CN112766150A - School classroom student learning behavior tracking analysis method based on big data and artificial intelligence and cloud management platform - Google Patents
School classroom student learning behavior tracking analysis method based on big data and artificial intelligence and cloud management platform Download PDFInfo
- Publication number
- CN112766150A CN112766150A CN202110066797.5A CN202110066797A CN112766150A CN 112766150 A CN112766150 A CN 112766150A CN 202110066797 A CN202110066797 A CN 202110066797A CN 112766150 A CN112766150 A CN 112766150A
- Authority
- CN
- China
- Prior art keywords
- learning behavior
- students
- student
- behavior
- face image
- 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- Withdrawn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 title claims abstract description 288
- 238000004458 analytical method Methods 0.000 title claims abstract description 55
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 27
- 238000011156 evaluation Methods 0.000 claims abstract description 93
- 238000007781 pre-processing Methods 0.000 claims abstract description 25
- 238000001514 detection method Methods 0.000 claims description 93
- 238000000605 extraction Methods 0.000 claims description 30
- 238000012545 processing Methods 0.000 claims description 10
- 239000000284 extract Substances 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000001815 facial effect Effects 0.000 claims description 6
- 238000003709 image segmentation Methods 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 5
- SPBWHPXCWJLQRU-FITJORAGSA-N 4-amino-8-[(2r,3r,4s,5r)-3,4-dihydroxy-5-(hydroxymethyl)oxolan-2-yl]-5-oxopyrido[2,3-d]pyrimidine-6-carboxamide Chemical compound C12=NC=NC(N)=C2C(=O)C(C(=O)N)=CN1[C@@H]1O[C@H](CO)[C@@H](O)[C@H]1O SPBWHPXCWJLQRU-FITJORAGSA-N 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 5
- 238000002360 preparation method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Tourism & Hospitality (AREA)
- Multimedia (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a big data and artificial intelligence based school classroom student learning behavior tracking analysis method and a cloud management platform, which are characterized in that by collecting image information of each student in a classroom and carrying out image preprocessing operation, thereby extracting the characteristics of the image information of each student, comparing the image information with the characteristics of different behavior types of the students, determining the behavior type characteristics and the face image deflection angle of each student, counting the learning behavior evaluation coefficients of each student in different subjects, the corresponding learning behavior grades and the student interest degrees of each subject, and the intelligent student education system has the characteristics of high intelligence and high reliability, reduces the labor cost, greatly improves the efficiency of analyzing the subject interestingness and the student learning behavior level, is convenient for different teachers to pertinently solve and improve the problems according to the evaluation results, and enhances the teaching efficiency of the teachers and the learning receiving efficiency of the students.
Description
Technical Field
The invention belongs to the technical field of learning behavior analysis, and particularly relates to a school classroom student learning behavior tracking analysis method and a cloud management platform based on big data and artificial intelligence.
Background
With the continuous progress of scientific technology, the artificial intelligence technology applying the information technology to classroom learning is rapidly developed, and classroom teaching quality of teachers is tracked by using classroom student behavior analysis. The behavior analysis is a technology for performing feature recognition and analysis on human behaviors by analyzing data such as videos and depth sensors and utilizing a specific algorithm, and the technology is widely applied to the fields of video classification, human-computer interaction, security monitoring and the like.
In the prior art, the research on the aspect of student evaluation mainly focuses on theory, basic data in the research work mainly depends on modes such as spot check questioning, questionnaire investigation, hall observation and subjective statistics performed by staffs such as teachers or teaching supervisors, and the like, a general mathematical statistics method is adopted for a result processing mode, no automatic, intelligent and funny equipment and means are used for providing a large amount of objective and quantitative data, and the data are used as references for improving the learning efficiency of students and improving the learning method.
Disclosure of Invention
Aiming at the problems, the invention provides a big data and artificial intelligence based school classroom student learning behavior tracking analysis method and a cloud management platform, which are used for carrying out feature extraction on image information of each student in a classroom by acquiring the image information of each student and carrying out image preprocessing operation, comparing the image information with different behavior type features of the students, determining the behavior type features and face image deflection angles of each student, counting learning behavior evaluation coefficients of each student in different subjects, corresponding learning behavior grades and student interest degrees of each subject, and displaying the learning behavior evaluation coefficients and the learning behavior grades, so that the problems in the prior art are solved;
the purpose of the invention can be realized by the following technical scheme:
a school classroom student learning behavior tracking analysis method based on big data and artificial intelligence comprises the following steps:
s1: acquiring image information of each student in a classroom and carrying out image preprocessing operation;
s2: extracting the characteristics of the image information of each student, and determining the behavior category characteristics and the face image deflection angle of each student;
s3: counting the learning behavior evaluation coefficients of the students in different disciplines, the corresponding learning behavior grades and the student interestingness of each discipline;
s4: displaying the learning behavior evaluation coefficients of the students in different disciplines, the corresponding learning behavior grades and the student interest degrees of the disciplines;
the school classroom student learning behavior tracking analysis method based on big data and artificial intelligence uses a school classroom student learning behavior tracking analysis system based on big data and artificial intelligence, and comprises an area division module, a plane coordinate division module, an image acquisition module, an image preprocessing module, a modeling analysis server, an image feature extraction module, a database, a management server and a display terminal;
the image acquisition module is respectively connected with the region division module, the image feature extraction module and the image preprocessing module, the image feature extraction module is respectively connected with the image preprocessing module, the modeling analysis server and the database, the modeling analysis server is respectively connected with the database and the display terminal, and the management server is respectively connected with the display terminal, the database and the plane coordinate division module;
the system comprises a plane coordinate dividing module, a management server, a teacher platform, a teacher position management module and a management server, wherein the plane coordinate dividing module is used for dividing position coordinates of students in a classroom, a plane rectangular coordinate system is established by taking the position of a first row of first students close to the leftmost side of the teacher platform as a coordinate origin, a first row of seats close to the teacher platform is taken as an X axis of the plane rectangular coordinate system, the direction from the left to the right of the coordinate origin is taken as the positive direction of the X axis of the plane rectangular coordinate system, a first column of seats close to the leftmost side of the teacher platform is taken as the Y axis of the plane rectangular coordinate system, the direction from the bottom to the top of the coordinate origin is taken as the positive direction of the Y axis;
the area division module is used for carrying out area division on the positions of all students in a classroom, dividing the positions of all students in the classroom into a plurality of detection subareas with the same area, numbering the divided detection subareas according to the sequence of the distance from each detection subarea to a teacher platform in turn from near to far, and sequentially marking the detection subareas as 1,2,. once, i,. once, g, and sequentially marking all students in each detection subarea as 1,2,. once, m,. once, n according to the preset sequence;
the image acquisition module comprises a high-definition camera, is arranged in the classroom and is used for acquiring images of all students in all detection subareas when various subjects are loaded in the classroom and respectively sending the acquired images of all students in all detection subareas when various subjects are loaded to the image preprocessing module and the image feature extraction module;
the image preprocessing module receives images of all students in all detection sub-areas in various disciplines, performs image segmentation on the received images of all students in all detection sub-areas in various disciplines, splices face feature areas obtained by image segmentation, removes background images outside the areas, changes reserved area images into images with consistent size and deflection angles of faces through geometric normalization processing, performs gray level transformation processing and image enhancement processing simultaneously to obtain processed face target images with deflection angles of all students in all detection sub-areas in various disciplines, and sends the processed face target images with deflection angles of all students in all detection sub-areas in various disciplines to the image feature extraction module;
the image feature extraction module receives the images of all students in all detection sub-areas sent by the image acquisition module when various subjects are entered, amplifies the received images of all students in all detection sub-areas when various subjects are entered, compares the behavior features of the students in all detection sub-areas with the behavior features of different types of students stored in the database when various subjects are entered, obtains the behavior type features of the students in the detection sub-areas when various subjects are entered, further obtains the behavior type features of all students in all detection sub-areas when various subjects are entered, and forms a behavior type feature set Api(api1,api2,...,apim,...,apin)，apim represents the behavior category characteristics of the mth student in the ith detection subarea in the pth subject, receives the face target images with deflection angles of all students in all detection subareas in various subjects sent by the image preprocessing module, extracts the deflection angles of the face target images of all students in all detection subareas in various subjects to form a face image deflection angle setBpi(bpi1,bpi2,...,bpim,...,bpin)，bpim represents the face image deflection angle of the mth student in the ith detection sub-area in the pth subject, and the image feature extraction module sends the behavior category feature set and the face image deflection angle set to the modeling analysis server;
the database is used for storing different behavior type characteristics of students, storing standard learning behavior characteristics of the students, storing a standard deflection angle range of a face image, storing a time threshold value when the deflection angle of the face image of the student is not in the standard deflection angle range of the face image, and storing learning behavior evaluation coefficient ranges corresponding to different learning behavior grades;
the modeling analysis server receives the behavior type feature set sent by the image feature extraction module, extracts standard learning behavior features stored in the database, compares the behavior type features of students in detection sub-areas with the standard learning behavior features stored in the database when various subjects exist in the behavior type feature set to form a behavior type feature comparison set A'pi(a′pi1,a′pi2,...,a′pim,...,a′pin)，a′pim is a comparison value between the behavior class characteristic and the standard learning behavior characteristic of the mth student in the ith detection subarea at the time of the pth subject, and a 'if the behavior class characteristic and the standard learning behavior characteristic of the mth student in the ith detection subarea at the time of the pth subject are successfully compared'pim is equal to a fixed numerical value R, and a 'is obtained if the behavior category characteristic of the mth student in the ith detection subarea fails to be compared with the standard learning behavior characteristic in the pth subject'pim is equal to 0, the modeling analysis server counts student behavior category matching coefficients of each subject according to the behavior category feature comparison set;
the modeling analysis server receives the face image deflection angle set sent by the image feature extraction module, extracts the standard deflection angle range of the face image stored in the database, and carries out face image deflection angles of students in detection subareas and the standard deflection angle range of the face image in various subjects in the face image deflection angle setContrast, forming a human face image deflection angle contrast set B'pi(b′pi1,b′pi2,...,b′pim,...,b′pin)，b′pim is a contrast value of a face image deflection angle of an mth student in an ith detection subarea of the pth subject and a face image standard deflection angle range, and b 'is obtained if the face image deflection angle of the mth student is in the face image standard deflection angle range'piIf the face image declination of the student is smaller than the minimum value of the face image standard declination range, taking an absolute value, if the face image declination of the student is larger than the maximum value of the face image standard declination range, taking a difference between the face image declination of the student and the maximum value of the face image standard declination range, taking an absolute value, and counting the time when the face image declination of all students in each detection subarea is not in the face image standard declination range in various disciplines;
the modeling analysis server compares the set according to the facial image deflection angles and counts the learning behavior evaluation coefficients of all students in different disciplines according to the time when the facial image deflection angles of all students in all detection sub-areas are not in the standard deflection angle range of the facial image when the students go into various disciplines, the learning behavior evaluation coefficients of all students in different disciplines are matched according to the student behavior types of all disciplines to count the student interest degrees of all disciplines, the learning behavior evaluation coefficients of all students in different disciplines are sent to the management server, and the student interest degrees of all disciplines are sent to the display terminal;
the management server receives learning behavior evaluation coefficients of students in different subjects and position coordinates of corresponding students, learning behavior evaluation coefficient ranges corresponding to different learning behavior grades stored in a database are extracted, the learning behavior evaluation coefficients of the students in different subjects are compared with the learning behavior evaluation coefficient ranges corresponding to different learning behavior grades stored in the database, if the learning behavior evaluation coefficients of the students in the subjects are in the learning behavior evaluation coefficient range corresponding to the primary learning behavior grade, the learning behavior grade of the students in the subjects is the primary learning behavior grade, if the learning behavior evaluation coefficients of the students in the subjects are in the learning behavior evaluation coefficient range corresponding to the secondary learning behavior grade, the learning behavior grade of the students in the subjects is the secondary learning behavior grade, and if the learning behavior evaluation coefficients of the students in the subjects are in the learning behavior evaluation coefficient range corresponding to the secondary learning behavior grade, the learning behavior evaluation system corresponding to the tertiary learning behavior grade is adopted If the learning behavior level of the student in the subject is three levels, the management server sends the learning behavior evaluation coefficients of the students in different subjects, the corresponding learning behavior levels and the position coordinates of the student to the display terminal;
and the display terminal receives the student interest degrees of the various disciplines sent by the modeling analysis server, receives the learning behavior evaluation coefficients of the various disciplines of the students sent by the management server, the corresponding learning behavior grades and the position coordinates of the students, and displays the learning behavior evaluation coefficients and the corresponding learning behavior grades.
Further, an upper limit value of the learning behavior evaluation coefficient range corresponding to the primary learning behavior level is smaller than a lower limit value of the learning behavior evaluation coefficient range corresponding to the secondary learning behavior level, and an upper limit value of the learning behavior evaluation coefficient range corresponding to the secondary learning behavior level is smaller than a lower limit value of the learning behavior evaluation coefficient range corresponding to the tertiary learning behavior level.
Further, the behavior type characteristics of the students comprise sleeping, eating, playing mobile phones, speaking with others and watching outside a window.
Further, the subject categories include mathematics, language, English, history, politics, physics, chemistry, music, and art.
Further, the formula for calculating the matching coefficient of the behavior types of the students in different disciplines is
Further, the calculation formula of the learning behavior evaluation coefficients of the students in different disciplines is
b′pim is the contrast value of the face image deflection angle of the mth student in the ith detection sub-area in the pth subject and the face image standard deflection angle range, YpimExpressed as the time when the face image deflection angle of the mth student in the ith detection sub-area of the pth discipline is not in the standard deflection angle range of the face image,
and the time threshold value is represented as that the deflection angle of the face image of the student is not in the standard deflection angle range of the face image.
Further, the subject interestingness is calculated by the formula
ηpExpressed as the student behavior class match coefficient, λ, at the last p disciplinespimAnd (3) representing the learning behavior evaluation coefficient of the mth student in the ith detection subarea in the upper pth subject.
The cloud management platform comprises a processor, a machine-readable storage medium and a network interface, wherein the machine-readable storage medium, the network interface and the processor are connected through a bus system, the network interface is used for being in communication connection with at least one school classroom student learning behavior tracking analysis terminal based on big data and artificial intelligence, the machine-readable storage medium is used for storing programs, instructions or codes, and the processor is used for executing the programs, the instructions or the codes in the machine-readable storage medium so as to execute the school classroom student learning behavior tracking analysis method based on big data and artificial intelligence.
Has the advantages that:
(1) the invention collects the image information of each student in the classroom and carries out image preprocessing operation, thereby carrying out feature extraction on the image information of each student, comparing the image information with different behavior type features of the students, determining the behavior type features and face image deflection angles of each student, counting the learning behavior evaluation coefficients of each student in different subjects, the corresponding learning behavior grades and the student interestingness of each subject, and displaying the learning behavior evaluation coefficients and the corresponding learning behavior grades.
(2) In the image acquisition module, images of students in different subjects in a classroom are acquired, so that reliable early-stage data preparation and reference bases are provided for later-stage statistics of learning behavior evaluation coefficients of the students in the different subjects, corresponding learning behavior grades and student interestingness of the subjects, and the image acquisition module has the characteristics of high authenticity and high data precision and accuracy.
(3) According to the invention, the learning behavior evaluation coefficients of the students in different subjects, the corresponding learning behavior grades and the student interest degrees of the subjects are displayed on the display terminal, so that different teachers can correspondingly adjust teaching modes according to the learning behavior grades of the students, the evaluation result is more scientific and reasonable, the problem is solved and improved in a targeted manner, and the teaching efficiency of the teachers and the learning receiving efficiency of the students are enhanced.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
FIG. 1 is a diagram of the steps of the method of the present invention.
FIG. 2 is a flow chart of the system of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious 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 derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a big data and artificial intelligence based school classroom student learning behavior tracking analysis method includes the following steps:
s1: acquiring image information of each student in a classroom and carrying out image preprocessing operation;
s2: extracting the characteristics of the image information of each student, and determining the behavior category characteristics and the face image deflection angle of each student;
s3: counting the learning behavior evaluation coefficients of the students in different disciplines, the corresponding learning behavior grades and the student interestingness of each discipline;
s4: displaying the learning behavior evaluation coefficients of the students in different disciplines, the corresponding learning behavior grades and the student interest degrees of the disciplines;
the school classroom student learning behavior tracking analysis method based on big data and artificial intelligence uses a school classroom student learning behavior tracking analysis system based on big data and artificial intelligence, and comprises an area division module, a plane coordinate division module, an image acquisition module, an image preprocessing module, a modeling analysis server, an image feature extraction module, a database, a management server and a display terminal;
the image acquisition module is respectively connected with the region division module, the image feature extraction module and the image preprocessing module, the image feature extraction module is respectively connected with the image preprocessing module, the modeling analysis server and the database, the modeling analysis server is respectively connected with the database and the display terminal, and the management server is respectively connected with the display terminal, the database and the plane coordinate division module;
the embodiment collects images of students in different subjects in a classroom, provides reliable early-stage data preparation and reference basis for later-stage statistics of learning behavior evaluation coefficients of the students in the different subjects, corresponding learning behavior grades and student interestingness of the students in the different subjects, and has the characteristics of high authenticity and high data precision and accuracy.
The system comprises a plane coordinate dividing module, a management server, a teacher platform, a teacher position management module and a management server, wherein the plane coordinate dividing module is used for dividing position coordinates of students in a classroom, a plane rectangular coordinate system is established by taking the position of a first row of first students close to the leftmost side of the teacher platform as a coordinate origin, a first row of seats close to the teacher platform is taken as an X axis of the plane rectangular coordinate system, the direction from the left to the right of the coordinate origin is taken as the positive direction of the X axis of the plane rectangular coordinate system, a first column of seats close to the leftmost side of the teacher platform is taken as the Y axis of the plane rectangular coordinate system, the direction from the bottom to the top of the coordinate origin is taken as the positive direction of the Y axis;
the area division module is used for carrying out area division on the positions of all students in a classroom, dividing the positions of all students in the classroom into a plurality of detection subareas with the same area, numbering the divided detection subareas according to the sequence of the distance from each detection subarea to a teacher platform in turn from near to far, and sequentially marking the detection subareas as 1,2,. once, i,. once, g, and sequentially marking all students in each detection subarea as 1,2,. once, m,. once, n according to the preset sequence;
the image acquisition module comprises a high-definition camera, is arranged in the classroom and is used for acquiring images of all students in all detection subareas when various subjects are loaded in the classroom and respectively sending the acquired images of all students in all detection subareas when various subjects are loaded to the image preprocessing module and the image feature extraction module;
the image preprocessing module receives images of all students in all detection sub-areas in various disciplines, performs image segmentation on the received images of all students in all detection sub-areas in various disciplines, splices face feature areas obtained by image segmentation, removes background images outside the areas, changes reserved area images into images with consistent size and deflection angles of faces through geometric normalization processing, performs gray level transformation processing and image enhancement processing simultaneously to obtain processed face target images with deflection angles of all students in all detection sub-areas in various disciplines, and sends the processed face target images with deflection angles of all students in all detection sub-areas in various disciplines to the image feature extraction module;
the image feature extraction module receives images of all students in each detection subarea when the students go into various disciplines sent by the image acquisition module, the discipline types comprise mathematics, Chinese, English, history, politics, physics, chemistry, music and art, the images of all students in each detection subarea when the students go into various disciplines are amplified, the behavior features of the students in the images of all students in each detection subarea when the students go into various disciplines are compared with the behavior features of the students of different types stored in the database, the behavior type features of the students in the detection subarea when the students go into the disciplines are obtained, and then the behavior type features of all students in each detection subarea when the students go into various disciplines are obtained to form a behavior type feature set Api(api1,api2,...,apim,...,apin)，apim represents the behavior category characteristics of the mth student in the ith detection subarea in the pth subject, receives the face target images with deflection angles of all students in all detection subareas in various subjects sent by the image preprocessing module, extracts the deflection angles of the face target images of all students in all detection subareas in various subjects to form a face image deflection angle set Bpi(bpi1,bpi2,…,bpim,…,bpin)，bpim represents the face image deflection angle of the mth student in the ith detection sub-area in the pth subject, and the image feature extraction module sends the behavior category feature set and the face image deflection angle set to the modeling analysis server;
the database is used for storing different behavior type characteristics of students, the behavior type characteristics of the students comprise sleeping, eating, playing mobile phones, speaking with others and watching outside a window, standard learning behavior characteristics of the students are stored, a face image standard deflection angle range is stored, a time threshold value that the face image deflection angle of the students is not in the face image standard deflection angle range is stored, learning behavior evaluation coefficient ranges corresponding to different learning behavior levels are stored, the upper limit value of the learning behavior evaluation coefficient range corresponding to the primary learning behavior level is smaller than the lower limit value of the learning behavior evaluation coefficient range corresponding to the secondary learning behavior level, and the upper limit value of the learning behavior evaluation coefficient range corresponding to the secondary learning behavior level is smaller than the lower limit value of the learning behavior evaluation coefficient range corresponding to the tertiary learning behavior level;
the modeling analysis server receives the behavior type feature set sent by the image feature extraction module, extracts standard learning behavior features stored in the database, compares the behavior type features of students in detection sub-areas with the standard learning behavior features stored in the database when various subjects exist in the behavior type feature set to form a behavior type feature comparison set A'pi(a′pi1,a′pi2,…,a′pim,...,a′pin)，a′pim is a comparison value between the behavior class characteristic and the standard learning behavior characteristic of the mth student in the ith detection subarea at the time of the pth subject, and a 'if the behavior class characteristic and the standard learning behavior characteristic of the mth student in the ith detection subarea at the time of the pth subject are successfully compared'pim is equal to a fixed numerical value R, and a 'is obtained if the behavior category characteristic of the mth student in the ith detection subarea fails to be compared with the standard learning behavior characteristic in the pth subject'pim is equal to 0, the modeling analysis server counts student behavior class matching coefficients of various disciplines according to the behavior class feature comparison set, and a calculation formula of the student behavior class matching coefficients of different disciplines is
The modeling analysis server receives the face image deflection angle set sent by the image feature extraction module, extracts a face image standard deflection angle range stored in the database, compares the face image deflection angle of each student in each detection sub-area in each subject in the face image deflection angle set with the face image standard deflection angle range to form a face image deflection angle comparison set B'pi(b′pi1,b′pi2,...,b′pim,...,b′pin)，b′pim is expressed asThe contrast value of the face image deflection angle of the mth student in the ith detection subarea of p disciplines and the standard deflection angle range of the face image is b 'if the face image deflection angle of the student is in the standard deflection angle range of the face image'piIf the face image declination of the student is smaller than the minimum value of the face image standard declination range, taking an absolute value, if the face image declination of the student is larger than the maximum value of the face image standard declination range, taking a difference between the face image declination of the student and the maximum value of the face image standard declination range, taking an absolute value, and counting the time when the face image declination of all students in each detection subarea is not in the face image standard declination range in various disciplines;
the modeling analysis server counts the learning behavior evaluation coefficients of the students in different subjects according to the time when the face image deflection angles of all the students in all the detection sub-areas are not in the standard deflection angle range of the face image when the face image deflection angles are compared with the set and go into various subjects, and the calculation formula of the learning behavior evaluation coefficients of the students in different subjects is
b′pim is the contrast value of the face image deflection angle of the mth student in the ith detection sub-area in the pth subject and the face image standard deflection angle range, YpimExpressed as the time when the face image deflection angle of the mth student in the ith detection sub-area of the pth discipline is not in the standard deflection angle range of the face image,
the time threshold value is represented as that the deflection angle of the face image of the student is not in the standard deflection angle range of the face image, the student interestingness of each subject is counted according to the matching coefficient of the student behavior types of each subject and the learning behavior evaluation coefficient of each student in different subjects, and the calculation formula of the student interestingness is
ηpExpressed as the student behavior class match coefficient, λ, at the last p disciplinespimThe learning behavior evaluation coefficients of the mth student in the ith detection sub-area in the pth discipline are expressed, the learning behavior evaluation coefficients of the different disciplines of the students are sent to the management server, and the student interestingness of the disciplines is sent to the display terminal;
the management server receives learning behavior evaluation coefficients of students in different subjects and position coordinates of corresponding students, learning behavior evaluation coefficient ranges corresponding to different learning behavior grades stored in a database are extracted, the learning behavior evaluation coefficients of the students in different subjects are compared with the learning behavior evaluation coefficient ranges corresponding to different learning behavior grades stored in the database, if the learning behavior evaluation coefficients of the students in the subjects are in the learning behavior evaluation coefficient range corresponding to the primary learning behavior grade, the learning behavior grade of the students in the subjects is the primary learning behavior grade, if the learning behavior evaluation coefficients of the students in the subjects are in the learning behavior evaluation coefficient range corresponding to the secondary learning behavior grade, the learning behavior grade of the students in the subjects is the secondary learning behavior grade, and if the learning behavior evaluation coefficients of the students in the subjects are in the learning behavior evaluation coefficient range corresponding to the secondary learning behavior grade, the learning behavior evaluation system corresponding to the tertiary learning behavior grade is adopted If the learning behavior level of the student in the subject is three levels, the management server sends the learning behavior evaluation coefficients of the students in different subjects, the corresponding learning behavior levels and the position coordinates of the student to the display terminal;
and the display terminal receives the student interest degrees of the various disciplines sent by the modeling analysis server, receives the learning behavior evaluation coefficients of the various disciplines of the students sent by the management server, the corresponding learning behavior grades and the position coordinates of the students, and displays the learning behavior evaluation coefficients and the corresponding learning behavior grades.
The embodiment displays the learning behavior evaluation coefficients of the students in different subjects, the corresponding learning behavior levels and the student interestingness of the students in the different subjects, so that different teachers can perform corresponding adjustment of teaching modes according to the learning behavior levels of the students, the evaluation result is more scientific and reasonable, the problem is improved in a targeted manner, and the teaching efficiency of the teachers and the learning receiving efficiency of the students are enhanced.
The cloud management platform comprises a processor, a machine-readable storage medium and a network interface, wherein the machine-readable storage medium, the network interface and the processor are connected through a bus system, the network interface is used for being in communication connection with at least one school classroom student learning behavior tracking analysis terminal based on big data and artificial intelligence, the machine-readable storage medium is used for storing programs, instructions or codes, and the processor is used for executing the programs, the instructions or the codes in the machine-readable storage medium so as to execute the school classroom student learning behavior tracking analysis method based on big data and artificial intelligence.
The invention collects the image information of each student in the classroom and carries out image preprocessing operation, thereby carrying out feature extraction on the image information of each student, comparing the image information with different behavior type features of the students, determining the behavior type features and face image deflection angles of each student, counting the learning behavior evaluation coefficients of each student in different subjects, the corresponding learning behavior grades and the student interestingness of each subject, and displaying the learning behavior evaluation coefficients and the corresponding learning behavior grades.
The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.
Claims (8)
1. Big data and artificial intelligence based school classroom student learning behavior tracking analysis method is characterized in that: the method comprises the following steps:
s1: acquiring image information of each student in a classroom and carrying out image preprocessing operation;
s2: extracting the characteristics of the image information of each student, and determining the behavior category characteristics and the face image deflection angle of each student;
s3: counting the learning behavior evaluation coefficients of the students in different disciplines, the corresponding learning behavior grades and the student interestingness of each discipline;
s4: displaying the learning behavior evaluation coefficients of the students in different disciplines, the corresponding learning behavior grades and the student interest degrees of the disciplines;
the school classroom student learning behavior tracking analysis method based on big data and artificial intelligence uses a school classroom student learning behavior tracking analysis system based on big data and artificial intelligence, and comprises an area division module, a plane coordinate division module, an image acquisition module, an image preprocessing module, a modeling analysis server, an image feature extraction module, a database, a management server and a display terminal;
the image acquisition module is respectively connected with the region division module, the image feature extraction module and the image preprocessing module, the image feature extraction module is respectively connected with the image preprocessing module, the modeling analysis server and the database, the modeling analysis server is respectively connected with the database and the display terminal, and the management server is respectively connected with the display terminal, the database and the plane coordinate division module;
the system comprises a plane coordinate dividing module, a management server, a teacher platform, a teacher position management module and a management server, wherein the plane coordinate dividing module is used for dividing position coordinates of students in a classroom, a plane rectangular coordinate system is established by taking the position of a first row of first students close to the leftmost side of the teacher platform as a coordinate origin, a first row of seats close to the teacher platform is taken as an X axis of the plane rectangular coordinate system, the direction from the left to the right of the coordinate origin is taken as the positive direction of the X axis of the plane rectangular coordinate system, a first column of seats close to the leftmost side of the teacher platform is taken as the Y axis of the plane rectangular coordinate system, the direction from the bottom to the top of the coordinate origin is taken as the positive direction of the Y axis;
the area division module is used for carrying out area division on the positions of all students in a classroom, dividing the positions of all students in the classroom into a plurality of detection subareas with the same area, numbering the divided detection subareas according to the sequence of the distance from each detection subarea to a teacher platform in turn from near to far, and sequentially marking the detection subareas as 1,2,. once, i,. once, g, and sequentially marking all students in each detection subarea as 1,2,. once, m,. once, n according to the preset sequence;
the image acquisition module comprises a high-definition camera, is arranged in the classroom and is used for acquiring images of all students in all detection subareas when various subjects are loaded in the classroom and respectively sending the acquired images of all students in all detection subareas when various subjects are loaded to the image preprocessing module and the image feature extraction module;
the image preprocessing module receives images of all students in all detection sub-areas in various disciplines, performs image segmentation on the received images of all students in all detection sub-areas in various disciplines, splices face feature areas obtained by image segmentation, removes background images outside the areas, changes reserved area images into images with consistent size and deflection angles of faces through geometric normalization processing, performs gray level transformation processing and image enhancement processing simultaneously to obtain processed face target images with deflection angles of all students in all detection sub-areas in various disciplines, and sends the processed face target images with deflection angles of all students in all detection sub-areas in various disciplines to the image feature extraction module;
the image feature extraction module receives the images of all students in all detection sub-areas sent by the image acquisition module when various subjects are entered, amplifies the received images of all students in all detection sub-areas when various subjects are entered, compares the behavior features of the students in all detection sub-areas with the behavior features of different types of students stored in the database when various subjects are entered, obtains the behavior type features of the students in the detection sub-areas when various subjects are entered, and further obtains the behavior type features of all students in all detection sub-areas when various subjects are enteredBehavior category characteristics, constituting a behavior category characteristic set Api(api1,api2,...,apim,...,apin)，apim represents the behavior category characteristics of the mth student in the ith detection subarea in the pth subject, receives the face target images with deflection angles of all students in all detection subareas in various subjects sent by the image preprocessing module, extracts the deflection angles of the face target images of all students in all detection subareas in various subjects to form a face image deflection angle set Bpi(bpi1,bpi2,...,bpim,...,bpin)，bpim represents the face image deflection angle of the mth student in the ith detection sub-area in the pth subject, and the image feature extraction module sends the behavior category feature set and the face image deflection angle set to the modeling analysis server;
the database is used for storing different behavior type characteristics of students, storing standard learning behavior characteristics of the students, storing a standard deflection angle range of a face image, storing a time threshold value when the deflection angle of the face image of the student is not in the standard deflection angle range of the face image, and storing learning behavior evaluation coefficient ranges corresponding to different learning behavior grades;
the modeling analysis server receives the behavior type feature set sent by the image feature extraction module, extracts standard learning behavior features stored in the database, compares the behavior type features of students in detection sub-areas with the standard learning behavior features stored in the database when various subjects exist in the behavior type feature set to form a behavior type feature comparison set A'pi(a′pi1,a′pi2,...,a′pim,...,a′pin)，a′pim is a comparison value between the behavior class characteristic and the standard learning behavior characteristic of the mth student in the ith detection subarea at the time of the pth subject, and a 'if the behavior class characteristic and the standard learning behavior characteristic of the mth student in the ith detection subarea at the time of the pth subject are successfully compared'pim is equal to a fixed value R, and if the student is in the p-th subject, the behavior category characteristics and the standard learning behavior of the mth student in the ith detection sub-areaAnd c, failing to compare features, then'pim is equal to 0, the modeling analysis server counts student behavior category matching coefficients of each subject according to the behavior category feature comparison set;
the modeling analysis server receives the face image deflection angle set sent by the image feature extraction module, extracts a face image standard deflection angle range stored in the database, compares the face image deflection angle of each student in each detection sub-area in each subject in the face image deflection angle set with the face image standard deflection angle range to form a face image deflection angle comparison set B'pi(b′pi1,b′pi2,...,b′pim,…,b′pin)，b′pim is a contrast value of a face image deflection angle of an mth student in an ith detection subarea of the pth subject and a face image standard deflection angle range, and b 'is obtained if the face image deflection angle of the mth student is in the face image standard deflection angle range'piIf the face image declination of the student is smaller than the minimum value of the face image standard declination range, taking an absolute value, if the face image declination of the student is larger than the maximum value of the face image standard declination range, taking a difference between the face image declination of the student and the maximum value of the face image standard declination range, taking an absolute value, and counting the time when the face image declination of all students in each detection subarea is not in the face image standard declination range in various disciplines;
the modeling analysis server compares the set according to the facial image deflection angles and counts the learning behavior evaluation coefficients of all students in different disciplines according to the time when the facial image deflection angles of all students in all detection sub-areas are not in the standard deflection angle range of the facial image when the students go into various disciplines, the learning behavior evaluation coefficients of all students in different disciplines are matched according to the student behavior types of all disciplines to count the student interest degrees of all disciplines, the learning behavior evaluation coefficients of all students in different disciplines are sent to the management server, and the student interest degrees of all disciplines are sent to the display terminal;
the management server receives learning behavior evaluation coefficients of students in different subjects and position coordinates of corresponding students, learning behavior evaluation coefficient ranges corresponding to different learning behavior grades stored in a database are extracted, the learning behavior evaluation coefficients of the students in different subjects are compared with the learning behavior evaluation coefficient ranges corresponding to different learning behavior grades stored in the database, if the learning behavior evaluation coefficients of the students in the subjects are in the learning behavior evaluation coefficient range corresponding to the primary learning behavior grade, the learning behavior grade of the students in the subjects is the primary learning behavior grade, if the learning behavior evaluation coefficients of the students in the subjects are in the learning behavior evaluation coefficient range corresponding to the secondary learning behavior grade, the learning behavior grade of the students in the subjects is the secondary learning behavior grade, and if the learning behavior evaluation coefficients of the students in the subjects are in the learning behavior evaluation coefficient range corresponding to the secondary learning behavior grade, the learning behavior evaluation system corresponding to the tertiary learning behavior grade is adopted If the learning behavior level of the student in the subject is three levels, the management server sends the learning behavior evaluation coefficients of the students in different subjects, the corresponding learning behavior levels and the position coordinates of the student to the display terminal;
and the display terminal receives the student interest degrees of the various disciplines sent by the modeling analysis server, receives the learning behavior evaluation coefficients of the various disciplines of the students sent by the management server, the corresponding learning behavior grades and the position coordinates of the students, and displays the learning behavior evaluation coefficients and the corresponding learning behavior grades.
2. The big data and artificial intelligence based school classroom student learning behavior tracking analysis method of claim 1, wherein: the upper limit value of the learning behavior evaluation coefficient range corresponding to the primary learning behavior level is smaller than the lower limit value of the learning behavior evaluation coefficient range corresponding to the secondary learning behavior level, and the upper limit value of the learning behavior evaluation coefficient range corresponding to the secondary learning behavior level is smaller than the lower limit value of the learning behavior evaluation coefficient range corresponding to the tertiary learning behavior level.
3. The big data and artificial intelligence based school classroom student learning behavior tracking analysis method of claim 1, wherein: the behavior type characteristics of the students comprise sleeping, eating things, playing mobile phones, speaking with other people and watching outside a window.
4. The big data and artificial intelligence based school classroom student learning behavior tracking analysis method of claim 1, wherein: the subject categories include mathematics, language, English, history, politics, physics, chemistry, music, and art.
5. The big data and artificial intelligence based school classroom student learning behavior tracking analysis method of claim 1, wherein: the calculation formula of the matching coefficient of the behavior types of the students in different disciplines is
6. The big data and artificial intelligence based school classroom student learning behavior tracking analysis method of claim 1, wherein: the calculation formula of the learning behavior evaluation coefficients of the students in different disciplines is
b′pim is the contrast value of the face image deflection angle of the mth student in the ith detection sub-area in the pth subject and the face image standard deflection angle range, YpimExpressed as the time when the face image deflection angle of the mth student in the ith detection sub-area of the pth discipline is not in the standard deflection angle range of the face image,
and the time threshold value is represented as that the deflection angle of the face image of the student is not in the standard deflection angle range of the face image.
7. The base of claim 1The big data and artificial intelligence school classroom student learning behavior tracking analysis method is characterized by comprising the following steps: the subject interestingness calculation formula is
ηpExpressed as the student behavior class match coefficient, λ, at the last p disciplinespimAnd (3) representing the learning behavior evaluation coefficient of the mth student in the ith detection subarea in the upper pth subject.
8. A cloud management platform, characterized in that: the cloud management platform comprises a processor, a machine-readable storage medium and a network interface, wherein the machine-readable storage medium, the network interface and the processor are connected through a bus system, the network interface is used for being in communication connection with at least one school classroom student learning behavior tracking and analyzing terminal based on big data and artificial intelligence, the machine-readable storage medium is used for storing programs, instructions or codes, and the processor is used for executing the programs, the instructions or the codes in the machine-readable storage medium to execute the school classroom student learning behavior tracking and analyzing method based on big data and artificial intelligence in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110066797.5A CN112766150A (en) | 2021-01-19 | 2021-01-19 | School classroom student learning behavior tracking analysis method based on big data and artificial intelligence and cloud management platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110066797.5A CN112766150A (en) | 2021-01-19 | 2021-01-19 | School classroom student learning behavior tracking analysis method based on big data and artificial intelligence and cloud management platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112766150A true CN112766150A (en) | 2021-05-07 |
Family
ID=75702978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110066797.5A Withdrawn CN112766150A (en) | 2021-01-19 | 2021-01-19 | School classroom student learning behavior tracking analysis method based on big data and artificial intelligence and cloud management platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112766150A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113158991A (en) * | 2021-05-21 | 2021-07-23 | 南通大学 | Embedded intelligent face detection and tracking system |
-
2021
- 2021-01-19 CN CN202110066797.5A patent/CN112766150A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113158991A (en) * | 2021-05-21 | 2021-07-23 | 南通大学 | Embedded intelligent face detection and tracking system |
| CN113158991B (en) * | 2021-05-21 | 2021-12-24 | 南通大学 | Embedded intelligent face detection and tracking system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111709409B (en) | Face living body detection method, device, equipment and medium | |
| CN110837784B (en) | Examination room peeping and cheating detection system based on human head characteristics | |
| CN109284737A (en) | A kind of students ' behavior analysis and identifying system for wisdom classroom | |
| CN111310731A (en) | Video recommendation method, device and equipment based on artificial intelligence and storage medium | |
| CN110135282B (en) | Examinee return plagiarism cheating detection method based on deep convolutional neural network model | |
| US11194997B1 (en) | Method and system for thermal infrared facial recognition | |
| CN112183238B (en) | Remote education attention detection method and system | |
| CN104123543A (en) | Eyeball movement identification method based on face identification | |
| CN106920256A (en) | A kind of effective missing child searching system | |
| CN111258433A (en) | Teaching interactive system based on virtual scene | |
| CN111563449A (en) | Real-time classroom attention detection method and system | |
| CN111444389A (en) | Conference video analysis method and system based on target detection | |
| CN114898460B (en) | Teacher nonverbal behavior detection method based on graph convolution neural network | |
| CN106529470A (en) | Gesture recognition method based on multistage depth convolution neural network | |
| CN111611854A (en) | Classroom condition evaluation method based on pattern recognition | |
| CN112766150A (en) | School classroom student learning behavior tracking analysis method based on big data and artificial intelligence and cloud management platform | |
| CN114187640A (en) | Learning situation observation method, system, equipment and medium based on online classroom | |
| CN115223179A (en) | Classroom teaching data processing method and system based on answer codes | |
| CN115937971B (en) | Method and device for identifying hand-lifting voting | |
| CN107330416B (en) | A kind of pedestrian's recognition methods again for estimating study based on differentiation structure | |
| CN111222374A (en) | Lie detection data processing method and device, computer equipment and storage medium | |
| CN110751062B (en) | Examinee attitude sequence generation method based on attitude voting | |
| CN112766230A (en) | Video streaming personnel online time length estimation method and corresponding system | |
| CN115019396A (en) | Learning state monitoring method, device, equipment and medium | |
| CN111241165B (en) | Artificial intelligence education system based on big data and data processing method |
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: 20210507 |