CN117952797B - Internet education supervision system and method based on artificial intelligence - Google Patents
Internet education supervision system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN117952797B CN117952797B CN202410323757.8A CN202410323757A CN117952797B CN 117952797 B CN117952797 B CN 117952797B CN 202410323757 A CN202410323757 A CN 202410323757A CN 117952797 B CN117952797 B CN 117952797B
- Authority
- CN
- China
- Prior art keywords
- comment
- test question
- test
- value
- questions
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 16
- 230000035945 sensitivity Effects 0.000 claims abstract description 70
- 238000012549 training Methods 0.000 claims abstract description 69
- 230000002452 interceptive effect Effects 0.000 claims abstract description 56
- 238000004458 analytical method Methods 0.000 claims abstract description 31
- 238000012550 audit Methods 0.000 claims abstract description 8
- 238000012360 testing method Methods 0.000 claims description 246
- 230000003993 interaction Effects 0.000 claims description 36
- 230000000903 blocking effect Effects 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 25
- 238000005516 engineering process Methods 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000007789 sealing Methods 0.000 claims description 9
- 238000013480 data collection Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000003058 natural language processing Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 238000007726 management method Methods 0.000 abstract 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000004148 unit process Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention provides an Internet education supervision system and method based on artificial intelligence, which relate to the technical field of education supervision and comprise an education supervision module, a management module and a management module, wherein the education supervision module comprises an interactive comment analysis unit and a question library analysis unit; the interactive comment analysis unit is used for carrying out text sensitivity audit analysis on the interactive and comment areas uploaded to the Internet education platform by the user to obtain comment sensitivity values; setting a corresponding sensitivity threshold of the comment sensitivity value, comparing the comment sensitivity value with the corresponding sensitivity threshold, and generating an interactive violation instruction if the comment sensitivity value is greater than or equal to the corresponding sensitivity threshold. The invention realizes the accurate and personalized education supervision, ensures the content quality and the learning effect on the education platform, and the students can obtain targeted coaching and training to better master knowledge points and improve the learning result, and meanwhile, the education supervision mechanism can also manage and supervise the internet education platform more effectively, thereby ensuring the compliance and quality of the platform.
Description
Technical Field
The invention relates to the technical field of education supervision, in particular to an Internet education supervision system and method based on artificial intelligence.
Background
With the rapid development of internet technology, the method is also applied to internet education, the rise of the internet education brings wide development space for education market, and meanwhile, the problems such as content quality, safety, personalized requirements and the like are also existed. Under this background, the traditional education supervision method and system have difficulty in meeting the increasing demands, and it is important to perfect the existing education supervision system.
However, in the process of using internet education supervision, some problems still exist:
1. Text sensitivity problems exist in the interactive and comment areas on traditional internet educational platforms, such as misspeeches, false propaganda or illegal information, etc.
2. Students may have difficulty in learning due to weakness of certain knowledge points, and lack special training of corresponding knowledge points according to wrong answers of the students.
Therefore, we propose an artificial intelligence based internet education supervision system and method to solve the above-mentioned problems.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention provides an Internet education supervision system and method based on artificial intelligence so as to solve the problems in the background art.
The aim of the invention can be achieved by the following technical scheme that:
the education supervision module is used for being connected with the Internet education platform and collecting education content data of the Internet education platform; the education supervision module comprises an interactive comment analysis unit, a question library analysis unit and a training test question selection module;
The interactive comment analysis unit is used for carrying out text sensitivity audit analysis on the interactive and comment areas uploaded to the Internet education platform by the user to obtain comment sensitivity values; setting a corresponding sensitivity threshold of the comment sensitivity value, comparing the comment sensitivity value with the corresponding sensitivity threshold, and generating an interactive violation instruction if the comment sensitivity value is greater than or equal to the corresponding sensitivity threshold;
The question library analysis unit is used for analyzing any test question in the test question library to obtain the test question difficulty TY, the optimal answer similarity JD and the correct-error value JF corresponding to the test question; comprehensively processing the optimal solution similarity, the test question difficulty and the correct and incorrect values, and obtaining a test question understanding value EX by using a formula EX=TYXe1+JDxe2+JFxe3; wherein e1, e2 and e3 respectively represent weights corresponding to the optimal solution similarity, the test question difficulty and the correct and incorrect values; marking the test questions corresponding to the test question understanding values lower than the set understanding threshold as the test questions which are not mastered; recording the unoccupied test questions corresponding to the knowledge points in the test question library, and numbering m; calculating the understanding value of the test question corresponding to the unoccupied test question corresponding to the knowledge point in the test question library, and utilizing a formula Obtaining a knowledge point to-be-trained value ED; wherein, mEX and mr respectively represent the test question understanding value and the corresponding weight of the unoccupied test question number m corresponding to the knowledge point in the test question library; setting a special training test question threshold corresponding to the knowledge point, and if the value to be trained of the knowledge point is larger than the corresponding special training test question threshold, generating a corresponding special test question training instruction;
The execution processing module is used for receiving the corresponding instruction to trigger the corresponding measures.
As a preferred embodiment of the present invention, the system further comprises a data collection module; the data collection module collects educational content data of the Internet educational platform through a crawler technology.
As a preferred implementation mode of the invention, the education supervision module further comprises a training test question selection module; the training test question selecting module is used for extracting the test question difficulty degrees of all the non-mastered test questions corresponding to the knowledge points and carrying out average value calculation to obtain a non-palm difficulty average value; setting difficulty bearing intervals of training test questions corresponding to knowledge points, matching the half-sole difficulty average value with the corresponding set difficulty bearing intervals to obtain a training test question difficulty degree selecting interval, marking test questions with test question difficulty degrees between the training test question difficulty degree selecting intervals as selectable training test questions, and generating a selectable test question list according to the size sequence of the half-sole difficulty average value; selecting a set number of selectable training test questions from the selectable test question list by adopting a question selecting method as training test questions; the method for selecting the questions comprises a sequential selecting method, a random selecting method and the like, wherein the sequential selecting method selects the questions from the question library to serve as training questions according to the sequence of the selectable training questions from the selectable question list, and the random selecting method randomly selects a set number of selectable training questions from the selectable question list to serve as training questions.
As a preferred implementation mode of the invention, text sensitive audit analysis is carried out on the interaction and comment areas uploaded to the Internet education platform by the user, and specifically comprises the following steps:
Setting a text sensitive word stock, matching any comment content or interactive content in the interaction and comment areas with the text sensitive word stock to obtain comment interaction text sensitive words, matching each comment interaction text sensitive word with a sensitivity coefficient Pi, and recording any comment content or the number of comment interaction text sensitive words in the interaction and comment areas as comment interaction sensitive word number P; calculating the number of mutual-evaluation sensitive words in any comment content or interaction content and the sensitivity coefficient corresponding to the mutual-evaluation sensitive words in the comment interaction text, and utilizing a formula Obtaining a comment sensitivity value PU; wherein,And respectively representing the sensitivity coefficient corresponding to the comment interactive text sensitive word indexed as p corresponding to the comment content or the ith comment interactive text sensitive word in the interactive content and the weight corresponding to the sensitivity coefficient.
As a preferred embodiment of the present invention, the test question analysis is performed on any test question in the test question library, specifically:
Identifying question types corresponding to the test questions, wherein each question type is matched with a relative difficulty coefficient z; acquiring questions and solving questions corresponding to the test questions, extracting test question keywords from the questions by using a natural language processing technology, and recording the number TY1 of the test question keywords; extracting knowledge points and steps applied in the step of solving the problems, and respectively recording the numbers of the knowledge points and the steps as TY2 and TY3; identifying the repeated use times TY4 of the test question keywords in the question solving step; recording the step length TY5 of the solving step; marking the relative difficulty coefficient of the questions corresponding to the test questions, the number of the keywords of the test questions, the knowledge points, the number of steps, the repeated use times and the step length as the difficulty information of the test questions; processing the difficult and easy information of the test question and utilizing the formula Obtaining the difficulty TY of the test question; wherein t1, t2, t3, t4 and t5 respectively represent the number of test question keywords, knowledge points, the number of steps, the number of repeated use times and the weight corresponding to the step length;
Obtaining the answer result of the test question library submitted by the user, and extracting the answer and the answer corresponding to the test question; processing the solving step and the corresponding test question setting step by using a similarity algorithm to obtain the solving similarity corresponding to the test question setting step; selecting the maximum answer similarity of the test question setting step as the optimal answer similarity, and representing the optimal answer similarity as JD;
Matching answers corresponding to the test questions with the set answers, and judging the correctness of the test questions; if the answers are consistent, the answer of the test question is correct; otherwise, the answer of the test question is wrong; the correctness of the answer of the test question is expressed as a binary variable marked as a positive error value and is expressed as JF;
As a preferred embodiment of the present invention, receiving a corresponding instruction triggers a corresponding measure; the method comprises the following steps:
when an interactive violation instruction is received, replacing or deleting comment interactive text sensitive words;
When a special test question training instruction is received, providing training test questions corresponding to knowledge points for a user and sending the training test questions to an Internet education platform logged in by the user; the user is concentrated through the internet education platform and trains the training test questions.
As a preferred embodiment of the present invention, the system further comprises a comment monitoring module; the comment monitoring module is used for monitoring and analyzing related information of the user triggering interactive violation instructions and obtaining the time mark of triggering the interactive violation instructions in a preset time area before the current moment as the time violation number DG1; calculating the difference between the adjacent moments triggering the interactive violation instructions according to the time sequence, marking the difference as the violation time difference, and calculating the variance of all the violation time differences in the preset time zone to obtain a violation value DG2; selecting the violating time difference smaller than the preset violating time threshold as the approaching violating time, and recording the number of the approaching violating time to obtain the common violating number DG3; processing the number of violations, the value of violations and the number of frequently violations, and obtaining a comprehensive violating value DG by using a formula DG=DG1×k1+DG2×k2+DG3×k3; wherein k1, k2 and k3 respectively represent the corresponding weights of the time violations, the wave violations and the frequency violations; setting a standard threshold value of the comprehensive violation value, comparing the comprehensive violation value with the standard threshold value, and if the comprehensive violation value is larger than the standard threshold value, generating a comment blocking instruction and sending the comment blocking instruction to an execution processing module; after receiving the comment blocking instruction, the execution processing module triggers a warning user and limits the interactive comment blocking function;
Recording the generation time of a comment blocking instruction, and calculating the time difference between the generation time of the current comment blocking instruction and the generation time of the last comment blocking instruction to obtain a blocking time difference; extracting the number of comment blocking instructions of a user as a total number of packages; weighting and calculating the sealing time difference and the total sealing number to obtain a sealing value; matching the seal value with the value range of the seal-forbidden interaction comment time group set by the seal value to obtain the time limit period of the corresponding seal-forbidden interaction comment; the time limit of the forbidden interactive comment is used for updating the time limit of the time limit seal forbidden interactive comment function.
As a preferred embodiment of the present invention, the present invention comprises the steps of:
S1: the method comprises the steps of connecting with an Internet education platform, and collecting education content data of the Internet education platform;
S11: performing text sensitivity auditing analysis on the interaction and comment areas uploaded to the Internet education platform by the user to obtain comment sensitivity values; setting a corresponding sensitivity threshold of the comment sensitivity value, comparing the comment sensitivity value with the corresponding sensitivity threshold, and generating an interactive violation instruction if the comment sensitivity value is greater than or equal to the corresponding sensitivity threshold; the interactive violation instruction is used for triggering the replacement or deletion of the comment interactive text sensitive words;
S12: analyzing any test question in the test question library to obtain the test question difficulty, the optimal answer similarity and the correct and incorrect value corresponding to the test question; comprehensively processing the optimal solution similarity, the test question difficulty and the correct and incorrect values to obtain a test question understanding value; marking the test questions corresponding to the test question understanding values lower than the set understanding threshold as the test questions which are not mastered; recording the unoccupied test questions corresponding to the knowledge points in the test question library and numbering; calculating a test question understanding value corresponding to an unoccupied test question corresponding to a knowledge point in a test question library, wherein the knowledge point is to be trained; setting a special training test question threshold corresponding to the knowledge point, and if the value to be trained of the knowledge point is larger than the corresponding special training test question threshold, generating a corresponding special test question training instruction;
s2: and receiving a corresponding instruction to trigger a corresponding measure.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the invention, the interactive comment analysis unit is used for identifying and processing incorrect language and false propaganda on the Internet education platform by using text sensitive audit analysis, so that good environment and order of the education platform are maintained.
2. According to the invention, the question library analysis unit processes the answers and the solving steps of the questions by using the machine learning and similarity algorithm, calculates the solving similarity and the difficulty of the questions, identifies whether the questions are answered correctly or not by a user, records the unoriented questions and the understanding values of the questions, is beneficial to evaluating the grasping conditions of students on different knowledge points, and provides basis for personalized coaching.
In summary, the invention realizes providing accurate and personalized education supervision, ensures the content quality and learning effect on the education platform, and students can obtain targeted coaching and training to better master knowledge points and improve learning results, and meanwhile, the education supervision organization can also manage and supervise the internet education platform more effectively, thereby ensuring the compliance and quality of the platform.
Drawings
The present invention is further described below with reference to the accompanying drawings for the convenience of understanding by those skilled in the art.
Fig. 1 is a schematic block diagram of an artificial intelligence based internet education supervision system of the present invention.
Fig. 2 is a flowchart of an artificial intelligence based internet education supervision method according to the present invention.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.
Referring to fig. 1-2, an artificial intelligence based internet education supervision system and method includes:
the education supervision module is used for being connected with the Internet education platform and collecting education content data of the Internet education platform; the education supervision module comprises an interactive comment analysis unit, a question library analysis unit and a training test question selection module;
The interactive comment analysis unit is used for carrying out text sensitivity audit analysis on the interactive and comment areas uploaded to the Internet education platform by the user to obtain comment sensitivity values; setting a corresponding sensitivity threshold of the comment sensitivity value, comparing the comment sensitivity value with the corresponding sensitivity threshold, and generating an interactive violation instruction if the comment sensitivity value is greater than or equal to the corresponding sensitivity threshold;
The question library analysis unit is used for analyzing any test question in the test question library to obtain the test question difficulty TY, the optimal answer similarity JD and the correct-error value JF corresponding to the test question; comprehensively processing the optimal solution similarity, the test question difficulty and the correct and incorrect values, and obtaining a test question understanding value EX by using a formula EX=TYXe1+JDxe2+JFxe3; wherein e1, e2 and e3 respectively represent weights corresponding to the optimal solution similarity, the test question difficulty and the correct and incorrect values; marking the test questions corresponding to the test question understanding values lower than the set understanding threshold as the test questions which are not mastered; recording the unoccupied test questions corresponding to the knowledge points in the test question library, and numbering m; calculating the understanding value of the test question corresponding to the unoccupied test question corresponding to the knowledge point in the test question library, and utilizing a formula Obtaining a knowledge point to-be-trained value ED; wherein, mEX and mr respectively represent the test question understanding value and the corresponding weight of the unoccupied test question number m corresponding to the knowledge point in the test question library; setting a special training test question threshold corresponding to the knowledge point, and if the value to be trained of the knowledge point is larger than the corresponding special training test question threshold, generating a corresponding special test question training instruction;
The execution processing module is used for receiving the corresponding instruction to trigger the corresponding measures.
In the application, the system also comprises a data collection module; the data collection module collects educational content data of the Internet educational platform through a crawler technology.
It should be noted that, during the data collection process using the crawler technology, relevant laws and regulations and privacy protocols are complied with, and obtaining educational content data of the internet education platform allows the authorization or permission to collect data using the crawler technology.
In the application, the education supervision module further comprises a training test question selection module; the training test question selecting module is used for extracting the test question difficulty degrees of all the non-mastered test questions corresponding to the knowledge points and carrying out average value calculation to obtain a non-palm difficulty average value; setting difficulty bearing intervals of training test questions corresponding to knowledge points, matching the half-sole difficulty average value with the corresponding set difficulty bearing intervals to obtain a training test question difficulty degree selecting interval, marking test questions with test question difficulty degrees between the training test question difficulty degree selecting intervals as selectable training test questions, and generating a selectable test question list according to the size sequence of the half-sole difficulty average value; selecting a set number of selectable training test questions from the selectable test question list by adopting a question selecting method as training test questions; the method for selecting the questions comprises a sequential selecting method, a random selecting method and the like, wherein the sequential selecting method selects the questions from the question library to serve as training questions according to the sequence of the selectable training questions from the selectable question list, and the random selecting method randomly selects a set number of selectable training questions from the selectable question list to serve as training questions.
It should be noted that, the test question selecting module is used for providing training test questions suitable for students, ensuring the difficulty and accuracy of quality evaluation of the test questions, and avoiding influence on learning effect due to too high or too low difficulty.
In the application, text sensitive audit analysis is carried out on the interaction and comment areas uploaded to the Internet education platform by the user, specifically:
Setting a text sensitive word stock, matching any comment content or interactive content in the interaction and comment areas with the text sensitive word stock to obtain comment interaction text sensitive words, matching each comment interaction text sensitive word with a sensitivity coefficient Pi, and recording any comment content or the number of comment interaction text sensitive words in the interaction and comment areas as comment interaction sensitive word number P; calculating the number of mutual-evaluation sensitive words in any comment content or interaction content and the sensitivity coefficient corresponding to the mutual-evaluation sensitive words in the comment interaction text, and utilizing a formula Obtaining a comment sensitivity value PU; wherein,And respectively representing the sensitivity coefficient corresponding to the comment interactive text sensitive word indexed as p corresponding to the comment content or the ith comment interactive text sensitive word in the interactive content and the weight corresponding to the sensitivity coefficient.
It should be noted that the text sensitive word library includes common sensitive words and words which are not easy to appear.
In the application, any test question in the test question library is subjected to test question analysis, which specifically comprises the following steps:
Identifying question types corresponding to the test questions, wherein each question type is matched with a relative difficulty coefficient z; acquiring questions and solving questions corresponding to the test questions, extracting test question keywords from the questions by using a natural language processing technology, and recording the number TY1 of the test question keywords; extracting knowledge points and steps applied in the step of solving the problems, and respectively recording the numbers of the knowledge points and the steps as TY2 and TY3; identifying the repeated use times TY4 of the test question keywords in the question solving step; recording the step length TY5 of the solving step; marking the relative difficulty coefficient of the questions corresponding to the test questions, the number of the keywords of the test questions, the knowledge points, the number of steps, the repeated use times and the step length as the difficulty information of the test questions; processing the difficult and easy information of the test question and utilizing the formula Obtaining the difficulty TY of the test question; wherein t1, t2, t3, t4 and t5 respectively represent the number of test question keywords, knowledge points, the number of steps, the number of repeated use times and the weight corresponding to the step length;
Obtaining the answer result of the test question library submitted by the user, and extracting the answer and the answer corresponding to the test question; processing the solving step and the corresponding test question setting step by using a similarity algorithm to obtain the solving similarity corresponding to the test question setting step; selecting the maximum answer similarity of the test question setting step as the optimal answer similarity, and representing the optimal answer similarity as JD;
Matching answers corresponding to the test questions with the set answers, and judging the correctness of the test questions; if the answers are consistent, the answer of the test question is correct; otherwise, the answer of the test question is wrong; the correctness of the answer of the test question is expressed as a binary variable marked as a positive error value and is expressed as JF; the positive and negative values are binary variables, for example, if the answer of the test question is correct, the positive and negative value is 1, and if the answer of the test question is wrong, the positive and negative value is 0;
in the application, corresponding instructions are received to trigger corresponding measures; the method comprises the following steps:
when an interactive violation instruction is received, replacing or deleting comment interactive text sensitive words;
When a special test question training instruction is received, providing training test questions corresponding to knowledge points for a user and sending the training test questions to an Internet education platform logged in by the user; the user is concentrated through the internet education platform and trains the training test questions.
In the application, the comment monitoring module is also included; the comment monitoring module is used for monitoring and analyzing related information of the user triggering interactive violation instructions and obtaining the time mark of triggering the interactive violation instructions in a preset time area before the current moment as the time violation number DG1; calculating the difference between the adjacent moments triggering the interactive violation instructions according to the time sequence, marking the difference as the violation time difference, and calculating the variance of all the violation time differences in the preset time zone to obtain a violation value DG2; selecting the violating time difference smaller than the preset violating time threshold as the approaching violating time, and recording the number of the approaching violating time to obtain the common violating number DG3; processing the number of violations, the value of violations and the number of frequently violations, and obtaining a comprehensive violating value DG by using a formula DG=DG1×k1+DG2×k2+DG3×k3; wherein k1, k2 and k3 respectively represent the corresponding weights of the time violations, the wave violations and the frequency violations; setting a standard threshold value of the comprehensive violation value, comparing the comprehensive violation value with the standard threshold value, and if the comprehensive violation value is larger than the standard threshold value, generating a comment blocking instruction and sending the comment blocking instruction to an execution processing module; after receiving the comment blocking instruction, the execution processing module triggers a warning user and limits the interactive comment blocking function;
Recording the generation time of a comment blocking instruction, and calculating the time difference between the generation time of the current comment blocking instruction and the generation time of the last comment blocking instruction to obtain a blocking time difference; extracting the number of comment blocking instructions of a user as a total number of packages; weighting and calculating the sealing time difference and the total sealing number to obtain a sealing value; matching the seal value with the value range of the seal-forbidden interaction comment time group set by the seal value to obtain the time limit period of the corresponding seal-forbidden interaction comment; the time limit of the forbidden interactive comment is used for updating the time limit of the time limit seal forbidden interactive comment function.
In the present application, the present application comprises the steps of:
S1: the method comprises the steps of connecting with an Internet education platform, and collecting education content data of the Internet education platform;
S11: performing text sensitivity auditing analysis on the interaction and comment areas uploaded to the Internet education platform by the user to obtain comment sensitivity values; setting a corresponding sensitivity threshold of the comment sensitivity value, comparing the comment sensitivity value with the corresponding sensitivity threshold, and generating an interactive violation instruction if the comment sensitivity value is greater than or equal to the corresponding sensitivity threshold;
S12: analyzing any test question in the test question library to obtain the test question difficulty TY, the optimal answer similarity JD and the correct-error value JF corresponding to the test question; comprehensively processing the optimal solution similarity, the test question difficulty and the correct and incorrect values, and obtaining a test question understanding value EX by using a formula EX=TYXe1+JDxe2+JFxe3; wherein e1, e2 and e3 respectively represent weights corresponding to the optimal solution similarity, the test question difficulty and the correct and incorrect values; marking the test questions corresponding to the test question understanding values lower than the set understanding threshold as the test questions which are not mastered; recording the unoccupied test questions corresponding to the knowledge points in the test question library, and numbering m; calculating a value to be trained of a knowledge point corresponding to a test question understanding value corresponding to an unoccupied test question in a knowledge point library, and utilizing a formula Obtaining a knowledge point to-be-trained value ED; wherein, mEX and mr respectively represent the test question understanding value and the corresponding weight of the unoccupied test question number m corresponding to the knowledge point in the test question library; setting a special training test question threshold corresponding to the knowledge point, and if the value to be trained of the knowledge point is larger than the corresponding special training test question threshold, generating a corresponding special test question training instruction;
s2: and receiving a corresponding instruction to trigger a corresponding measure.
Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the invention is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (6)
1. Internet education supervisory systems based on artificial intelligence, its characterized in that includes:
the education supervision module is used for being connected with the Internet education platform and collecting education content data of the Internet education platform; the education supervision module comprises an interactive comment analysis unit, a question library analysis unit and a training test question selection module;
The interactive comment analysis unit is used for carrying out text sensitivity audit analysis on the interactive and comment areas uploaded to the Internet education platform by the user to obtain comment sensitivity values; setting a corresponding sensitivity threshold of the comment sensitivity value, comparing the comment sensitivity value with the corresponding sensitivity threshold, and generating an interactive violation instruction if the comment sensitivity value is greater than or equal to the corresponding sensitivity threshold;
The question library analysis unit is used for analyzing any test question in the test question library to obtain the test question difficulty, the optimal answer similarity and the correct and incorrect value corresponding to the test question; comprehensively processing the optimal solution similarity, the test question difficulty and the correct and incorrect values to obtain a test question understanding value; marking the test questions corresponding to the test question understanding values lower than the set understanding threshold as the test questions which are not mastered; recording the unoccupied test questions corresponding to the knowledge points in the test question library and numbering; calculating a test question understanding value corresponding to an unoccupied test question corresponding to a knowledge point in a test question library, wherein the knowledge point is to be trained; setting a special training test question threshold corresponding to the knowledge point, and if the value to be trained of the knowledge point is larger than the corresponding special training test question threshold, generating a corresponding special test question training instruction;
the execution processing module is used for receiving the corresponding instruction to trigger the corresponding measure;
the test question analysis is carried out on any test question in the test question library, specifically:
Identifying question types corresponding to the test questions, wherein each question type is matched with a relative difficulty coefficient; a step of acquiring questions and solving questions corresponding to the test questions, extracting test question keywords from the questions by using a natural language processing technology, and recording the number of the test question keywords; extracting knowledge points and steps used in the step of solving the problems, and recording the number of the knowledge points and the steps respectively; identifying the repeated use times of the test question keywords in the question solving step as repeated use times; recording the step length of the solving step; marking the relative difficulty coefficient of the questions corresponding to the test questions, the number of the keywords of the test questions, the knowledge points, the number of steps, the repeated use times and the step length as the difficulty information of the test questions; processing the test question difficulty information to obtain test question difficulty;
obtaining the answer result of the test question library submitted by the user, and extracting the answer and the answer corresponding to the test question; processing the solving step and the corresponding test question setting step by using a similarity algorithm to obtain the solving similarity corresponding to the test question setting step; selecting the maximum answer similarity of the test question setting step as the optimal answer similarity;
Matching answers corresponding to the test questions with the set answers, and judging the correctness of the test questions; if the answers are consistent, the answer of the test question is correct; otherwise, the answer of the test question is wrong; the correctness of the answer of the test question is expressed as a binary variable marked as a positive error value;
The comment monitoring module is also included; the comment monitoring module is used for monitoring and analyzing related information of the user triggering the interactive violation instruction and obtaining the time mark of triggering the interactive violation instruction in a preset time area before the current moment as the time violation number; calculating the difference between the adjacent moments triggering the interactive violation instructions according to the time sequence, marking the difference as the violation time difference, and calculating the variance of all the violation time differences in the preset time zone to obtain the violation wave value; selecting the violating time difference smaller than the preset violating time threshold as the approaching violating time, and recording the number of the approaching violations to obtain the frequent violations; processing the time violation number, the violation wave value and the frequent violation number to obtain a comprehensive violation value; setting a standard threshold value of the comprehensive violation value, comparing the comprehensive violation value with the standard threshold value, and if the comprehensive violation value is larger than the standard threshold value, generating a comment blocking instruction and sending the comment blocking instruction to an execution processing module; after receiving the comment blocking instruction, the execution processing module triggers a warning user and limits the interactive comment blocking function;
Recording the generation time of a comment blocking instruction, and calculating the time difference between the generation time of the current comment blocking instruction and the generation time of the last comment blocking instruction to obtain a blocking time difference; extracting the number of comment blocking instructions of a user as a total number of packages; weighting and calculating the sealing time difference and the total sealing number to obtain a sealing value; matching the seal value with the value range of the seal-forbidden interaction comment time group set by the seal value to obtain the time limit period of the corresponding seal-forbidden interaction comment; the time limit of the forbidden interactive comment is used for updating the time limit of the time limit seal forbidden interactive comment function.
2. The artificial intelligence based internet education supervision system according to claim 1, further comprising a data collection module; the data collection module collects educational content data of the Internet education platform through a crawler technology.
3. The artificial intelligence based internet education and supervision system according to claim 1, wherein the education and supervision module further comprises a training test question selection module; the training test question selecting module is used for extracting the test question difficulty levels of all the non-mastered test questions corresponding to the knowledge points and carrying out average value calculation to obtain a non-palm difficulty average value; setting difficulty bearing intervals of training test questions corresponding to knowledge points, matching the half-sole difficulty average value with the corresponding set difficulty bearing intervals to obtain a training test question difficulty degree selecting interval, marking test questions with test question difficulty degrees between the training test question difficulty degree selecting intervals as selectable training test questions, and generating a selectable test question list according to the size sequence of the half-sole difficulty average value; and selecting a set number of selectable training test questions from the selectable test question list by adopting a question selecting method as training test questions.
4. The artificial intelligence based internet education supervision system according to claim 1, wherein text sensitive audit analysis is performed on the interaction and comment area uploaded to the internet education platform by the user, specifically:
Setting a text sensitive word stock, matching any comment content or interactive content in the interaction and comment areas with the text sensitive word stock to obtain comment interaction text sensitive words, matching each comment interaction text sensitive word with a sensitivity coefficient, and recording any comment content or comment interaction text sensitive words in the interaction and comment areas as comment interaction word numbers; and calculating the number of the mutual-evaluation sensitive words in any comment content or interaction content and the sensitivity coefficient corresponding to the mutual-evaluation sensitive words in the comment interaction text to obtain a comment sensitivity value.
5. The artificial intelligence based internet education supervisory system according to claim 1 wherein receiving the corresponding instruction triggers the corresponding measure; the method comprises the following steps:
when an interactive violation instruction is received, replacing or deleting comment interactive text sensitive words;
When a special test question training instruction is received, providing training test questions corresponding to knowledge points for a user and sending the training test questions to an Internet education platform logged in by the user; the user is concentrated through the internet education platform and trains the training test questions.
6. An artificial intelligence based internet education supervision method characterized by being applied to the artificial intelligence based internet education supervision system according to any one of claims 1 to 5, the method comprising the steps of:
S1: the method comprises the steps of connecting with an Internet education platform, and collecting education content data of the Internet education platform;
S11: performing text sensitivity auditing analysis on the interaction and comment areas uploaded to the Internet education platform by the user to obtain comment sensitivity values; setting a corresponding sensitivity threshold of the comment sensitivity value, comparing the comment sensitivity value with the corresponding sensitivity threshold, and generating an interactive violation instruction if the comment sensitivity value is greater than or equal to the corresponding sensitivity threshold;
S12: analyzing any test question in the test question library to obtain the test question difficulty, the optimal answer similarity and the correct and incorrect value corresponding to the test question; comprehensively processing the optimal solution similarity, the test question difficulty and the correct and incorrect values to obtain a test question understanding value; marking the test questions corresponding to the test question understanding values lower than the set understanding threshold as the test questions which are not mastered; recording the unoccupied test questions corresponding to the knowledge points in the test question library and numbering; calculating a test question understanding value corresponding to an unoccupied test question corresponding to a knowledge point in a test question library, wherein the knowledge point is to be trained; setting a special training test question threshold corresponding to the knowledge point, and if the value to be trained of the knowledge point is larger than the corresponding special training test question threshold, generating a corresponding special test question training instruction;
s2: and receiving a corresponding instruction to trigger a corresponding measure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410323757.8A CN117952797B (en) | 2024-03-21 | 2024-03-21 | Internet education supervision system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410323757.8A CN117952797B (en) | 2024-03-21 | 2024-03-21 | Internet education supervision system and method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117952797A CN117952797A (en) | 2024-04-30 |
| CN117952797B true CN117952797B (en) | 2024-06-14 |
Family
ID=90796292
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410323757.8A Active CN117952797B (en) | 2024-03-21 | 2024-03-21 | Internet education supervision system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117952797B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111949822A (en) * | 2020-08-20 | 2020-11-17 | 山东大学 | Intelligent education video service system based on cloud computing and mobile terminal and operation method thereof |
| CN112508334A (en) * | 2020-11-06 | 2021-03-16 | 华中师范大学 | Personalized paper combining method and system integrating cognitive characteristics and test question text information |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11741848B2 (en) * | 2006-10-11 | 2023-08-29 | Cynthia Elnora ASHBY | Interactive system and method for diagnosing test-taking errors based on blooms taxonomy |
| CN107622709A (en) * | 2017-09-18 | 2018-01-23 | 哈尔滨成长科技有限公司 | Knowledge point Grasping level evaluation method, medium and electronic equipment |
| CN111445153B (en) * | 2020-03-31 | 2023-04-14 | 华中师范大学 | Method and system for estimating and correcting objective test question attribute mode for education measurement |
| CN113657723A (en) * | 2021-07-26 | 2021-11-16 | 弘成科技发展有限公司 | Knowledge point mastering condition diagnosis method, test question recommendation method and device |
| CN113688226A (en) * | 2021-08-24 | 2021-11-23 | 科学出版社成都有限责任公司 | Exercise practice method, system and storage medium based on big data |
| CN116263782A (en) * | 2021-12-10 | 2023-06-16 | 上海终身教育科技有限公司 | Intelligent winding method, system and storage medium based on question bank |
| CN114781710B (en) * | 2022-04-12 | 2022-12-23 | 云南师范大学 | Knowledge tracking method for difficulty characteristics of comprehensive learning process and question knowledge points |
| CN117150151B (en) * | 2023-11-01 | 2024-02-20 | 之江实验室 | Wrong question analysis and test question recommendation system and method based on large language model |
-
2024
- 2024-03-21 CN CN202410323757.8A patent/CN117952797B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111949822A (en) * | 2020-08-20 | 2020-11-17 | 山东大学 | Intelligent education video service system based on cloud computing and mobile terminal and operation method thereof |
| CN112508334A (en) * | 2020-11-06 | 2021-03-16 | 华中师范大学 | Personalized paper combining method and system integrating cognitive characteristics and test question text information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117952797A (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gambi et al. | Generating effective test cases for self-driving cars from police reports | |
| CN107256650B (en) | Exercise pushing method and system and terminal equipment | |
| Van Der Flier et al. | An iterative item bias detection method | |
| Yan et al. | TMOSS: Using intermediate assignment work to understand excessive collaboration in large classes | |
| Wise et al. | Using retest data to evaluate and improve effort‐moderated scoring | |
| Arifi et al. | Automatic program assessment using static and dynamic analysis | |
| Gonzalez et al. | Scaling methods and procedures for the TIMSS 2003 mathematics and science scales | |
| Li et al. | Early prediction of course grades: models and feature selection | |
| Morris et al. | Using transformer language models to validate peer-assigned essay scores in massive open online courses (MOOCs) | |
| CN111507584A (en) | Data analysis system and method | |
| Johnson et al. | Discrimination of automatically generated questions used as formative practice | |
| Pardos et al. | Determining the significance of item order in randomized problem sets. | |
| CN117952797B (en) | Internet education supervision system and method based on artificial intelligence | |
| CN116664001B (en) | Student skill assessment method and system based on artificial intelligence | |
| CN111724050A (en) | Teaching risk early warning method based on teaching process data | |
| Belov | Robust detection of examinees with aberrant answer changes | |
| Broisin et al. | Design and evaluation of a semantic indicator for automatically supporting programming learning | |
| Glorfeld et al. | Validation of a model for predicting aptitude for introductory computing | |
| Poturić et al. | Identification of predictive factors for student failure in STEM oriented course | |
| CN115409257A (en) | Score distribution prediction method and system based on condition density estimation model | |
| McKibben et al. | To model or not to model: false positive detection error in camera surveys | |
| Kamis et al. | An Investigation of Reliability Coefficients Estimated for Decision Studies in Generalizability Theory. | |
| Braught et al. | Tool design and student testing behavior in an introductory java course | |
| Mostafavi et al. | Data-driven proficiency profiling: proof of concept | |
| Rashidah et al. | Investigating Students’ Difficulties in Understanding Confidence Intervals in Linear Regression Models |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |