Learning state monitoring method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses a learning state monitoring method and device, equipment and a storage medium, and the method comprises the steps: receiving the answer information of a target student submitted by a user side, and obtaining the answer correction information and answer data sequence of the target student; obtaining an answer data sub-sequence, answer correction sub-information and answer accuracy from the answer data sequence and the answer correction information; obtaining the answer plagiarism rate of the target student in the target time period according to the answer data subsequences of the target student and the selected students; and determining the learning state of the target student in the target time period based on the answer plagiarism rate and the answer correct rate. The answer information of the students is used as the monitoring basis of the learning state, and the correct rate and plagiarism condition of the homework of each student in the target time period are analyzed to analyze the learning state of the students, so that the current defects and deficiencies of the students can be judged according to the learning state, a teaching mode is made in a targeted manner, and the teaching efficiency is improved. The teaching quality is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of teaching methods, and in particular to a method and device, equipment and storage medium for monitoring a learning state. Background Art

[0002] Teaching students in accordance with their aptitude is an important teaching method and principle. In teaching, teachers choose learning methods suitable for each student's characteristics according to their cognitive level, learning ability and their own qualities to provide targeted teaching and make up for the deficiencies in students' learning process.

[0003] Usually, teachers will observe students' learning situation and judge their learning status. According to current regulations, the number of students in each class is generally set between 40 and 50. For teachers, the large number of students makes it difficult for them to discover the learning status of each student in time and make further improvement plans, which cannot improve the teaching quality. Summary of the invention

[0004] Based on this, it is necessary to propose a learning status monitoring method and device, equipment and storage medium to monitor the students' learning process, understand the students' learning status, and then formulate different teaching plans for different learning statuses to improve the teaching quality.

[0005] To achieve the above-mentioned purpose, the present application provides a first aspect of a method for monitoring a learning state, the method comprising:

[0006] Receiving answer information of a target student submitted by a user terminal, wherein the answer information includes a target question and answer data submitted by the target student based on the target question;

[0007] Searching for a first number, a first standard answer, and a first release time corresponding to the target question in a preset question bank, wherein the question bank includes a plurality of questions, and numbers, standard answers, and release times corresponding to the questions, and the target question belongs to the question bank;

[0008] Correcting the answer data according to the first standard answer to obtain the answer correction information of the target student, and sorting the answer data corresponding to the target question according to the first release time of the target question and the first number to obtain the answer data sequence of the target student;

[0009] From the answer data sequence and the answer correction information, select the answer data subsequence and the answer correction subinformation whose first release time is within the target time period, calculate the correct rate according to the answer data subsequence and the answer correction subinformation, and obtain the answer correct rate of the target student within the target time period;

[0010] Performing similarity analysis on the answer data subsequences of the target student and each selected student to obtain the plagiarism rate of the target student in the target time period;

[0011] The learning status of the target student in the target time period is determined based on the plagiarism rate and the correct answer rate.

[0012] Furthermore, the question bank also includes question types corresponding to the questions, and the question types include at least objective questions and subjective questions;

[0013] The similarity analysis of the answer data subsequences of the target student and each selected student to obtain the plagiarism rate of the target student in the target time period specifically includes:

[0014] Obtaining a target answer data subsequence with the same release time in the answer data subsequence of the target student;

[0015] Based on the question type, the answer data in the target answer data subsequence is decomposed to obtain an objective question answer subsequence and a subjective question answer subsequence;

[0016] Performing similarity calculations on the objective question answer subsequences and the subjective question answer subsequences of the target student and each selected student, respectively, to obtain a first answer plagiarism rate of the objective question and a second answer plagiarism rate of the subjective question corresponding to the answer data subsequences;

[0017] A weighted calculation is performed based on the first answer plagiarism rate and the second answer plagiarism rate corresponding to all target answer data subsequences in the answer data subsequence to obtain the answer plagiarism rate of the target student in the target time period.

[0018] Further, the similarity calculation is performed on the objective question answer subsequences and the subjective question answer subsequences of the target student and each selected student respectively to obtain the first answer plagiarism rate of the objective question and the second answer plagiarism rate of the subjective question corresponding to the answer data subsequence, specifically including:

[0019] Using the Smith-Waterman algorithm, a similarity analysis is performed between the target student's objective question answer subsequence and the selected students' objective question answer subsequences to determine the target student's first answer plagiarism rate;

[0020] The text similarity between the target student's subjective question answer subsequence and the selected students' subjective question answer subsequences is calculated to determine the target student's second answer plagiarism rate.

[0021] Further, the Smith-Waterman algorithm is used to perform similarity analysis on the objective question answer subsequence of the target student and the objective question answer subsequences of each selected student to determine the first answer plagiarism rate of the target student, specifically including:

[0022] Finding two sequence segments with the highest similarity between the target student's objective question answer subsequence and the objective question answer subsequences of each selected student based on the Smith-Waterman algorithm;

[0023] If the length of the sequence segment is greater than a preset length threshold, determining a first correct rate of the sequence segment of the target student according to the question answering and correcting sub-information;

[0024] When the first accuracy is lower than a preset first accuracy threshold, calculating a first similarity between the two sequence segments;

[0025] When the first similarity is greater than a preset first similarity threshold, the first answer plagiarism rate of the target student is calculated according to the first correct rate and the first similarity.

[0026] Furthermore, the text similarity calculation is performed on the subjective question answer subsequence of the target student and the subjective question answer subsequences of each selected student to determine the second answer plagiarism rate of the target student, specifically including:

[0027] Calculating the text similarity between the target student's subjective question answer subsequence and the subjective question answer subsequences of each selected student;

[0028] When the text similarity is greater than a second similarity threshold, determining a second correct rate of the target student's subjective question answer subsequence according to the answer correction sub-information;

[0029] A second plagiarism rate of the target student is calculated based on the second accuracy rate and the text similarity.

[0030] Furthermore, the weighted calculation is performed based on the first answer plagiarism rate and the second answer plagiarism rate corresponding to all target answer data subsequences in the answer data subsequence to obtain the answer plagiarism rate of the target student in the target time period, specifically including:

[0031] Performing weighted calculation on the first answer plagiarism rate and the second answer plagiarism rate corresponding to the target answer data subsequence to obtain a third answer plagiarism rate;

[0032] Based on a preset mathematical operation method, the plagiarism rate of all the third answers of the target student in the answer data subsequence is calculated to obtain the plagiarism rate of the target student in the target time period.

[0033] Furthermore, determining the learning status of the target student in the target time period based on the plagiarism rate and the correct answer rate specifically includes:

[0034] When the target student's correct answer rate in the target time period is greater than a preset third correct rate, it is confirmed that the student's learning status in the target time period is good;

[0035] When the student's correct answer rate in the target time period is not greater than the third correct answer rate, and the plagiarism rate in the answer is not greater than a preset plagiarism rate threshold, it is confirmed that there is a problem with the student's learning status in the target time period;

[0036] When the answer plagiarism rate is greater than the plagiarism rate threshold, it is confirmed that the student has plagiarized within the target time period.

[0037] To achieve the above-mentioned purpose, the second aspect of the present application provides a learning status monitoring device, the device comprising a data acquisition module, a data analysis module and a status judgment module;

[0038] The data collection module is used to receive the answer information of the target student submitted by the user end, wherein the answer information includes the target question and the answer data submitted by the target student based on the target question;

[0039] Searching for a first number, a first standard answer, and a first release time corresponding to the target question in a preset question bank, wherein the question bank includes a plurality of questions, and numbers, standard answers, and release times corresponding to the questions, and the target question belongs to the question bank;

[0040] The data analysis module is used to correct the answer data according to the first standard answer to obtain the answer correction information of the target student, and sort the answer data corresponding to the target question according to the first release time of the target question and the first number to obtain the answer data sequence of the target student;

[0041] From the answer data sequence and the answer correction information, select the answer data subsequence and the answer correction subinformation whose first release time is within the target time period, calculate the correct rate according to the answer data subsequence and the answer correction subinformation, and obtain the answer correct rate of the target student within the target time period;

[0042] Performing similarity analysis on the answer data subsequences of the target student and each selected student to obtain the plagiarism rate of the target student in the target time period;

[0043] The state judgment module is used to determine the learning state of the target student in the target time period based on the plagiarism rate and the correct answer rate.

[0044] To achieve the above-mentioned purpose, the third aspect of the present application provides a computer-readable storage medium storing a computer program, characterized in that when the computer program is executed by a processor, the processor executes the steps of the method described in the first aspect.

[0045] To achieve the above-mentioned purpose, the fourth aspect of the present application provides a computer device, including a memory and a processor, characterized in that the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method described in the first aspect.

[0046] The embodiments of the present invention have the following beneficial effects:

[0047] The embodiment of the present invention provides a method for monitoring a learning status, the method comprising: receiving answer information of a target student submitted by a user end, wherein the answer information comprises a target question and answer data submitted by the target student based on the target question; searching a preset question bank for a first number, a first standard answer and a first release time corresponding to the target question, the question bank comprising a plurality of questions, as well as numbers, standard answers and release times corresponding to the questions, and the target question belongs to the question bank; correcting the answer data according to the first standard answer to obtain answer correction information of the target student, and correcting the answer data according to the first release time and the first number of the target question. The answer data corresponding to the title is sorted to obtain the answer data sequence of the target student; from the answer data sequence and the answer correction information, the answer data subsequence and the answer correction subinformation whose first release time is within the target time period are selected, and the correct rate is calculated according to the answer data subsequence and the answer correction subinformation to obtain the correct rate of the target student's answer within the target time period; the answer data subsequences of the target student and the selected students are analyzed similarly to obtain the plagiarism rate of the target student's answer within the target time period; the learning status of the target student within the target time period is determined based on the plagiarism rate and the correct rate of the answer. By using the student's answer information as the basis for monitoring the learning status, analyzing the correct rate and plagiarism of each student's homework within the target time period, the student's learning status is analyzed, so that the student's current shortcomings and deficiencies can be judged according to the learning status, and then targeted teaching methods can be made to improve the teaching quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] in:

[0050] Figure 1 A flow chart of a method for monitoring a learning state according to an embodiment of the present invention;

[0051] Figure 2 is a structural block diagram of a monitoring device for a learning state according to an embodiment of the present invention;

[0052] Figure 3 1 is a diagram showing the internal structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Homework and periodic examinations are important means to test students' mastery of knowledge points after learning them. Therefore, the embodiments of the present invention determine students' learning status and mastery of knowledge points by analyzing students' answers to homework and / or examinations.

[0055] The present invention proposes a method for monitoring learning status. By monitoring the learning status of students, teachers can analyze the learning status of students and formulate targeted teaching methods to correct students' learning attitudes and methods, which can effectively improve students' learning efficiency. Figure 1 , Figure 1 The following is a flow chart of a method for monitoring a learning state in an embodiment of the present invention, wherein the method comprises:

[0056] Step 110, receiving the target student's answer information submitted by the user, wherein the answer information includes the target question and the answer data submitted by the target student based on the target question.

[0057] In an embodiment of the present invention, the user terminal can be in the form of a mobile application, a web application, a desktop software, a client software, etc., and students or teachers upload students' answer information to the server through the user terminal. For example, all students in a class submit answer information through the user terminal, or the teacher collects students' answer information and submits it through the user terminal. Based on the answer information submitted by the teacher and / or students through the user terminal, the learning status of each student in a class is understood.

[0058] In one embodiment of the present invention, the answer information may be online answer information or offline answer information.

[0059] Online answer information refers to the answer data that students make based on the questions in the homework or exam after receiving it on the user side, and then upload the answer data to the user side. If the server needs to collect the student's online answer information, it can send a data collection request to the user side. After receiving the data collection request, the user side sends the online answer information uploaded by the student to the server.

[0060] Offline answer data refers to the answer data given by students based on the questions in the paper homework or test paper after they receive the published paper homework or test paper. Students or teachers can take photos of the homework or test paper after the students answer and upload them to the user end. When it is necessary to obtain the student's answer information, the server sends a data collection request to the user end. After receiving the data collection request, the user end sends the student's offline answer information to the server.

[0061] In one embodiment of the present invention, after receiving offline answer information, the image content can be converted into text content and saved for subsequent data analysis.

[0062] Step 120, searching a preset question bank for a first number, a first standard answer and a first release time corresponding to a target question, wherein the question bank contains a plurality of questions, and numbers, standard answers and release times corresponding to the questions, and the target question belongs to the question bank.

[0063] In an embodiment of the present invention, the question bank contains a large number of questions, and the questions in the homework and test papers issued to students are all extracted from the question bank. The question bank not only contains the original questions, but also contains the number, standard answer and release time corresponding to each question.

[0064] Specifically, each question has a unique number for quick identification; the release time of the question is the time when the question is released to students for answering. It is understandable that there can be many questions at the same release time. For example, the release time of homework or exam questions released on the same day is the same.

[0065] After obtaining the student's answer information, you can look up the release time, standard answer and number corresponding to each question answered by the student in the question bank.

[0066] Step 130, correct the answer data according to the first standard answer to obtain the answer correction information of the target student, sort the answer data corresponding to the target question according to the first release time and the first number of the target question, and obtain the answer data sequence of the target student.

[0067] After obtaining the release time, standard answer and number corresponding to each question answered by the student, the student's answer data can be corrected according to the standard answer of each question to determine whether the student's answer data is correct.

[0068] Specifically, by searching the question bank for the first standard answer corresponding to the target question answered by the target student, the answer data of the target question of the target student is corrected according to the first standard answer. Through this method, the answer correction information of all questions of the target student is obtained, and the answer correction information may include correct or wrong, score and other information.

[0069] Since the order of answer information uploaded by students or teachers is different, in order to facilitate subsequent data analysis, the answer data can be pre-processed and the answer data of all students can be sorted.

[0070] Specifically, the target student's answer data are sorted according to a preset numbering sequence and time sequence to obtain the target student's answer data sequence.

[0071] For example, Table 1 is the answer information of the target students. Table 1 contains the answer data of the questions answered by the target students, the numbers corresponding to the questions and the release time. Based on this, the answer data sequence of the target students can be arranged in chronological order and order of number size as A(A1, A2, A3, …), where A1(a1, a2, a3, …), A2(a4, a5, a6, …), A3(a7, a8, a9, …), …; where An is the answer data sequence with the same release time, and an is the answer data.

[0072] Table 1 Target students' answer information table

[0073] Question answering data First Number First release time Question 1 a1 101 24.01.01 Question 2 a2 102 24.01.01 Question 3 a3 103 24.01.01 Question 4 a4 104 24.01.02 Question 5 a5 105 24.01.02 Question 6 a6 106 24.01.02 Question 7 a7 107 24.01.03 Question 8 a8 108 24.01.03 Question 9 a9 109 24.01.03 …… …… …… ……

[0074] Step 140, from the answer data sequence and the answer correction information, filter the answer data subsequence and the answer correction subinformation whose first release time is within the target time period, calculate the accuracy rate based on the answer data subsequence and the answer correction subinformation, and obtain the answer accuracy rate of the target student within the target time period.

[0075] In the embodiment of the present invention, the learning status of students can be monitored in sections according to the teaching content. Since most teaching methods at this stage are chapter teaching, the learning status of each student in the class in each chapter can be observed to examine the students' mastery of the knowledge points in a certain chapter, and whether the students have plagiarism and other issues.

[0076] Specifically, it can be judged based on the students' answering situation in the teaching time period of each chapter. According to the actual teaching situation, the target time period is selected, and the answer data subsequence and answer correction sub-information corresponding to the questions released in the target time period are obtained.

[0077] For example, assuming that the target time period is 24.01.01-24.01.03, the first release time of the target student's answered questions refers to Table 1, then the target student's answer data subsequence is A'(A1, A2, A3), where A1(a1, a2, a3, ...), A2(a4, a5, a6, ...), A3(a7, a8, a9, ...); among them, An is the answer data sequence with the same release time, and an is the answer data.

[0078] After obtaining the answer data subsequence and the answer correction sub-information, the answer data corresponding to all questions in the answer data subsequence are corrected using the answer correction sub-information, and the correct answer rate of the target student in the target time period is calculated based on the correction results.

[0079] Step 150, performing similarity analysis on the target student's answer data subsequences and the selected students' answer data subsequences to obtain the target student's answer plagiarism rate within the target time period.

[0080] In the embodiment of the present invention, answer information of many students is obtained, for example, answer information of all students in a class is obtained. It is understandable that each student needs to answer the same questions, and the questions are uniformly released to the students, so the release time of the same questions is the same for the students.

[0081] In an embodiment of the present invention, it is analyzed whether each student has plagiarized during the target time period and the degree of plagiarism. Specifically, a similarity analysis is performed between the target student's answer data subsequence and the other students' answer data subsequence to determine the student's plagiarism rate. The other students are students selected by the teacher. For example, the other students may be students in the same class as the target student, and the questions in the answer information submitted by the other students are consistent with the questions in the answer information submitted by the target student.

[0082] In one embodiment of the present invention, Table 2 is the answer information of the target student, and Table 3 is the answer information of other students. Assuming that the target time period is 24.01.01-24.01.03, the answer data subsequence of the target student is A'(A1, A2, A3), where A1(a1, a2, a3), A2(a4, a5, a6), A3(a7, a8, a9), and the answer data subsequence of any other student is B'(B1, B2, B3), where B1(b1, b2, b3), b2(b4, b5, b6), b3(b7, b8, b9). The similarity between the answer data subsequence A' and the answer data subsequence B' can be calculated to obtain the answer plagiarism rate of the target student in the target time period.

[0083] By performing similarity analysis on the target student's answer data subsequence and the answer data subsequence of every other student, the answer data subsequence among other students that is most similar to the target student's answer data subsequence is obtained, and then the target student's answer plagiarism rate within the target time period is calculated based on the two answer data subsequences.

[0084] Table 2 Target students' answer information

[0085] Question answering data First Number First release time Question 1 a1 101 24.01.01 Question 2 a2 102 24.01.01 Question 3 a3 103 24.01.01 Question 4 a4 104 24.01.02 Question 5 a5 105 24.01.02 Question 6 a6 106 24.01.02 Question 7 a7 107 24.01.03 Question 8 a8 108 24.01.03 Question 9 a9 109 24.01.03

[0086] Table 3 Other students' answer information

[0087] Question answering data First Number First release time Question 1 b1 101 24.01.01 Question 2 b2 102 24.01.01 Question 3 b3 103 24.01.01 Question 4 b4 104 24.01.02 Question 5 b5 105 24.01.02 Question 6 b6 106 24.01.02 Question 7 b7 107 24.01.03 Question 8 b8 108 24.01.03 Question 9 b9 109 24.01.03

[0088] Step 160, determining the learning status of the target student in the target time period based on the plagiarism rate and the correct answer rate.

[0089] When students have a poor grasp of a certain chapter, it can be reflected in the correct rate of their answers; or when students have a bad attitude towards learning, it can be reflected in the plagiarism rate of their answers. Therefore, the learning status of students in the target time period can be determined based on the plagiarism rate and correct rate of the target students. This makes it easier for teachers or parents to make corrections based on the students' learning status or develop effective teaching plans.

[0090] The learning status monitoring method proposed by the present invention monitors the learning status of students by collecting their answer information. By using comprehensive data and scientific analysis methods to monitor the learning status of students in different time periods, it is helpful for teachers or parents to understand the learning status of students in a timely manner, and make correct guidance and further teaching plans, thereby achieving the purpose of improving teaching quality.

[0091] Taking into account the diversity of question types, an embodiment of the present invention also proposes different similarity analysis methods according to the characteristics of the answer data corresponding to different question types. The similarity analysis is performed on the answer data of students through the similarity analysis methods corresponding to different question types to improve the accuracy of the analysis results.

[0092] In the embodiment of the present invention, the question bank also includes question types corresponding to the questions, and the question types include at least objective questions and subjective questions. Based on this, similarity analysis is performed on the target student and the selected students' answer data subsequences to obtain the target student's answer plagiarism rate within the target time period, specifically including:

[0093] Step 151. Obtain the target answer data subsequence with the same release time in the target student's answer data subsequence.

[0094] The same release time can be understood as the questions being released at the same time, and the questions released at the same time can also be considered as homework or exams assigned on the same day.

[0095] Referring to Table 1, the target answer data subsequence can be A1 (a1, a2, a3, ...), A2 (a4, a5, a6, ...), A3 (a7, a8, a9, ...), ...; where an is the answer data.

[0096] Taking into account that the target students may plagiarize different objects every day, the embodiment of the present invention selects to analyze the students' answer data subsequences corresponding to the questions released at the same time. The analysis results obtained will be more accurate than the analysis results of the answer data subsequences corresponding to the questions released at all times within the target time period.

[0097] Step 152: Based on the question type, the answer data in the target answer data subsequence is disassembled to obtain an objective question answer subsequence and a subjective question answer subsequence.

[0098] In an embodiment of the present invention, answer data are classified according to question type, and a target answer data subsequence is decomposed into different types of answer data subsequences, and then the characteristics of each type of answer data subsequence are analyzed to improve the accuracy of the analysis result.

[0099] In one embodiment of the present invention, Table 4 is a table of answer information of student c, and the target answer data subsequence of student c is Ci(c1, c2, c3, ..., c21), where cn is the answer data. Since the question types are divided into two categories: subjective questions and objective questions, the target answer subsequence can be disassembled to obtain the objective question answer subsequence Ci 客 (c1, c2, c3, ..., c12) and the subjective question answering subsequence Ci 主(c13, c14, c15,..., c21).

[0100] Table 4: Student c’s answer information

[0101]

[0102]

[0103] Step 153, respectively calculate the similarity between the objective question answer subsequences and the subjective question answer subsequences of the target student and each selected student to obtain the first answer plagiarism rate of the objective question and the second answer plagiarism rate of the subjective question corresponding to the answer data subsequences.

[0104] Since the content of answer data between objective questions and subjective questions is quite different, in order to reduce the error of answer plagiarism rate, the embodiment of the present invention selects different analysis methods according to the characteristics of each question type to calculate the answer plagiarism rate of different types of answer data respectively.

[0105] In one embodiment of the present invention, the answer plagiarism rate is the similarity between the objective question answer subsequence or subjective question answer subsequence of the target student and the objective question answer subsequence or subjective question answer subsequence of other students.

[0106] Specifically, similarity calculation is performed on the objective question answer subsequences and subjective question answer subsequences of the target student and each selected student, respectively, to obtain the first answer plagiarism rate of the objective question and the second answer plagiarism rate of the subjective question corresponding to the answer data subsequences, specifically including:

[0107] Step 1531. Use the Smith-Waterman algorithm to perform similarity analysis on the target student's objective question answer subsequence and the selected students' objective question answer subsequence to determine the target student's first answer plagiarism rate.

[0108] The answer data filled in by the students when answering the objective questions are basically options, such as A, B, C, ... In one embodiment of the present invention, the objective question answer subsequences of the target student and other students can refer to Table 5. It can be seen that the most similar objective question answer subsequence to the target student is the answer subsequence of student 2. Therefore, the plagiarism rate of the first answer of the target student can be determined based on the similarity between the objective question answer subsequences of the target student and student 2.

[0109] Table 5 is an example table of student objective question answering subsequences

[0110] Objective Question Answering Subsequence Target students (A,C,D,A,C,D,B,A,A,A) Student 1 (A,B,D,B,B,D,B,B,B,B) Student 2 (A,C,D,A,C,D,B,A,B,B)

[0111] In order to improve the accuracy of calculating the plagiarism rate of answers and reduce misjudgment, in the embodiment of the present invention, the Smith-Waterman algorithm is used to perform similarity analysis on the objective question answer subsequence of the target student and the objective question answer subsequence of each selected student to determine the plagiarism rate of the first answer of the target student, specifically including:

[0112] A. Based on the Smith-Waterman algorithm, find the two sequence segments with the highest similarity between the target student's objective question answer subsequence and the objective question answer subsequences of each selected student.

[0113] The Smith-Waterman algorithm is an algorithm for local sequence alignment (as opposed to global alignment) to find similar regions between sequences. The purpose of this algorithm is not to align the entire sequence, but to find fragments with high similarity between two sequences.

[0114] For example, based on the example table of student objective question answer subsequences in Table 5, it can be seen that the sequence segment with the highest similarity to the target student is (A, C, D, A, C, D, B, A) of student 2.

[0115] B. If the length of the sequence segment is greater than a preset length threshold, the first accuracy rate of the sequence segment of the target student is determined according to the answer correction sub-information.

[0116] In order to reduce misjudgment, before calculating the plagiarism rate of the first answer, first determine the length of the sequence segment with the highest similarity. Compare the length of the sequence segment with the preset length threshold. If the length of the sequence segment is greater than the preset length threshold, the plagiarism rate of the answer can be calculated. If it is not greater than the preset length threshold, it is considered that the student does not plagiarize, and the plagiarism rate of the first answer is zero.

[0117] In one embodiment of the present invention, the length threshold may be the total length of the objective question answer subsequence of the target student*a (0.5<a≤1).

[0118] In the embodiment of the present invention, if the target student and other students have a high degree of similarity in sequence segments and a high degree of accuracy, the target student is not considered to have plagiarized; if the target student and other students have a high degree of similarity in sequence segments but a low degree of accuracy, the target student is considered to have plagiarized. Therefore, before confirming the calculation of the plagiarism rate of the answer, the first accuracy rate of the target student's sequence segments is first calculated according to the answer correction sub-information.

[0119] C. When the first accuracy is lower than a preset first accuracy threshold, a first similarity between the two sequence segments is calculated.

[0120] Specifically, the first accuracy rate is compared with a preset first accuracy rate threshold. When the first accuracy rate is not lower than the preset first accuracy rate threshold, it is considered that the target student has not plagiarized, and the plagiarism rate of the student's first answer is zero; when the first accuracy rate is lower than the preset first accuracy rate threshold, it is considered that the target student has plagiarized, and the similarity between the two sequence fragments can be calculated.

[0121] D. When the first similarity is greater than a preset first similarity threshold, the first answer plagiarism rate of the target student is calculated according to the first correct rate and the first similarity.

[0122] Specifically, if the similarity between the target student's sequence fragment and the sequence fragment with the highest similarity of other students is too low, it is considered that the target student does not plagiarize. Therefore, the first similarity is compared with the preset first similarity threshold. When the first similarity is not greater than the preset first similarity threshold, it is considered that the target student does not plagiarize, and the first answer plagiarism rate is zero; when the first similarity is greater than the preset first similarity threshold, it is considered that the target student plagiarizes, and the target student's first answer plagiarism rate is calculated based on the first correct rate and the first similarity.

[0123] In one embodiment of the present invention, the first answer plagiarism rate corresponding to the objective question answer subsequence in the target question answer data subsequence can be calculated by the following formula:

[0124]

[0125] Among them, P1 is the first answer plagiarism rate, z is the first correct rate, and T is the first similarity.

[0126] Step 1532, calculate the text similarity between the target student's subjective question answer subsequence and the selected students' subjective question answer subsequences to determine the target student's second answer plagiarism rate.

[0127] There is no fixed answer to the subjective question. The plagiarism rate of the target student’s second answer can be determined by calculating the text similarity of each answer data in the subjective question answer subsequence.

[0128] Specifically, the text similarity calculation is performed between the target student's subjective question answer subsequence and the selected students' subjective question answer subsequences to determine the target student's second answer plagiarism rate, specifically including:

[0129] E. Calculate the text similarity between the target student's subjective question answer subsequence and the subjective question answer subsequences of each selected student.

[0130] Specifically, the similarity between the text content in the subjective question answer subsequence of the target student and the text content in the subjective question answer subsequence of each selected student is calculated; if the text content similarity between the subjective question answer subsequence of the target student and a certain student is the highest, the text similarity between the target student and the student is used as the text similarity of the target student.

[0131] Refer to Table 6, which shows the subjective question answer subsequences of the target student and other students. The text similarity between the subjective question answer subsequence of the target student and the subjective question answer subsequences of students 1 to 4 is calculated respectively. If the text similarity between the subjective question answer subsequences of the target student and students 1 to 4 is 40%, 50%, 60%, and 70% respectively, then the text similarity of 70% between student 4 and the target student is taken as the text similarity of the target student.

[0132] Table 6 Example of subsequences of students' subjective questions

[0133] Subjective question answering subsequence Target students (a1, a2, a3, a4, a5, a6, a6, a7, a8) Student 1 (b1, b2, b3, b4, b5, b6, b6, b7, b8) Student 2 (c1, c2, c3, c4, c5, c6, c6, c7, c8) Student 3 (d1, d2, d3, d4, d5, d6, d6, d7, d8) Student 4 (e1, e2, e3, e4, e5, e6, e6, e7, e8)

[0134] F. When the text similarity is greater than a second similarity threshold, the second accuracy rate of the target student's subjective question answer subsequence is determined based on the answer correction sub-information.

[0135] Specifically, if the text similarity between the target student and other students is too low, it is considered that the target student does not plagiarize. Therefore, the text similarity is compared with the preset second similarity threshold. When the text similarity is not greater than the preset second similarity threshold, it is considered that the target student does not plagiarize, and the second answer plagiarism rate is zero; when the text similarity is greater than the preset second similarity threshold, it is considered that the target student plagiarizes, and the second correct rate of the target student's subjective question answer subsequence is calculated based on the answer correction sub-information.

[0136] G. Calculate the target student’s second answer plagiarism rate based on the second accuracy rate and text similarity.

[0137] In the embodiment of the present invention, the second answer plagiarism rate corresponding to the subjective question answer subsequence in the target answer data subsequence can be calculated by the following formula:

[0138]

[0139] Among them, P2 is the second answer plagiarism rate, z2 is the second correct rate, and T2 is the second similarity.

[0140] Step 154: Perform a weighted calculation based on the first answer plagiarism rate and the second answer plagiarism rate corresponding to all target answer data subsequences in the answer data subsequence to obtain the answer plagiarism rate of the target student in the target time period.

[0141] In one embodiment of the present invention, the answer plagiarism rate of the target answer data subsequence can be calculated based on the first answer plagiarism rate and the second answer plagiarism rate corresponding to the target answer data subsequence, and then the answer plagiarism rate of the target student in the target time period can be calculated based on the answer plagiarism rates of all target answer data subsequences in the answer data subsequence.

[0142] Specifically, a weighted calculation is performed based on the first answer plagiarism rate and the second answer plagiarism rate corresponding to all target answer data subsequences in the answer data subsequence to obtain the answer plagiarism rate of the target student in the target time period, specifically including:

[0143] Step 1541. Perform weighted calculation on the first answer plagiarism rate and the second answer plagiarism rate corresponding to the target answer data subsequence to obtain the third answer plagiarism rate.

[0144] Step 1542, based on a preset mathematical operation method, calculate the plagiarism rate of all third answers of the target student in the answer data subsequence to obtain the plagiarism rate of the target student in the target time period.

[0145] Specifically, the target student's answer plagiarism rate in the target time period may be an average of all third answer plagiarism rates, or may be a weighted value of all third answer plagiarism rates.

[0146] In another embodiment of the present invention, a weighted calculation is performed based on the first answer plagiarism rate and the second answer plagiarism rate corresponding to all target answer data subsequences in the answer data subsequence to obtain the answer plagiarism rate of the target student in the target time period, which may also be:

[0147] Perform average calculation or weighted calculation on the first answer plagiarism rates of all target answer data subsequences in the answer data subsequence to obtain the target first answer plagiarism rate; perform average calculation or weighted calculation on the second answer plagiarism rates of all target answer data subsequences in the answer data subsequence to obtain the target second answer plagiarism rate; perform weighted calculation on the target first answer plagiarism rate and the target second answer plagiarism rate to obtain the answer plagiarism rate of the target student in the target time period.

[0148] After obtaining the students' plagiarism rate and correct answer rate, the target students' learning status in the target time period can be determined based on the plagiarism rate and correct answer rate:

[0149] Step 161. When the target student's correct answer rate in the target time period is greater than the preset third correct rate, it is confirmed that the student's learning status in the target time period is good.

[0150] Step 162: When the student's correct answer rate within the target time period is not greater than the third correct rate, and the plagiarism rate is not greater than the preset plagiarism rate threshold, it is confirmed that there is a problem with the student's learning status within the target time period.

[0151] Specifically, confirming that there are problems with the students' learning status within the target time period means that the students have not mastered the knowledge points within the target period firmly and have made many wrong answers. They need to strengthen their learning of the knowledge points within the target time period and adjust their learning plans reasonably.

[0152] Step 163. When the plagiarism rate of the answer is greater than the plagiarism rate threshold, it is confirmed that the student has plagiarized during the target time period.

[0153] By monitoring students' learning status in different time periods through their answer data, parents or teachers can effectively monitor students' learning situation and propose targeted teaching plans based on their learning status, greatly improving the teaching quality.

[0154] The present invention also provides a monitoring device for the learning state, which can be found in Figure 2 , Figure 2 The device for monitoring the learning state in the embodiment of the present invention includes a data acquisition module 201 , a data analysis module 202 and a state determination module 203 .

[0155] The data collection module 201 is used to receive the answer information of the target student submitted by the user end, wherein the answer information includes the target question and the answer data submitted by the target student based on the target question. The first number, the first standard answer and the first release time corresponding to the target question are searched in a preset question bank, the question bank includes multiple questions, as well as the numbers, standard answers and release times corresponding to the questions, and the target question belongs to the question bank;

[0156] The data analysis module 202 is used to correct the answer data according to the first standard answer, obtain the answer correction information of the target student, sort the answer data corresponding to the target question according to the first release time and the first number of the target question, and obtain the answer data sequence of the target student. From the answer data sequence and the answer correction information, select the answer data subsequence and answer correction subinformation whose first release time is within the target time period, calculate the correct rate according to the answer data subsequence and answer correction subinformation, and obtain the answer correct rate of the target student within the target time period; perform similarity analysis on the answer data subsequences of the target student and each selected student, and obtain the answer plagiarism rate of the target student within the target time period.

[0157] The state determination module 203 is used to determine the learning state of the target student in the target time period based on the plagiarism rate and the correct answer rate.

[0158] The embodiment of the present invention proposes a method for monitoring the learning status. By using the students' answer information as the basis for monitoring the learning status, and analyzing the accuracy and plagiarism of each student's homework within the target time period, the students' learning status is analyzed so that the students' current shortcomings and deficiencies can be judged according to the learning status, and then targeted teaching methods can be made to improve the teaching quality.

[0159] Figure 3 FIG. 1 shows an internal structure diagram of a computer device in one embodiment of the present invention. The computer device may be a terminal or a system. Figure 3 As shown, the computer device includes a processor, a memory and a network interface connected via a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor may implement each step in the above method embodiment. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor may implement each step in the above method embodiment. Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0160] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes each step in the above method embodiment.

[0161] In one embodiment, a computer-readable storage medium is proposed, which stores a computer program. When the computer program is executed by a processor, the processor executes each step in the above method embodiment. A person of ordinary skill in the art can understand that all or part of the processes in the above embodiment method can be completed by instructing the relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium, and the program can include the processes of the embodiments of the above methods when executed. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0162] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0163] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for monitoring a learning state, characterized in that: The method comprises: Receiving answer information of a target student submitted by a user terminal, wherein the answer information includes a target question and answer data submitted by the target student based on the target question; Searching for a first number, a first standard answer, and a first release time corresponding to the target question in a preset question bank, wherein the question bank includes a plurality of questions, and numbers, standard answers, and release times corresponding to the questions, and the target question belongs to the question bank; Correcting the answer data according to the first standard answer to obtain the answer correction information of the target student, and sorting the answer data corresponding to the target question according to the first release time of the target question and the first number to obtain the answer data sequence of the target student; From the answer data sequence and the answer correction information, select the answer data subsequence and the answer correction subinformation whose first release time is within the target time period, calculate the correct rate according to the answer data subsequence and the answer correction subinformation, and obtain the answer correct rate of the target student within the target time period; Performing similarity analysis on the answer data subsequences of the target student and each selected student to obtain the plagiarism rate of the target student in the target time period; The learning status of the target student in the target time period is determined based on the plagiarism rate and the correct answer rate.

2. The method according to claim 1, characterized in that The question bank also includes question types corresponding to the questions, and the question types include at least objective questions and subjective questions; The similarity analysis of the answer data subsequences of the target student and each selected student to obtain the plagiarism rate of the target student in the target time period specifically includes: Obtaining a target answer data subsequence with the same release time in the answer data subsequence of the target student; Based on the question type, the answer data in the target answer data subsequence is decomposed to obtain an objective question answer subsequence and a subjective question answer subsequence; Performing similarity calculations on the objective question answer subsequences and the subjective question answer subsequences of the target student and each selected student, respectively, to obtain a first answer plagiarism rate of the objective question and a second answer plagiarism rate of the subjective question corresponding to the answer data subsequences; A weighted calculation is performed based on the first answer plagiarism rate and the second answer plagiarism rate corresponding to all target answer data subsequences in the answer data subsequence to obtain the answer plagiarism rate of the target student in the target time period.

3. The method according to claim 2, characterized in that The similarity calculation is performed on the objective question answer subsequences and the subjective question answer subsequences of the target student and each selected student respectively to obtain the first answer plagiarism rate of the objective question and the second answer plagiarism rate of the subjective question corresponding to the answer data subsequence, specifically including: Using the Smith-Waterman algorithm, a similarity analysis is performed between the target student's objective question answer subsequence and the selected students' objective question answer subsequences to determine the target student's first answer plagiarism rate; The text similarity between the target student's subjective question answer subsequence and the selected students' subjective question answer subsequences is calculated to determine the target student's second answer plagiarism rate.

4. The method according to claim 3, characterized in that The method of using the Smith-Waterman algorithm to perform similarity analysis on the target student's objective question answer subsequence and the selected students' objective question answer subsequences to determine the target student's first answer plagiarism rate specifically includes: Searching for two sequence segments with the highest similarity between the target student's objective question answer subsequence and the objective question answer subsequences of each selected student based on the Smith-Waterman algorithm; If the length of the sequence segment is greater than a preset length threshold, determining a first correct rate of the sequence segment of the target student according to the question answering and correcting sub-information; When the first accuracy is lower than a preset first accuracy threshold, calculating a first similarity between the two sequence segments; When the first similarity is greater than a preset first similarity threshold, the first answer plagiarism rate of the target student is calculated according to the first correct rate and the first similarity.

5. The method according to claim 3, characterized in that The calculating of text similarity between the subjective question answer subsequence of the target student and the subjective question answer subsequences of each selected student to determine the second answer plagiarism rate of the target student specifically includes: Calculating the text similarity between the target student's subjective question answer subsequence and the subjective question answer subsequences of each selected student; When the text similarity is greater than a second similarity threshold, determining a second correct rate of the target student's subjective question answer subsequence according to the answer correction sub-information; A second plagiarism rate of the target student is calculated based on the second accuracy rate and the text similarity.

6. The method according to claim 2, characterized in that The step of performing weighted calculation based on the first answer plagiarism rate and the second answer plagiarism rate corresponding to all target answer data subsequences in the answer data subsequence to obtain the answer plagiarism rate of the target student in the target time period specifically includes: Performing weighted calculation on the first answer plagiarism rate and the second answer plagiarism rate corresponding to the target answer data subsequence to obtain a third answer plagiarism rate; Based on a preset mathematical operation method, the plagiarism rate of all the third answers of the target student in the answer data subsequence is calculated to obtain the plagiarism rate of the target student in the target time period.

7. The method according to claim 1, characterized in that The determining the learning status of the target student in the target time period based on the plagiarism rate and the correct answer rate specifically includes: When the target student's correct answer rate in the target time period is greater than a preset third correct rate, it is confirmed that the student's learning status in the target time period is good; When the student's correct answer rate in the target time period is not greater than the third correct answer rate, and the plagiarism rate in the answer is not greater than a preset plagiarism rate threshold, it is confirmed that there is a problem with the student's learning status in the target time period; When the answer plagiarism rate is greater than the plagiarism rate threshold, it is confirmed that the student has plagiarized within the target time period.

8. A learning status monitoring device, characterized in that: The device includes a data acquisition module, a data analysis module and a state judgment module; The data collection module is used to receive the answer information of the target student submitted by the user end, wherein the answer information includes the target question and the answer data submitted by the target student based on the target question; Searching for a first number, a first standard answer, and a first release time corresponding to the target question in a preset question bank, wherein the question bank includes a plurality of questions, and numbers, standard answers, and release times corresponding to the questions, and the target question belongs to the question bank; The data analysis module is used to correct the answer data according to the first standard answer to obtain the answer correction information of the target student, and sort the answer data corresponding to the target question according to the first release time of the target question and the first number to obtain the answer data sequence of the target student; From the answer data sequence and the answer correction information, select the answer data subsequence and the answer correction subinformation whose first release time is within the target time period, calculate the correct rate according to the answer data subsequence and the answer correction subinformation, and obtain the answer correct rate of the target student within the target time period; Performing similarity analysis on the answer data subsequences of the target student and each selected student to obtain the plagiarism rate of the target student in the target time period; The state judgment module is used to determine the learning state of the target student in the target time period based on the plagiarism rate and the correct answer rate.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

10. A computer device comprising a memory and a processor, characterized in that: The memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

Images