阅读说明：本技术 一种基于互动的课堂教学分析系统及方法 (Classroom teaching analysis system and method based on interaction ) 是由 陈俞伶 于 2020-05-06 设计创作，主要内容包括：本发明公开了一种基于互动的课堂教学分析系统及方法,所述分析系统包括语音采集模块、语音识别模块、动作采集模块、头部状态检测模块和监测结果发送模块,所述语音采集模块用于采集课堂上的即时语音信息,所述语音识别模块用于识别语音采集模块采集到的语音信息是否为老师的提问,所述动作采集模块用于采集各个学生的动作姿态并据此选取监测对象,所述头部状态监测模块用于采集监测对象的头部状态,根据监测对象的头部状态变换判断监测对象是否存在传小纸条行为,所述监测结果发送模块在判断监测对象存在传小纸条行为时,获取监测对象的座位位置,并将监测对象的座位位置发送给老师。(The invention discloses a classroom teaching analysis system and method based on interaction, the analysis system comprises a voice acquisition module, a voice recognition module, an action acquisition module, a head state detection module and a monitoring result sending module, the voice acquisition module is used for acquiring instant voice information in a classroom, the voice recognition module is used for recognizing whether the voice information acquired by the voice acquisition module is a question of a teacher, the action acquisition module is used for acquiring action postures of students and selecting a monitoring object according to the action postures, the head state monitoring module is used for acquiring the head state of the monitoring object, judging whether the monitoring object has the behavior of transmitting the small paper slips according to the head state change of the monitoring object, when the monitoring result sending module judges that the monitoring object has the behavior of transmitting the small paper slips, the seat position of the monitoring object is acquired, and the seat position of the monitoring object is sent to a teacher.)

1. The utility model provides a classroom teaching analytic system based on interaction which characterized in that: the analysis system comprises a voice acquisition module, a voice recognition module, an action acquisition module, a head state detection module and a monitoring result sending module, wherein the voice acquisition module is used for acquiring instant voice information in a classroom, the voice recognition module is used for recognizing whether the voice information acquired by the voice acquisition module is a question of a teacher, the action acquisition module is used for acquiring action postures of students and selecting a monitoring object according to the action postures, the head state monitoring module is used for acquiring the head state of the monitoring object, judging whether the monitoring object has a small paper slip transmission behavior according to the head state change of the monitoring object, and the monitoring result sending module acquires the seat position of the monitoring object and sends the seat position of the monitoring object to the teacher when judging that the monitoring object has the small paper slip transmission behavior.

2. The interaction-based classroom teaching analysis system of claim 1, wherein: the voice recognition module comprises a voice feature recognition module and a voice tone recognition module, the voice feature recognition module is used for matching voice information collected by the voice collection module with voice features of a pre-stored teacher and judging whether the voice information is the voice of the teacher, the voice tone recognition module carries out text conversion on the voice information to obtain a corresponding text when judging that the collected voice information is the voice of the teacher, carries out word segmentation on the text and obtains a corresponding word segmentation result, and judges whether the voice information is a question of the teacher according to whether a question word is contained in the word segmentation result.

3. The interaction-based classroom teaching analysis system of claim 1, wherein: the motion acquisition module comprises a hand lifting judgment module, a first distance judgment module and a monitoring object selection module, wherein the hand lifting judgment module acquires motion postures of students and identifies whether the students lift hands in a classroom, the first distance judgment module is used for acquiring a first distance between a seat position of the students without lifting hands and an instant position of a teacher and comparing the first distance with a supervision distance threshold, and the monitoring object selection module selects the students without lifting hands as a first monitoring object and selects the students without lifting hands adjacent to the first monitoring object as a second monitoring object when the first distance is greater than the supervision distance threshold.

4. The interaction-based classroom teaching analysis system of claim 3, wherein: the head state monitoring module comprises a second distance judging module, a head image collecting module, a head state identifying module, a time point collecting module and an interval duration comparing module, the second distance judging module is used for collecting the instant position of a teacher after a monitoring object is selected, and transmitting information to the head image collecting module when the second distance between the instant position of the teacher and the seat position of the first monitoring object is judged to be larger than a supervision distance threshold value, the head image collecting module collects head images of the first monitoring object and the second monitoring object, the head state identifying module identifies whether the head states of the first monitoring object and the second monitoring object are changed or not according to the images collected by the head image collecting module, whether the head states are changed from head lowering to head raising or from head raising to head lowering, and the time point collecting module is used for respectively collecting the time points when the head states of the first monitoring object and the second monitoring object are changed, the interval duration comparison module calculates the interval time difference of the time points acquired by the time point acquisition module, compares the interval time difference with a time difference threshold value, and judges whether the first monitoring object and the second monitoring object transmit small paper slips or not according to the comparison result.

5. The interaction-based classroom teaching analysis system of claim 3, wherein: the monitoring result sending module comprises a position obtaining module and a position sending module, the position obtaining module is used for obtaining and judging the seat position of the monitoring object which transfers the small paper slips and transmitting the seat position to the position sending module, and the position sending module sends the seat position of the monitoring object which transfers the small paper slips to a teacher.

6. A classroom teaching analysis method based on interaction is characterized in that: the analysis method comprises the following steps:

step S1: acquiring instant voice information in a classroom, and acquiring action postures of students when the instant voice information is determined to be a question of a teacher;

step S2: selecting a monitoring object according to the collected action posture of the student;

step S3: acquiring the head state of a monitored object, and judging whether the monitored object has a behavior of transferring small paper slips or not according to the head state change of the monitored object;

step S4: and when the small paper slip transmitting behavior of the monitored object is judged, the seat position of the monitored object is obtained, and the seat position of the monitored object is sent to a teacher.

7. The interaction-based classroom teaching analysis method of claim 6, wherein: the step S1 further includes:

the method comprises the steps of collecting instant voice information in a classroom, matching the instant voice information with pre-stored voice characteristics of a teacher, judging whether the instant voice information is the voice of the teacher or not, if the collected voice information is judged to be the voice of the teacher, performing text conversion on the voice information to obtain a corresponding text, performing word segmentation on the text to obtain a corresponding word segmentation result, if the word segmentation result contains a question word, determining that the instant voice information is the question of the teacher, and collecting action postures of students.

8. The interaction-based classroom teaching analysis method of claim 6, wherein: the step S2 further includes:

identifying whether each student lifts hands in a classroom according to the collected action gestures of each student, collecting a first distance between the seat position of the student and the immediate position of a teacher if a certain student does not lift hands, selecting the student as a first monitoring object if the first distance is greater than a supervision distance threshold, respectively collecting the action gestures of the students adjacent to the first monitoring object,

if there is a student adjacent to the first monitored object who does not hold his or her hands, then the student adjacent to the first monitored object who does not hold his or her hands is the second monitored object.

9. The interaction-based classroom teaching analysis method of claim 8, wherein: the step S3 further includes:

and acquiring the instant position of the teacher, respectively starting to acquire and monitor head images of the first monitoring object and the second monitoring object when a second distance between the instant position of the teacher and the seat position of the first monitoring object is greater than a supervision distance threshold, and judging that the first monitoring object and the second monitoring object transmit small paper slips according to the head state changes of the first monitoring object and the second monitoring object.

10. The interaction-based classroom teaching analysis method of claim 9, wherein: the step S3 further includes:

when only one monitoring object is in head lowering state in the first monitoring object and the second monitoring object, the monitoring object with head lowering is set as a receiving party, the other monitoring object is set as a sending party,

judging whether the sender is in a head-up state, monitoring the head state of the receiver if the sender is in the head-up state, acquiring the current time as a first time when the receiver is monitored to be switched from head-down to head-up, starting to monitor the head state of the sender at the moment, acquiring the current time as a second time when the sender is switched from head-up to head-down, calculating the interval time difference between the first time and the second time, and judging that the first monitored object and the second monitored object transmit small paper slips if the interval time difference is larger than or equal to a time difference threshold value.

Technical Field

The invention relates to the field of classroom teaching analysis, in particular to a classroom teaching analysis system and method based on interaction.

Background

The students in middle and primary schools are not strong enough due to the fact that the grades are small, the students do not study carefully in a classroom, behaviors such as stubborn errors, small paper slips and the like which affect the learning in class often occur, and teachers need to pay attention to observe and manage the learning states of the students besides teaching when the students are in class, so that the working efficiency of the teachers is reduced.

Disclosure of Invention

The invention aims to provide a classroom teaching analysis system and method based on interaction so as to solve the problems in the prior art.

In order to achieve the purpose, the invention provides the following technical scheme:

an interactive classroom teaching analysis system comprises a voice acquisition module, a voice recognition module, an action acquisition module, a head state detection module and a monitoring result sending module, the voice acquisition module is used for acquiring instant voice information in a classroom, the voice recognition module is used for recognizing whether the voice information acquired by the voice acquisition module is a question of a teacher, the action acquisition module is used for acquiring action postures of students and selecting a monitoring object according to the action postures, the head state monitoring module is used for acquiring the head state of the monitoring object, judging whether the monitoring object has the behavior of transmitting the small paper slips according to the head state change of the monitoring object, when the monitoring result sending module judges that the monitoring object has the behavior of transmitting the small paper slips, the seat position of the monitoring object is acquired, and the seat position of the monitoring object is sent to a teacher.

Preferably, the voice recognition module comprises a voice feature recognition module and a voice tone recognition module, the voice feature recognition module is used for matching the voice information acquired by the voice acquisition module with the pre-stored voice feature of the teacher and judging whether the voice information is the voice of the teacher, the voice tone recognition module performs text conversion on the voice information to obtain a corresponding text when judging that the acquired voice information is the voice of the teacher, performs word segmentation on the text, acquires a corresponding word segmentation result, and judges whether the voice information is the question of the teacher according to whether the word segmentation result contains a question word or not.

Preferably, the action collection module comprises a hand lifting judgment module, a first distance judgment module and a monitoring object selection module, wherein the hand lifting judgment module collects action postures of students and identifies whether the students lift hands in a classroom, the first distance judgment module is used for collecting a first distance between a seat position of the students without lifting hands and an instant position of a teacher and comparing the first distance with a supervision distance threshold, and the monitoring object selection module selects the students without lifting hands as the first monitoring object and selects the students without lifting hands adjacent to the first monitoring object as the second monitoring object when the first distance is greater than the supervision distance threshold.

Preferably, the head state monitoring module comprises a second distance judging module, a head image collecting module, a head state identifying module, a time point collecting module and an interval duration comparing module, the second distance judging module is used for collecting the instant position of the teacher after the monitoring object is selected, and transmitting information to the head image collecting module when the second distance between the instant position of the teacher and the seat position of the first monitoring object is judged to be larger than the supervision distance threshold, the head image collecting module collects the head images of the first monitoring object and the second monitoring object, the head state identifying module identifies whether the head states of the first monitoring object and the second monitoring object are changed or not according to the images collected by the head image collecting module, and whether the head states are changed from head lowering to head raising or from head raising to head lowering, the time point collecting module is used for respectively collecting the head states of the first monitoring object and the second monitoring object And the interval duration comparison module calculates the interval time difference of the time points acquired by the time point acquisition module, compares the interval time difference with a time difference threshold value, and judges whether the first monitoring object and the second monitoring object transmit small paper slips or not according to the comparison result.

Preferably, the monitoring result sending module comprises a position obtaining module and a position sending module, the position obtaining module is used for obtaining and judging the seat position of the monitoring object which transfers the small paper slip and transmitting the seat position to the position sending module, and the position sending module is used for sending the seat position of the monitoring object which transfers the small paper slip to the teacher.

An interaction-based classroom teaching analysis method, comprising the following steps:

step S1: acquiring instant voice information in a classroom, and acquiring action postures of students when the instant voice information is determined to be a question of a teacher;

step S2: selecting a monitoring object according to the collected action posture of the student;

step S3: acquiring the head state of a monitored object, and judging whether the monitored object has a behavior of transferring small paper slips or not according to the head state change of the monitored object;

step S4: and when the small paper slip transmitting behavior of the monitored object is judged, the seat position of the monitored object is obtained, and the seat position of the monitored object is sent to a teacher.

Preferably, the step S1 further includes:

the method comprises the steps of collecting instant voice information in a classroom, matching the instant voice information with pre-stored voice characteristics of a teacher, judging whether the instant voice information is the voice of the teacher or not, if the collected voice information is judged to be the voice of the teacher, performing text conversion on the voice information to obtain a corresponding text, performing word segmentation on the text to obtain a corresponding word segmentation result, if the word segmentation result contains a question word, determining that the instant voice information is the question of the teacher, and collecting action postures of students.

Preferably, the step S2 further includes:

identifying whether each student lifts hands in a classroom according to the collected action gestures of each student, collecting a first distance between the seat position of the student and the immediate position of a teacher if a certain student does not lift hands, selecting the student as a first monitoring object if the first distance is greater than a supervision distance threshold, respectively collecting the action gestures of the students adjacent to the first monitoring object,

if there is a student adjacent to the first monitored object who does not hold his or her hands, then the student adjacent to the first monitored object who does not hold his or her hands is the second monitored object.

Preferably, the step S3 further includes:

and acquiring the instant position of the teacher, respectively starting to acquire and monitor head images of the first monitoring object and the second monitoring object when a second distance between the instant position of the teacher and the seat position of the first monitoring object is greater than a supervision distance threshold, and judging that the first monitoring object and the second monitoring object transmit small paper slips according to the head state changes of the first monitoring object and the second monitoring object.

Preferably, the step S3 further includes:

when only one monitoring object is in head lowering state in the first monitoring object and the second monitoring object, the monitoring object with head lowering is set as a receiving party, the other monitoring object is set as a sending party,

judging whether the sender is in a head-up state, monitoring the head state of the receiver if the sender is in the head-up state, acquiring the current time as a first time when the receiver is monitored to be switched from head-down to head-up, starting to monitor the head state of the sender at the moment, acquiring the current time as a second time when the sender is switched from head-up to head-down, calculating the interval time difference between the first time and the second time, and judging that the first monitored object and the second monitored object transmit small paper slips if the interval time difference is larger than or equal to a time difference threshold value.

Compared with the prior art, the invention has the beneficial effects that: the method selects the suspected note-passing object according to the hand-lifting state of the students when asking questions of the teacher, starts to monitor the head state of the suspected note-passing object, judges whether the suspected note-passing object passes the notes according to the head-lowering and head-lifting conditions of the suspected note-passing object, acquires the positions of the students when judging that the students pass the notes, and sends the positions to the teacher without observing the classmates by the teacher, thereby improving the working efficiency of the teacher.

Drawings

FIG. 1 is a block diagram of an interaction-based classroom teaching analysis system according to the present invention;

fig. 2 is a flow chart of the interaction-based classroom teaching analysis method of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Referring to fig. 1-2, in an embodiment of the present invention, an interactive classroom teaching analysis system includes a voice acquisition module, a voice recognition module, an action acquisition module, a head state detection module, and a monitoring result sending module, where the voice acquisition module is configured to acquire instant voice information in a classroom, the voice recognition module is configured to recognize whether the voice information acquired by the voice acquisition module is a question of a teacher, the action acquisition module is configured to acquire an action posture of each student and select a monitoring object based on the action posture, the head state monitoring module is configured to acquire a head state of the monitoring object, and determine whether a small paper slip transmission behavior exists in the monitoring object according to a head state transformation of the monitoring object, and the monitoring result sending module obtains a seat position of the monitoring object when determining that the small paper slip transmission behavior exists in the monitoring object, and transmits the seat position of the monitoring object to the teacher.

The voice recognition module comprises a voice feature recognition module and a voice tone recognition module, the voice feature recognition module is used for matching voice information collected by the voice collection module with voice features of a pre-stored teacher and judging whether the voice information is the voice of the teacher, the voice tone recognition module carries out text conversion on the voice information to obtain a corresponding text when judging that the collected voice information is the voice of the teacher, carries out word segmentation on the text and obtains a corresponding word segmentation result, and judges whether the voice information is a question of the teacher according to whether a question word is contained in the word segmentation result.

The motion acquisition module comprises a hand lifting judgment module, a first distance judgment module and a monitoring object selection module, wherein the hand lifting judgment module acquires motion postures of students and identifies whether the students lift hands in a classroom, the first distance judgment module is used for acquiring a first distance between a seat position of the students without lifting hands and an instant position of a teacher and comparing the first distance with a supervision distance threshold, and the monitoring object selection module selects the students without lifting hands as a first monitoring object and selects the students without lifting hands adjacent to the first monitoring object as a second monitoring object when the first distance is greater than the supervision distance threshold.

The head state monitoring module comprises a second distance judging module, a head image collecting module, a head state identifying module, a time point collecting module and an interval duration comparing module, the second distance judging module is used for collecting the instant position of a teacher after a monitoring object is selected, and transmitting information to the head image collecting module when the second distance between the instant position of the teacher and the seat position of the first monitoring object is judged to be larger than a supervision distance threshold value, the head image collecting module collects head images of the first monitoring object and the second monitoring object, the head state identifying module identifies whether the head states of the first monitoring object and the second monitoring object are changed or not according to the images collected by the head image collecting module, whether the head states are changed from head lowering to head raising or from head raising to head lowering, and the time point collecting module is used for respectively collecting the time points when the head states of the first monitoring object and the second monitoring object are changed, the interval duration comparison module calculates the interval time difference of the time points acquired by the time point acquisition module, compares the interval time difference with a time difference threshold value, and judges whether the first monitoring object and the second monitoring object transmit small paper slips or not according to the comparison result.

The monitoring result sending module comprises a position obtaining module and a position sending module, the position obtaining module is used for obtaining and judging the seat position of the monitoring object which transfers the small paper slips and transmitting the seat position to the position sending module, and the position sending module sends the seat position of the monitoring object which transfers the small paper slips to a teacher.

An interaction-based classroom teaching analysis method, comprising the following steps:

step S1: the method comprises the following steps of collecting instant voice information in a classroom, and collecting action postures of students when the instant voice information is confirmed to be a question of a teacher:

the method comprises the steps of collecting instant voice information in a classroom, matching the instant voice information with pre-stored voice characteristics of a teacher, judging whether the instant voice information is the voice of the teacher or not, if the collected voice information is judged to be the voice of the teacher, performing text conversion on the voice information to obtain a corresponding text, performing word segmentation on the text to obtain a corresponding word segmentation result, if the word segmentation result contains a question word, determining that the instant voice information is the question of the teacher, and collecting action postures of students.

Step S2: identifying whether each student lifts hands in a classroom according to the collected action gestures of each student, collecting a first distance between the seat position of the student and the immediate position of a teacher if a certain student does not lift hands, selecting the student as a first monitoring object if the first distance is greater than a supervision distance threshold, respectively collecting the action gestures of the students adjacent to the first monitoring object,

if the students adjacent to the first monitoring object do not have hands, the students adjacent to the first monitoring object without hands are the second monitoring object;

step S3: acquiring the instant position of the teacher, respectively starting to acquire head images of the first monitoring object and the second monitoring object when a second distance between the instant position of the teacher and the seat position of the first monitoring object is greater than a supervision distance threshold,

when only one monitoring object is in head lowering state in the first monitoring object and the second monitoring object, the monitoring object with head lowering is set as a receiving party, the other monitoring object is set as a sending party,

judging whether a sender is in a head-up state, monitoring the head state of a receiver if the sender is in the head-up state, acquiring the current time as a first time when the receiver is monitored to be switched from head-down to head-up, starting to monitor the head state of the sender at the moment, acquiring the current time as a second time when the sender is switched from head-up to head-down, calculating the interval time difference between the first time and the second time, and judging that a first monitoring object and a second monitoring object transmit small paper slips if the interval time difference is greater than or equal to a time difference threshold value;

when a teacher asks questions and two adjacent students do not hold hands to answer, the two students are judged to have the behavior of transmitting small paper slips possibly, and the behaviors of the two students are monitored; when the mr is nearer from the student, the student often can not pass the small note in order not to let the mr discover, so just can pass the note when the mr leaves than far away, when coming the passback note, the student need to look over the note with leaning on, consequently whether judge whether these two students have the action of passing the note through monitoring two students in turn leaning on.

Step S4: when judging that the monitoring object has the action of transferring the small paper slips, the seat position of the monitoring object is obtained, the seat position of the monitoring object is sent to a teacher, when the student has the action of transferring the small paper slips, the seat position of the student is directly sent to the teacher, the action process that the teacher observes the student is omitted, and the burden of the teacher in teaching is relieved.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.