CN110716920A - Student behavior automatic analysis method and system based on face recognition - Google Patents
Student behavior automatic analysis method and system based on face recognition Download PDFInfo
- Publication number
- CN110716920A CN110716920A CN201910921829.8A CN201910921829A CN110716920A CN 110716920 A CN110716920 A CN 110716920A CN 201910921829 A CN201910921829 A CN 201910921829A CN 110716920 A CN110716920 A CN 110716920A
- Authority
- CN
- China
- Prior art keywords
- student
- school
- time
- behavior
- data
- 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.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 31
- 230000006399 behavior Effects 0.000 claims description 84
- 238000000034 method Methods 0.000 claims description 12
- 208000027418 Wounds and injury Diseases 0.000 claims description 4
- 230000006378 damage Effects 0.000 claims description 4
- 208000014674 injury Diseases 0.000 claims description 4
- 230000037081 physical activity Effects 0.000 claims description 4
- 230000001815 facial effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000003997 social interaction Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/211—Schema design and management
- G06F16/212—Schema design and management with details for data modelling support
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- 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
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/44—Event detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a student behavior automatic analysis method and a system based on face recognition, belonging to the technical field of smart campuses, wherein the analysis method comprises the following steps: s1, acquiring identification event data of students in various places in the school; s2, adding behavior classification information to the identification event data of each student according to the identification event data and a preset student behavior classification table, and establishing an identification event classification information database; the analysis system comprises a camera, a local area network, a data server and a data reading device. The invention can automatically acquire mass behavior data of students in schools, and can help teachers to know behavior habits and interests of the students by analyzing the behavior data.
Description
Technical Field
The invention relates to the technical field of smart campuses, in particular to a student behavior automatic analysis method and system based on face recognition.
Background
The teaching is carried out according to the differences of the characters, interests and hobbies and specialties of students, and is the basic requirement of modern education. In the present stage, a teacher generally can only know the personality, interest and special features of students through talking with students or parents of the students, interacting with the students in a classroom, observing behaviors of the students in a school, correcting homework of the students and other activities, so the mode is long in period and low in efficiency, and the teacher does not have the energy to observe and analyze activities of the students in the school carefully due to the fact that the number of the teacher is small and the number of the students is large, and the knowledge of the conditions of the personality, interest and special features of the students is limited.
If the teacher only adopts observation and communication mode to know the student status, the specific conditions of the students are less; if only the teacher's analysis and summarization were relied upon, then analyzing student behavior would take too much time and effort from the teacher. This problem is caused in part by the lack of means for automated collection and analysis of student behavior.
Disclosure of Invention
With the increasing development of network communication and the continuous progress of artificial intelligence technology, the campus informatization and intelligence degree is higher and higher nowadays, and it is possible to deploy a large number of cameras with human faces and motion pattern recognition in the campus. The invention aims to overcome the defects in the prior art and provide a method and a system for automatically collecting the behavior of students and automatically analyzing the interests and hobbies of the students by using the facilities and the data analysis technology.
In order to achieve the above purpose, the invention provides the following technical scheme:
a student behavior automatic analysis method based on face recognition comprises the following steps:
s1, acquiring identification event data of each place of the student in the school, wherein the identification event data comprises face images, shooting time and camera numbers of the student, and the camera numbers correspond to the places;
and S2, adding behavior classification information to students corresponding to each face image according to the identification event data and a preset student behavior classification table, and establishing an identification event classification information database.
Further, the specific step of step S2 includes:
acquiring identity information corresponding to the face image;
obtaining place information according to the corresponding relation between the camera number and each place;
according to the identity information and the place information, behavior classification corresponding to the identity information is obtained from a preset student behavior classification table;
and establishing an identification event classification information database for each student corresponding to the identity information, wherein each piece of information in the identification event classification information database comprises identity information, shooting time, place information and behavior classification information of the student.
Further, the method for automatically analyzing the student behavior based on the face recognition further comprises the following steps: and step S3, analyzing the characters and interests of the students according to the identification event classification information database.
As a preferred scheme, the method for analyzing the characters and interests of students comprises the following steps: and calculating the time proportion corresponding to each classification according to the data in the identification event classification information database.
Further, the time proportion corresponding to each classification is calculated according to the classification level of the behavior classification.
Further, the preset student behavior classification table comprises the grades: major classes, minor classes and major groups,
the broad categories include, but are not limited to: study, physical activity, dining, injury and free time;
each major category is divided into a plurality of minor categories, each minor category is divided into a plurality of major groups, and the corresponding places of each major group correspond to the camera numbers.
Preferably, the major class further includes an in-out school, and the minor class of the in-out school includes: returning to school, leaving school and temporarily going out, wherein the large group of returning schools comprises normal returning schools and late schools; the large group of departure schools comprises normal departure schools and early quitting; the large group for temporary outgoing comprises temporary outgoing school in class time and temporary outgoing school in rest time.
Further, the step of classifying the normal school return, late school, normal school leaving, early school leaving, temporary school leaving during class time and temporary school leaving during rest time comprises:
acquiring face images of students, student identity information corresponding to the face images of the students and corresponding school returning moments by a camera at an entrance of a school door;
acquiring a face image of the same student, student identity information corresponding to the face image of the student and a corresponding moment of departure from school by a camera at an exit of a school door of the school;
when the school returning time is earlier than or equal to the school entering time of the preset work and rest time table, judging that the identity information of the student corresponds to the student and is normal school returning, otherwise, the school returning time is late; when the leaving school time is later than or equal to the leaving school time of the preset work and rest time table, judging that the identity information of the student corresponds to the student to be a normal leaving school, and otherwise, judging that the student is early returned;
when the leaving school time and the returning school time appear in the preset school time, the temporary school leaving of the student identity information corresponding to the school time of the student is judged; and when the leaving school moment and the returning school moment appear in the preset rest time, the temporary school leaving is judged according to the rest time of the students corresponding to the student identity information.
The same concept provides a student behavior automatic analysis system based on face recognition, and the system comprises: the system comprises a camera, a local area network, a data server and a data reading device;
the data server prestores student identity information, and the student identity information comprises: student name, ID, and facial photo; the data server prestores a student behavior classification table; the data server receives the identification event data through the local area network; the data server also adds behavior classification information to students corresponding to each face image according to the student behavior classification table, and establishes an identification event classification information database;
the system comprises cameras, a data server and a client side, wherein the cameras are arranged in all places in a school and are numbered, the camera numbers correspond to the places and are used for acquiring identification event data of students in all the places in the school, the identification event data comprise face images of the students, shooting time and camera numbers, and the identification event data are sent to the data server through a local area network; the camera also reads prestored student identity information from the data server, and acquires the name and ID of the student corresponding to the face image by adopting a face recognition algorithm according to the student identity information;
the data reading device is used for reading and displaying data in the data server.
Preferably, the data server can also analyze the characters and interests of the students according to the identification event classification information database, and send the analysis result to the data reading device through the local area network.
Compared with the prior art, the invention has the beneficial effects that:
after the method and the system are implemented, mass behavior data of students in schools can be automatically acquired and analyzed, and data and analysis conclusions can help teachers to know behavior habits and interests of the students. Therefore, the working efficiency of the teacher can be greatly improved, and the teacher is helped to implement different education methods according to behavior habits and interests of different students, so that the purposes of improving the teaching quality and giving play to the specialties of the students are achieved.
Drawings
Fig. 1 is a flowchart of a method for automatically analyzing student behavior based on face recognition in embodiment 1;
fig. 2 is a block diagram of an automatic student behavior analysis system based on face recognition in embodiment 1.
Detailed Description
The present invention will be described in further detail with reference to test examples and specific embodiments. It should be understood that the scope of the above-described subject matter is not limited to the following examples, and any techniques implemented based on the disclosure of the present invention are within the scope of the present invention.
Example 1
As shown in fig. 1, an automatic student behavior analysis method based on face recognition includes the following steps:
s1, acquiring identification event data of the student at each place in the school, wherein the identification event data comprises face images, shooting time and camera numbers of the student, and the camera numbers correspond to the places;
and S2, adding behavior classification information to students corresponding to each face image according to the identification event data and a preset student behavior classification table, establishing an identification event classification information database, and performing multi-level classification on the student behavior classification table according to the behaviors of the students in the school.
As a specific example, the correspondence relationship between the camera number and each location in step S2 means that the functions of each location in the school are set, and the locations are classified into multiple stages according to the functions, for example, there is a "study location" category, and there are subclasses such as "classroom" and "reading room" below the "study location" category; there are "sport places" and there are also "football court", "basketball court", "table tennis court", "fitness facilities" and other subclasses under this class. The number of levels of the function classification of the place is related to the specific function of the place, and corresponds to the classification of the major class, the minor class and the major group of the preset student behavior classification table. The cameras are installed in places with various function classifications, the cameras are numbered, the camera numbers correspond to the places in a corresponding relationship, functions of places where students are located corresponding to the face images can be judged by identifying the camera numbers and the collected face images, and data support is provided for the behaviors of the students according to the classification of the preset student behavior classification table.
The mode classification is carried out on all places in a school, the mode classification is carried out on all places, the mode classification is divided into an open type and a closed type, if the places are closed, an entrance camera is arranged at an entrance of the places, an exit camera is arranged at an exit, and the time of entering and leaving can be obtained while the number of the entrance camera and the number of the exit camera collect images, so that the state information of students in the places is determined. If the place is an open place, the camera is installed at a position which is convenient for capturing a portrait and has a good visual field, and the state of entering the place is reflected by which camera number, and the state of leaving the place is reflected by which camera number.
The specific steps of S2 include:
and comparing the face image in the acquired identification event data with a face photo in prestored student identity information by adopting a face identification algorithm to obtain the identity information of the student corresponding to the face image, wherein the prestored student identity information comprises the name and the ID of the student, the face photo for identification, the class of the student and the like. And (3) enabling the identity information of the students to correspond to the corresponding acquired identification event data one by one, establishing an identification event classification information database, and storing the identification event classification information database for use. For example: every time the camera identifies the face of the student, the camera (or the background algorithm server) sends a message to the data server, wherein the message comprises the ID, the occurrence time, the camera ID and the like of the identified student. The data server is thereby informed of the occurrence of the "student identified" event. Examples are: "the student S1 is recognized by the camera C1 at time T1", "the student S1 is recognized by the camera C2 at time T2", and the like.
And obtaining the place information according to the corresponding relation between the camera number and each place. For example, assuming that the camera C1 is installed at the entrance of the "school bookroom" and the camera C2 is installed at the exit of the "school bookroom", the above-mentioned "student S1 is recognized by the camera C1 at the time T1" is further defined as "student S1 enters the bookroom at the time T1", "student S1 is recognized by the camera C2 at the time T2" is further defined as "student S1 leaves the bookroom at the time T2", and data preparation is made for the subsequent student behavior classification.
And obtaining the behavior classification corresponding to the identity information of the student from the preset student behavior classification table according to the place information. To facilitate statistical analysis, the system performs multiple levels of classification of behaviors that a student may make in a school, and table 1 is an example of a classification of student behaviors. The primary classification is a high-level classification (in order to embody the classification level, the primary classification is named as a large class), and includes: study, physical activities, dining, school, injury and free time. The classification lower than the first classification is a second classification (named as a subclass), wherein the learning class is divided into a class and a reading class; the large category of physical activities includes five categories of physical education, self-exercise, games, artistic activities and labor. The classification one lower than the second classification is a third classification (named as a big group), wherein, taking a self-exercising subclass as an example, the three big groups include table tennis, badminton and football.
TABLE 1 student behavior Classification Table
The behavior of the student can be classified according to the location information corresponding to the serial number of the camera in the identification event data. For example: after obtaining two information of "student S1 enters the viewing room at time T1" and "student S1 leaves the viewing room at time T2", it is found that the time period from time T1 to time T2, the student S1 can find the corresponding "reading in the viewing room" in the three-level classification according to Table 1, so the third-level classification (the third-level classification name can be defined as a large group) is "reading in the viewing room", the corresponding second-level classification (the second-level classification name can be defined as a small group) is "reading", and the corresponding first-level classification (the first-level classification name can be defined as a large group) is "learning".
Only a portion of the above table 1 activities may be identified with relative accuracy by the system described herein. Such as activities performed in a well-defined, single enclosed indoor environment; the school entrance is provided with the behavior of entering and exiting the school under the control of the barrier gate. Some special behaviors, such as singing, walking, chatting, playing, putting, etc., cannot be judged by a simple face recognition algorithm and need to rely on a more complex pattern recognition algorithm. However, the framework created by the present invention can be expanded to address these future behaviors that can only be accurately determined.
Furthermore, according to an identification event classification information database, an identification event classification information database can be established for students corresponding to each face image, wherein each piece of information in the identification event classification information database comprises identity information, shooting time, place information, behavior classification information and the like of the students.
Further, the analysis method may further include step S3: and calculating the time proportion corresponding to each classification according to the data in the identification event classification information database in a period of time.
Taking the behavior analysis of a single student as an example, the step of S3 includes:
the total time length in the database of the identification event classification information of the same student is obtained for a period of time, for example, 7 days per week × 24 hours per day, 168 hours.
And calculating the time length occupied by each class of the students corresponding to each face image in the student behavior classification table. For example, the total length of time for "reading in a reading room" is 10 hours.
The time length occupied by each category is divided by the total time length to obtain the time proportion corresponding to each category, for example, the time proportion corresponding to 'reading in a reading room' is 5.95%.
Wherein, the step of calculating the time length occupied by each class of students corresponding to each face image in the student behavior classification table comprises:
establishing an identification event classification information score database for students corresponding to each face image according to the identification event classification information database;
sorting the data in the identification event classification information sub-database according to time sequence;
acquiring the number of a camera at an entrance and the corresponding shooting time of an entering place;
acquiring the camera number at the departure place and the shooting time of the departure place corresponding to the camera number at the entrance;
when the classification information is the same, obtaining a time period of the classification information according to the time period between the shooting time of the entering place and the shooting time of the leaving place;
and accumulating the time periods corresponding to the same classification information to obtain the duration of the time length occupied by each classification.
The time proportion corresponding to each classification can be counted according to the classification level, and the method comprises the following steps: the time weight corresponding to each major class, the time weight corresponding to each minor class and the time weight corresponding to each major group.
If student S enters the viewing room at time T1 and leaves the viewing room at time T2, a piece of behavior data is generated: student A stayed in the viewing room for T2-T1 from time T1. Since the function of the reading room is reading, the student is considered to have performed the "reading indoors" activity in the time period, and according to table 1, the behavior is classified into "learning" in the first stage, reading "in the second stage, and reading" in the reading room in the third stage.
As another example, student S entered the closed badminton stadium at time T1 and exited the badminton stadium at time T2, then a piece of behavioral data was generated: student A stayed in the badminton stadium for T2-T1 from time T1. Since the badminton stadium functions as a badminton shuttlecock, the student is considered to have performed a "badminton" activity for the time period. According to table 1, the behaviors are classified as "literary activities" at the first level, as "self-exercises" at the second level, and as "shuttlecocks" at the third level.
In particular, the large class also includes in-and-out schools, and the small class of in-and-out schools includes: returning to school, leaving school and temporarily going out, wherein the large group of returning schools comprises normal returning schools and late schools; the large group of departure schools comprises normal departure schools and early quitting; the large group for temporary outgoing comprises temporary outgoing school in class time and temporary outgoing school in rest time.
The steps of classifying the normal school return, late school, normal school leaving, early school leaving, temporary school leaving during class time and temporary school leaving during rest time comprise:
acquiring face images of students and corresponding school returning moments by a camera at an entrance of a school door of a school;
acquiring a face image of the same student and a corresponding school leaving moment through a camera at an exit of a school door of the school;
acquiring student identity information corresponding to the face image of the student according to the face image of the student;
when the school returning time is earlier than or equal to the school entering time of a preset work and rest time table, judging that the identity information of the student corresponds to the student as normal school returning, otherwise, judging that the school returning time is late; when the leaving school time is later than or equal to the leaving school time of a preset work and rest time table, judging that the student identity information corresponds to the student to be a normal leaving school, and otherwise, judging that the student is early returned;
when the leaving school time and the returning school time appear in the preset school time, the student identity information is judged to temporarily go out of school corresponding to the school time of the student; and when the leaving school time and the returning school time appear in the preset rest time, judging that the student identity information temporarily leaves the school corresponding to the student rest time.
The analysis method of events entering and exiting school is illustrated as follows:
1) if the event indicates that a student enters or leaves the door of the school, and the student enters or leaves the school for the first time or the last time in a normal school entering and leaving period, the behavior is recorded as the 'returning school' or 'leaving school' of the student, whether the 'returning school' is the 'normal returning school' or 'late school' is judged according to the returning school time specified by the school, and whether the 'leaving school' is the 'normal leaving school' or 'early leaving'.
Assume that a school specifies that a student arrives at school before 5:30 pm on sunday each week, departs from school after 5:30 pm on friday, walks to school before 8:00 am on each day from monday to friday, and departs from school after 5:40 pm. Then:
if the posted student S entered the school gate at T1 (5:00 PM on a certain Sunday) and no other event occurred for the student to enter the school gate before time T1 during the day, then the system records this event as "student S normally returned at time T1" because 5:00 PM is earlier than school-specified return time. The behaviors are classified into "in and out school" in the first class, "return school" in the second class, and "normal return school" in the third class.
As another example, a walk-behind student S leaves the school gate at T1 (5:00 pm on a certain wednesday), and no other event occurs for the student to leave the school gate after time T1 during the day, then the system records this event as "student S recedes early at time T1" because 5:00 pm is earlier than the school-specified departure time. The behaviors are classified into 'in and out school' in the first class, 'out school' in the second class and 'early exit' in the third class.
2) If two adjacent events indicate that a student walks out of a school gate first and then walks into the school gate, but the school-entering event is not the first time of the student in a normal school-entering and school-exiting period, and the school-exiting event is not the last time of the student in a normal school-entering and school-exiting period, the school-entering event is recorded as the temporary school-exiting event of the student, the exiting time is the difference of two time occurrence times, and then the temporary school-exiting event is judged to be the school-entering time or the rest time according to the comparison of the school-leaving time table and the class schedule of the student.
For example: student S leaves the school gate at time T1 (2: 08 in the afternoon on a certain day), and leaves the school gate at time T2 (2: 31 in the afternoon on the same day). And the student had an event of going out of the school gate after time T1 and the student had an event of going into the school gate before time T2 within the day, then the system records this event as "student S temporarily going out at 2:08 pm on a day monday and returning at 2:31 pm on the same day". The student has a behavior of 'going out temporarily in class hours' because the student has a course arrangement in the time period of 2:08 in the afternoon to 2:31 in the afternoon.
Analyzing the 'student recognized' event reported by the camera according to the method, obtaining 'student behavior' data, and then carrying out statistical analysis according to the student behavior activity to obtain the interests and hobbies of the students; but also to perform analysis statistics of group and group according to schools, classes, etc.
Based on the same conception, the invention also provides a student behavior automatic analysis system based on face recognition, which comprises: the system comprises a camera, a local area network, a data server and a data reading device, and is shown in a system block diagram in FIG. 2.
The data server prestores student identity information, and the student identity information comprises: student name, ID, and facial photo; the data server prestores a student behavior classification table which is classified in multiple stages according to the behavior of students in schools; the data server receives the identification event data via the local area network. The data server adds behavior classification information to students corresponding to each face image according to a prestored student behavior classification table, and establishes and stores an identification event classification information database.
The system comprises cameras, a data server and a client side, wherein the cameras are arranged in all places in a school and are numbered, the camera numbers correspond to the places and are used for acquiring identification event data of students in all the places in the school, the identification event data comprise face images of the students, shooting time and camera numbers, and the identification event data are sent to the data server through a local area network; the camera also reads pre-stored student identity information from the data server, and acquires the name and the ID of the student corresponding to the face image by adopting a face recognition algorithm according to the student identity information.
The data reading device is used for reading and displaying data in the data server.
Furthermore, the data server can analyze the personality and interest of the student according to the data in the event classification information database, and send the analysis result to the data reading device through the local area network.
The data server records and stores the event data, converts the event data into student behavior data according to the steps of the method and stores the student behavior data. Under the requirement of users such as teachers, parents and the like or under the driving of planning tasks, the data server can generate various student behavior statistics including the statistics of individual students and groups at all levels according to the student behavior data. Because the system carries out multi-stage classification on the behavior activities of the students, various relatively accurate classification statistics can be carried out, and analysis results in the aspects of the personality and the interests of the students can be obtained according to the classification statistics.
For example, it can be counted that within a certain period of time, a) how much time a student spends in learning out of class accounts, so that it can be known whether the student likes to learn; B) the length of time and the occupation amount of the table tennis and the badminton are counted, and further, the occupation amount of time and the occupation amount of the table tennis and the badminton can be counted, so that whether the student likes sports or not and what kind of sports are enjoyed can be known; C) the students can go out for a while by how many times later, how many times earlier, so that whether abnormal social interaction exists in the period of time of the students can be analyzed; D) the student can enter the sanitary room for a plurality of times and occupy a plurality of times, so that the primary analysis and the like can be carried out on the injury and disease conditions of the student in the period.
Claims (10)
1. A student behavior automatic analysis method based on face recognition is characterized by comprising the following steps:
s1, acquiring identification event data of each place of the student in the school, wherein the identification event data comprises face images, shooting time and camera numbers of the student, and the camera numbers correspond to the places;
and S2, adding behavior classification information to students corresponding to each face image according to the identification event data and a preset student behavior classification table, and establishing an identification event classification information database.
2. The automatic student behavior analysis method based on face recognition as claimed in claim 1, wherein the specific steps of step S2 include:
acquiring identity information corresponding to the face image;
obtaining location information according to the corresponding relation between the camera number and each location;
according to the identity information and the place information, behavior classification corresponding to the identity information is obtained from the preset student behavior classification table;
and establishing an identification event classification information database for each student corresponding to the identity information, wherein each piece of information in the identification event classification information database comprises identity information, shooting time, place information and behavior classification information of the student.
3. The automatic student behavior analysis method based on face recognition as claimed in claim 1, further comprising a step S3 of analyzing the personality and hobbies of students based on the recognition event classification information database.
4. The method for automatically analyzing the behaviors of the student based on the face recognition as claimed in claim 3, wherein the method for analyzing the characters and interests of the student comprises the following steps: and calculating the time proportion corresponding to each classification according to the data in the identification event classification information database.
5. The automatic student behavior analysis method based on face recognition as claimed in claim 4, wherein the time proportion corresponding to each classification is calculated according to the level of the behavior classification.
6. The automatic student behavior analysis method based on face recognition according to any one of claims 1-5, wherein the preset student behavior classification table comprises grades: major classes, minor classes and major groups,
the broad categories include, but are not limited to: study, physical activity, dining, injury and free time;
each large class is divided into a plurality of small classes, each small class is divided into a plurality of large groups, and the corresponding places of each large group correspond to the camera numbers in a corresponding manner.
7. The automatic student behavior analysis method based on face recognition as claimed in claim 6, wherein the major group further comprises an in-out school, the minor group of the in-out school comprises a return school, a leaving school and a temporary out, and the major group of the return school comprises a normal return school and a late school; the large group of departure schools comprises normal departure schools and early quitting; the large group for temporary outgoing comprises temporary outgoing school in class time and temporary outgoing school in rest time.
8. The automatic student behavior analysis method based on face recognition as claimed in claim 7 wherein the step of classifying the normal school return, late school, normal school leaving, early school leaving, temporary school class time leaving and temporary school rest time leaving comprises:
acquiring face images of students, student identity information corresponding to the face images of the students and corresponding school returning moments by a camera at a school door entrance;
acquiring a face image of the same student, student identity information corresponding to the face image of the student and a corresponding moment of departure from school by a camera at an exit of a school gate;
when the school returning time is earlier than or equal to the school entering time of a preset work and rest time table, judging that the identity information of the student corresponds to the student as normal school returning, otherwise, judging that the school returning time is late; when the leaving school time is later than or equal to the leaving school time of a preset work and rest time table, judging that the student identity information corresponds to the student to be a normal leaving school, and otherwise, judging that the student is early returned;
when the leaving school time and the returning school time appear in the preset school time, the student identity information is judged to temporarily go out of school corresponding to the school time of the student; and when the leaving school time and the returning school time appear in the preset rest time, judging that the student identity information temporarily leaves the school corresponding to the student rest time.
9. An automatic student behavior analysis system based on face recognition is characterized by comprising: the system comprises a camera, a local area network, a data server and a data reading device;
the data server prestores student identity information, and the student identity information comprises: student name, ID, and facial photo; the data server prestores a student behavior classification table; the data server receives the identification event data through a local area network; the data server adds behavior classification information to students corresponding to the face images according to the student behavior classification table and establishes an identification event classification information database;
the cameras are installed in various places in a school and are numbered, the camera numbers correspond to the various places and are used for acquiring identification event data of students in the various places in the school, the identification event data comprise face images of the students, shooting time and the camera numbers, and the identification event data are sent to a data server through the local area network; the camera also reads prestored student identity information from the data server, and acquires the name and ID of a student corresponding to the face image by adopting a face recognition algorithm according to the student identity information;
the data reading device is used for reading and displaying the data in the data server.
10. The system as claimed in claim 9, wherein the data server further analyzes the personality and hobbies of the student according to the database of the identification event classification information, and transmits the analysis result to the data reading device through a local area network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910921829.8A CN110716920A (en) | 2019-09-27 | 2019-09-27 | Student behavior automatic analysis method and system based on face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910921829.8A CN110716920A (en) | 2019-09-27 | 2019-09-27 | Student behavior automatic analysis method and system based on face recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110716920A true CN110716920A (en) | 2020-01-21 |
Family
ID=69211021
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910921829.8A Pending CN110716920A (en) | 2019-09-27 | 2019-09-27 | Student behavior automatic analysis method and system based on face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110716920A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111738884A (en) * | 2020-06-23 | 2020-10-02 | 北京航空航天大学云南创新研究院 | Student behavior diagnosis and management method based on intelligent campus student position information |
| CN115331346A (en) * | 2022-08-30 | 2022-11-11 | 深圳市巨龙创视科技有限公司 | Campus access control management method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108347490A (en) * | 2018-04-25 | 2018-07-31 | 衢州龙瀚计算机科技有限公司 | A kind of campus application apparatus and system based on biological identification technology |
| CN109636688A (en) * | 2018-12-11 | 2019-04-16 | 武汉文都创新教育研究院（有限合伙） | A kind of students ' behavior analysis system based on big data |
| CN109684514A (en) * | 2018-12-11 | 2019-04-26 | 武汉文都创新教育研究院（有限合伙） | Students ' behavior positioning system and method based on track data |
| CN208834319U (en) * | 2018-06-06 | 2019-05-07 | 吴可迪 | A kind of novel student intelligent information system that classes are over leaves school |
| CN110009539A (en) * | 2019-04-12 | 2019-07-12 | 烟台工程职业技术学院(烟台市技师学院) | A kind of student is in school learning state smart profile system and application method |
-
2019
- 2019-09-27 CN CN201910921829.8A patent/CN110716920A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108347490A (en) * | 2018-04-25 | 2018-07-31 | 衢州龙瀚计算机科技有限公司 | A kind of campus application apparatus and system based on biological identification technology |
| CN208834319U (en) * | 2018-06-06 | 2019-05-07 | 吴可迪 | A kind of novel student intelligent information system that classes are over leaves school |
| CN109636688A (en) * | 2018-12-11 | 2019-04-16 | 武汉文都创新教育研究院（有限合伙） | A kind of students ' behavior analysis system based on big data |
| CN109684514A (en) * | 2018-12-11 | 2019-04-26 | 武汉文都创新教育研究院（有限合伙） | Students ' behavior positioning system and method based on track data |
| CN110009539A (en) * | 2019-04-12 | 2019-07-12 | 烟台工程职业技术学院(烟台市技师学院) | A kind of student is in school learning state smart profile system and application method |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111738884A (en) * | 2020-06-23 | 2020-10-02 | 北京航空航天大学云南创新研究院 | Student behavior diagnosis and management method based on intelligent campus student position information |
| CN115331346A (en) * | 2022-08-30 | 2022-11-11 | 深圳市巨龙创视科技有限公司 | Campus access control management method and device, electronic equipment and storage medium |
| CN115331346B (en) * | 2022-08-30 | 2024-02-13 | 深圳市巨龙创视科技有限公司 | Campus access control management method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lames et al. | On the search for reliable performance indicators in game sports | |
| Mukala et al. | Exploring students’ learning behaviour in moocs using process mining techniques | |
| CN107958351A (en) | Teaching quality assessment cloud service platform | |
| CN108154304A (en) | There is the server of Teaching Quality Assessment | |
| CN110009210B (en) | Comprehensive assessment method for student class listening level based on attention degree and concentration degree | |
| CN105791299A (en) | Unattended monitoring type intelligent on-line examination system | |
| Hoover | The role of the community in transition to the adult world for students with disabilities | |
| CN107169902A (en) | The classroom teaching appraisal system of micro- Expression analysis based on artificial intelligence | |
| CN111353921A (en) | Examination management method and system and electronic equipment | |
| CN111311131A (en) | Intelligent classroom teaching behavior analysis method, storage medium and intelligent television | |
| CN111275345B (en) | Classroom informatization evaluation and management system and method based on deep learning | |
| CN110716920A (en) | Student behavior automatic analysis method and system based on face recognition | |
| CN105373774B (en) | A kind of detection method of preschool teacher's school's corporal punishment child's behavior | |
| CN109711377A (en) | Standardize examinee's positioning and method of counting in the single-frame images of examination hall monitoring | |
| CN106846522B (en) | Roll call device and roll call method used for same | |
| Vogler et al. | Relationship of Presage, Context, and Process Variables to ALT–PE of Elementary Level Mainstreamed Students | |
| CN114529987A (en) | Intelligent teaching monitoring device and method based on cloud data online education for colleges and universities | |
| CN110309753A (en) | A kind of race process method of discrimination, device and computer equipment | |
| CN112990705A (en) | On-line training platform for personalized recommended courses | |
| CN114241596A (en) | Behavior analysis method, device and equipment | |
| CN114550097A (en) | Cross-school-area linkage attendance checking method and system based on artificial intelligence | |
| US20190385477A1 (en) | System and method for sports social media application | |
| Kalani et al. | What are the factors influencing Iran’s sports talent identification process? Findings of a qualitative study | |
| Rife et al. | ALT-PE Versions I and II: Evolution of a Student-Centered Observation System in Physical Education. | |
| CN113920396B (en) | Method, system and equipment for quantitatively evaluating visual cognitive ability of special post personnel |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200121 |