CN114819574A - Student learning habit analysis system based on big data - Google Patents
Student learning habit analysis system based on big data Download PDFInfo
- Publication number
- CN114819574A CN114819574A CN202210402263.XA CN202210402263A CN114819574A CN 114819574 A CN114819574 A CN 114819574A CN 202210402263 A CN202210402263 A CN 202210402263A CN 114819574 A CN114819574 A CN 114819574A
- Authority
- CN
- China
- Prior art keywords
- learning
- teaching
- course
- deviation
- student
- 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.)
- Withdrawn
Links
- 230000006399 behavior Effects 0.000 claims abstract description 107
- 238000011156 evaluation Methods 0.000 claims abstract description 22
- 238000001514 detection method Methods 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims description 12
- 230000003139 buffering effect Effects 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 3
- 230000002411 adverse Effects 0.000 claims 1
- 238000011161 development Methods 0.000 abstract description 5
- 239000012141 concentrate Substances 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Educational Technology (AREA)
- Computer Security & Cryptography (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Computer Hardware Design (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
Abstract
The invention discloses a student learning habit analysis system based on big data, which relates to the technical field of online teaching and comprises a behavior analysis module, a behavior evaluation module, a course auxiliary module and a teaching analysis module; the behavior analysis module is used for identifying bad learning behaviors through a learning behavior detection model; the behavior evaluation module is used for analyzing the learning deviation coefficient of the student according to the recognition result and reminding the student of attentive learning in time; the teaching analysis module is used for acquiring learning deviation coefficients of all students in real time and performing teaching deviation analysis; if the teaching deviation value is larger than or equal to the teaching threshold value, reminding a teacher of changing the teaching content or the teaching mode of the current teaching course so as to improve the teaching quality and efficiency; the course auxiliary module is used for analyzing course preferences of the students according to the course learning records, judging whether extraclass tutoring needs to be carried out on the students or not, providing correct guidance for the healthy development of the students and avoiding partial subjects of the students.
Description
Technical Field
The invention relates to the technical field of online teaching, in particular to a student learning habit analysis system based on big data.
Background
Students are the main subjects of teaching activities, and classroom teaching is the most important ー links in the learning process of students. How the student plays the main role in the teaching activities directly influences the teaching quality. Monitoring the learning behavior of the student is the most effective and direct method for analyzing the learning process of the student. Therefore, the study status of the students is researched and analyzed by collecting and recording the study behaviors of the students, and the study status is specifically solved, so that the study status is the key for improving talent quality.
In the prior art, the learning behavior prediction of students is a relatively complex matter, and the main reasons are that the acquisition of student behavior data is less, an alarm data model cannot be established, and the acquired data is also not abundant, standard and imperfect; furthermore, the behavior of the students is prejudged and intervened in advance, so that correct guidance is provided for the healthy development of the students, and the purpose of avoiding partial discipline is achieved; meanwhile, an effective evaluation on the teaching quality of a teacher according to the learning behaviors of students is not formed at present; based on the defects, the invention provides a student learning habit analysis system based on big data.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a student learning habit analysis system based on big data.
In order to achieve the above object, an embodiment according to a first aspect of the present invention provides a big data based student learning habit analysis system, which includes an online monitoring module, a behavior evaluation module, a course auxiliary module, and a teaching analysis module;
the online monitoring module is used for collecting video data of a student in the learning process through a camera of a network control student end after the authentication is successful, and sending the collected video data to the behavior analysis module; the behavior analysis module is used for acquiring images in the video data frame by frame, inputting the images into the learning behavior detection model for identifying bad learning behaviors and acquiring identification results;
the behavior evaluation module is used for acquiring the recognition result of bad learning behaviors and analyzing the learning deviation coefficient of students, and if the learning deviation coefficient XP is larger than or equal to the deviation threshold, a behavior reminding signal is generated;
the behavior evaluation module is further used for fusing the learning deviation coefficient XP with the corresponding course to form a course learning record and storing the course learning record with a timestamp to the cloud platform; the course auxiliary module is used for analyzing the course preference of the student according to the course learning record with the timestamp stored in the cloud platform and judging whether the student needs to be assisted extracurricularly;
the teaching analysis module is connected with the behavior evaluation module and is used for acquiring learning deviation coefficients of all students in real time and performing teaching deviation analysis; if the teaching deviation value JP is larger than or equal to the teaching threshold value, the teaching deviation value JP indicates that the attraction degree of the current classroom teaching to students is low, and teaching reminding information is generated to a teacher end; and reminding the teacher to change the teaching content or teaching mode of the current teaching course.
Further, the specific analysis steps of the behavior evaluation module are as follows:
in a complete classroom teaching, acquiring all bad learning behavior recognition results of students;
counting the occurrence frequency of the bad learning behaviors as C1, and accumulating the duration time of each bad learning behavior to obtain a total behavior duration ZT; calculating the time difference between the starting time of the first bad learning behavior and the ending time of the last bad learning behavior to obtain a deviation duration PT;
learning deviation coefficients XP of corresponding students are calculated by using a formula XP (C1 × a1+ ZT × a2)/(PT × a3), wherein a1, a2 and a3 are all coefficient factors.
Further, the specific analysis steps of the course auxiliary module are as follows:
acquiring all course learning records of the students in a preset time period according to the time stamp;
aiming at the same course, acquiring a learning deviation coefficient of each classroom teaching of the student and marking the learning deviation coefficient as KPm, and if the learning deviation coefficient KPm is smaller than a preset first deviation coefficient, feeding back a preference signal to a course auxiliary module;
the number of occurrences of the statistical preference signal is P1; intercepting a time period between adjacent preference signals as a preference buffering period; counting the number of classroom teaching times in each preference buffering period as buffering frequency Li; comparing the buffered frequency Li to a frequency threshold;
counting the number of times that Li is greater than a frequency threshold as P2, and when Li is greater than the frequency threshold, obtaining the difference between Li and the frequency threshold and summing to obtain an over-slow value CH 1; calculating the super-slow coefficient CS by using a formula of P2 Xg 1+ CH1 Xg 2, wherein g1 and g2 are coefficient factors;
using formulas
Calculating to obtain a student preference value KP for the course, wherein g3 and g4 are coefficient factors; if the KP is less than the preference threshold, indicating that the interest of the student on the course is low, and generating a course auxiliary signal; the course auxiliary module is used for feeding back the course auxiliary signal and the corresponding course to the controller; and after receiving the course auxiliary signal, the controller arranges the teacher to give out-of-class guidance to the students for the course.
Further, the specific analysis steps of the teaching analysis module are as follows:
in a complete classroom teaching, learning deviation coefficients of all students are obtained and marked as XPi, and the learning deviation coefficients XPi are compared with a deviation threshold value; counting the number of times that XPi is larger than or equal to the deviation threshold value as C2; when the XPi is larger than or equal to the deviation threshold, obtaining the difference value between the XPi and the deviation threshold and summing to obtain a deviation excess value PZ;
the teaching deviation value JP corresponding to the teacher is calculated by using the formula JP of C2 × a4+ PZ × a5, wherein a4 and a5 are coefficient factors.
Furthermore, the behavior evaluation module is used for feeding back the behavior reminding signal to the controller, and the controller sends learning reminding information to the student end after receiving the behavior reminding signal to remind the student of paying attention to learning.
Further, the bad learning behaviors include head support, eastern western views, backrest of the chair, pen rotation, lying down on the table and leg shaking; the recognition result carries a start time and an end time corresponding to the bad learning behavior.
Further, the learning behavior detection model obtaining method comprises the following steps:
taking bad learning behavior pictures obtained from a camera and a network as a parameter training set, and establishing an error reverse propagation neural network model;
the error reverse propagation neural network model at least comprises a hidden layer; training, testing and checking the error reverse propagation neural network through a training set, a testing set and a checking set;
and marking the trained error reverse propagation neural network as a learning behavior detection model.
Furthermore, the teacher end and the student end are respectively connected with an authentication module, and the authentication module is used for verifying login requests of the teacher end and the student end; the verification method is face identification or fingerprint identification.
Compared with the prior art, the invention has the beneficial effects that:
1. the behavior analysis module is used for acquiring images in video data frame by frame, inputting the images into a learning behavior detection model for identifying bad learning behaviors and acquiring an identification result; the behavior evaluation module is used for acquiring the recognition result of bad learning behaviors and analyzing the learning deviation coefficient of the student; in a complete classroom teaching, acquiring all bad learning behavior recognition results of students; calculating to obtain a learning deviation coefficient XP of a corresponding student according to the occurrence frequency and duration of the bad learning behaviors, and generating a behavior reminding signal if XP is larger than or equal to a deviation threshold; the controller sends corresponding learning reminding information to the student end after receiving the behavior reminding signal to remind the student to concentrate on learning;
2. in a complete classroom teaching, the teaching analysis module is used for acquiring learning deviation coefficients of all students in real time and performing teaching deviation analysis; acquiring learning deviation coefficients of all students and marking the learning deviation coefficients as XPi, and comparing the learning deviation coefficients XPi with a deviation threshold value; combining the times C2 that XPi is greater than the deviation threshold value and the deviation excess value PZ, calculating to obtain a teaching deviation value JP corresponding to a teacher, if the JP is greater than or equal to the teaching threshold value, indicating that the attraction degree of the current classroom teaching to students is low, generating teaching reminding information to a teacher end, and reminding the teacher to change the teaching content or teaching mode of the current teaching course so as to improve the teaching quality and efficiency;
3. the course auxiliary module is used for analyzing the course preference of the students according to the course learning record with the timestamp stored in the cloud platform, and acquiring the learning deviation coefficient of each class teaching of the students and marking the coefficient as KPm aiming at the same course; if the learning deviation coefficient KPm is smaller than a preset first deviation coefficient, feeding back a preference signal to the course auxiliary module; calculating to obtain a preference value KP of the student to the course according to the occurrence condition of the preference signal, if the KP is less than a preference threshold value, indicating that the student has low interest in the course, and generating a course auxiliary signal; after receiving the course auxiliary signal, the controller arranges a teacher to give out-of-class guidance to the students for the course; the intervention is performed in advance, so that correct guidance is provided for the healthy development of students, and the partial disciplines of the students are avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a system block diagram of a big data-based student learning habit analysis system according to the invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
As shown in fig. 1, a big data-based student learning habit analysis system comprises a teacher end, a student end, an authentication module, an online monitoring module, a behavior analysis module, a behavior evaluation module, a controller, a cloud platform, a course auxiliary module and a teaching analysis module;
the teacher end and the student end are respectively connected with the authentication module, and the authentication module is used for verifying login requests of the teacher end and the student end; the verification mode is face identification or fingerprint identification;
the online monitoring module is used for collecting video data of a student in the learning process through a camera of the network control student end after the authentication is successful, and sending the collected video data to the behavior analysis module; the behavior analysis module is used for acquiring images in the video data frame by frame, inputting the images into the learning behavior detection model for identifying bad learning behaviors and acquiring identification results; the bad learning behaviors comprise head supporting, eastern looking, backrest, pen rotating, table lying, leg shaking and the like; the identification result carries the starting time and the ending time of the corresponding bad learning behavior;
the learning behavior detection model obtaining method comprises the following steps:
taking bad learning behavior pictures obtained from a camera and a network as a parameter training set, and establishing an error reverse propagation neural network model; the error reverse propagation neural network model at least comprises a hidden layer;
training, testing and checking the error reverse propagation neural network through a training set, a testing set and a checking set, and marking the trained error reverse propagation neural network as a learning behavior detection model;
the behavior evaluation module is in communication connection with the behavior analysis module and is used for acquiring recognition results of bad learning behaviors and analyzing learning deviation coefficients of students, and the specific analysis steps are as follows:
in a complete classroom teaching, acquiring all bad learning behavior recognition results of students;
counting the occurrence frequency of the bad learning behaviors as C1, and accumulating the duration time of each bad learning behavior to obtain a total behavior duration ZT;
calculating the time difference between the starting time of the first bad learning behavior and the ending time of the last bad learning behavior to obtain a deviation duration PT; calculating a learning deviation coefficient XP of a corresponding student by using a formula XP (C1 × a1+ ZT × a2)/(PT × a3), wherein a1, a2 and a3 are coefficient factors;
comparing the learning deviation coefficient XP with a deviation threshold value; if XP is greater than or equal to the deviation threshold value, generating a behavior reminding signal; the behavior evaluation module is used for feeding back the behavior reminding signal to the controller; the controller sends corresponding learning reminding information to the student end after receiving the behavior reminding signal to remind the student to concentrate on learning;
the behavior evaluation module is further used for fusing the learning deviation coefficient XP with the corresponding course to form a course learning record and storing the course learning record with a timestamp to the cloud platform;
the course auxiliary module is connected with the cloud platform and used for analyzing course preferences of the students according to the course learning records with timestamps stored in the cloud platform and judging whether extraclass tutoring needs to be carried out on the students or not; the specific analysis steps are as follows:
acquiring all course learning records of the students in a preset time period according to the time stamp;
aiming at the same course, acquiring a learning deviation coefficient of each class teaching of the student and marking the coefficient as KPm, wherein m is 1, …, n; wherein m represents the mth classroom teaching; if the learning deviation coefficient KPm is smaller than a preset first deviation coefficient, feeding back a preference signal to the course auxiliary module;
the number of occurrences of the statistical preference signal is P1; intercepting a time period between adjacent preference signals as a preference buffering period; counting the number of classroom teaching times in each preference buffering time period as buffering frequency Li; comparing the buffered frequency Li to a frequency threshold;
counting the number of times that Li is greater than a frequency threshold value to be P2, and when Li is greater than the frequency threshold value, obtaining the difference between Li and the frequency threshold value and summing the difference to obtain an ultra-slow value CH 1; calculating the super-slow coefficient CS by using a formula of P2 Xg 1+ CH1 Xg 2, wherein g1 and g2 are coefficient factors;
using formulas
Calculating to obtain a student preference value KP for the course, wherein g3 and g4 are coefficient factors; comparing the preference value KP with a preference threshold; if the KP is less than the preference threshold, indicating that the interest of the student on the course is low, and generating a course auxiliary signal;
the course auxiliary module is used for feeding back the course auxiliary signal and the corresponding course to the controller; after receiving the course auxiliary signal, the controller arranges a teacher to give out-of-class guidance to the students for the course; intervention is performed in advance, correct guidance is provided for the healthy development of students, and the partial discipline of the students is avoided;
in this embodiment, the teaching analysis module is connected to the behavior evaluation module, and is configured to obtain learning deviation coefficients of all students in real time and perform teaching deviation analysis; the specific analysis steps are as follows:
in a complete classroom teaching, learning deviation coefficients of all students are obtained and marked as XPi, i is 1, …, n; wherein i represents the ith student;
comparing the learned deviation coefficient XPi with a deviation threshold; counting the number of times that XPi is larger than or equal to the deviation threshold value as C2; when the XPi is larger than or equal to the deviation threshold, obtaining the difference value between the XPi and the deviation threshold and summing to obtain a deviation excess value PZ; calculating a teaching deviation value JP corresponding to the teacher by using a formula of JP (C2 × a4+ PZ × a 5), wherein a4 and a5 are coefficient factors;
comparing the teaching deviation value JP with a teaching threshold value; if JP is larger than or equal to the teaching threshold value, the teaching method indicates that the attraction degree of the current classroom teaching to students is low, teaching reminding information is generated to a teacher end, and the teacher is reminded to change the teaching content or teaching mode of the current teaching course so as to improve the teaching quality and efficiency.
The above formulas are all calculated by removing dimensions and taking numerical values thereof, the formula is a formula which is obtained by acquiring a large amount of data and performing software simulation to obtain the closest real situation, and the preset parameters and the preset threshold value in the formula are set by the technical personnel in the field according to the actual situation or obtained by simulating a large amount of data.
The working principle of the invention is as follows:
when the student learning habit analysis system works, the online monitoring module is used for collecting video data in the learning process of the student through a camera of a network control student end after authentication is successful, and sending the collected video data to the behavior analysis module; the behavior analysis module is used for acquiring images in the video data frame by frame, inputting the images into the learning behavior detection model for identifying bad learning behaviors and acquiring identification results; the behavior evaluation module is used for acquiring the recognition result of the bad learning behavior and analyzing the learning deviation coefficient of the student; in a complete classroom teaching, acquiring all bad learning behavior recognition results of students; calculating to obtain a learning deviation coefficient XP of a corresponding student according to the occurrence frequency and duration of the bad learning behaviors, and generating a behavior reminding signal if XP is larger than or equal to a deviation threshold; the controller sends corresponding learning reminding information to the student end after receiving the behavior reminding signal to remind the student to concentrate on learning;
in a complete classroom teaching, the teaching analysis module is used for acquiring learning deviation coefficients of all students in real time and performing teaching deviation analysis; acquiring learning deviation coefficients of all students and marking the learning deviation coefficients as XPi, and comparing the learning deviation coefficients XPi with a deviation threshold value; combining the times C2 that XPi is greater than the deviation threshold value and the deviation excess value PZ, calculating to obtain a teaching deviation value JP corresponding to a teacher, if the JP is greater than or equal to the teaching threshold value, indicating that the attraction degree of the current classroom teaching to students is low, generating teaching reminding information to a teacher end, and reminding the teacher to change the teaching content or teaching mode of the current teaching course so as to improve the teaching quality and efficiency;
the course auxiliary module is connected with the cloud platform and used for analyzing course preferences of students according to the course learning records with timestamps stored in the cloud platform, and acquiring learning deviation coefficients of each class teaching of the students and marking the learning deviation coefficients as KPm for the same course; if the learning deviation coefficient KPm is smaller than a preset first deviation coefficient, feeding back a preference signal to the course auxiliary module; calculating to obtain a preference value KP of the student to the course according to the occurrence condition of the preference signal, if the KP is less than a preference threshold value, indicating that the student has low interest in the course, and generating a course auxiliary signal; after receiving the course auxiliary signal, the controller arranges a teacher to give out-of-class guidance to the students for the course; the intervention is performed in advance, so that correct guidance is provided for the healthy development of students, and the partial disciplines of the students are avoided.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise forms disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (8)
1. A student learning habit analysis system based on big data is characterized by comprising a student end, a teacher end, an online monitoring module, a behavior evaluation module, a controller, a course auxiliary module and a teaching analysis module;
the online monitoring module is used for collecting video data of a student in the learning process through a camera of a network control student end after the authentication is successful, and sending the collected video data to the behavior analysis module; the behavior analysis module is used for acquiring images in the video data frame by frame, inputting the images into the learning behavior detection model for identifying bad learning behaviors and acquiring identification results;
the behavior evaluation module is used for acquiring the recognition result of bad learning behaviors, analyzing the learning deviation coefficient of the student, and generating a behavior reminding signal if the learning deviation coefficient XP is larger than or equal to the deviation threshold;
the behavior evaluation module is further used for fusing the learning deviation coefficient XP with the corresponding course to form a course learning record and storing the course learning record with a timestamp to the cloud platform; the course auxiliary module is used for analyzing the course preference of the student according to the course learning record with the timestamp stored in the cloud platform and judging whether the student needs to be assisted extracurricularly;
the teaching analysis module is connected with the behavior evaluation module and is used for acquiring learning deviation coefficients of all students in real time and performing teaching deviation analysis; if the teaching deviation value JP is larger than or equal to the teaching threshold value, the teaching deviation value JP indicates that the attraction degree of the current classroom teaching to students is low, and teaching reminding information is generated to a teacher end; and reminding the teacher to change the teaching content or teaching mode of the current teaching course.
2. The big data-based student learning habit analysis system according to claim 1, wherein the behavior evaluation module comprises the following specific analysis steps:
in a complete classroom teaching, acquiring all bad learning behavior recognition results of students;
counting the occurrence frequency of the bad learning behaviors as C1, and accumulating the duration time of each bad learning behavior to obtain a total behavior duration ZT; calculating the time difference between the starting time of the first bad learning behavior and the ending time of the last bad learning behavior to obtain a deviation duration PT;
learning deviation coefficients XP of corresponding students are calculated by using a formula XP (C1 × a1+ ZT × a2)/(PT × a3), wherein a1, a2 and a3 are all coefficient factors.
3. The big data-based student learning habit analysis system according to claim 2, wherein the course assistance module specifically analyzes the steps as follows:
acquiring all course learning records of the students in a preset time period according to the time stamp;
aiming at the same course, acquiring a learning deviation coefficient of each classroom teaching of the student and marking the learning deviation coefficient as KPm, and if the learning deviation coefficient KPm is smaller than a preset first deviation coefficient, feeding back a preference signal to a course auxiliary module;
the number of occurrences of the statistical preference signal is P1; intercepting a time period between adjacent preference signals as a preference buffering period; counting the number of classroom teaching times in each preference buffering time period as buffering frequency Li; comparing the buffered frequency Li to a frequency threshold; counting the number of times that Li is greater than a frequency threshold value to be P2, and when Li is greater than the frequency threshold value, obtaining the difference between Li and the frequency threshold value and summing the difference to obtain an ultra-slow value CH 1; calculating the super-slow coefficient CS by using a formula of P2 Xg 1+ CH1 Xg 2, wherein g1 and g2 are coefficient factors;
using formulas
Calculating to obtain a student preference value KP for the course, wherein g3 and g4 are coefficient factors; if the KP is less than the preference threshold, indicating that the interest of the student on the course is low, and generating a course auxiliary signal; the course auxiliary module is used for feeding back the course auxiliary signal and the corresponding course to the controller; and after receiving the course auxiliary signal, the controller arranges the teacher to give out-of-class guidance to the students for the course.
4. The big data-based student learning habit analysis system according to claim 2, wherein the specific analysis steps of the teaching analysis module are as follows:
in a complete classroom teaching, learning deviation coefficients of all students are obtained and marked as XPi, and the learning deviation coefficients XPi are compared with a deviation threshold value; counting the number of times that XPi is larger than or equal to the deviation threshold value as C2; when the XPi is larger than or equal to the deviation threshold, obtaining the difference value between the XPi and the deviation threshold and summing to obtain a deviation excess value PZ;
the teaching deviation value JP corresponding to the teacher is calculated by using the formula JP of C2 × a4+ PZ × a5, wherein a4 and a5 are coefficient factors.
5. The student learning habit analysis system based on big data as claimed in claim 1, wherein the behavior evaluation module is configured to feed back a behavior reminding signal to the controller, and the controller sends a learning reminding message to the student end after receiving the behavior reminding signal, so as to remind the student of concentrating on learning.
6. The big-data-based student learning habit analysis system according to claim 1, wherein the adverse learning behaviors comprise head stretching, eastern western views, backrest, pen rotating, lying down table and leg shaking; the recognition result carries a start time and an end time corresponding to the bad learning behavior.
7. The big data-based student learning habit analysis system according to claim 1, wherein the learning behavior detection model is obtained by:
taking bad learning behavior pictures obtained from a camera and a network as a parameter training set, and establishing an error reverse propagation neural network model;
the error reverse propagation neural network model at least comprises a hidden layer; training, testing and checking the error reverse propagation neural network through a training set, a testing set and a checking set;
and marking the trained error reverse propagation neural network as a learning behavior detection model.
8. The big-data-based student learning habit analysis system according to claim 1, wherein the teacher end and the student end are respectively connected with an authentication module, and the authentication module is used for verifying login requests of the teacher end and the student end; the verification method is face identification or fingerprint identification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210402263.XA CN114819574A (en) | 2022-04-18 | 2022-04-18 | Student learning habit analysis system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210402263.XA CN114819574A (en) | 2022-04-18 | 2022-04-18 | Student learning habit analysis system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114819574A true CN114819574A (en) | 2022-07-29 |
Family
ID=82536844
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210402263.XA Withdrawn CN114819574A (en) | 2022-04-18 | 2022-04-18 | Student learning habit analysis system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114819574A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115330271A (en) * | 2022-10-13 | 2022-11-11 | 山东中创和泰信息咨询有限公司 | Internet-based education training management platform and management method |
-
2022
- 2022-04-18 CN CN202210402263.XA patent/CN114819574A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115330271A (en) * | 2022-10-13 | 2022-11-11 | 山东中创和泰信息咨询有限公司 | Internet-based education training management platform and management method |
| CN115330271B (en) * | 2022-10-13 | 2023-10-10 | 招投研究院(广州)有限公司 | Education and training management platform and management method based on Internet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108281052B (en) | A kind of on-line teaching system and online teaching method | |
| US9666088B2 (en) | Video-based teacher assistance | |
| CN114038256B (en) | Teaching interactive system based on artificial intelligence | |
| CN106547815B (en) | Big data-based targeted job generation method and system | |
| CN113139885A (en) | Teaching management system and management method thereof | |
| CN111523444B (en) | Classroom behavior detection method based on improved Openpost model and facial micro-expression | |
| CN113781853B (en) | Teacher-student remote interactive education platform based on terminal | |
| CN112862639B (en) | Education method of online education platform based on big data analysis | |
| CN114422820A (en) | Education interactive live broadcast system and live broadcast method | |
| CN114819574A (en) | Student learning habit analysis system based on big data | |
| CN112085883A (en) | Intelligent invigilation anti-cheating system | |
| CN111523445A (en) | Examination behavior detection method based on improved Openpos model and facial micro-expression | |
| CN111405054A (en) | Intelligent teaching assistant system and method | |
| CN113822907A (en) | Image processing method and device | |
| CN112990705A (en) | On-line training platform for personalized recommended courses | |
| CN112926934A (en) | Teaching evaluation method, system and computer readable storage medium | |
| CN112116841A (en) | Personalized remote education system and method based on deep learning | |
| CN114786032B (en) | Training video management method and system | |
| CN114724229B (en) | Learning state detection system and method for online education platform | |
| CN114549253A (en) | Online teaching system for evaluating lecture listening state in real time | |
| CN114037358A (en) | Academic situation analysis method and system based on college interactive classroom activity data | |
| CN113409635A (en) | Interactive teaching method and system based on virtual reality scene | |
| CN117576604B (en) | Classroom interaction method and device based on image recognition | |
| CN114898449B (en) | Foreign language teaching auxiliary method and device based on big data | |
| CN114743541B (en) | Interactive system for English listening and speaking learning |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220729 |