WO2023029355A1 - Big data-based student attendance management system and method - Google Patents

Abstract

Disclosed are a big data-based student attendance management system and method, which relate to the technical field of big data-based student management. The system comprises a monitoring terminal, a student attendance analysis module, a student abnormal behavior analysis module and an attendance summarization module. The monitoring terminal obtains the monitoring cameras located in different places, retrieves student data, adjusts shooting angles and sets the size of imaging areas. The student attendance analysis module acquires the distribution of the numbers of student head areas acquired by the monitoring cameras in different time periods, thereby analyzing the attendance of the students. The student abnormal behavior analysis module obtains the difference in the numbers of the student heads between different time periods, and analyzes whether the difference is due to abnormal student behavior shielding the student heads or abnormal queue distribution leading to reduced student attendance. The attendance summarization module sends a compared attendance summary table to a teacher terminal, and publishes the attendance score in time. Deliberate absence of students can be prevented.

Description

A system and method for student attendance management based on big data technical field

The invention relates to the technical field of big data student management, in particular to a big data-based student attendance management system and method.

Background technique

Student attendance refers to the number of students participating in activities or in class, as a means of restricting students in class; when students participate in class, teachers can monitor students' class records by roll call or fingerprint entry, which can Monitor and screen the number of students attending; however, when students participate in activities, such as: students participating in flag raising activities, participating in centennial school celebrations, etc., due to the large number of participants, it is impossible to monitor the actual number of students participating in time, resulting in many The student does not participate in the activity and does not attend school;

During the process of queuing up in the queue, the number of students' heads cannot be accurately identified due to the students' actions such as tying shoelaces, bending over, and supporting the waist, and deviations will occur during the detection process. Therefore, only one analysis of the students' heads The attendance rate will produce errors, so it is necessary to propose a new technical solution to solve the problem of attendance rate of students in attendance activities.

Contents of the invention

The purpose of the present invention is to provide a big data-based student attendance management system and method to solve the problems raised in the above-mentioned background technology.

In order to solve the above technical problems, the present invention provides the following technical solutions: a student attendance management system based on big data, the system includes a monitoring terminal, a student attendance analysis module, a student abnormal behavior analysis module and an attendance rate summary module;

The monitoring terminal obtains the monitoring terminals distributed in different locations, retrieves student data information, adjusts the shooting angle and sets the size of the shooting area;

The student attendance analysis module obtains the distribution of the head area of the students in different time periods on the monitoring end, and then analyzes the attendance rate of the students;

The student abnormal behavior analysis module obtains the difference in the number of students' heads in different time periods, and analyzes whether the resulting difference is the reason why students cover the heads of students or the abnormal distribution of queues leads to the decrease in the number of students attending;

The attendance rate summary analysis module sends the compared attendance summary table to the teacher's terminal, and publishes the attendance score in time;

The attendance rate summary module is connected with the monitoring terminal, the student attendance analysis module, and the student abnormal behavior analysis module.

Further, the monitoring terminal includes an angle shooting adjustment unit, a data acquisition unit, a data analysis unit and an area size setting unit;

The angle shooting adjustment unit calls the monitoring terminals distributed in the activity place, controls the monitoring terminals and shoots the students from different angles; thus, the number of attendance of the students can be better obtained;

The data acquisition unit analyzes the height distribution and the student spacing distribution in the student queue according to the image taken by the monitoring terminal; thus it can be judged whether the students are evenly distributed, so that the head portraits of the students can be better intercepted and clearly identified. part of the image;

The data analysis unit analyzes and compares the height of the students and the distance between the students to determine whether the arrangement of the students is evenly distributed;

The area size setting unit intercepts the size of the captured image according to the arrangement of the students to analyze the attendance status of the students.

Further, the student attendance analysis module includes a first monitoring analysis unit, a student head frame selection processing unit, a student head quantity summary unit, a second monitoring analysis unit, and a head quantity comparative analysis unit;

The first monitoring and analysis unit controls the monitoring terminal to intercept the distribution image of the student queue for the first time and analyze the attendance numbers of the students according to the distribution of the student queue;

The student head frame selection processing unit selects the student head unit according to the intercepted image and summarizes the number of student heads;

The second monitoring and analysis unit controls the monitoring terminal to intercept the distribution image of the student queue for the second time and analyze the attendance numbers of the students according to the distribution of the student queue;

The number of heads comparison analysis unit analyzes the difference between the number of attendances analyzed by the first intercepted image and the number of attendances analyzed by the second intercepted image, and judges whether the result of the difference is greater than the first preset difference and smaller than the first preset difference. Two preset values, when the difference result does not meet the above conditions, analyze whether the difference result is greater than the second preset difference;

The output end of the head number comparison analysis unit is connected with the input end of the first monitoring analysis unit, the image partition detection unit, the student head frame selection processing unit, the student head number summary unit, and the second monitoring analysis unit.

Further, the student’s abnormal behavior analysis module includes an image area abnormal comparison unit, a monitoring terminal call monitoring unit, a queue abnormal change analysis unit, a queue angle presentation unit, a queue familiarity analysis unit, and a student attendance rate verification unit;

The image area anomaly comparison unit detects that the difference between the number of attendances analyzed by the first intercepted image and the number of attendances analyzed by the second intercepted image is greater than the first preset value and smaller than the second preset value, and analyzes the intercepted Whether there is an abnormal image area in the image, and send it to the monitoring terminal to call the monitoring unit for monitoring;

The monitoring terminal calls the monitoring unit, calls the continuous blank area and compares the average area sum of the head area of the student, and analyzes whether the student's movement blocks the head area;

The queue abnormal change analysis unit detects that the difference between the number of attendance analyzed by the first intercepted image and the number of attendance analyzed by the second intercepted image is greater than the second preset difference, and analyzes whether the number of attendance in the queue has changed;

The queue angle presentation unit analyzes the angles between adjacent queues according to the queue distribution of the first intercepted image and the second intercepted image;

The queue familiarity analysis unit analyzes whether the familiarity between the queues is greater than the third preset value according to the actions of the students in the queue, thereby analyzing whether the queue is originally a sub-queue split by a whole queue;

The student attendance rate verification unit verifies the student's attendance rate according to the actions of the students in the queue;

The output end of the student attendance rate verification unit is connected to the input end of the image area abnormal comparison unit, the monitor terminal call monitoring unit, the queue abnormal change analysis unit, the queue angle presentation unit and the queue familiarity analysis unit.

Further, the attendance rate summary analysis module includes a teacher terminal verification unit, an attendance score announcement unit and a reminder warning unit;

The teacher's terminal verification unit receives and verifies the student's attendance rate and summarizes and analyzes it;

The attendance score announcement unit analyzes the attendance scores of the students according to the student attendance summary results:

The reminder and warning unit sends the attendance score to the students and warns the deduction result of the non-attendance students.

A method for managing student attendance based on big data, the method performs the following steps:

Step Z01: call the monitoring terminal to take pictures of the students, adjust the position and size of the shooting area according to the height of the students and the arrangement interval in the queue, select the head area of the students in each queue in the image, and analyze according to the first monitoring the number of heads of students in the queue;

Step Z02: Set the number of students' heads in the second monitoring and analysis queue, and determine the difference between the number of students' heads in the first monitoring period and the second monitoring period. When the set value is less than the second preset value, analyze whether the area of the blank area of continuous students in the queue is the average area formed by the head area of the number of students, and analyze the student's action when the condition is not met; when the first monitoring period and the second monitoring period When the difference in the number of students' heads is greater than the second preset value, analyze whether the included angle between the two adjacent queues satisfies the included angle condition, and when the included angle between the adjacent two queues satisfies the included angle condition, further analysis Familiarity among students to determine whether students are present;

Step Z03: Obtain an attendance summary table according to the attendance of the students, and publish the attendance scores of the students to warn the students. In the step Z01, the collection of height distribution of students in the queue is obtained as W={w ₁ , w ₂ , w ₃ ...w _n }, n refers to the number of students, and the distance between students in the queue is D={d ₁₂ , d ₂₃ , d ₃₄ ...d _n(n-1) }, d _(n-1)n refers to the distance between the n-1th student and the nth student in line, and obtains and compares the distance between different students ;

When it is detected that d _(n+1)n -d _(n+1)(n+2) = 0, it means that the distance between the students of this cohort is evenly distributed, when it is detected that d _(n+1)n -d ₍ When _n+1)(n+2) ≠0, it means that the distance between students in this cohort is not evenly distributed;

Arbitrary numerical analysis w _i -w _i-1 <wi ₊₁ -w _i , when this condition is met, it means that the students in the cohort are distributed in increasing order; uneven;

When it is detected that the queue spacing is uniformly distributed and the distribution of students in the queue is increasing sequentially, select the queue and analyze the number of students' heads, where d _(n+1)n is the distance between the nth student and the n+1th student d _{(n+1)(n+2) is} the distance between the n+1th student and the n+2th student; w _i refers to the height of the i-th student, w _i+1 , w _i+1 refers to the height of the i+1th student and the height of the i-1th student;

When the students are not satisfied with the sequential increase or the arrangement is uneven, if the arrangement and combination of students are randomly distributed, the tall students in front will affect the detection of the overhead image of the short students, thus affecting the judgment of the attendance rate of the entire student.

In the step Z02, the head images of the students in the queue are acquired according to the selected area, and the set of the area of the head images of the students is L={l ₁ , l ₂ , l ₃ ...l _n };

The average area of the student's head image is

When it is detected that the student head detection area in the queue contains a continuous blank area and the area of the blank area is not equal to the average area sum of the student head images and the number of students in the queue is less than the actual number of students, it means that there are student head areas in the blank area not detected;

When the number of student head areas in the blank area is set to be equal to the actual number in the second monitoring analysis, it means that the blank area did not detect the student head area due to abnormal movements during the first monitoring analysis and the second monitoring analysis time period;

In the step Z02, the difference in the number of students distributed by adjacent cohorts in the first monitoring analysis is greater than the third preset value, and the number of students distributed in adjacent cohorts in the second monitoring analysis is smaller than the third preset value When the students in the adjacent queue face the pointed direction as the start direction point, and the students in the adjacent queue turn away from the pointed direction as the end direction point, the data vectors formed by the adjacent queue are respectively

and

Analyze Data Vectors

and data vector

The angle θ between is specifically as the following formula:

Among them, θ represents

and

the angle between,

and

respectively represent the modulus of the queue vector;

When θ=0° or 180°, it means that there is no angle between adjacent queues, and there is no tendency for adjacent queues to approach each other. When θ∈(0°, 180°), it means that there is a gap between adjacent queues. Corner, adjacent queues contain a tendency to move closer to each other.

When a data vector is detected

and

When the angle between is θ∈(0°, 180°), the familiarity in the adjacent queue is obtained, and when it is detected that the familiarity in the adjacent team is higher than the third preset value, it means that the familiarity between the adjacent teams is Two branch teams with high familiarity and split by the whole team; when it is detected that the familiarity of adjacent teams is lower than the third preset value, it means that the familiarity between adjacent teams is low and not formed by a whole team The two teams formed by splitting indicate that the queue has shifted and the queue contains the number of students who did not attend;

Judgment is made by the following formula:

Q=Q ₀ +Q _i ;

Q _i =k·α;

k refers to the number of action interactions between adjacent queues, α refers to the familiarity coefficient, Q refers to the total familiarity between adjacent queues, Q ₀ refers to the static familiarity, and Q _i refers to the dynamic familiarity.

Compared with the prior art, the beneficial effects achieved by the present invention are:

The set monitoring analyzes the attendance rate of students in the first monitoring period and the second monitoring period, in case some students fail to detect the student's attendance due to behavioral actions; detect the number of students' heads in the first monitoring period and the second monitoring period When the difference is greater than the first preset value and less than the second preset value, analyze whether the area of the blank area of the continuous students in the queue is the average area formed by the head areas of different students; When the difference is greater than the second preset value, analyze whether the included angle between two adjacent queues satisfies the included angle condition. When the included angle between adjacent two queues meets the included angle condition, further analyze the familiarity of students Value, so as to analyze the attendance of students, can reduce students' laziness, so as to strengthen the management of students and actively participate in school activities.

Description of drawings

The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the description, and are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the attached picture:

Fig. 1 is the student attendance detection step schematic diagram of a kind of student attendance management system based on big data of the present invention;

Fig. 2 is a module composition schematic diagram of a kind of student attendance management system based on big data of the present invention;

Fig. 3 is the original queue distribution schematic diagram of a kind of student attendance management system based on big data of the present invention;

Fig. 4 is a schematic diagram of queue changes of a student attendance management system based on big data in the present invention.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

Please refer to Fig. 1-Fig. 4, the present invention provides technical scheme:

A student attendance management system based on big data, the system includes a monitoring terminal, a student attendance analysis module, a student abnormal behavior analysis module and an attendance rate summary module;

The monitoring terminal obtains the monitoring terminals distributed in different locations, retrieves student data information, adjusts the shooting angle and sets the size of the shooting area;

The student attendance analysis module obtains the distribution of the head area of the students in different time periods on the monitoring end, and then analyzes the attendance rate of the students;

The student abnormal behavior analysis module obtains the difference in the number of students' heads in different time periods, and analyzes whether the resulting difference is the reason why students cover the heads of students or the abnormal distribution of queues leads to the decrease in the number of students attending;

The attendance rate summary analysis module sends the compared attendance summary table to the teacher's terminal, and publishes the attendance score in time;

The attendance rate summary module is connected with the monitoring terminal, the student attendance analysis module, and the student abnormal behavior analysis module.

Further, the monitoring terminal includes an angle shooting adjustment unit, a data acquisition unit, a data analysis unit and an area size setting unit;

The angle shooting adjustment unit calls the monitoring terminals distributed in the activity place, controls the monitoring terminals and shoots the students from different angles;

The data acquisition unit analyzes the height distribution and the student spacing distribution in the student queue according to the image taken by the monitoring terminal;

The data analysis unit analyzes and compares the height of the students and the distance between the students to determine whether the arrangement of the students is evenly distributed;

When detecting the height of the students, it is used to determine whether the current queuing status of the queue is distributed sequentially or randomly; random distribution means that the distribution does not follow the height from low to high or from high to low;

The area size setting unit intercepts the size of the captured image according to the arrangement of the students and analyzes the student attendance status, thereby more clearly showing the current attendance status and increasing the clarity of identification. If the area size is not adjusted during identification, the identified student The number of heads will not be accurate;

Further, the student attendance analysis module includes a first monitoring analysis unit, a student head frame selection processing unit, a student head quantity summary unit, a second monitoring analysis unit, and a head quantity comparative analysis unit;

The first monitoring and analysis unit controls the monitoring terminal to intercept the student queue distribution image and analyze the attendance number of students for the first time according to the distribution of the student queue;

The student head frame selection processing unit selects the student head unit according to the intercepted image and summarizes the number of student heads;

The second monitoring and analysis unit controls the monitoring terminal to intercept the distribution image of the student queue for the second time and analyze the attendance numbers of the students according to the distribution of the student queue;

The number of heads comparison analysis unit analyzes the difference between the number of attendances analyzed by the first intercepted image and the number of attendances analyzed by the second intercepted image, and judges whether the result of the difference is greater than the first preset difference and smaller than the first preset difference. Two preset values, when the difference result does not meet the above conditions, analyze whether the difference result is greater than the second preset difference;

The first preset value is smaller than the second preset value, and the preset value is the number of attendance;

The third preset value is standard familiarity;

The fourth preset value is the standard difference in the number of students in adjacent queues;

The output end of the head number comparison analysis unit is connected with the input end of the first monitoring analysis unit, the image partition detection unit, the student head frame selection processing unit, the student head number summary unit, and the second monitoring analysis unit.

Further, the student’s abnormal behavior analysis module includes an image area abnormal comparison unit, a monitoring terminal call monitoring unit, a queue abnormal change analysis unit, a queue angle presentation unit, a queue familiarity analysis unit, and a student attendance rate verification unit;

The image area anomaly comparison unit detects that the difference between the number of attendances analyzed by the first intercepted image and the number of attendances analyzed by the second intercepted image is greater than the first preset value and smaller than the second preset value, and analyzes the intercepted Whether there is an abnormal image area in the image, and send it to the monitoring terminal to call the monitoring unit for monitoring;

The monitoring terminal calls the monitoring unit, calls the continuous blank area and compares the average area sum of the head area of the student, and analyzes whether the student's movement blocks the head area;

The continuous blank area refers to the continuous undetected area in the team; the continuous blank area refers to the area where students bend over;

The average area of the student's head area refers to the average area of the remaining student's head area except for the continuous undetected area area;

Comparing the continuous blank area with the average area sum of the student's head area refers to judging how much the area of the student's head area can be included in the area of the blank area.

The queue abnormal change analysis unit detects that the difference between the number of attendance analyzed by the first intercepted image and the number of attendance analyzed by the second intercepted image is greater than the second preset difference, and analyzes whether the number of attendance in the queue has changed;

The queue angle presentation unit analyzes the angles between adjacent queues according to the queue distribution of the first intercepted image and the second intercepted image;

The queue familiarity analysis unit analyzes whether the familiarity between the queues is greater than the third preset value according to the actions of the students in the queue, thereby analyzing whether the queue is originally a sub-queue split by a whole queue;

The student attendance rate verification unit verifies the student's attendance rate according to the actions of the students in the queue;

The output end of the student attendance rate verification unit is connected to the input end of the image area abnormal comparison unit, the monitor terminal call monitoring unit, the queue abnormal change analysis unit, the queue angle presentation unit and the queue familiarity analysis unit.

Further, the attendance rate summary analysis module includes a teacher terminal verification unit, an attendance score announcement unit and a reminder warning unit;

The teacher's terminal verification unit receives and verifies the student's attendance rate and summarizes and analyzes it;

The attendance score publishing unit analyzes the attendance scores of the students according to the student attendance summary results;

The reminder warning unit sends the attendance score to the student and warns the deduction result of the non-attendance student;

When verifying the student's attendance, the total score - attendance score is the number of points deducted for each non-attendance * the number of non-attendance, and the attendance score of the student in this semester can be obtained and displayed to the student. When the number of attendance in this semester is greater than the preset When the number of times, the student is punished.

A method for managing student attendance based on big data, the method performs the following steps:

Step Z01: call the monitoring terminal to take pictures of the students, adjust the position and size of the shooting area according to the height of the students and the arrangement interval in the queue, select the head area of the students in each queue in the image, and analyze according to the first monitoring the number of heads of students in the queue;

Step Z02: Set the number of students' heads in the second monitoring and analysis queue, and determine the difference between the number of students' heads in the first monitoring period and the second monitoring period. When the set value is less than the second preset value, analyze whether the area of the blank area of continuous students in the queue is the average area formed by the head area of the number of students, and analyze the student's action when the condition is not met; when the first monitoring period and the second monitoring period When the difference in the number of students' heads is greater than the second preset value, analyze whether the included angle between the two adjacent queues satisfies the included angle condition, and when the included angle between the adjacent two queues satisfies the included angle condition, further analysis Familiarity among students to determine whether students are present;

Step Z03: Obtain an attendance summary table according to the attendance of the students, and publish the attendance scores of the students to warn the students. In the step Z01, the collection of height distribution of students in the queue is obtained as W={w ₁ , w ₂ , w ₃ ...w _n }, n refers to the number of students, and the distance between students in the queue is D={d ₁₂ , d ₂₃ , d ₃₄ ...d _n(n-1) }, d _(n-1)n refers to the distance between the n-1th student and the nth student in line, and obtains and compares the distance between different students ;

When it is detected that d _(n+1)n -d _(n+1)(n+2) = 0, it means that the distance between the students of this cohort is evenly distributed, when it is detected that d _(n+1)n -d ₍ When _n+1)(n+2) ≠0, it means that the distance between students in this cohort is not evenly distributed;

Arbitrary numerical analysis w _i -w _i-1 <wi ₊₁ -w _i , when this condition is met, it means that the students in the cohort are distributed in increasing order; uneven;

When it is detected that the queue spacing is evenly distributed and the distribution of students in the queue is increasing sequentially, select the queue and analyze the number of students'heads; where, d _(n+1)n is the distance between the nth student and the n+1th student d _{(n+1)(n+2) is} the distance between the n+1th student and the n+2th student; wi refers to the height of the i-th student, wi+1, wi-1 Refers to the height of the i+1th student and the height of the i-1th student;

In the step Z02, the head images of the students in the queue are acquired according to the selected area, and the set of the area of the head images of the students is L={l ₁ , l ₂ , l ₃ ...l _n };

The average area of the student's head image is

When it is detected that the student head detection area in the queue contains a continuous blank area and the area of the blank area is not equal to the average area sum of the student head images and the number of students in the queue is less than the actual number of students, it means that there are student head areas in the blank area not detected;

When the number of student head areas in the blank area is set to be equal to the actual number in the second monitoring analysis, it means that the blank area did not detect the student head area due to abnormal movements during the first monitoring analysis and the second monitoring analysis time period;

The average area of the head image is set to determine that the area of the head image composed of multiple consecutive students is equal to the area of the blank area, and to analyze whether the area of the blank area is composed of multiple head areas, so as to analyze the area of the head image in the blank area. The number of students contained; and the average area of the image is set to better analyze the number of students contained in the blank area, because the size of the head area of each student is inconsistent.

In said step Z02, the difference in the number of students distributed in adjacent cohorts in the first monitoring analysis is greater than the fourth preset value, and the number of students distributed in adjacent cohorts in the second monitoring analysis is smaller than the fourth preset value When the student in the adjacent queue is facing the pointed direction as the starting direction point, the student in the adjacent queue is facing away from the pointed direction as the end point, and the student is facing the direction pointing to the direction as the end point O, the data vector formed by the adjacent queue respectively

and

Analyze Data Vectors

and data vector

The angle θ between is specifically as the following formula:

Among them, θ represents

and

the angle between,

and

respectively represent the modulus of the queue vector;

When θ=0° or 180°, it means that there is no angle between adjacent queues, and there is no tendency for adjacent queues to approach each other. When θ∈(0°, 180°), it means that there is a gap between adjacent queues. corner, adjacent queues contain a tendency to approach each other;

The set included angle is to be able to analyze whether there is an intersection between the two queues. When the included angle is included, it means that there is an included angle in the two queues; and when the included angle is larger, the indicated included angle is the closer.

When a data vector is detected

and

When the angle between is θ∈(0°, 180°), the familiarity in the adjacent queue is obtained, and when it is detected that the familiarity in the adjacent team is higher than the third preset value, it means that the familiarity between the adjacent teams is Two branch teams with high familiarity and split by the whole team; when it is detected that the familiarity of adjacent teams is lower than the third preset value, it means that the familiarity between adjacent teams is low and not formed by a whole team The two teams formed by splitting indicate that the queue has shifted and the queue contains the number of students who did not attend;

Judgment is made by the following formula:

Q=Q ₀ +Q _i ;

Q _i =k·α;

k refers to the number of action interactions between adjacent queues, α refers to the familiarity coefficient, Q refers to the total familiarity between adjacent queues, Q ₀ refers to the static familiarity, Q _i refers to the dynamic familiarity;

The actions between adjacent queues can be shoulder-to-shoulder chatting and close to each other. The Q ₀ set in the formula refers to the basic familiarity between students. Although students have not communicated with each other, they are familiar with each other, so this It is the familiarity between students; when the students are close to each other to chat, only the students have actions and exchanges, and the familiarity will change accordingly. Therefore, the _Qi set here is also essential.

Example 1:

Students of the same grade in the activity room are participating in listening to the speech, and the queue of students is from low to high standing up to enter and listen to the speech. According to the first monitoring terminal to take pictures of the area, the second monitoring terminal takes pictures of the area, According to the photo verification of the adjacent teams on the first monitoring terminal and the second monitoring terminal, it is detected that the number of adjacent teams in the area has changed. The vector of the adjacent team is A=(1, 2, 5), and the other vector team The vector B=(2, 2, 7);

Analyze Data Vectors

and data vector

The angle θ between them;

When θ=31∈(0, 180), it means that there is an angle between adjacent queues, and adjacent queues contain a tendency to approach each other;

Embodiment 2, as shown in Fig. 3, Fig. 4 is the trend graph that is close to each other in the adjacent queue, wherein the left side vector is

the right side is a vector

It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is a relationship between these entities or operations. There is no such actual relationship or order between them. Furthermore, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes elements not expressly listed. other elements of or also include elements inherent in such a process, method, article, or device.

Finally, it should be noted that: the above is only a preferred embodiment of the present invention, and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, it still The technical solutions recorded in the foregoing embodiments may be modified, or some technical features thereof may be equivalently replaced. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims (9)

1. A student attendance management system based on big data, characterized in that: the system includes a monitoring terminal, a student attendance analysis module, a student abnormal behavior analysis module and an attendance rate summary module;

   The monitoring terminal obtains the monitoring terminals distributed in different locations, retrieves student data information, adjusts the shooting angle and sets the size of the shooting area;

   The student attendance analysis module obtains the distribution of the head area of the students in different time periods on the monitoring end, and then analyzes the attendance rate of the students;

   The student abnormal behavior analysis module obtains the difference in the number of students' heads in different time periods, and analyzes whether the resulting difference is the reason why students cover the heads of students or the abnormal distribution of queues leads to the decrease in the number of students attending;

   The attendance rate summary analysis module sends the compared attendance summary table to the teacher's terminal, and publishes the attendance score in time;

   The attendance rate summary module is connected with the monitoring terminal, the student attendance analysis module, and the student abnormal behavior analysis module;

   The student abnormal behavior analysis module includes an image area abnormal comparison unit, a monitoring terminal call monitoring unit, a queue abnormal change analysis unit, a queue angle presentation unit, a queue familiarity analysis unit, and a student attendance rate verification unit;

   The image area anomaly comparison unit detects that the difference between the number of attendances analyzed by the first intercepted image and the number of attendances analyzed by the second intercepted image is greater than the first preset value and smaller than the second preset value, and analyzes the intercepted Whether there is an abnormal image area in the image, and send it to the monitoring terminal to call the monitoring unit for monitoring;

   The monitoring terminal calls the monitoring unit, calls the continuous blank area and compares the average area sum of the head area of the student, and analyzes whether the student's movement blocks the head area;

   The queue abnormal change analysis unit detects that the difference between the number of attendance analyzed by the first intercepted image and the number of attendance analyzed by the second intercepted image is greater than the second preset difference, and analyzes whether the number of attendance in the queue has changed;

   The queue angle presentation unit analyzes the angles between adjacent queues according to the queue distribution of the first intercepted image and the second intercepted image;

   The queue familiarity analysis unit analyzes whether the familiarity between the queues is greater than the third preset value according to the actions of the students in the queue, thereby analyzing whether the queue is originally a sub-queue split by a whole queue;

   The student attendance rate verification unit verifies the student's attendance rate according to the actions of the students in the queue;

   The output end of the student attendance rate verification unit is connected to the input end of the image area abnormal comparison unit, the monitor terminal call monitoring unit, the queue abnormal change analysis unit, the queue angle presentation unit and the queue familiarity analysis unit.
2. A kind of student attendance management system based on big data according to claim 1, characterized in that: the monitoring terminal includes an angle shooting adjustment unit, a data collection unit, a data analysis unit and an area size setting unit;

   The angle shooting adjustment unit calls the monitoring terminals distributed in the activity place, controls the monitoring terminals and shoots the students from different angles;

   The data acquisition unit analyzes the height distribution and the student spacing distribution in the student queue according to the image taken by the monitoring terminal;

   The data analysis unit analyzes and compares the height of the students and the distance between the students to determine whether the arrangement of the students is evenly distributed;

   The area size setting unit intercepts the size of the captured image according to the arrangement of the students to analyze the attendance status of the students.
3. A kind of student attendance management system based on big data according to claim 1, characterized in that: the student attendance analysis module includes a first monitoring and analysis unit, a student head frame selection processing unit, a student head quantity summary unit, The second monitoring analysis unit and the head quantity comparison analysis unit;

   The first monitoring and analysis unit controls the monitoring terminal to intercept the student queue distribution image for the first time and analyze the number of attendance of students according to the distribution of the student queue;

   The student head frame selection processing unit selects the student head unit according to the intercepted image and summarizes the number of student heads;

   The second monitoring and analysis unit controls the monitoring terminal to intercept the distribution image of the student queue for the second time and analyze the attendance numbers of the students according to the distribution of the student queue;

   The number of heads comparison analysis unit analyzes the difference between the number of attendances analyzed by the first intercepted image and the number of attendances analyzed by the second intercepted image, and judges whether the result of the difference is greater than the first preset difference and smaller than the first preset difference. Two preset values, when the difference result does not meet the above conditions, analyze whether the difference result is greater than the second preset difference;

   The output end of the head number comparison analysis unit is connected with the input end of the first monitoring analysis unit, the image partition detection unit, the student head frame selection processing unit, the student head number summary unit, and the second monitoring analysis unit.
4. A kind of student attendance management system based on big data according to claim 1, characterized in that: the attendance rate summary analysis module includes a teacher terminal verification unit, an attendance score announcement unit and a reminder warning unit;

   The teacher's terminal verification unit receives and verifies the student's attendance rate and summarizes and analyzes it;

   The attendance score publishing unit analyzes the attendance scores of the students according to the student attendance summary results;

   The reminder and warning unit sends the attendance score to the students and warns the deduction result of the non-attendance students.
5. A method for managing student attendance based on big data, characterized in that: the method performs the following steps:

   Step Z01: call the monitoring terminal to take pictures of the students, adjust the position and size of the shooting area according to the height of the students and the arrangement interval in the queue, select the head area of the students in each queue in the image, and analyze according to the first monitoring the number of heads of students in the queue;

   Step Z02: Set the number of students' heads in the second monitoring and analysis queue, and determine the difference between the number of students' heads in the first monitoring and the second monitoring period. When the difference in the number of students' heads in the first monitoring and second monitoring period is greater than the first preset When the set value is less than the second preset value, analyze whether the area of the blank area of continuous students in the queue is the average area formed by the head area of the number of students, and analyze the student's action when the condition is not met; when the first monitoring and the second monitoring period When the difference in the number of students' heads is greater than the second preset value, analyze whether the included angle between the two adjacent queues satisfies the included angle condition, and when the included angle between the adjacent two queues satisfies the included angle condition, further analysis Familiarity among students to determine whether students are present;

   Step Z03: Obtain an attendance summary table according to the attendance of the students, and publish the attendance scores of the students to warn the students.
6. A method for managing student attendance based on big data according to claim 5, characterized in that: in the step Z01, the collection of height distribution of students in the acquisition queue is W={w ₁ , w ₂ , w ₃ .. .w _n }, n refers to the number of students, the distance between students in the queue is D={d ₁₂ , d ₂₃ , d ₃₄ ...d _n(n-1) }, d _(n-1)n refers to the n- The distance between 1 student and the nth student in line, get and compare the distance between different students;

   When it is detected that d _(n+1)n -d _(n+1)(n+2) = 0, it means that the distance between the students of this cohort is evenly distributed, when it is detected that d _(n+1)n -d ₍ When _n+1)(n+2) ≠0, it means that the distance between students in this cohort is not evenly distributed;

   Arbitrary numerical analysis w _i -w _i-1 <wi ₊₁ -w _i , when this condition is met, it means that the students in the cohort are distributed in increasing order; uneven;

   When it is detected that the queue spacing is evenly distributed and the distribution of students in the queue is increasing sequentially, select the queue and analyze the number of students'heads; where, d _(n+1)n is the distance between the nth student and the n+1th student d _{(n+1)(n+2) is} the distance between the n+1th student and the n+2th student; wi refers to the height of the i-th student, wi+1, wi-1 It refers to the height of the i+1th student and the height of the i-1th student.
7. A kind of student attendance management method based on big data according to claim 5, it is characterized in that: in described step Z02, obtain the student's head image in the queue according to the framed area, the collection of student's head image area is L= { l ₁ , l ₂ , l ₃ ... l _n };

   The average area of the student's head image is

   

   When it is detected that the student head detection area in the queue contains a continuous blank area and the area of the blank area is not equal to the average area sum of the student head images and the number of students in the queue is less than the actual number of students, it means that there are student head areas in the blank area not detected;

   When the number of student head areas in the blank area is set to be equal to the actual number in the second monitoring analysis, it means that the blank area did not detect the student head area due to abnormal movements during the first monitoring analysis and the second monitoring analysis time period.
8. A method for managing student attendance based on big data according to claim 5, characterized in that: in said step Z02, the difference in the number of students distributed by adjacent queues in the first monitoring analysis is greater than the third preset Value, when the number of students distributed in the adjacent cohort in the second monitoring analysis is less than the third preset value; the students in the adjacent cohort face the pointed direction as the start direction point, and the students in the adjacent cohort turn away from the pointed direction as the end direction points, the data vectors formed by adjacent queues are

   

   and

   

   Analyze Data Vectors

   

   and data vector

   

   The angle θ between is specifically as the following formula:

   

   Among them, θ represents

   

   and

   

   the angle between,

   

   and

   

   respectively represent the modulus of the queue vector;

   When θ=0° or 180°, it means that there is no angle between adjacent queues, and there is no tendency for adjacent queues to approach each other. When θ∈(0°, 180°), it means that there is a gap between adjacent queues. Corner, adjacent queues contain a tendency to move closer to each other.
9. A kind of student attendance management method based on big data according to claim 8, is characterized in that: when detecting data vector

   

   and

   

   When the angle between is θ∈(0°, 180°), the familiarity in the adjacent queue is obtained, and when it is detected that the familiarity in the adjacent team is higher than the third preset value, it means that the familiarity between the adjacent teams is Two branch teams with high familiarity and split by the whole team; when it is detected that the familiarity of adjacent teams is lower than the third preset value, it means that the familiarity between adjacent teams is low and not formed by a whole team The two teams formed by splitting indicate that the queue has shifted and the queue contains the number of students who did not attend;

   Judgment is made by the following formula:

   Q=Q ₀ +Q _i ;

   Q _i =k·α;

   k refers to the number of action interactions between adjacent queues, α refers to the familiarity coefficient, Q refers to the total familiarity between adjacent queues, Q ₀ refers to the static familiarity, and Q _i refers to the dynamic familiarity.

Images