CN116259004A - Student learning state detection method and system applied to online education - Google Patents
Student learning state detection method and system applied to online education Download PDFInfo
- Publication number
- CN116259004A CN116259004A CN202310023798.0A CN202310023798A CN116259004A CN 116259004 A CN116259004 A CN 116259004A CN 202310023798 A CN202310023798 A CN 202310023798A CN 116259004 A CN116259004 A CN 116259004A
- Authority
- CN
- China
- Prior art keywords
- student
- state
- class
- students
- information
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 134
- 230000005856 abnormality Effects 0.000 claims abstract description 81
- 230000002159 abnormal effect Effects 0.000 claims abstract description 47
- 238000000034 method Methods 0.000 claims abstract description 15
- 239000013598 vector Substances 0.000 claims description 27
- 238000013468 resource allocation Methods 0.000 claims description 14
- 230000003044 adaptive effect Effects 0.000 claims description 8
- 230000009286 beneficial effect Effects 0.000 abstract description 10
- 230000014509 gene expression Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000003443 Unconsciousness Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Psychiatry (AREA)
- Computing Systems (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a student learning state detection method and system applied to online education, wherein the method comprises the following steps: when an online education classroom is opened, acquiring first state information of a teaching teacher in the online education classroom; generating a student learning state abnormality detection template based on the first state information and a preset student learning state abnormality detection template generation library; acquiring second state information of students in class in an online education classroom; and based on the student learning state abnormality detection template, carrying out student learning state abnormality detection on the students in class according to the second state information. The method and the system for detecting the learning state of the student applied to the online education greatly improve the applicability of abnormal detection of the learning state of the student, overcome the limitation problem, and improve the convenience without paying attention to the learning state of the student to the teaching teacher in the online classroom, thereby being beneficial to the teaching of the teaching teacher and improving the teaching quality to a certain extent.
Description
Technical Field
The invention relates to the technical field of computer data processing, in particular to a student learning state detection method and system applied to online education.
Background
Some social personnel can learn by listening to the class in the form of an online class. Secondly, some schools inconvenient for offline teaching can arrange teachers and students to take the form of online class for class.
However, online class is usually executed in a multi-person video mode, so that a teacher needs to pay attention to the learning state of the student in order to ensure the class listening quality of the student, and at the moment, the video picture of each student needs to be checked one by one to determine whether the student is listening carefully to the class, so that the online class is complex, and the teacher occupies part of the energy applied to teaching by the teacher.
The prior art also provides a solution to the problem, such as an online classroom concentration recognition method, system, device and medium with the publication number of CN115546861a in chinese patent literature, wherein student expressions are recognized based on student videos, and the concentration of students is determined based on the student expressions, so that the online classroom concentration recognition method, system, device and medium can replace teachers to pay attention to the learning state of students.
However, when actually taking class, the judging time and the judging means of whether the students attend class are determined by the class state of the teacher; for example: when a teacher is in teaching, prompting the student to rest for 5 minutes, wherein the student is reasonable to do any inattention action, and misjudgment can be caused if the teacher still determines whether the student is attentive or not based on the student video; also for example: the teacher gives interactive follow-up prompts, and at the moment, whether the student is focused on judging whether the student is to follow-up or not is judged. Secondly, the situation that the expression recognition is not possible occurs possibly; for example: the teacher prompts the student to complete the exercise on the textbook, the student may be running low/countersunk, and may not be able to recognize the expression.
Therefore, the solution given above has a limitation in specific application, namely, the applicability is low, and needs to be solved.
Disclosure of Invention
The invention aims to provide a student learning state detection method and system applied to online education, which greatly improve the applicability of student learning state abnormality detection, overcome the limitation problem, and improve the convenience without paying attention to the learning state of students by a teacher in online class, thereby being beneficial to the teacher in teaching and improving the teaching quality to a certain extent.
The student learning state detection method applied to online education provided by the embodiment of the invention comprises the following steps:
when an online education classroom is opened, acquiring first state information of a teaching teacher in the online education classroom;
generating a student learning state abnormality detection template based on the first state information and a preset student learning state abnormality detection template generation library;
acquiring second state information of a class student in the online education classroom;
and based on the student learning state abnormality detection template, carrying out student learning state abnormality detection on the lesson-listening students according to the second state information.
Preferably, the acquiring the first status information of the teaching teacher in the online education classroom includes:
pushing a preset teaching teacher state selection table to a first mobile terminal of the teaching teacher;
acquiring a teaching teacher state selected by the teaching teacher from the teaching teacher state selection table;
determining first state information based on the teaching teacher state;
and/or the number of the groups of groups,
acquiring first speaking information of the teaching teacher through the first mobile terminal;
determining first state information based on the first announcement information;
and/or the number of the groups of groups,
acquiring a lesson image of the teaching teacher through the first mobile terminal;
extracting first action information of the teaching teacher from the lesson-taking image;
first state information is determined based on the first action information.
Preferably, generating the student learning state abnormality detection template based on the first state information and a preset student learning state abnormality detection template generation library includes:
analyzing the information category number of the first state information;
when the information category number is unique, determining a student learning state abnormality detection rule corresponding to the first state information from the student learning state abnormality detection template generation library;
generating a student learning state abnormality detection template based on the student learning state abnormality detection rule;
when the information variety number is not the same, analyzing a state information feature set of the first state information based on a preset feature analysis template;
constructing a first feature description vector of the first state information based on the state information feature set;
extracting a plurality of groups of second feature description vectors and a student learning state abnormality detection rule set which are in one-to-one correspondence from the student learning state abnormality detection template generation library;
calculating the vector similarity between the first feature description vector and any one of the second feature description vectors;
and generating a student learning state abnormality detection template based on the student learning state abnormality detection rule set corresponding to the second feature description vector with the maximum vector similarity.
Preferably, the obtaining the second status information of the students in the online education classroom includes:
acquiring second speaking information of the lecture-listening student through a second mobile terminal of the lecture-listening student;
determining second state information based on the second utterance information;
and/or the number of the groups of groups,
acquiring a class-listening image of the class-listening student through the second mobile terminal;
extracting second action information of the lecture-attending student from the lecture-attending image;
and determining second state information based on the second action information.
Preferably, the student learning state detection method applied to online education further comprises:
acquiring a class listening record of the class listening student;
dividing the lecture-attending students into important students and non-important students based on the lecture-attending record;
and carrying out adaptive allocation of detection resources for detecting abnormal learning states of the students on the important students and the non-important students.
Preferably, based on the lecture notes, dividing the lecture notes into key students includes:
extracting abnormal learning state records generated in the history of the students in class from the class-listening records;
determining a learning state anomaly frequency of the lecture-attending student based on the learning state anomaly record;
when the abnormal frequency of the learning state is greater than or equal to a preset abnormal frequency threshold of the learning state, taking the corresponding students on class as key students;
and/or the number of the groups of groups,
acquiring a class-answering serious state upper limit prediction basis of the class-answering students;
inputting the class carefully state upper limit prediction into a preset class carefully state upper limit prediction model to determine the class carefully state upper limit;
extracting a first continuous class-listening situation within a latest preset time range of the class-listening students from the class-listening record;
determining, based on the first continuous lecture-attending situation, whether the lecture-attending student reaches the lecture-attending serious state upper limit;
and when yes, taking the students corresponding to the class as important students.
Preferably, the obtaining the upper limit prediction basis of the class carefully-listening state of the class-listening student includes:
acquiring the recording time of the learning state abnormal record;
based on the recording time, the learning state abnormality is recorded and unfolded on a preset time axis;
retrieving a target learning state abnormal record meeting a preset first retrieval condition from the time axis;
extracting a second continuous class-listening situation in the time range before the recording time of the target learning state abnormal record from the class-listening record, and taking the second continuous class-listening situation as a class-listening serious state upper limit prediction basis;
wherein the first search condition includes: the total number of the abnormal learning state records with the abnormal recording types of the preset types in the preset time distance before and after the abnormal learning state records on the time axis is larger than or equal to a preset number threshold;
and/or the number of the groups of groups,
acquiring student information of the students in class;
generating a template based on preset search conditions, and generating a second search condition according to the student information;
and retrieving the upper limit of other class-listening serious states meeting the second retrieval condition from a preset class-listening serious state upper limit collection library, and taking the upper limit as a class-listening serious state upper limit prediction basis.
Preferably, the adaptive allocation of detection resources for detecting abnormal learning states of students for the key students and the non-key students includes:
respectively counting the total number of the first students of the important students and the total number of the second students of the non-important students;
calculating a number ratio of the first student total to the second student total;
determining a detection resource allocation strategy corresponding to the number ratio from a preset detection resource allocation strategy library;
and respectively distributing the detection resources to the key students and the non-key students based on the detection resource distribution strategy.
The student learning state detection system applied to online education provided by the embodiment of the invention is characterized by comprising:
the teaching teacher state information acquisition module is used for acquiring first state information of a teaching teacher in the online education classroom when the online education classroom is started;
the student learning state abnormality detection template generation module is used for generating a student learning state abnormality detection template based on the first state information and a preset student learning state abnormality detection template generation library;
the class-listening student status information acquisition module is used for acquiring second status information of class-listening students in the online education classroom;
and the student learning state abnormality detection module is used for detecting the student learning state abnormality of the lesson-listening student according to the second state information based on the student learning state abnormality detection template.
Preferably, the instruction teacher state information obtaining module obtains first state information of an instruction teacher in the online education classroom, and performs the following operations:
pushing a preset teaching teacher state selection table to a first mobile terminal of the teaching teacher;
acquiring a teaching teacher state selected by the teaching teacher from the teaching teacher state selection table;
determining first state information based on the teaching teacher state;
and/or the number of the groups of groups,
acquiring first speaking information of the teaching teacher through the first mobile terminal;
determining first state information based on the first announcement information;
and/or the number of the groups of groups,
acquiring a lesson image of the teaching teacher through the first mobile terminal;
extracting first action information of the teaching teacher from the lesson-taking image;
first state information is determined based on the first action information.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of a student learning state detection method applied to online education in an embodiment of the invention;
fig. 2 is a schematic diagram of a student learning state detection system applied to online education according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The embodiment of the invention provides a student learning state detection method applied to online education, which is shown in figure 1 and comprises the following steps:
step S1: when an online education classroom is opened, acquiring first state information of a teaching teacher in the online education classroom;
step S2: generating a student learning state abnormality detection template based on the first state information and a preset student learning state abnormality detection template generation library;
step S3: acquiring second state information of a class student in the online education classroom;
step S4: and based on the student learning state abnormality detection template, carrying out student learning state abnormality detection on the lesson-listening students according to the second state information.
The working principle and the beneficial effects of the technical scheme are as follows:
the first state information includes: in lectures, reminding students to rest, taking actions in the lectures, reminding students to finish textbook exercises and the like. The second state information includes: listening to the expressions and actions made by the lessons, etc. The student learning state abnormality detection template is generated by first state information of a teaching teacher; for example: in the lecture, a teacher uses a student learning state abnormality detection template to detect whether the expression and the action of the student are inattentive or not; also for example: the teacher prompts the student to rest, and the abnormal learning state detection template of the student does not carry out any detection; for another example: the teacher makes the clapping action, and the student learning state abnormality detection template is used for detecting whether the student follows the clapping action; next, for example: the teacher prompts the students to finish textbook exercises, and the student learning state abnormality detection template is used for detecting whether the students are low-headed or countersunk to finish exercises.
When the method is specifically applied, the state of the teaching teacher is continuously acquired, the judging time and the judging means for whether the students attend to the class or not are determined based on the state of the teaching teacher, and the abnormal detection of the learning state of the students is comprehensively and adaptively carried out on the students attending to the class based on the judging time and the judging means.
According to the method and the device, the applicability of abnormal detection of the learning state of the students is greatly improved, the problem of limitation is solved, secondly, the teaching teacher who carries out teaching in an online classroom is not required to pay attention to the learning state of the students, convenience is improved, the teaching teacher who carries out teaching is benefited to put energy into teaching, and teaching quality is improved to a certain extent.
In one embodiment, obtaining first status information of a teaching teacher in the online education classroom includes:
pushing a preset teaching teacher state selection table to a first mobile terminal of the teaching teacher;
acquiring a teaching teacher state selected by the teaching teacher from the teaching teacher state selection table;
determining first state information based on the teaching teacher state;
and/or the number of the groups of groups,
acquiring first speaking information of the teaching teacher through the first mobile terminal;
determining first state information based on the first announcement information;
and/or the number of the groups of groups,
acquiring a lesson image of the teaching teacher through the first mobile terminal;
extracting first action information of the teaching teacher from the lesson-taking image;
first state information is determined based on the first action information.
The working principle and the beneficial effects of the technical scheme are as follows:
the determination of the first state information on behalf of the teaching teacher may be in three ways: first, pushing a state selection table of a teaching teacher for the teacher to select; the teaching teacher's state selection list contains the options of teaching, reminding students to rest, doing actions on class, reminding students to complete textbook exercise, etc. Second, based on the instruction teacher's speech determination; for example: the teacher speaks "rest 5 minutes", then the first state information is for reminding the student to rest, and the teacher speaks "continue to take lessons", then the first state information is for taking lessons etc.. Third, based on the instruction teacher action determination; for example: and if the teacher makes yoga demonstration actions, the first state information prompts the student to do yoga follow-up.
According to the embodiment of the invention, three modes are introduced to determine the first state information of the teaching teacher, so that the applicability of the system is improved.
In one embodiment, generating the student learning state abnormality detection template based on the first state information and a preset student learning state abnormality detection template generation library includes:
analyzing the information category number of the first state information;
when the information category number is unique, determining a student learning state abnormality detection rule corresponding to the first state information from the student learning state abnormality detection template generation library;
generating a student learning state abnormality detection template based on the student learning state abnormality detection rule;
when the information variety number is not the same, analyzing a state information feature set of the first state information based on a preset feature analysis template;
constructing a first feature description vector of the first state information based on the state information feature set;
extracting a plurality of groups of second feature description vectors and a student learning state abnormality detection rule set which are in one-to-one correspondence from the student learning state abnormality detection template generation library;
calculating the vector similarity between the first feature description vector and any one of the second feature description vectors;
and generating a student learning state abnormality detection template based on the student learning state abnormality detection rule set corresponding to the second feature description vector with the maximum vector similarity.
The working principle and the beneficial effects of the technical scheme are as follows:
generally, the number of information types of the first state information is unique, at this time, a student learning state abnormality detection rule corresponding to the first state information is determined from a student learning state abnormality detection template generation library, and a student learning state abnormality detection template is generated; for example: if the teacher only prompts the rest state of the student, the abnormal detection rule of the learning state of the student is that no detection is performed, and a template is generated; also for example: if the teacher is only in a state in the lecture, the abnormal detection rule of the learning state of the student should be to detect whether the expression and the action of the student are inattentive or not, and generate a template.
However, there are cases where the number of information types is not unique; for example: the teacher is performing dance teaching and making leg lifting actions, but verbally says "do not follow first, see me demonstration", and at this time, the teacher states are two. At this time, a state information feature set of the first state information is analyzed based on the feature analysis template; for example: the extracted state information feature set includes a teacher speaking including an action demonstration instruction that the teacher also makes an action, and the teacher is performing dance teaching or the like. Based on the state information feature set, constructing a first feature description vector of the first state information, wherein the greater the vector similarity between the first feature description vector and the second feature description vector is, the more suitable the corresponding student learns the state abnormality detection rule set to execute; for example: when the teacher speaks, the abnormal detection rule set of the learning state of the student corresponding to the second feature description vector with the maximum vector similarity comprises the steps of detecting whether the student looks for demonstration, detecting whether the student does not learn to act, and the like. A student learning state abnormality detection template is generated based on the student learning state abnormality detection rule set.
According to the embodiment of the invention, the only state and the non-only state of the teacher are considered, the generation of the abnormal detection template of the learning state of the student is respectively carried out, and the applicability of the system is further improved.
In one embodiment, obtaining second status information of a class student of the online education classroom includes:
acquiring second speaking information of the lecture-listening student through a second mobile terminal of the lecture-listening student;
determining second state information based on the second utterance information;
and/or the number of the groups of groups,
acquiring a class-listening image of the class-listening student through the second mobile terminal;
extracting second action information of the lecture-attending student from the lecture-attending image;
and determining second state information based on the second action information.
The working principle and the beneficial effects of the technical scheme are as follows:
"and/or" represents the determination of the second status information of the students in class in two ways: first, determining based on student speech; for example: the students read the text content, and state states of the students are read text and the like. Second, determining based on student actions; for example: the student makes leg lifting actions, and states of the student are illustrated as leg lifting and the like; also for example: when the student makes an expression action of laughing, the student is in a laughing state.
According to the embodiment of the invention, the second state information of the students in class is determined in two ways, so that the applicability of the system is improved.
In one embodiment, the student learning state detection method applied to online education further comprises:
acquiring a class listening record of the class listening student;
dividing the lecture-attending students into important students and non-important students based on the lecture-attending record;
and carrying out adaptive allocation of detection resources for detecting abnormal learning states of the students on the important students and the non-important students.
The working principle and the beneficial effects of the technical scheme are as follows:
normally, the students in the class have different classes, some students can easily have inattention, and other students cannot. If each student detects at all times, the allocation of detection resources may be unreasonable. Therefore, based on the lecture notes of the lecture students, the lecture students are divided into important students and non-important students, and then adaptive allocation of detection resources is performed.
According to the embodiment of the invention, students in class are subjected to important and non-important division, and then the adaptive allocation of detection resources for abnormal detection of the learning state of the students is performed, so that the allocation rationality of the detection resources is improved.
In one embodiment, dividing the lecture student into accent students based on the lecture notes includes:
extracting abnormal learning state records generated in the history of the students in class from the class-listening records;
determining a learning state anomaly frequency of the lecture-attending student based on the learning state anomaly record;
when the abnormal frequency of the learning state is greater than or equal to a preset abnormal frequency threshold of the learning state, taking the corresponding students on class as key students;
and/or the number of the groups of groups,
acquiring a class-answering serious state upper limit prediction basis of the class-answering students;
inputting the class carefully state upper limit prediction into a preset class carefully state upper limit prediction model to determine the class carefully state upper limit;
extracting a first continuous class-listening situation within a latest preset time range of the class-listening students from the class-listening record;
determining, based on the first continuous lecture-attending situation, whether the lecture-attending student reaches the lecture-attending serious state upper limit;
and when yes, taking the students corresponding to the class as important students.
The working principle and the beneficial effects of the technical scheme are as follows:
there are two ways in which the "and/or" representation divides the students in class into important students: firstly, determining abnormal frequency of learning states of students in class based on the record of learning in class, wherein the abnormal frequency is too high, which indicates that the history of the students is poor, the possibility of inattention of the learning states is high, and the abnormal frequency is used as a key student; the students in class can record the record of class when they have abnormal learning state, which is not focused on the expressions in class and do not get low head/countersink. Secondly, determining whether the students reach the upper limit of the serious state of the class based on the class-listening record, if so, indicating that the students have higher possibility of being unconscious in the learning state after the students, and taking the students as important students; the method comprises the steps of determining a class carefully state upper limit, inputting a class carefully state upper limit prediction basis into a class carefully state upper limit prediction model, wherein the class carefully state upper limit prediction model is an artificial intelligent model which is obtained by training a neural network model to be converged by utilizing a large number of logic records of manual class carefully state upper limit prediction based on the class carefully state upper limit prediction basis, and can replace manual class carefully state upper limit prediction based on the class carefully state upper limit prediction basis; the logical record may be, for example: the upper limit prediction of the class-taking serious state is based on the fact that the student frequently does not pay attention to expressions after the historic continuous class-taking total duration reaches 30 minutes, 33 minutes and the like, and the upper limit of the class-taking serious state is determined to be the class-taking serious state and the upper limit of the class-taking total duration is 30 minutes; the first continuous lecture listening situation includes: class time, class type (dance class, math class, etc.), follow-up action type, follow-up time, etc.
According to the embodiment of the invention, two ways are introduced to divide the class-answering students into important students, so that the comprehensiveness and rationality of the important student division are improved, particularly, the second way, when the students continuously answer classes for a long time, the upper limit of the class-answering serious state exists, whether the students reach the upper limit of the class-answering serious state or not is judged based on the continuous class-answering condition of the students, if so, the students are taken as the important students, and the accuracy and the applicability of the important student division are improved.
In one embodiment, obtaining the class carefully state upper limit prediction basis of the class student includes:
acquiring the recording time of the learning state abnormal record;
based on the recording time, the learning state abnormality is recorded and unfolded on a preset time axis;
retrieving a target learning state abnormal record meeting a preset first retrieval condition from the time axis;
extracting a second continuous class-listening situation in the time range before the recording time of the target learning state abnormal record from the class-listening record, and taking the second continuous class-listening situation as a class-listening serious state upper limit prediction basis;
wherein the first search condition includes: the total number of the abnormal learning state records with the abnormal recording types of the preset types in the preset time distance before and after the abnormal learning state records on the time axis is larger than or equal to a preset number threshold;
and/or the number of the groups of groups,
acquiring student information of the students in class;
generating a template based on preset search conditions, and generating a second search condition according to the student information;
and retrieving the upper limit of other class-listening serious states meeting the second retrieval condition from a preset class-listening serious state upper limit collection library, and taking the upper limit as a class-listening serious state upper limit prediction basis.
The working principle and the beneficial effects of the technical scheme are as follows:
the "and/or" means that there are two ways of obtaining the upper limit prediction basis of the class carefully state of the students who are attending the class: first, based on the continuous lecture situation determination before the lecture students have no concentration in their own history; the learning state abnormality is recorded on a time axis, recording time and time points on the time axis are set in one-to-one correspondence, a first search condition is set, and the preset type is an abnormality recording type representing fatigue, small opening difference and the like of students, for example: and when the learning state abnormal records of the preset type are more in the time distance before and after the learning state abnormal records, the condition that the students are not attentive is indicated, and the previous second continuous learning condition is extracted as the learning serious state upper limit prediction basis. Second, based on the upper limit of the class carefully state of other students; student information including grade information, age information, sex information, good subject information, historical subject performance information, and the like, and generating a second search condition from the student information based on the search condition generation template: the grade of the search student is x (same as the class student), the age of the search student is xx (same as the class student), the sex of the search student is x (same as the class student), the similarity of the good subject information of the search student and the good subject information of the class student is more than or equal to 90%, and the similarity of the historical subject information of the search student and the historical subject information of the class student is more than or equal to 85%; the preset class-listening serious state upper limit collection library has class-listening serious state upper limits of different students, and the sources are as follows: 1. the upper limit of the class carefully-attending state of the other class-attending students is predicted, and 2 is given by relevant specialists who study the class of the students.
According to the method, the upper limit prediction basis of the class listening state of students is obtained in two ways, the comprehensiveness of the upper limit prediction basis of the class listening state is improved, the comprehensiveness of the upper limit prediction is indirectly improved, particularly in the second obtaining mode, the upper limit of other class listening state searched needs to meet the second search condition, if the upper limit of the class listening state does not meet the second search condition, the value of the upper limit prediction basis of the class listening state is low, and the accuracy of the prediction basis selection is improved.
In one embodiment, the adaptive allocation of detection resources for detecting abnormal learning state of students to the important students and the non-important students includes:
respectively counting the total number of the first students of the important students and the total number of the second students of the non-important students;
calculating a number ratio of the first student total to the second student total;
determining a detection resource allocation strategy corresponding to the number ratio from a preset detection resource allocation strategy library;
and respectively distributing the detection resources to the key students and the non-key students based on the detection resource distribution strategy.
The working principle and the beneficial effects of the technical scheme are as follows:
when the proper detection resource allocation is carried out, the detection resource allocation strategy is determined from the detection resource allocation strategy library based on the number ratio of important students to non-important students, and the detection resource allocation strategy is executed, so that the larger the number ratio is, the more students needing to be subjected to the student learning state detection are indicated, and the more important detection resources are allocated to each important student by the detection resource allocation strategy. The detection resources are detection frequencies, and the more the allocated detection resources are, the higher the frequency of detecting the learning state of the students is.
According to the embodiment of the invention, the detection resource allocation strategy library is introduced, the detection resource allocation strategy is determined and executed based on the number ratio library of important students and non-important students, and the rationality and allocation efficiency of carrying out suitable detection resource allocation on the important students and the non-important students are improved.
The embodiment of the invention provides a student learning state detection system applied to online education, as shown in fig. 2, comprising:
the teaching teacher state information acquisition module 1 is used for acquiring first state information of a teaching teacher in an online education classroom when the online education classroom is in class;
a student learning state abnormality detection template generation module 2, configured to generate a student learning state abnormality detection template based on the first state information and a preset student learning state abnormality detection template generation library;
a class student status information acquisition module 3, configured to acquire second status information of a class student in the online education classroom;
and the student learning state abnormality detection module 4 is used for detecting the student learning state abnormality of the lesson-listening student according to the second state information based on the student learning state abnormality detection template.
In one embodiment, the instruction teacher status information obtaining module 1 obtains first status information of an instruction teacher in the online education classroom, and performs the following operations:
pushing a preset teaching teacher state selection table to a first mobile terminal of the teaching teacher;
acquiring a teaching teacher state selected by the teaching teacher from the teaching teacher state selection table;
determining first state information based on the teaching teacher state;
and/or the number of the groups of groups,
acquiring first speaking information of the teaching teacher through the first mobile terminal;
determining first state information based on the first announcement information;
and/or the number of the groups of groups,
acquiring a lesson image of the teaching teacher through the first mobile terminal;
extracting first action information of the teaching teacher from the lesson-taking image;
first state information is determined based on the first action information.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. A student learning state detection method applied to online education, comprising:
when an online education classroom is opened, acquiring first state information of a teaching teacher in the online education classroom;
generating a student learning state abnormality detection template based on the first state information and a preset student learning state abnormality detection template generation library;
acquiring second state information of a class student in the online education classroom;
and based on the student learning state abnormality detection template, carrying out student learning state abnormality detection on the lesson-listening students according to the second state information.
2. The method for detecting a learning state of a student applied to an online education as claimed in claim 1, wherein acquiring first state information of a teaching teacher in the online education classroom comprises:
pushing a preset teaching teacher state selection table to a first mobile terminal of the teaching teacher;
acquiring a teaching teacher state selected by the teaching teacher from the teaching teacher state selection table;
determining first state information based on the teaching teacher state;
and/or the number of the groups of groups,
acquiring first speaking information of the teaching teacher through the first mobile terminal;
determining first state information based on the first announcement information;
and/or the number of the groups of groups,
acquiring a lesson image of the teaching teacher through the first mobile terminal;
extracting first action information of the teaching teacher from the lesson-taking image;
first state information is determined based on the first action information.
3. The method for detecting the learning state of a student applied to online education as claimed in claim 1, wherein generating the learning state abnormality detection template of the student based on the first state information and a preset learning state abnormality detection template generation library comprises:
analyzing the information category number of the first state information;
when the information category number is unique, determining a student learning state abnormality detection rule corresponding to the first state information from the student learning state abnormality detection template generation library;
generating a student learning state abnormality detection template based on the student learning state abnormality detection rule;
when the information variety number is not the same, analyzing a state information feature set of the first state information based on a preset feature analysis template;
constructing a first feature description vector of the first state information based on the state information feature set;
extracting a plurality of groups of second feature description vectors and a student learning state abnormality detection rule set which are in one-to-one correspondence from the student learning state abnormality detection template generation library;
calculating the vector similarity between the first feature description vector and any one of the second feature description vectors;
and generating a student learning state abnormality detection template based on the student learning state abnormality detection rule set corresponding to the second feature description vector with the maximum vector similarity.
4. The method for detecting a learning state of a student applied to online education as claimed in claim 1, wherein acquiring second state information of a class student in the online education classroom comprises:
acquiring second speaking information of the lecture-listening student through a second mobile terminal of the lecture-listening student;
determining second state information based on the second utterance information;
and/or the number of the groups of groups,
acquiring a class-listening image of the class-listening student through the second mobile terminal;
extracting second action information of the lecture-attending student from the lecture-attending image;
and determining second state information based on the second action information.
5. The method for detecting the learning state of a student for online education as claimed in claim 1, further comprising:
acquiring a class listening record of the class listening student;
dividing the lecture-attending students into important students and non-important students based on the lecture-attending record;
and carrying out adaptive allocation of detection resources for detecting abnormal learning states of the students on the important students and the non-important students.
6. The method for detecting a learning state of a student applied to online education of claim 5, wherein dividing the lecture-attending student into key students based on the lecture-attending record, comprising:
extracting abnormal learning state records generated in the history of the students in class from the class-listening records;
determining a learning state anomaly frequency of the lecture-attending student based on the learning state anomaly record;
when the abnormal frequency of the learning state is greater than or equal to a preset abnormal frequency threshold of the learning state, taking the corresponding students on class as key students;
and/or the number of the groups of groups,
acquiring a class-answering serious state upper limit prediction basis of the class-answering students;
inputting the class carefully state upper limit prediction into a preset class carefully state upper limit prediction model to determine the class carefully state upper limit;
extracting a first continuous class-listening situation within a latest preset time range of the class-listening students from the class-listening record;
determining, based on the first continuous lecture-attending situation, whether the lecture-attending student reaches the lecture-attending serious state upper limit;
and when yes, taking the students corresponding to the class as important students.
7. The method for detecting a learning state of a student for online education as claimed in claim 6, wherein obtaining a class carefully-based upper limit prediction basis of the class-based student comprises:
acquiring the recording time of the learning state abnormal record;
based on the recording time, the learning state abnormality is recorded and unfolded on a preset time axis;
retrieving a target learning state abnormal record meeting a preset first retrieval condition from the time axis;
extracting a second continuous class-listening situation in the time range before the recording time of the target learning state abnormal record from the class-listening record, and taking the second continuous class-listening situation as a class-listening serious state upper limit prediction basis;
wherein the first search condition includes: the total number of the abnormal learning state records with the abnormal recording types of the preset types in the preset time distance before and after the abnormal learning state records on the time axis is larger than or equal to a preset number threshold;
and/or the number of the groups of groups,
acquiring student information of the students in class;
generating a template based on preset search conditions, and generating a second search condition according to the student information;
and retrieving the upper limit of other class-listening serious states meeting the second retrieval condition from a preset class-listening serious state upper limit collection library, and taking the upper limit as a class-listening serious state upper limit prediction basis.
8. The method for detecting the learning state of a student applied to online education as claimed in claim 5, wherein the adaptive allocation of detection resources for detecting abnormality of the learning state of the student to the important student and the non-important student comprises:
respectively counting the total number of the first students of the important students and the total number of the second students of the non-important students;
calculating a number ratio of the first student total to the second student total;
determining a detection resource allocation strategy corresponding to the number ratio from a preset detection resource allocation strategy library;
and respectively distributing the detection resources to the key students and the non-key students based on the detection resource distribution strategy.
9. A student learning state detection system for online education, comprising:
the teaching teacher state information acquisition module is used for acquiring first state information of a teaching teacher in the online education classroom when the online education classroom is started;
the student learning state abnormality detection template generation module is used for generating a student learning state abnormality detection template based on the first state information and a preset student learning state abnormality detection template generation library;
the class-listening student status information acquisition module is used for acquiring second status information of class-listening students in the online education classroom;
and the student learning state abnormality detection module is used for detecting the student learning state abnormality of the lesson-listening student according to the second state information based on the student learning state abnormality detection template.
10. The student learning state detection system for online education as claimed in claim 9, wherein the teaching teacher state information acquisition module acquires first state information of a teaching teacher in the online education classroom, performs the following operations:
pushing a preset teaching teacher state selection table to a first mobile terminal of the teaching teacher;
acquiring a teaching teacher state selected by the teaching teacher from the teaching teacher state selection table;
determining first state information based on the teaching teacher state;
and/or the number of the groups of groups,
acquiring first speaking information of the teaching teacher through the first mobile terminal;
determining first state information based on the first announcement information;
and/or the number of the groups of groups,
acquiring a lesson image of the teaching teacher through the first mobile terminal;
extracting first action information of the teaching teacher from the lesson-taking image;
first state information is determined based on the first action information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310023798.0A CN116259004B (en) | 2023-01-09 | 2023-01-09 | Student learning state detection method and system applied to online education |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310023798.0A CN116259004B (en) | 2023-01-09 | 2023-01-09 | Student learning state detection method and system applied to online education |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116259004A true CN116259004A (en) | 2023-06-13 |
| CN116259004B CN116259004B (en) | 2023-08-15 |
Family
ID=86683629
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310023798.0A Active CN116259004B (en) | 2023-01-09 | 2023-01-09 | Student learning state detection method and system applied to online education |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116259004B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116596719A (en) * | 2023-07-18 | 2023-08-15 | 江西科技学院 | Computer room computer teaching quality management system and method |
| CN117499748A (en) * | 2023-11-02 | 2024-02-02 | 江苏濠汉信息技术有限公司 | Classroom teaching interaction method and system based on edge calculation |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100120012A1 (en) * | 2008-11-13 | 2010-05-13 | Park Duck-Yong | System for providing online learning contents |
| WO2015061788A1 (en) * | 2013-10-25 | 2015-04-30 | Kadenze, Inc. | Self organizing maps (soms) for organizing, categorizing, browsing and/or grading large collections of assignments for massive online education systems |
| CN109697682A (en) * | 2019-01-21 | 2019-04-30 | 武汉迈辽网络科技有限公司 | A kind of on-line education system based on mobile intelligent terminal |
| WO2019089482A1 (en) * | 2017-11-06 | 2019-05-09 | Microsoft Technology Licensing, Llc | Electronic document content extraction and document type determination |
| US10445885B1 (en) * | 2015-10-01 | 2019-10-15 | Intellivision Technologies Corp | Methods and systems for tracking objects in videos and images using a cost matrix |
| CN111598750A (en) * | 2020-05-12 | 2020-08-28 | 湖北美和易思教育科技有限公司 | Student online learning state evaluation method and system based on rumination ratio algorithm |
| CN113988572A (en) * | 2021-10-22 | 2022-01-28 | 吴壮潮 | Child online education and teaching system of big data cloud platform |
| CN114187640A (en) * | 2021-12-16 | 2022-03-15 | 湖北美和易思教育科技有限公司 | Learning situation observation method, system, equipment and medium based on online classroom |
| KR102405464B1 (en) * | 2021-09-23 | 2022-06-07 | 김재근 | Method and apparatus for providing non-face-to-face online education service |
| CN114724229A (en) * | 2022-05-23 | 2022-07-08 | 北京英华在线科技有限公司 | Learning state detection system and method for online education platform |
| CN114743274A (en) * | 2022-06-09 | 2022-07-12 | 深圳市纬亚森科技有限公司 | Multimedia remote teaching management system and method based on Internet of things |
| CN114760442A (en) * | 2022-04-06 | 2022-07-15 | 英才(广州)在线教育科技有限公司 | Monitoring system for online education management |
| CN114936952A (en) * | 2022-05-06 | 2022-08-23 | 深圳市微酷智能科技有限公司 | Digital education internet learning system |
| US20220319181A1 (en) * | 2021-04-06 | 2022-10-06 | AspectO Technologies Pvt Ltd | Artificial intelligence (ai)-based system and method for managing education of students in real-time |
| CN115205764A (en) * | 2022-09-15 | 2022-10-18 | 深圳市企鹅网络科技有限公司 | Online learning concentration monitoring method, system and medium based on machine vision |
| CN115511670A (en) * | 2022-08-04 | 2022-12-23 | 河南工业贸易职业学院 | Online education method and online education platform |
-
2023
- 2023-01-09 CN CN202310023798.0A patent/CN116259004B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100120012A1 (en) * | 2008-11-13 | 2010-05-13 | Park Duck-Yong | System for providing online learning contents |
| WO2015061788A1 (en) * | 2013-10-25 | 2015-04-30 | Kadenze, Inc. | Self organizing maps (soms) for organizing, categorizing, browsing and/or grading large collections of assignments for massive online education systems |
| US10445885B1 (en) * | 2015-10-01 | 2019-10-15 | Intellivision Technologies Corp | Methods and systems for tracking objects in videos and images using a cost matrix |
| WO2019089482A1 (en) * | 2017-11-06 | 2019-05-09 | Microsoft Technology Licensing, Llc | Electronic document content extraction and document type determination |
| CN109697682A (en) * | 2019-01-21 | 2019-04-30 | 武汉迈辽网络科技有限公司 | A kind of on-line education system based on mobile intelligent terminal |
| CN111598750A (en) * | 2020-05-12 | 2020-08-28 | 湖北美和易思教育科技有限公司 | Student online learning state evaluation method and system based on rumination ratio algorithm |
| US20220319181A1 (en) * | 2021-04-06 | 2022-10-06 | AspectO Technologies Pvt Ltd | Artificial intelligence (ai)-based system and method for managing education of students in real-time |
| KR102405464B1 (en) * | 2021-09-23 | 2022-06-07 | 김재근 | Method and apparatus for providing non-face-to-face online education service |
| CN113988572A (en) * | 2021-10-22 | 2022-01-28 | 吴壮潮 | Child online education and teaching system of big data cloud platform |
| CN114187640A (en) * | 2021-12-16 | 2022-03-15 | 湖北美和易思教育科技有限公司 | Learning situation observation method, system, equipment and medium based on online classroom |
| CN114760442A (en) * | 2022-04-06 | 2022-07-15 | 英才(广州)在线教育科技有限公司 | Monitoring system for online education management |
| CN114936952A (en) * | 2022-05-06 | 2022-08-23 | 深圳市微酷智能科技有限公司 | Digital education internet learning system |
| CN114724229A (en) * | 2022-05-23 | 2022-07-08 | 北京英华在线科技有限公司 | Learning state detection system and method for online education platform |
| CN114743274A (en) * | 2022-06-09 | 2022-07-12 | 深圳市纬亚森科技有限公司 | Multimedia remote teaching management system and method based on Internet of things |
| CN115511670A (en) * | 2022-08-04 | 2022-12-23 | 河南工业贸易职业学院 | Online education method and online education platform |
| CN115205764A (en) * | 2022-09-15 | 2022-10-18 | 深圳市企鹅网络科技有限公司 | Online learning concentration monitoring method, system and medium based on machine vision |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116596719A (en) * | 2023-07-18 | 2023-08-15 | 江西科技学院 | Computer room computer teaching quality management system and method |
| CN116596719B (en) * | 2023-07-18 | 2023-09-19 | 江西科技学院 | Computer room computer teaching quality management system and method |
| CN117499748A (en) * | 2023-11-02 | 2024-02-02 | 江苏濠汉信息技术有限公司 | Classroom teaching interaction method and system based on edge calculation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116259004B (en) | 2023-08-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Huang et al. | Trends, research issues and applications of artificial intelligence in language education | |
| CN116259004B (en) | Student learning state detection method and system applied to online education | |
| US11721230B2 (en) | Personalized learning system and method for the automated generation of structured learning assets based on user data | |
| US8682241B2 (en) | Method and system for improving the quality of teaching through analysis using a virtual teaching device | |
| Sorour et al. | Comment data mining to estimate student performance considering consecutive lessons | |
| Stewart et al. | Multimodal modeling of collaborative problem-solving facets in triads | |
| Pugh et al. | Say What? Automatic Modeling of Collaborative Problem Solving Skills from Student Speech in the Wild. | |
| Gao | Research and implementation of intelligent evaluation system of teaching quality in universities based on artificial intelligence neural network model | |
| Raleiras et al. | Automatic learning styles prediction: A survey of the State-of-the-Art (2006–2021) | |
| CN110189238A (en) | Method, apparatus, medium and the electronic equipment of assisted learning | |
| Kour et al. | Analysis of student performance using Machine learning Algorithms | |
| Shan et al. | Research on classroom online teaching model of “learning” wisdom music on wireless network under the background of artificial intelligence | |
| Firoozi et al. | Using active learning methods to strategically select essays for automated scoring | |
| CN117037552A (en) | Intelligent classroom interaction system and method | |
| CN111563697A (en) | Online classroom student emotion analysis method and system | |
| Tan et al. | Does informativeness matter? Active learning for educational dialogue act classification | |
| US10453354B2 (en) | Automatically generated flash cards | |
| Mosharraf et al. | Improving student success rates through a semi-personalized feedback system | |
| Cohen et al. | Temporal Data Mining for Educational Applications. | |
| KR20190112499A (en) | Server with built-in learner-tailored coding cloud training platform, learner-tailored coding education system and its methods | |
| Nguyen et al. | Using feed-forward backprop, perceptron, and self-organizing algorithms to predict students’ online behavior | |
| Liu et al. | Educational Development Technology in Artificial Intelligence Era | |
| Yun et al. | Self-paced graph memory for learner GPA prediction and it’s application in learner multiple evaluation | |
| Zhu et al. | Fidgety Speech Emotion Recognition for Learning Process Modeling | |
| Zheng et al. | Automated Multi-Mode Teaching Behavior Analysis: A Pipeline Based Event Segmentation and Description |
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 | ||
| GR01 | Patent grant |