree, the parent knowledge point is a composite knowledge point composed of several knowledge points, and the child knowledge points expand and elaborate on the parent knowledge point from different aspects, different angles, and different categories. The closer the node is to the root node, the wider the range of knowledge points covered by the node; the farther the node is from the root node, the finer the granularity of the knowledge point represented by the node. The subdivided knowledge points are more conducive to reflecting wrong questions, and the importance of each knowledge point to this chapter varies greatly.

[0017] In any of the above schemes, it is preferred that each answer question information includes one or more knowledge points, and one knowledge point can be distributed in different answer question information. The features of each answer question information are extracted, and the knowledge point element set F contained in each answer question information is F = (a1, a2, ..., a i ).

[0018] In any of the above schemes, preferably, by formula Calculate the weight of each knowledge point; where n is the number of wrong questions in the wrong question database, a i is the i-th knowledge point in the knowledge point element set F, f j (a i ) is the proportion of the i-th knowledge point in the j-th question, Z ai is the number of questions with the i-th knowledge point in the wrong question bank, c i is the important eigenvalue of the i-th knowledge point in the learned chapter, W ai is the weight of the i-th knowledge point in the knowledge point element set F.

[0019] In any of the above schemes, it is preferred to compare the weights of all knowledge points in the wrong question bank. The size of the weight can be used to determine the students' weaker grasp of knowledge points in the chapter they have studied. Then, by analyzing the weights of all knowledge points in the wrong question bank, the students' learning situation and the importance of the actual chapter knowledge points can be combined to provide enhanced learning guidance to the students, so as to achieve the purpose of helping students master all knowledge points in the chapter and improve their academic performance.

[0020] In any of the above schemes, it is preferred that the weights of the knowledge points can map the students' mastery of each knowledge point in the chapter they have studied and the importance of the knowledge points in the chapters they have studied, and then by sorting the weights of the knowledge points, the students can be trained on wrong questions according to the weight values ​​of the knowledge points.

[0021] In any of the above schemes, it is preferred that the cloud question bank is extracted according to the knowledge points in the wrong question bank, and the wrong question test paper is generated in the order of knowledge point weight sorting. The greater the knowledge point weight, the more questions about the knowledge point are included in the wrong question test paper, and the smaller the knowledge point weight, the fewer questions about the knowledge point are included in the wrong question test paper.

[0022] A training and error correction device for online education, the device comprising:

[0023] The judgment module is used to collect the students' answer text information in real time, judge whether the answer information in the answer text information is correct, and summarize the answer text information with incorrect answer information into the wrong question database;

[0024] The calculation module is used to count the knowledge points in the wrong question database and calculate the weight of each knowledge point;

[0025] The generation module is used to extract questions from the cloud question bank according to the weight of the knowledge points, sort them according to the weight of the knowledge points, and generate wrong question test papers.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] The present invention provides a training and error correction method and device for online education. The method and device collect the answer text information of students in real time, judge whether the answer information in the answer text information is correct, and summarize the answer text information with wrong answer information into a wrong question bank; count the knowledge points in the wrong question bank, and calculate the weight of each knowledge point; extract questions from the cloud question bank according to the weight of the knowledge point, and sort them according to the weight of the knowledge point to generate a wrong question test paper; in the training process, the errors of the same, similar and similar questions of the students can be collected, and the learning situation of the students for each knowledge point can be analyzed; by combining the learning situation of the students with the important situation of the knowledge points in the actual chapter, the students are given enhanced learning guidance, so as to help the students master all the knowledge points in the chapter and improve their learning performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings are used for further understanding of the present invention and are used to explain the present invention together with the embodiments of the present invention, but do not constitute a limitation of the present invention.

[0029] Figure 1 It is a flow chart of a training and error correction method for online education according to the present invention;

[0030] Figure 2 It is a module schematic diagram of a training and error correction device for online education according to the present invention; DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0032] It should be noted that when an element is referred to as being "fixed to" or "disposed on" another element, it can be directly on the other element or indirectly on the other element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or indirectly connected to the other element.

[0033] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0034] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0035] In order to better understand the above technical solution, the technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0036] The present invention provides a method for correcting errors in online education. Figure 1 As shown, the method comprises the following steps:

[0037] Step 1: collect the students' answer text information in real time, determine whether the answer information in the answer text information is correct, and summarize the answer text information with incorrect answer information into the wrong question database.

[0038] Specifically, the students' answer text information is collected, and the answer text information includes answer title information and answer answer information. Usually, answer title information is generally divided into analytical questions and non-analytical questions. When students answer questions, the attributes of answers to different question types are not the same. For non-analytical questions, the answer information is generally expressed as a direct result answer, and for analytical questions, the answer information is generally expressed as a process-result answer.

[0039] Furthermore, due to different question types, students' answer information is quite different. When judging the correctness of students' answer information, it is necessary to classify the answer information.

[0040] Furthermore, the student's answer information result value is compared with the standard answer result value in the cloud question bank. If it is correct, the answer question information is categorized; if it is wrong, the answer text information is summarized in the wrong question bank.

[0041] Furthermore, when answering questions, there may be a situation where the result is correct but the process is not correct. For the same question, multiple methods can be used to answer it. In order to achieve the accuracy of the answer judgment, a second judgment is required on the answer process. The judgment process is as follows: the answer question information is classified. If it is a non-analysis question, the student's answer is judged to be correct. If it is an analysis question, the student's answer process is analyzed. If the analysis of the answer process is correct, the student's answer is judged to be correct; if the analysis of the answer result is incorrect, the answer text information is summarized in the wrong question bank.

[0042] Step 2: Count the knowledge points in the wrong question bank and calculate the weight of each knowledge point.

[0043] Specifically, in the learning process of students, knowledge points can well reflect the degree of students' mastery of knowledge. In the teaching process, the course is usually divided into multiple chapters and a knowledge point system is established for teaching. The knowledge system is a collection of knowledge points. Knowledge points exist in a certain structure. There are hierarchical relationships, predecessor relationships and association relationships between each knowledge point. The hierarchical relationship means that a knowledge point can contain several sub-knowledge points, and the relationship between knowledge points can form a tree structure; for example, the root node of the tree can be set as the course content, its child nodes are chapter contents, and further down are composite knowledge points, which can be subdivided into several basic knowledge points; from the knowledge point hierarchical relationship tree diagram, it can be seen that each node represents a knowledge point, and there is a horizontal brother relationship and a vertical parent-child relationship between nodes. In this hierarchical structure tree, the parent knowledge point is a composite knowledge point composed of several knowledge points, and the child knowledge points expand and elaborate on the parent knowledge point from different aspects, different angles, and different categories. The closer the node is to the root node, the wider the range of knowledge points covered by the node; the farther the node is from the root node, the finer the granularity of the knowledge point represented by the node. The subdivided knowledge points are more conducive to reflecting wrong questions, and the importance of each knowledge point to this chapter varies greatly.

[0044] Furthermore, each answer question information may include one or several knowledge points, and one knowledge point may also be distributed in different answer question information. When providing error correction guidance to students, the weight of each knowledge point in the right and wrong question bank is calculated to obtain the knowledge points that the students are weak in, and the students are guided based on the importance of the knowledge points in the chapters they are studying, thereby maximizing the improvement of students' academic performance.

[0045] Furthermore, the features of each answer question information are extracted, and the knowledge point element set F contained in each answer question information is F = (a1, a2, ..., a i ), using the formula Calculate the weight of each knowledge point; where n is the number of wrong questions in the wrong question database, a i is the i-th knowledge point in the knowledge point element set F, f j (a i ) is the proportion of the i-th knowledge point in the j-th question, Z ai is the number of questions with the i-th knowledge point in the wrong question bank, c i is the important eigenvalue of the i-th knowledge point in the learned chapter, W ai is the weight of the i-th knowledge point in the knowledge point element set F.

[0046] Furthermore, the weights of all knowledge points in the wrong question bank are compared. The size of the weight can be used to determine the students' weaker knowledge points in the chapters they have studied. Then, by analyzing the weights of all knowledge points in the wrong question bank, the students' learning situation and the importance of the actual chapter knowledge points can be combined to provide students with enhanced learning guidance, so as to help them master all knowledge points in the chapter and improve their academic performance.

[0047] Step 3: Extract questions from the cloud question bank according to the knowledge point weights, sort them according to the knowledge point weights, and generate a wrong question test paper.

[0048] Specifically, the weights of knowledge points can reflect students' mastery of each knowledge point in the chapter they have studied and the importance of the knowledge point in the chapter they have studied. Then, by sorting the weights of the knowledge points, students can be trained on wrong questions based on the weight values ​​of the knowledge points.

[0049] Furthermore, by analyzing the weights of all knowledge points in the wrong question bank, the student's learning situation is obtained, and wrong question test paper training is conducted based on the student's mastery of the knowledge points of the learned chapters. Based on the knowledge points in the wrong question bank, the cloud question bank is extracted, and the wrong question test paper is generated in the order of the knowledge point weight sorting. The greater the knowledge point weight, the more questions about the knowledge point are included in the wrong question test paper, and the smaller the knowledge point weight, the fewer questions about the knowledge point are included in the wrong question test paper.

[0050] Furthermore, after the students have been trained on the wrong questions, they are corrected again through the above steps 1-3 until the students have answered all the wrong questions correctly.

[0051] The present invention also provides a training and error correction device for online education, such as Figure 2 As shown, the device comprises:

[0052] The judgment module is used to collect the students' answer text information in real time, judge whether the answer information in the answer text information is correct, and summarize the answer text information with incorrect answer information into the wrong question database;

[0053] The calculation module is used to count the knowledge points in the wrong question database and calculate the weight of each knowledge point;

[0054] The generation module is used to extract questions from the cloud question bank according to the weight of the knowledge points, sort them according to the weight of the knowledge points, and generate wrong question test papers.

[0055] Compared with the prior art, the present invention provides the following beneficial effects:

[0056] The present invention provides a training and error correction method and device for online education. The method and device collect the answer text information of students in real time, judge whether the answer information in the answer text information is correct, and summarize the answer text information with wrong answer information into a wrong question bank; count the knowledge points in the wrong question bank, and calculate the weight of each knowledge point; extract questions from the cloud question bank according to the weight of the knowledge point, and sort them according to the weight of the knowledge point to generate a wrong question test paper; in the training process, the errors of the same, similar and similar questions of the students can be collected, and the learning situation of the students for each knowledge point can be analyzed; by combining the learning situation of the students with the important situation of the knowledge points in the actual chapter, the students are given enhanced learning guidance, so as to help the students master all the knowledge points in the chapter and improve their learning performance.

[0057] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A training and error correction method for online education, characterized in that: The method comprises the following steps: Collect students' answer text information in real time, determine whether the answer information in the answer text information is correct, and summarize the answer text information with incorrect answer information into the wrong question database; Each answer question information includes one or more knowledge points. A knowledge point can be distributed in different answer question information. The features of each answer question information are extracted. Then, the knowledge point element set F contained in each answer question information is F = (a1, a2, ..., a i ); Statistics are collected for the knowledge points in the wrong question bank, and the weight of each knowledge point is calculated; Calculate the weight of each knowledge point; where n is the number of wrong questions in the wrong question database, a i is the i-th knowledge point in the knowledge point element set F, f j (a i ) is the proportion of the i-th knowledge point in the j-th question, Z ai is the number of questions with the i-th knowledge point in the wrong question bank, c i is the important eigenvalue of the i-th knowledge point in the learned chapter, W ai is the weight of the i-th knowledge point in the knowledge point element set F; Questions are extracted from the cloud question bank according to the weight of the knowledge points, and sorted according to the weight of the knowledge points to generate wrong question test papers. The larger the weight of the knowledge point, the more questions about the knowledge point the wrong question test paper contains, and the smaller the weight of the knowledge point, the fewer questions about the knowledge point the wrong question test paper contains.

2. The error correction method for online education according to claim 1, characterized in that: The answer text information includes answer title information and answer answer information. The answer title information includes analytical questions and non-analyzed questions. The answer answer information includes direct result answers and process-result answers.

3. The error correction method for online education according to claim 2, characterized in that: The student's answer information result value is compared with the standard answer result value in the cloud question bank. If it is correct, the answer question information is classified; if it is wrong, the answer text information is summarized in the wrong question bank.

4. The error correction method for online education according to claim 3, characterized in that: The question information is categorized. If it is a non-analytic question, the student's answer is judged to be correct. If it is an analytic question, the student's answer process is analyzed.

5. The error correction method for online education according to claim 4, characterized in that: If the analysis and answering process is correct, the student's answer is judged to be correct; if the analysis and answering result is wrong, the answer text information will be summarized in the wrong question bank.

6. A training and error correction device for online education, characterized in that: The device comprises: The judgment module is used to collect the students' answer text information in real time, judge whether the answer information in the answer text information is correct, and summarize the answer text information with wrong answer information into the wrong question database; each answer question information includes one or more knowledge points, and a knowledge point can be distributed in different answer question information. The features of each answer question information are extracted, and the knowledge point element set F contained in each answer question information is F = (a1, a2, ..., a i ); The calculation module is used to count the knowledge points in the wrong question database and calculate the weight of each knowledge point; Calculate the weight of each knowledge point; where n is the number of wrong questions in the wrong question database, a i is the i-th knowledge point in the knowledge point element set F, f j (a i ) is the proportion of the i-th knowledge point in the j-th question, Z ai is the number of questions with the i-th knowledge point in the wrong question bank, c i is the important eigenvalue of the i-th knowledge point in the learned chapter, W ai is the weight of the i-th knowledge point in the knowledge point element set F The generation module is used to extract questions from the cloud question bank according to the weight of the knowledge point, and sort them according to the weight of the knowledge point to generate a wrong question test paper. The larger the weight of the knowledge point, the more questions about the knowledge point are included in the wrong question test paper, and the smaller the weight of the knowledge point, the fewer questions about the knowledge point are included in the wrong question test paper.

Images