Teacher emotion recognition intervention method and system based on interaction behaviors

Abstract

The invention discloses a teacher emotion recognition intervention method and system based on interactive behaviors, and relates to the technical field of wisdom education, and the method comprises the steps: 1, data preparation: recognizing the identity of a target teacher, calling a database of an educational administration system according to the identity of the teacher, and searching and determining matched teaching data; step 2, emotion analysis and intervention: defining the current moment as t1, the starting moment and the ending moment of a certain course of a target teacher as t2 and t3 respectively, and the generation time of the latest historical assessment score as t4; judging whether the time difference obtained from t1-t4 is greater than a preset question answering period or not, and if so, executing a course tracking process; if not, calling a corresponding historical assessment score and analyzing the emotion of the teacher; and if the current emotion of the teacher meets the preset bad condition, analyzing a teaching plan of a class corresponding to the historical assessment score, and generating a teaching suggestion. The method has the effects of relieving the unhealthy emotion of the teacher in the teaching activity and improving the teaching quality.

Description

Technical Field

[0001] The present application relates to the field of smart education technology, and in particular to a teacher emotion recognition intervention method and system based on interactive behavior. Background Art

[0002] With the introduction of a new generation of electronic blackboards, the teaching model has changed: traditionally, teachers in the classroom are often unable to take into account the status of all students in a timely manner, and some students lag behind in learning, affecting the teaching effect; but now with the help of cameras and AI algorithms, the system can collect, identify, and analyze videos during class, give teachers prompts during the teaching process, and promptly detect students' inattention and other situations, so that teachers can adjust their teaching strategies and improve teaching effects; and the electronic blackboard can also cooperate with microphones to actively summarize the teacher's class content, form teaching records, and help teachers simplify teaching summaries and other tasks.

[0003] However, the components of the above-mentioned electronic blackboards and other smart classrooms mostly focus on students, and pay relatively little attention to teachers.

[0004] Nowadays, the teaching pressure of teachers has not been greatly reduced with the introduction of smart classrooms. In addition to teaching tasks, various activities, inspections at all levels, evaluations, material writing, etc. make many teachers feel that they are overloaded with work, causing a large number of teachers to be troubled by emotions such as anxiety, which in turn affects the quality of teaching and is not conducive to the long-term work of teachers. In serious cases, some teachers choose to change industries. Summary of the invention

[0005] In order to alleviate negative emotions in teachers' teaching activities and improve teaching quality, this application provides a teacher emotion recognition intervention method and system based on interactive behavior.

[0006] In the first aspect, the present application provides a teacher emotion recognition intervention method based on interactive behavior, which adopts the following technical solution: A teacher emotion recognition intervention method based on interactive behavior, including: Step 1: Data preparation, which includes: Identify the identity of the target teacher, and call the database of the teaching system according to the teacher's identity to search and determine the matching teaching data; the teaching data includes the class, the course schedule, the students' historical assessment scores, and the teaching plan of any class; Step 2: Emotional analysis and intervention, which includes: Define the current time as t1, the start time and end time of a course of the target teacher as t2 and t3 respectively, and the generation time of the latest historical assessment score is t4; Determine whether the time difference obtained from t1-t4 is greater than the preset question-answering cycle. If so, execute the course tracking process; if not, call the corresponding historical assessment results and analyze the teacher's emotions; If the teacher's current mood meets the preset adverse conditions, the teaching plan of the class corresponding to the historical assessment results is analyzed and teaching suggestions are generated; The course tracking process includes: if the relationship between t1 and a certain course is t2<t1<t3, then executing the on-site emotion analysis method and the on-site emotion intervention method; Wherein, the on-site emotion analysis method includes: Determine the class that the target teacher teaches according to the course schedule, and request to call the monitoring data of the corresponding class; Analyze teachers' emotions based on monitoring data, and use on-site emotional intervention methods according to the analysis results.

[0007] Optionally, calling the corresponding historical assessment scores and analyzing the teacher's emotions includes: If the current situation is the first to n1th time of analyzing emotions based on grades, the pre-stored emotion scoring table is output and sent to the target teacher, requesting active emotion scoring, receiving emotion scoring feedback, and updating the emotion scoring table; wherein the emotion scoring table at least records the mathematical relationship between grades and emotion scores; If this is the n2th time to analyze emotions based on grades, a similarity analysis is performed based on the emotion score table, the record with the highest similarity is taken, and the corresponding emotion score is output; wherein n2>n1, and n1 is a preset value.

[0008] Optionally, analyzing the teaching plan of the class corresponding to the historical assessment results and generating teaching suggestions includes: If the teaching plan includes teaching arrangements and lesson plans, then the teaching arrangements will be used to determine whether the next course of the class corresponding to the score is an assessment question-answering session; If the next class is a Q&A session, then: Call the assessment data of the corresponding class, identify, and summarize the wrong question data; Based on the analysis of wrong question data, the preset textbook database is searched to determine the knowledge points of the questions and their positions in the textbooks, and question-answering reference data is generated as suggestions and sent to designated student representatives.

[0009] Optionally, the analyzing the teaching plan of the class corresponding to the historical assessment results and generating teaching suggestions also includes: If the next course is not an assessment Q&A session, then: Determine the course topics according to the teaching schedule; Search the preset teaching material database and lesson plans according to the course topic to obtain the teaching content; Analyze and determine whether there are knowledge points in the teaching content that correspond to the wrong question data. If so, divide the teaching content, exchange the teaching content that matches the wrong question data with the teaching content of subsequent courses, update the teaching content as suggestions, and use the teaching content that matches the wrong question data as suggestions during assessment and question-answering.

[0010] Optionally, the method for obtaining the teaching plan includes: establishing a work companion AI, setting a hardware body carried by the AI, and configuring accompanying logic for the hardware body; The accompanying logic includes: Receive user binding instructions and bind teachers to hardware entities; If the current moment meets the preset audio collection conditions, the audio data in the environment is obtained; wherein the audio collection conditions include that the current moment is a preset interactive accompanying period; If there are new historical assessment results, and the current time is determined to be a non-class time according to the course schedule, the current time is determined to meet the preset audio collection conditions, and the user is prompted to inquire about the assessment Q&A plan and historical assessment results; Identify and analyze audio data to obtain assessment question-answering plans and teaching arrangements, and update teaching arrangements based on the assessment question-answering plans.

[0011] Optionally, the accompanying logic further includes: Call the audio feedback data of the teaching after the historical assessment Q&A planning inquiry, and bind the corresponding historical assessment results; Call the teacher's emotions obtained by analyzing the historical grades based on the emotion rating table; Perform acoustic feature analysis on audio feedback data and bind it to the teacher's emotions to generate an acoustic feature set under emotions for training the emotion recognition model. If the current environment meets the preset emotion model verification conditions, the audio data will be analyzed using the trained and pre-imported emotion recognition model to generate emotion analysis results, and the teacher will be requested to evaluate it, and the acoustic feature set under the emotion will be updated based on the evaluation.

[0012] Optionally, analyzing the teacher's emotions based on monitoring data and processing them with an on-site emotional intervention method according to the analysis results includes: The audio data during teaching is obtained through the portable electronic device pre-worn by the teacher; Analyze audio data using emotion recognition models to generate emotion analysis results; If the emotion result meets the preset adverse conditions, the image is extracted for facial expression recognition and behavior recognition, and the emotion analysis result is generated based on the recognition result; The on-site emotion intervention method includes: if the portable electronic device meets the preset physical contact wearing condition and has a vibration function, then when the emotion analysis result meets the preset adverse condition, a vibration triggering message is sent.

[0013] Optionally, the accompanying logic further includes: Establish a pairing relationship with other hardware entities; Get the bound teacher's work tasks and corresponding deadlines, and issue expiration warnings; Identify work tasks and conduct task load assessment; If the current task volume exceeds the preset threshold, it will inquire whether other paired hardware entities have the same task record, and send an experience sharing request if the same task record exists.

[0014] In the second aspect, the present application provides a teacher emotion recognition intervention system based on interactive behavior, which adopts the following technical solutions: A teacher emotion recognition intervention system based on interactive behavior includes a cloud background and a hardware body for being placed on a teacher's desk, wherein the cloud background is used to load and execute a computer program of any of the teacher emotion recognition intervention methods based on interactive behavior described above, and the hardware body is configured with accompanying logic.

[0015] To sum up, the present application includes the following beneficial technical effects: on the one hand, after each student assessment, the teacher's mood can be analyzed and evaluated through the assessment results, and when the mood is not good, the teacher can be guided to adjust the teaching plan and alleviate the emotions in the teaching process; on the other hand, in daily classes, the monitoring in the classroom is utilized, and the teacher's mood is evaluated through analysis and monitoring, and intervention is carried out, so that this method can alleviate the negative emotions in teachers' teaching activities and improve the quality of teaching. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the main process of the method of this application; Figure 2 It is a schematic diagram of the architecture of this application. DETAILED DESCRIPTION

[0017] The following is combined with Figure 1-2 This application is described in further detail.

[0018] The embodiment of the present application discloses a teacher emotion recognition intervention method based on interactive behavior.

[0019] Reference Figure 1The teacher emotion recognition intervention method based on interactive behavior aims to use smart classrooms and smart campuses to collect the daily interactive behaviors of teachers and students, use artificial intelligence to analyze and evaluate teachers' daily emotions, flexibly adjust teachers' teaching plans, give suggestions, guide them to relieve negative emotions, and improve teaching quality; this method includes: Step 1: Data preparation; Step 2: Emotional analysis and intervention.

[0020] The above step 1, data preparation, includes: Identify the identity of the target teacher, and call the database of the teaching system based on the teacher's identity to search and determine the matching teaching data.

[0021] In this embodiment, this method is established on the basis of smart classrooms and smart campuses, and should be able to obtain videos of relevant teaching behaviors for face recognition, and obtain the identity of the target teacher in conjunction with pre-established teacher file data.

[0022] The above teaching data include the class, the course schedule, the students' historical assessment scores, and the teaching plan of any class. The teaching plan here includes: the teaching arrangements of each class and the corresponding lesson plans.

[0023] The above step 2, emotion analysis and intervention, includes: S1. Define the current time as t1, the start time and end time of a course of the target teacher are t2 and t3 respectively, and the generation time of the latest historical assessment score is t4.

[0024] It is understandable that a teacher can have multiple classes per day, so there will be multiple sets of t2 and t3 in a day.

[0025] S2. Determine whether the time difference obtained from t1-t4 is greater than the preset question-answering cycle. If so, execute the course tracking process; if not, call the corresponding historical assessment results and analyze the teacher's emotions.

[0026] The above-mentioned historical assessment results refer to the test results in this embodiment, so the above-mentioned question-answering cycle refers to the latest interval time for explaining and answering questions on the test paper, and this value is set by teachers or relevant school personnel.

[0027] It should be noted that if a class has already explained the test paper corresponding to a certain history assessment result, then even if the time difference is less than the preset question-and-answer period, the course tracking process will be executed, that is, the test paper has been taken out and analyzed, and the impact of the test results on the teacher's emotions will no longer be directly analyzed.

[0028] S31. If the teacher's current mood meets the preset adverse conditions, the teaching plan of the class corresponding to the historical assessment results is analyzed and teaching suggestions are generated.

[0029] S32, the course tracking process includes: if the relationship between t1 and a certain course is t2<t1<t3, then executing the on-site emotion analysis method and the on-site emotion intervention method.

[0030] Among them, the on-site sentiment analysis methods include: S321. Determine the class taught by the target teacher according to the curriculum schedule, and request to call the monitoring data of the corresponding class; the monitoring data comes from the camera in the classroom, which can be a component of the smart classroom.

[0031] S322. Analyze teachers' emotions based on monitoring data, and use on-site emotion intervention methods according to the analysis results.

[0032] According to the above content, this method: on the one hand, after each student assessment, it can analyze and evaluate the teacher's emotions through the assessment results, and guide the teacher to adjust the teaching plan in bad times to alleviate the emotions in the teaching process; on the other hand, in daily classes, the monitoring in the classroom is used to analyze and evaluate the teacher's emotions and intervene, so that this method can alleviate the negative emotions in teachers' teaching activities and improve the quality of teaching.

[0033] Regarding the above call of the corresponding historical assessment scores and analysis of teacher emotions, there are two situations: The first one is that if the current situation is the first to n1th time of analyzing emotions based on grades, the pre-stored emotion scoring table is output and sent to the target teacher, requesting active emotion scoring, receiving emotion scoring feedback, and updating the emotion scoring table.

[0034] First of all, the assessment score here does not refer to the score of a single student, but the average score after removing the highest and lowest scores. The emotional scoring table is shown in Table 1 below. Table 1 takes the example of a score with a full score of 100 and a score with a full score of 10.

[0035] Table 1: Emotional rating table score score Score calculation mood 0-50 1-3 50 / 3, divided into three levels of scoring, according to the proportion of each level, the score corresponding to the largest level is taken as the score Difference 51-70 4-6 Same as above Poor 71-85 7-8 Same as above ordinary 85-100 9-10 Same as above excellent The above table 1 is a preset and has different matching degrees for each teacher. Therefore, in the first n1 times, this method will actively ask teachers to report their emotional expressions on grades and update the emotional rating table to improve the accuracy of the ratings; among them, n1 can be =4.

[0036] The second method is that if this is the n2th time to analyze emotions based on grades, a similarity analysis is performed based on the emotion score table, the record with the highest similarity is taken, and the corresponding emotion score is output.

[0037] Among them, similarity analysis is to calculate the difference between the assessment results and the scores of each level. The pair with the smallest difference has the highest similarity; n2>n1, and n1 is the preset value.

[0038] According to the above settings, this method can quantify teachers' emotions through data and provide support for subsequent emotional intervention; at the same time, because different teachers will have different emotional rating scales, the evaluation is relatively accurate.

[0039] On the premise of obtaining the emotion score and the above Table 1, the above-mentioned bad condition can be: the emotion corresponding to the emotion score is "bad" or "not good"; if the teacher's current emotion meets the bad condition, the teaching plan of the class corresponding to the historical assessment score is analyzed and teaching suggestions are generated, specifically: According to the teaching arrangement, determine whether the next course of the corresponding class is an examination question-answering session. If so, that is, the teacher of the next course arranges a question-answering session on the test paper, then: 1) Call the assessment data of the corresponding class (i.e., images of electronic test papers and paper test papers), identify, and summarize the wrong question data.

[0040] Among them, electronic test paper recognition includes text recognition, error symbol recognition, and score recognition; while paper test paper recognition first recognizes the image, and can only perform OCR recognition and extraction on the questions with error symbol features, and then recognize the extracted content.

[0041] The wrong question data can be bound according to the student name on the corresponding test paper, and the wrong question data of the same student can be summarized to form a wrong question set that matches the individual; the data statistics generated by previous assessments will be determined by the teacher whether to be distributed to the students.

[0042] 2) Based on the analysis of wrong question data, the preset textbook database is searched to determine the knowledge points of the questions and their positions in the textbooks, and reference data for answering questions is generated as suggestions, which are then sent to designated student representatives.

[0043] The above-mentioned method for determining the knowledge points includes: searching for the corresponding reference answers according to the wrong questions, determining the knowledge points according to the keywords in the reference answers; and searching the electronic textbooks according to the knowledge points to determine the locations. The method of sending data to the student agent is as follows: The data is sent to the computer of the class corresponding to the student representative. The student representative (who can be a class representative) checks the computer notifications in the class every day. After receiving the data, he can ask the teacher and print out the relevant data and distribute it to classmates after obtaining consent.

[0044] According to the above settings, this method can help teachers organize the wrong question data, knowledge points, etc. of the test before they prepare to explain the test paper, saving some preparation work; and it can also send relevant data to students in advance so that students can prepare in advance, reducing the difficulty of communication and understanding in the process of answering questions, so as to alleviate teachers' bad emotions and improve teaching quality.

[0045] In another embodiment of the method, if it is determined according to the teaching arrangement that the next course is not an examination question-answering course, then: 1) Determine the course topic based on the teaching schedule, for example: the chapter name in the textbook.

[0046] 2) Search the preset teaching materials database and lesson plans according to the course topic to obtain the teaching content.

[0047] 3) Analyze and determine whether there are knowledge points in the teaching content that correspond to the wrong question data. If so, when there is no continuity in the teaching content of subsequent courses, split the teaching content, exchange the teaching content that matches the wrong question data with the teaching content of subsequent courses, update the teaching content as suggestions, and use the teaching content that matches the wrong question data as suggestions during assessment and question answering; if not, end.

[0048] The above analysis can be: compare the knowledge points and teaching contents, and if there are identical items, they exist; and the determination of the continuity relationship can be: whether the subsequent teaching content is based on the knowledge points of the previous teaching content.

[0049] According to the above content, firstly, this method can analyze whether there are parts of the next course that are the same as the knowledge points in the wrong questions. If so, on the one hand, the order of the class content can be changed to reduce the chance that the teacher will be affected by bad test results; on the other hand, the teaching content and the wrong questions can be paired to provide teachers with suggestions on how to explain the teaching content when explaining the test papers, thereby reducing the repetition of knowledge points and combining them with practical applications to allow students to better understand and improve the quality of teaching.

[0050] Reference Figure 2 In one embodiment of the method, the method of obtaining the teaching plan includes: establishing a work companion AI, setting a hardware body on which the AI ​​is carried, and configuring accompanying logic for the hardware body.

[0051] The hardware body can be a computer or a notebook, but a more preferred one is an independent intelligent ornament. The outer shell of the ornament can be a cartoon shape, etc., and an integrated circuit board with data analysis and processing capabilities is installed inside. The integrated circuit board is integrated with a WIFI module and an audio module, and a battery is installed inside the ornament to power the circuit board, and the circuit board is integrated with a charging circuit. The ornament is placed on the teacher's desk and used as a "companion elf".

[0052] The accompanying logic mentioned above includes: 1) Receive user binding instructions and bind the teacher to the hardware entity.

[0053] It is understandable that for the sake of data security, the above-mentioned "Companion Elf" needs to be bound to the corresponding teacher. The binding method can be to register an account through the corresponding App and enter the teacher's identity. After binding, the audio collected by the "Companion Elf" is stored locally and can only be copied, deleted, and modified under the operation of the teacher with corresponding authority.

[0054] 2) If the current moment meets the preset audio collection conditions, the audio data in the environment is obtained.

[0055] Among them, the audio collection conditions include that the current time is a preset interactive accompaniment period, for example: the current time is a weekday and the time is 9:00-17:00; it can be understood that the audio collection conditions are not only met in time, but also other environmental conditions, user behavior conditions, etc.; for example: if the teacher feels that the current time is relatively inappropriate, he can actively close it; that is, in this method, the "accompaniment wizard" is not always doing audio collection.

[0056] 3) If new historical assessment results appear, and the current time is determined to be non-class time according to the course schedule, the current time is judged to meet the preset audio collection conditions, and the user is prompted to inquire about the assessment Q&A plan and historical assessment results.

[0057] Among them, the inquiry can be issued through the corresponding audio; if a display screen is integrated on the hardware body, the inquiry and assessment results can be displayed on the display screen.

[0058] 4) Identify and analyze audio data to obtain assessment and question-answering plans and teaching arrangements, and update teaching arrangements based on the assessment and question-answering plans.

[0059] Among them, the assessment and question-answering plan includes, for example: when will the assessment and question-answering be conducted, how many classes will be needed to complete the assessment and question-answering, etc.

[0060] The teaching arrangement is based on the consideration that if the use of this method requires teachers to enter information manually, it will increase the work pressure of teachers. Therefore, this method allows the teaching arrangement to be entered by voice and in the form of daily interaction. It should be noted that if the teaching arrangement has been made before, and the plan for the assessment and Q&A is proposed at this time, the teaching arrangement needs to be updated.

[0061] In another embodiment of the method, the accompanying logic further comprises: Call the audio feedback data of the teaching after the historical assessment Q&A planning inquiry, and bind the corresponding historical assessment results; Call the teacher's emotions obtained by analyzing the historical grades based on the emotion rating table; The acoustic feature analysis of the audio feedback data is performed and bound to the teacher's emotions to generate an acoustic feature set under the emotions, which is used to train the emotion recognition model. It can be understood that audio recognition and speech emotion recognition are both existing technologies, so they will not be elaborated.

[0062] If the current environment meets the preset emotion model verification conditions, for example, the verification time selected by the teacher and the model analysis shows that the teacher's previous conversation is excellent, the audio data will be analyzed using the trained and pre-imported emotion recognition model to generate emotion analysis results, and the teacher will be requested to evaluate it, and the acoustic feature set under the emotion will be updated based on the evaluation.

[0063] According to the above settings, the above hardware entity (or: companion elf) in this method can use the feedback audio obtained from inquiries after the results of previous assessments are released, and combine it with the aforementioned emotion scoring standard table to automatically generate sample data for training the model; at the same time, it also cross-validates the accuracy of the emotion scoring table.

[0064] In this method, the teacher's emotions are analyzed based on monitoring data, and processed with on-site emotional intervention methods according to the analysis results. It can be to extract monitoring data, perform teacher identification, teacher facial expression recognition, teacher behavior recognition, and determine the teacher's emotions based on the facial expression and behavior recognition results. When the emotions meet the preset adverse conditions, such as: angry expressions, bad behavioral actions, they are processed with on-site emotional intervention methods.

[0065] The on-site emotional intervention method can be: the computer in the classroom will pop up a prompt. It should be noted here that the pop-up prompt will not be projected when the classroom projection is turned on.

[0066] Based on the above, in another embodiment, the method: analyzes the teacher's emotions based on monitoring data, and processes the teacher's emotions with an on-site emotional intervention method according to the analysis results, which includes: The audio data during teaching is obtained through the portable electronic devices pre-worn by the teacher; that is, the teacher needs to wear portable electronic devices, such as smart watches, smart bracelets, smart rings, and use the electronic devices to collect audio data in the classroom and send it to the aforementioned "companion elf" through the network.

[0067] Analyze audio data using emotion recognition models to generate emotion analysis results; If the emotional result meets the preset adverse conditions, the image is extracted for facial expression recognition and behavior recognition, and the emotional analysis result is generated based on the recognition result. For example, an angry expression indicates a bad mood; throwing books or slamming the table indicates a bad mood.

[0068] The on-site emotion intervention method includes: if the portable electronic device meets the preset physical contact wearing conditions and has a vibration function, then when the emotion analysis result meets the preset adverse conditions, a vibration trigger message is sent.

[0069] According to the above settings, this application can provide hidden prompts when teachers are in a bad mood more accurately and flexibly; at the same time, it can process the monitoring data.

[0070] The above accompanying logic also includes: Establish a pairing relationship with other hardware entities; for example, Teacher A and Teacher B establish a friend relationship, and the devices distribute access rights to some data (such as the task name and list mentioned below) to each other.

[0071] (Through audio data recognition) obtain the bound teacher's work tasks (such as activities, evaluations) and corresponding deadlines, and issue a timed expiration warning. The advance time of the warning can be set by the teacher himself; Identify work tasks and conduct task volume assessment, for example, task quantity statistics. More accurately, developers preset the task volume values ​​represented by various tasks in advance, and then accumulate the task volume values ​​corresponding to all tasks; If the current task volume exceeds the preset threshold, other paired hardware entities will be asked whether they have the same task records (devices access each other's historical figure lists), and if the same task records exist, an experience sharing request will be sent. The request can be displayed in the form of a pop-up window for the corresponding teacher to view and respond.

[0072] The above settings can automatically analyze the historical records of other teachers and seek help from other experienced teachers when a teacher is under too much work pressure (i.e., the workload is heavy). This is especially important for new teachers and newly hired teachers. It can speed up the integration of new teachers into their work and significantly reduce their work pressure.

[0073] The embodiment of the present application also discloses a teacher emotion recognition intervention system based on interactive behavior.

[0074] Reference Figure 2 The teacher emotion recognition intervention system based on interactive behavior includes a cloud background and a hardware body for being placed on the teacher's desk, wherein the cloud background is used to load and execute a computer program of any of the teacher emotion recognition intervention methods based on interactive behavior as described above, and the hardware body is configured with accompanying logic.

[0075] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A teacher emotion recognition intervention method based on interactive behavior, characterized in that: include: Step 1: Data preparation, which includes: Identify the identity of the target teacher, and call the database of the teaching system according to the teacher's identity to search and determine the matching teaching data; the teaching data includes the class, the course schedule, the students' historical assessment scores, and the teaching plan of any class; Step 2: Emotional analysis and intervention, which includes: Define the current time as t1, the start time and end time of a course of the target teacher as t2 and t3 respectively, and the generation time of the latest historical assessment score is t4; Determine whether the time difference obtained from t1-t4 is greater than the preset question-answering cycle. If so, execute the course tracking process; if not, call the corresponding historical assessment results and analyze the teacher's emotions; If the teacher's current mood meets the preset adverse conditions, the teaching plan of the class corresponding to the historical assessment results is analyzed and teaching suggestions are generated; The course tracking process includes: if the relationship between t1 and a certain course is t2<t1<t3, then executing the on-site emotion analysis method and the on-site emotion intervention method; Wherein, the on-site emotion analysis method includes: Determine the class that the target teacher teaches according to the course schedule, and request to call the monitoring data of the corresponding class; Analyze teachers' emotions based on monitoring data, and use on-site emotional intervention methods according to the analysis results.

2. The teacher emotion recognition intervention method based on interactive behavior according to claim 1 is characterized by: The calling of the corresponding historical assessment scores and analyzing the teacher's emotions includes: If the current situation is the first to n1th time of analyzing emotions based on grades, the pre-stored emotion scoring table is output and sent to the target teacher, requesting active emotion scoring, receiving emotion scoring feedback, and updating the emotion scoring table; wherein the emotion scoring table at least records the mathematical relationship between grades and emotion scores; If this is the n2th time to analyze emotions based on grades, a similarity analysis is performed based on the emotion score table, the record with the highest similarity is taken, and the corresponding emotion score is output; wherein n2>n1, and n1 is a preset value.

3. The teacher emotion recognition intervention method based on interactive behavior according to claim 2 is characterized by: The analysis of the teaching plan of the class corresponding to the historical assessment results and the generation of teaching suggestions include: If the teaching plan includes teaching arrangements and lesson plans, then the teaching arrangements will be used to determine whether the next course of the class corresponding to the score is an assessment question-answering session; If the next class is a Q&A session, then: Call the assessment data of the corresponding class, identify, and summarize the wrong question data; Based on the analysis of wrong question data, the preset textbook database is searched to determine the knowledge points of the questions and their positions in the textbooks, and question-answering reference data is generated as suggestions and sent to designated student representatives.

4. The teacher emotion recognition intervention method based on interactive behavior according to claim 3 is characterized by: The analyzing of the teaching plan of the class corresponding to the historical assessment results and generating teaching suggestions also includes: If the next course is not an assessment Q&A session, then: Determine the course topics according to the teaching schedule; Search the preset teaching material database and lesson plans according to the course topic to obtain the teaching content; Analyze and determine whether there are knowledge points in the teaching content that correspond to the wrong question data. If so, divide the teaching content, exchange the teaching content that matches the wrong question data with the teaching content of subsequent courses, update the teaching content as suggestions, and use the teaching content that matches the wrong question data as suggestions during assessment and question-answering.

5. The teacher emotion recognition intervention method based on interactive behavior according to claim 3 is characterized in that: The method of obtaining the teaching plan includes: establishing a work companion AI, setting a hardware body carried by the AI, and configuring accompanying logic for the hardware body; The accompanying logic includes: Receive user binding instructions and bind teachers to hardware entities; If the current moment meets the preset audio collection conditions, the audio data in the environment is obtained; wherein the audio collection conditions include that the current moment is a preset interactive accompanying period; If there are new historical assessment results, and the current time is determined to be a non-class time according to the course schedule, the current time is determined to meet the preset audio collection conditions, and the user is prompted to inquire about the assessment Q&A plan and historical assessment results; Identify and analyze audio data to obtain assessment question-answering plans and teaching arrangements, and update teaching arrangements based on the assessment question-answering plans.

6. The teacher emotion recognition intervention method based on interactive behavior according to claim 5 is characterized in that: The accompanying logic further includes: Call the audio feedback data of the teaching after the historical assessment Q&A planning inquiry, and bind the corresponding historical assessment results; Call the teacher's emotions obtained by analyzing the historical grades based on the emotion rating table; Perform acoustic feature analysis on audio feedback data and bind it to the teacher's emotions to generate an acoustic feature set under emotions for training the emotion recognition model. If the current environment meets the preset emotion model verification conditions, the audio data will be analyzed using the trained and pre-imported emotion recognition model to generate emotion analysis results, and the teacher will be requested to evaluate it, and the acoustic feature set under the emotion will be updated based on the evaluation.

7. The teacher emotion recognition intervention method based on interactive behavior according to claim 6 is characterized in that: The method of analyzing the teacher's emotions based on monitoring data and using an on-site emotional intervention method to handle the teacher's emotions according to the analysis results includes: The audio data during teaching is obtained through the portable electronic device pre-worn by the teacher; Analyze audio data using emotion recognition models to generate emotion analysis results; If the emotion result meets the preset adverse conditions, the image is extracted for facial expression recognition and behavior recognition, and the emotion analysis result is generated based on the recognition result; The on-site emotion intervention method includes: if the portable electronic device meets the preset physical contact wearing condition and has a vibration function, then when the emotion analysis result meets the preset adverse condition, a vibration triggering message is sent.

8. The teacher emotion recognition intervention method based on interactive behavior according to claim 7 is characterized in that: The accompanying logic further includes: Establish a pairing relationship with other hardware entities; Get the bound teacher's work tasks and corresponding deadlines, and issue expiration warnings; Identify work tasks and conduct task load assessment; If the current task volume exceeds the preset threshold, it will inquire whether other paired hardware entities have the same task record, and send an experience sharing request if the same task record exists.

9. A teacher emotion recognition intervention system based on interactive behavior, characterized by: It includes a cloud background and a hardware body for being placed on a teacher's desk, wherein the cloud background is used to load and execute a computer program of the teacher emotion recognition intervention method based on interactive behavior as described in any one of claims 1 to 4, and the hardware body is configured with accompanying logic.

Images