Remote teaching tutoring platform based on big data

Abstract

The invention discloses a remote teaching tutoring platform based on big data, and the platform comprises the steps: positioning a time period when a student puzzles a knowledge point, analyzing the acceptance degree value of the student to the knowledge point corresponding to the time period, and adjusting the teaching speed according to the acceptance degree average value. According to the invention, by positioning the nth time period in which the students are confused to the teaching knowledge points, and taking the confusion of the students to the teaching knowledge points as initial positioning, the time for monitoring whether the students receive the knowledge points or not by a remote teaching auxiliary platform can be effectively shortened; meanwhile, whether the students can complete the listening progress or not is predicted by analyzing the acceptance degree values of the students on the knowledge points, the monitoring stability is improved, finally, the teacher is prompted to adjust the teaching speed based on the monitoring result, the learning progress of most students in remote teaching can be concerned while the teaching efficiency is considered, and the teaching efficiency is improved. And the teaching speed is properly reduced to meet the questioning requirements of the students, and the system has the characteristics of high remote teaching monitoring capability and high humanization degree.

Description

Technical Field

[0001] The present invention relates to the technical field of teaching assistance platforms, and specifically to a remote teaching tutoring platform based on big data. Background Art

[0002] In today's digital age, education is constantly evolving and innovating. The emergence of the big data precise teaching platform has broken the limitations of time and space. No matter where students are, as long as they have access to the Internet, they can enjoy high-quality educational resources anytime and anywhere. This undoubtedly provides strong support for the popularization and fairness of education, adds wings of innovation to education, and makes teaching more precise, efficient, and personalized.

[0003] In the prior art, through the analysis of students' learning data, the big data precise teaching platform can accurately monitor students' class status and formulate the most suitable teaching plan in real time. However, due to the different digestion abilities of students for the teaching content during the process of listening carefully, some students are unable to understand the teaching content in a short time, which easily leads to their inability to keep up with the teaching rhythm and greatly reduces learning efficiency. At the same time, although some students can understand the teaching content in a short time, there are gaps in the subsequent teaching of knowledge points, and they still cannot keep up with the teaching rhythm. On the other hand, teachers also need to maintain the teaching speed to ensure the progress of teaching knowledge points. Therefore, it is necessary to design a remote teaching tutoring platform based on big data with strong remote teaching monitoring ability and high degree of humanization. Summary of the Invention

[0004] The purpose of the present invention is to provide a remote teaching tutoring platform based on big data to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: A remote teaching tutoring platform based on big data, comprising:

[0006] Locate the nth time period when students are confused about the taught knowledge points during the learning process of students, wherein each time period within the learning process corresponds to teaching one of the taught knowledge points;

[0007] Analyze the acceptance degree value of the students for the knowledge points corresponding to the nth time period during the n + 1th time period;

[0008] According to the time periods and acceptance degree values when all students in the class are confused, obtain the average acceptance degree of all students for each knowledge point, and adjust the teaching speed according to the average acceptance degree.

[0009] According to the above technical solution, locating the nth time period when students are confused about the taught knowledge points during the learning process of students includes;

[0010] Take the class - listening images of the student, identify the class - listening characteristics and the body characteristics of the student in the class - listening images, retrieve the body characteristics of the student in the database, record the number of preset response results corresponding to different body characteristics according to the retrieval results of the database, and judge whether the student is confused about the teaching knowledge points by judging the proportion of the number of different preset response results in the current single time period. Among them, the preset response results include understanding the teaching knowledge points and not understanding the teaching knowledge points;

[0011] If the ratio of the number of understanding the teaching knowledge points to the number of not understanding the teaching knowledge points is lower than A%, then position the current single time period as the time period when the student is confused about the teaching knowledge points, where A% is the lowest limit value of the ratio corresponding to the situation that the student is not confused about the teaching knowledge points.

[0012] According to the above - mentioned technical solution, the recording of the number of preset response results corresponding to different body characteristics according to the retrieval results of the database includes:

[0013] Simultaneously take the teaching images of the teacher. When the number of recorded preset response results corresponding to different body characteristics is lower than the minimum sample size M, identify the teacher's teaching characteristics based on the teacher's teaching images, record the student's class - listening characteristics at the student side and the teacher's teaching characteristics at the teacher side respectively during the current teaching knowledge point process, and synchronously input them into the database;

[0014] When it is detected that the occurrence time of the student's class - listening characteristics and the occurrence time of the teacher's teaching characteristics at the teacher side are not within the preset same synchronous time - period range, position the current single time period as the time period when the student is confused about the teaching knowledge points. Among them, the platform interface includes a student side and a teacher side, and the platform interface floats on the playback screen of the remote teaching tutoring platform for display.

[0015] According to the above - mentioned technical solution, the analysis of the acceptance degree value of the student for the knowledge points corresponding to the nth time period in the (n + 1)th time period includes:

[0016] After positioning the nth time period when the student is confused about the teaching knowledge points, record the different body characteristics of the student and the corresponding preset response results. The recording of the preset response results corresponding to the different body characteristics of the student includes G levels;

[0017] After positioning the nth time period when the student is confused about the teaching knowledge points, the acceptance degree value of the student for the knowledge points in the (n + 1)th time period where G 01 is the preset response result level corresponding to the body characteristics that appear when positioning the nth time period when the student is confused about the teaching knowledge points, Gcr For the preset response result level corresponding to the limb feature that appears within the (n + 1)-th time period, G c1 > G cr , where r is the level of the limb feature obtained by recording, and c is the number of bits of the mark when the limb feature appears in the n-th time period.

[0018] According to the above technical solution, each time period within the learning process corresponds to teaching one teaching knowledge point, including:

[0019] Match the duration of the time period when the student is confused recorded with the acceptance degree value of the student for the knowledge point, and based on the matching result, prompt the teacher to adjust the actual teaching speed according to the real-time detection result, where the duration of each time period within the student's learning process is not fixed.

[0020] According to the above technical solution, obtaining the average acceptance degree of all students for each knowledge point based on the time periods when all students in the class are confused and the acceptance degree values, and adjusting the teaching speed according to the average acceptance degree, includes:

[0021] Determine the difficult points of the students and mark them on the interface of the remote teaching tutoring platform;

[0022] After obtaining and positioning the average acceptance degree value of the students for the knowledge point in the (n + 1)-th time period after the n-th time period when all students are confused about the teaching knowledge point, when the average acceptance degree value is lower than the threshold acceptance degree value by each percentage point, prompt to reduce the teaching speed by 10%, and the maximum reduction of the teaching speed can be 50%. Real-time test the current teaching speed of the teacher and display the test result to the teacher through the teacher terminal;

[0023] When it is monitored that the average acceptance degree value is higher than the threshold acceptance degree value, end the difficult point marking event and control the difficult points to be cancelled and displayed on the playback interface.

[0024] According to the above technical solution, a remote teaching tutoring system based on big data includes:

[0025] A positioning module, which is used to locate the n-th time period when the students are confused about the teaching knowledge point in the learning process of the students, where each time period within the learning process corresponds to teaching one teaching knowledge point;

[0026] An analysis module, which is used to analyze the acceptance degree value of the students for the knowledge point corresponding to the n-th time period in the (n + 1)-th time period;

[0027] An adjustment module, which is used to obtain the average acceptance degree of all students for each knowledge point according to the time periods when all students in the classroom are confused and the reception degree values, and adjust the teaching speed according to the average acceptance degree.

[0028] According to the above technical solution, the positioning module includes:

[0029] An identification module, which is used to capture the listening images of the students, identify the listening characteristics and body characteristics of the students in the listening images, retrieve the body characteristics of the students in the database, record the number of preset response results corresponding to different body characteristics according to the retrieval results of the database, and judge whether the students are confused about the teaching knowledge points by judging the proportion of the number of different preset response results in the current single time period. Among them, the preset response results include understanding the teaching knowledge points and not understanding the teaching knowledge points; if the ratio of the number of understanding the teaching knowledge points to the number of not understanding the teaching knowledge points is lower than A%, the current single time period is positioned as the time period when the students are confused about the teaching knowledge points, where A% is the lowest limit value of the ratio corresponding to the students not being confused about the teaching knowledge points.

[0030] A synchronous monitoring module, which is used to synchronously capture the teaching images of the teacher. When the number of preset response results corresponding to different body characteristics is lower than the minimum sample size M, identify the teacher's teaching characteristics based on the teacher's teaching images, record the listening characteristics of the students at the student end and the teaching characteristics of the teacher at the teacher end respectively during the current teaching knowledge point process, and synchronously input them into the database. When it is detected that the appearance time of the listening characteristics of the students and the appearance time of the teaching characteristics of the teacher at the teacher end are not within the preset same synchronous time period range, the current single time period is positioned as the time period when the students are confused about the teaching knowledge points. Among them, the platform interface includes a student end and a teacher end, and the platform interface floats on the playback screen of the remote teaching and tutoring platform for display.

[0031] According to the above technical solution, the analysis module includes:

[0032] A focusing module, which is used to record the different body characteristics of the students and the corresponding preset response results after the nth time period when the students are confused about the teaching knowledge points. The recording of the preset response results corresponding to the different body characteristics of the students includes G levels;

[0033] An acceptance degree value acquisition module, which is used to acquire the acceptance degree value of the students for the knowledge points in the (n + 1)th time period after the nth time period when the students are confused about the teaching knowledge points Where G 01For the preset response result level corresponding to the limb characteristics when positioning the nth time period when the student is confused about the knowledge points taught, G cr For the preset response result level corresponding to the limb characteristics that appear in the (n + 1)th time period, G c1 > G cr , r is the level of the limb characteristics obtained by the record, and c is the number of bits of the mark of the limb characteristics that appear in the nth time period.

[0034] According to the above technical solution, the adjustment module includes:

[0035] A matching module, which is used to match the duration of the time period when the student is confused obtained by the record with the acceptance degree value of the student for the knowledge points, and based on the matching result, prompt the teacher to adjust the actual teaching speed according to the real-time detection result. Among them, the duration of each time period in the student's learning process is not fixed.

[0036] A teaching speed adjustment module, which is used to determine the difficult points of the students and mark them on the interface of the remote teaching tutoring platform; obtain and locate the average acceptance degree value of the students for the knowledge points in the (n + 1)th time period after the nth time period when all students are confused about the knowledge points taught. When the average acceptance degree value is lower than the boundary acceptance degree value by each percentage point, prompt to reduce the teaching speed by 10%. The maximum reduction of the teaching speed can be 50%. The current teaching speed of the teacher is tested in real time and the test result is displayed to the teacher through the teacher terminal; when it is monitored that the average acceptance degree value is higher than the boundary acceptance degree value, end the difficult point marking event and control the difficult points to be cancelled and displayed on the playing interface.

[0037] Compared with the prior art, the beneficial effects achieved by the present invention are: by monitoring the learning process of the students, positioning the nth time period when the students are confused about the knowledge points taught, and using the confusion of the students about the knowledge points taught as the initial positioning, it can effectively reduce the monitoring time of the remote teaching assistance platform for whether the students accept the knowledge points; at the same time, analyze the acceptance degree value of the students for the knowledge points in the (n + 1)th time period after the nth time period when the students are confused about the knowledge points taught, further predict whether the students can complete the listening progress, improve the monitoring stability, and finally prompt the teacher to adjust the teaching speed based on the monitoring result, which can pay attention to the learning progress of most students in remote teaching while taking into account the teaching efficiency, and appropriately reduce the teaching speed to meet the question needs of the students. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They 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 drawings:

[0039] Figure 1 It is a flowchart of a remote teaching tutoring platform based on big data provided by an embodiment of the present invention. Specific embodiments

[0040] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0041] Please refer to Figure 1 , a flowchart of a remote teaching tutoring platform based on big data provided by an embodiment of the present invention, as Figure 1 It can be seen that the remote teaching tutoring platform based on big data includes:

[0042] Step S1: Locate the nth time period when the student is confused about the taught knowledge points during the learning process of the student, where each time period within the learning process corresponds to teaching one of the taught knowledge points;

[0043] Step S2: Analyze the acceptance degree value of the student for the knowledge points corresponding to the nth time period during the (n + 1)th time period;

[0044] Step S3: Obtain the average acceptance degree of all students for each knowledge point according to the time periods and acceptance degree values when all students in the class are confused, and adjust the teaching speed according to the average acceptance degree.

[0045] In the present invention, by monitoring the learning process of the student, the nth time period when the student is confused about the taught knowledge points is located. Using the confusion of the student about the taught knowledge points as the initial positioning can effectively reduce the monitoring time of whether the student accepts the knowledge points by the remote teaching assistance platform; at the same time, analyze the acceptance degree value of the student for the knowledge points during the (n + 1)th time period after locating the nth time period when the student is confused about the taught knowledge points, further predict whether the student can complete the listening progress, improve the monitoring stability, and finally prompt the teacher to adjust the teaching speed based on the monitoring results, which can pay attention to the learning progress of most students in remote teaching while taking into account the teaching efficiency, and appropriately reduce the teaching speed to meet the question needs of the students.

[0046] In some preferred embodiments, the locating the nth time period when the student is confused about the taught knowledge points during the learning process of the student includes;

[0047] Step S11: Take the listening image of the student, identify the listening characteristics and limb characteristics of the student in the listening image, retrieve the limb characteristics of the student in the database, record the number of preset response results corresponding to different limb characteristics according to the retrieval result of the database, and judge whether the student is confused about the teaching knowledge points by judging the proportion of the number of different preset response results within the current single time period, where the preset response results include understanding the teaching knowledge points and not understanding the teaching knowledge points;

[0048] Step S12: If the ratio of the number of understanding the teaching knowledge points to the number of not understanding the teaching knowledge points is lower than A%, then position the current single time period as the time period when the student is confused about the teaching knowledge points, where A% is the lowest limit value of the ratio corresponding to the student not being confused about the teaching knowledge points.

[0049] In a preferred embodiment, the retrieval results of the limb characteristics in the database include:

[0050] Detect the characteristic that the student's head swings up and down in the vertical plane, mark it as the first limb characteristic and set the corresponding preset response result in the database as understanding the teaching knowledge points;

[0051] Detect the recorded characteristic of the student's fingers, mark it as the second limb characteristic and set the corresponding preset response result in the database as understanding the teaching knowledge points;

[0052] Detect the characteristic that the student's head swings left and right in the horizontal plane, mark it as the third limb characteristic and set the corresponding preset response result in the database as understanding the teaching knowledge points;

[0053] Detect the characteristic of frowning in the eyebrow area of the student's face, mark it as the fourth limb characteristic and set the corresponding preset response result in the database as not understanding the teaching knowledge points;

[0054] This application is based on the situation that the student is listening attentively on the remote teaching assistance platform. The situation of the student being inattentive or distracted is not within the monitoring scope. Therefore, when the student is listening attentively and not confused, the situation of being unable to accept knowledge points will not occur in a short time period. Therefore, positioning the student's confusion about the teaching knowledge points as the initial positioning can effectively reduce the monitoring time of the remote teaching assistance platform for whether the student accepts the knowledge points and improve the monitoring stability.

[0055] In the prior art, it is mainly solved by monitoring means at the result level. The classroom is tested regularly, and the stage learning state of students is judged by whether students can complete the test questions. However, if a student fails to complete the test questions, it is impossible to judge whether it will affect the learning acceptance value of the student in the subsequent listening process. Since the teaching content often combines the process and the conclusion, even if there are problems in the understanding of the process, it may not affect the understanding of the conclusion. Therefore, the prior art cannot solve the problem of adjusting the teaching rhythm based on the accurate monitoring of the acceptance degree of students for the teaching knowledge points.

[0056] In some preferred embodiments, the recording of the preset response result quantities corresponding to different limb features according to the retrieval result of the database includes:

[0057] Step S13: Simultaneously capture the teaching image of the teacher. When the recorded preset response result quantities corresponding to different limb features are lower than the minimum sample size M, identify the teaching features of the teacher based on the teaching image of the teacher, and record and simultaneously input the student learning features at the student side and the teaching features of the teacher at the teacher side into the database during the process of the current teaching knowledge point.

[0058] Step S14: When it is detected that the appearance time of the student learning features and the appearance time of the teaching features of the teacher at the teacher side are not within the preset same synchronization time period range, the synchronization time period is used to respectively determine the time difference between the appearance time of the student learning features and the appearance time of the teaching features of the teacher at the teacher side, and record the specific synchronization time period range according to the time difference. The synchronization time period range is smaller than the single time period, and the current single time period is positioned as the time period when the student is confused about the teaching knowledge point. Among them, the platform interface includes the student side and the teacher side, and the platform interface floats on the playback screen of the remote teaching tutoring platform for display.

[0059] In some preferred embodiments, the class start time is recorded from 0 to 60 minutes since the class starts, the single time period is 5 minutes, and there are 12 time periods in total. The appearance time of the student learning features is detected 41 minutes after the class starts, and the appearance time of the teaching features of the teacher at the teacher side is detected 43 minutes after the class starts. The preset synchronization time period is 2 minutes. Then, the first synchronization time period is 40 - 42 minutes, and the second synchronization time period is 42 - 44 minutes. At this time, the appearance time of the student learning features and the appearance time of the teaching features of the teacher at the teacher side are not within the preset same synchronization time period range. Then, the time period of 40 - 45 minutes is positioned as the time period when the student is confused about the teaching knowledge point.

[0060] In some preferred embodiments, the analysis of the acceptance degree value of the student for the knowledge point corresponding to the nth time period in the (n + 1)th time period includes:

[0061] Step S21: after locating the nth time period in which the student is confused about the teaching knowledge point, recording the different limb characteristics of the student and the corresponding preset reaction results, wherein the preset reaction results corresponding to the different limb characteristics of the student include G levels, G is a variable value, G is divided according to the amplitude values of the different limb characteristics of the student, and the specific value of G is determined according to the maximum amplitude value of the different limb characteristics of the student and the preset value of the average single amplitude change;

[0062] After the nth time period in which the student is confused about the teaching knowledge point, the student's acceptance degree value of the knowledge point in the n+1th time period Among them G 01 is the preset reaction result level corresponding to the limb features appearing when locating the nth time period in which the student is confused about the teaching knowledge point, G cr is the preset reaction result level corresponding to the limb feature appearing in the n+1th time period, G c1 >G cr , r is the level of the limb features obtained by the record, r is less than or equal to the maximum level of the limb features obtained, c is the number of marker bits of the limb features appearing in the nth time period, and c is less than the maximum number of limb feature markers retrieved from the database.

[0063] The difference between the acceptance level and confusion is as follows: confusion refers to students' misunderstanding of the knowledge points currently being taught, such as small steps within a knowledge point, but it does not affect students' continued listening to the class, and they only need to self-study or ask for advice after the course is over; and the level of students' acceptance level of knowledge points will affect whether students can currently understand the conclusion of the knowledge points and whether it will affect the next knowledge points being taught. If students' acceptance level of knowledge points is too low, it may cause students to be completely unable to keep up with the teaching rhythm in the next teaching time.

[0064] Different body features are used to monitor and judge whether students are confused about knowledge under normal circumstances, but the degree of acceptance of knowledge points cannot be obtained. However, since the degree of acceptance of knowledge is based on the judgment that students may be able to understand the next knowledge point after they are confused about the knowledge, when students are confused about the knowledge points in n time periods, if they still cannot understand the knowledge points in the n+1 time period due to the failure to master the knowledge points in the n time periods, they will feel irritated. At this time, the body features change under the confusion situation. Therefore, the degree of acceptance of knowledge points in the n+1th time period can be obtained by detecting the changes in the different body features and the corresponding reaction results.

[0065] In some preferred embodiments, the student marks the position of the difficult points on the playback interface by clicking on one or more grids on the grid interface, and uploads the position data of the grids clicked by the student, the grid interface composition information, and the playback interface size information of the student side to the remote teaching assistance platform;

[0066] The remote teaching assistance platform includes a module for receiving the grid position data, grid interface composition information, and playback interface size information uploaded by the student side and pushing them to the teacher side;

[0067] The size information of the course live broadcast interface on the teacher side, the size information of the playback interface on the student side, and the grid position data sent by the student side are used to display the acceptance degree value result of the student for the knowledge points and finally determine the difficult points of the student.

[0068] In some preferred embodiments, each time period within the learning process corresponds to teaching one of the teaching knowledge points, including:

[0069] Step S22: Match the duration of the time period when the student is confused recorded with the acceptance degree value of the student for the knowledge point, and based on the matching result, prompt the teacher to adjust the actual teaching speed according to the real-time detection result, where the duration of each time period within the student's learning process is not fixed.

[0070] In some preferred embodiments, according to the time periods when all students in the class are confused and the acceptance degree values, obtaining the average acceptance degree value of all students for each knowledge point, and adjusting the teaching speed according to the average acceptance degree value, including:

[0071] Step S31: Determine the difficult points of the students and mark them on the interface of the remote teaching tutoring platform;

[0072] Step S32: After obtaining and positioning the nth time period when all students are confused about the teaching knowledge point, obtain the average acceptance degree value of the students for the knowledge point in the (n + 1)th time period. For each percentage point that the average acceptance degree value is lower than the threshold acceptance degree value, prompt to reduce the teaching speed by 10%. The maximum reduction of the teaching speed can be 50%. Real-time test the current teaching speed of the teacher and display the test result to the teacher through the teacher side;

[0073] Step S33: When it is monitored that the average acceptance degree value is higher than the threshold acceptance degree value, end the difficult point marking event and control the difficult points to be hidden on the playback interface.

[0074] Based on the same concept as the above embodiments, an embodiment of the present invention further provides a remote teaching tutoring system based on big data, including:

[0075] A positioning module, which is used to locate the nth time period when a student is confused about a taught knowledge point during the student's learning process, where each time period in the learning process corresponds to teaching one of the taught knowledge points;

[0076] An analysis module, which is used to analyze the acceptance degree value of the student for the knowledge point corresponding to the nth time period during the (n + 1)th time period;

[0077] An adjustment module, which is used to obtain the average acceptance degree of all students for each knowledge point according to the time periods when all students in the class are confused and the acceptance degree values, and adjust the teaching speed according to the average acceptance degree.

[0078] In this embodiment, the positioning module includes:

[0079] An identification module, which is used to take a listening image of the student, identify the listening characteristics and body characteristics of the student in the listening image, retrieve the body characteristics of the student in a database, record the preset response result quantities corresponding to different body characteristics according to the retrieval result of the database, and judge whether the student is confused about the taught knowledge point by judging the proportion of different preset response result quantities within the current single time period, where the preset response results include understanding the taught knowledge point and not understanding the taught knowledge point; if the quantity ratio of understanding the taught knowledge point to not understanding the taught knowledge point is lower than A%, the current single time period is positioned as the time period when the student is confused about the taught knowledge point, where A% is the lowest limit value of the quantity ratio corresponding to the student not being confused about the taught knowledge point.

[0080] A synchronous monitoring module, which is used to synchronously take a teaching image of the teacher. When the preset response result quantities corresponding to different body characteristics are lower than the minimum sample quantity M, identify the teacher's teaching characteristics based on the teacher's teaching image, record the student's listening characteristics at the student end and the teacher's teaching characteristics at the teacher end respectively during the process of the current taught knowledge point and synchronously input them into the database. When it is detected that the appearance time of the student's listening characteristics and the appearance time of the teacher's teaching characteristics at the teacher end are not within the preset same synchronous time period range, the current single time period is positioned as the time period when the student is confused about the taught knowledge point, where the platform interface includes a student end and a teacher end, and the platform interface floats and is displayed on the playback screen of the remote teaching tutoring platform.

[0081] In this embodiment, the analysis module includes:

[0082] Focus module, which is used to record different body characteristics of the student and the corresponding preset response results after the nth time period when the student is confused about the teaching knowledge points. The recording of the preset response results corresponding to different body characteristics of the student includes G levels;

[0083] Acceptance value acquisition module, which is used to acquire the acceptance value of the student for the knowledge points in the (n + 1)th time period after the nth time period when the located student is confused about the teaching knowledge points where G 01 is the preset response result level corresponding to the body characteristics that appear in the nth time period when the located student is confused about the teaching knowledge points, and G cr is the preset response result level corresponding to the body characteristics that appear in the (n + 1)th time period, and G c1 > G cr , r is the level of the recorded body characteristics, and c is the number of digits of the body characteristics that appear in the nth time period.

[0084] In this embodiment, the adjustment module includes:

[0085] Matching module, which is used to match the duration of the time period when the student is confused recorded with the acceptance value of the student for the knowledge points, and prompt the teacher to adjust the actual teaching speed according to the real-time detection result based on the matching result. Among them, the duration of each time period in the learning process of the student is not fixed.

[0086] Teaching speed adjustment module, which is used to determine the difficult points of the students and mark them on the interface of the remote teaching tutoring platform; acquire the average acceptance value of the students for the knowledge points in the (n + 1)th time period after the nth time period when all the located students are confused about the teaching knowledge points. When the average acceptance value is lower than the threshold acceptance value by each percentage point, prompt to reduce the teaching speed by 10%. The maximum reduction of the teaching speed can be 50%. Real-time test the current teaching speed of the teacher and display the test result to the teacher through the teacher terminal; when it is monitored that the average acceptance value is higher than the threshold acceptance value, end the difficult point marking event and control the difficult points to cancel the display on the playback interface

[0087] It should be noted that in this text, 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 any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0088] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A remote teaching tutoring platform based on big data, characterized in that: Including: Locate the nth time period when the student is confused about the taught knowledge point during the student's learning process, where each time period within the learning process corresponds to teaching one of the taught knowledge points; Analyze the acceptance degree value of the student for the knowledge point corresponding to the nth time period during the (n + 1)th time period; Based on the time periods when all students in the class are confused and the acceptance degree values, obtain the average acceptance degree of all students for each knowledge point, and adjust the teaching speed according to the average acceptance degree.

2. The remote teaching and tutoring platform based on big data according to claim 1, characterized in that: The locating the nth time period when the student is confused about the taught knowledge point during the student's learning process includes; Take a picture of the student's listening image, identify the student's listening characteristics and body characteristics in the listening image, retrieve the student's body characteristics in the database, record the number of preset response results corresponding to different body characteristics according to the retrieval result of the database, and judge whether the student is confused about the taught knowledge point by judging the proportion of the number of different preset response results within the current single time period, where the preset response results include understanding the taught knowledge point and not understanding the taught knowledge point; If the ratio of the number of understanding the taught knowledge point to the number of not understanding the taught knowledge point is lower than A%, then locate the current single time period as the time period when the student is confused about the taught knowledge point, where A% is the lowest limit value of the ratio corresponding to the student not being confused about the taught knowledge point.

3. The remote teaching and tutoring platform based on big data according to claim 2, characterized in that: The recording the number of preset response results corresponding to different body characteristics according to the retrieval result of the database includes: Synchronously take a picture of the teacher's teaching image. When the number of recorded preset response results corresponding to different body characteristics is lower than the minimum sample size M, identify the teacher's teaching characteristics based on the teacher's teaching image, record the student's listening characteristics at the student end and the teacher's teaching characteristics at the teacher end respectively during the current taught knowledge point process, and synchronously input them into the database; When it is detected that the appearance time of the student's listening characteristics and the appearance time of the teacher's teaching characteristics at the teacher end are not within the preset same synchronous time period range, locate the current single time period as the time period when the student is confused about the taught knowledge point, where the platform interface includes a student end and a teacher end, and the platform interface floats on the playback screen of the remote teaching tutoring platform for display.

4. The remote teaching tutoring platform based on big data according to claim 2, characterized in that: The analyzing the acceptance degree value of the student for the knowledge point corresponding to the nth time period during the (n + 1)th time period includes: After locating the nth time period when the student is confused about the taught knowledge point, record the student's different body characteristics and the corresponding preset response results. The recording the preset response results corresponding to the student's different body characteristics includes G levels; After the nth time period when the positioning student is confused about the teaching knowledge point, the acceptance degree value of the knowledge point by the student in the (n + 1)th time period Where G 01 is the preset response result level corresponding to the body feature when positioning the nth time period when the student is confused about the teaching knowledge point, G cr is the preset response result level corresponding to the body feature that appears in the (n + 1)th time period, G c1 > G cr , r is the level of the body feature obtained by the record, and c is the number of bits of the body feature that appears in the nth time period.

5. A remote teaching tutoring platform based on big data according to claim 1, characterized in that: Each time period within the learning process corresponds to teaching one of the taught knowledge points, including: Match the duration of the time period when the student is confused with the acceptance degree value of the student for the knowledge point, and based on the matching result, prompt the teacher to adjust the actual teaching speed according to the real-time detection result, where the duration of each time period within the student's learning process is not fixed.

6. The remote teaching and tutoring platform based on big data according to claim 5, wherein: Obtaining the average acceptance degree of all students for each knowledge point according to the time periods and reception degree values when all students in the classroom are confused, and adjusting the teaching speed according to the average acceptance degree, including: Determining the difficult points of the students and marking them on the interface of the remote teaching tutoring platform; Obtaining and positioning the average acceptance degree value of the students for the knowledge point in the (n + 1)-th time period after the n-th time period when all students are confused about the taught knowledge point. For each percentage point by which the average acceptance degree value is lower than the threshold acceptance degree value, prompt to reduce the teaching speed by 10%. The maximum reduction of the teaching speed can be 50%. Real-time test the current teaching speed of the teacher and display the test result to the teacher through the teacher terminal; When it is monitored that the average acceptance degree value is higher than the threshold acceptance degree value, end the difficult point marking event and control the difficult points to be cancelled from display on the playback interface.

7. A remote teaching and tutoring system based on big data, characterized in that: Including: A positioning module, which is used to position the n-th time period when the students are confused about the taught knowledge point during the learning process of the students. Each time period in the learning process corresponds to teaching one of the taught knowledge points; An analysis module, which is used to analyze the acceptance degree value of the students for the knowledge point corresponding to the n-th time period in the (n + 1)-th time period; An adjustment module, which is used to obtain the average acceptance degree of all students for each knowledge point according to the time periods and reception degree values when all students in the classroom are confused, and adjust the teaching speed according to the average acceptance degree.

8. A remote teaching tutoring platform based on big data according to claim 7, characterized in that: The positioning module includes: An identification module, which is used to take a listening image of the student, identify the listening characteristics and limb characteristics of the student in the listening image, retrieve the limb characteristics of the student in the database, record the number of preset response results corresponding to different limb characteristics according to the retrieval result of the database, and judge whether the student is confused about the taught knowledge point by judging the proportion of the number of different preset response results within the current single time period. The preset response results include understanding the taught knowledge point and not understanding the taught knowledge point; if the ratio of the number of understanding the taught knowledge point to the number of not understanding the taught knowledge point is lower than A%, then the current single time period is positioned as the time period when the student is confused about the taught knowledge point, where A% is the lowest limit value of the ratio corresponding to the situation where the student is not confused about the taught knowledge point; Synchronization monitoring module, which is used to synchronously capture the teaching images of the teacher. When the number of preset response results corresponding to different limb features is lower than the minimum sample size M, it identifies the teacher's teaching features based on the teacher's teaching images, records the student's listening features at the student end and the teacher's teaching features at the teacher end respectively during the current teaching knowledge point process, and synchronously inputs them into the database. When it is detected that the occurrence time of the student's listening features and the occurrence time of the teacher's teaching features at the teacher end are not within the preset same synchronization time period range, the current single time period is positioned as the time period when the student is confused about the teaching knowledge point. Among them, the platform interface includes a student end and a teacher end, and the platform interface is displayed floating on the playback screen of the remote teaching tutoring platform.

9. The remote teaching tutoring platform based on big data according to claim 8, characterized in that: The analysis module includes: Focusing module, which is used to record different limb features of the student and the corresponding preset response results after positioning the nth time period when the student is confused about the teaching knowledge point. The recording of the preset response results corresponding to different limb features of the student includes G levels; Acceptance level value acquisition module, which is used to acquire the acceptance level value of the student for the knowledge points taught during the (n + 1)-th time period after the n-th time period when the positioned student has confusion about the knowledge points taught where G 01 is the preset response result level corresponding to the body feature that appears at the n-th time period when the positioned student has confusion about the knowledge points taught, G cr is the preset response result level corresponding to the body feature that appears during the (n + 1)-th time period, G c1 > G cr , r is the level of the body feature obtained by recording, and c is the number of bits of the mark of the body feature that appears at the n-th time period.

10. A remote teaching tutoring platform based on big data according to claim 9, characterized in that: The adjustment module includes: Matching module, which is used to match the duration of the time period when the student is confused recorded with the acceptance degree value of the student for the knowledge point, and prompt the teacher to adjust the actual teaching speed according to the real-time detection result based on the matching result. Among them, the duration of each time period in the student's learning process is not fixed. Teaching speed adjustment module, which is used to determine the difficult points of the students and mark them on the interface of the remote teaching tutoring platform; obtain the average acceptance degree value of the students for the knowledge point in the (n + 1)th time period after positioning the nth time period when all students are confused about the teaching knowledge point. When the average acceptance degree value is lower than each percentage point of the threshold acceptance degree value, it prompts to reduce the teaching speed by 10%. The maximum reduction of the teaching speed can be 50%. It tests the current teaching speed of the teacher in real time and displays the test result to the teacher through the teacher end; when it is monitored that the average acceptance degree value is higher than the threshold acceptance degree value, it ends the difficult point marking event and controls the cancellation of the display of the difficult points on the playback interface.

Images