Intelligent teaching methods, systems, devices, equipment and readable storage media

Abstract

This application discloses an intelligent teaching method, system, device, equipment, and readable storage medium, relating to the field of intelligent education technology. The method includes the following steps: acquiring the performance characteristics of a student while learning a course; predicting the student's learning efficiency value based on the performance characteristics; adjusting the difficulty of the course in real time when the efficiency value differs from a preset threshold by a preset difference; retrieving test questions corresponding to the adjusted course and, during the teaching process, releasing the test questions based on the real-time playback progress of the adjusted course for the student to test their learning progress in real time; and adjusting the difficulty of the course in real time based on the student's completion of the test questions. This application achieves the effect of automatically adjusting the difficulty of the learning course during the learning process based on the student's learning situation.

Description

Technical Field

[0001] This application relates to the field of intelligent education technology, and in particular to an intelligent teaching method, system, device, equipment, and readable storage medium. Background Technology

[0002] With the continuous development of internet technology, compared with traditional information acquisition methods, the knowledge and information that can be obtained through the internet are becoming more and more extensive and comprehensive. More and more people are choosing online applications to acquire new knowledge and information.

[0003] When people use online education, they also pay attention to the actual educational effect of online education and the intelligence of modern education. For example, some educational modules with added AI functions can automatically track and predict the user's learning progress by providing test questions and collecting the user's answers. They can also automatically generate learning plans or recommend corresponding courses.

[0004] However, the aforementioned intelligent solutions all require users to provide corresponding test results and use existing learning records as sample data for prediction in order to realize AI functions. In other words, users need to complete the course before the intelligent education system can make further recommendations. When users encounter difficult courses or have poor learning results, the system cannot recommend switching to other courses that are more suitable for them in real time. As a result, current intelligent education systems lead to a poor user experience. Summary of the Invention

[0005] In view of this, this application provides an intelligent teaching method, system, device, equipment, and readable storage medium, aiming to improve the user experience when using the intelligent education system.

[0006] To achieve the above objectives, this application provides an intelligent teaching method, which includes the following steps:

[0007] To obtain the characteristics of students' performance status while learning courses;

[0008] Based on the aforementioned performance characteristics, the learning efficiency value of the student is predicted. When the difference between the efficiency value and a preset threshold is greater than a preset difference, the difficulty of the course being studied by the student is adjusted in real time.

[0009] Based on the adjusted difficulty of the course, retrieve the corresponding test questions and, during the teaching process, release the test questions according to the real-time playback progress of the adjusted difficulty of the course so that the students can test their learning progress in real time.

[0010] The difficulty of the courses studied by the students is adjusted in real time based on their performance on the test questions.

[0011] For example, the state performance characteristics include a first performance characteristic and a second performance characteristic, and the step of obtaining the student's state performance characteristics while learning the course includes:

[0012] Acquire the facial expression features of the trainees, as well as the movement features of the trainees;

[0013] Determine the facial expression features and the motion features according to the time when they change;

[0014] If the time specified matches the preset question time in the course, then the facial expression features and the action features will be used as the first performance features.

[0015] If the time specified does not match the preset questioning time for the course, then the facial expression features and the action features will be used as the second performance features.

[0016] For example, the step of predicting the efficiency value of the learner's learning efficiency based on the state performance characteristics includes:

[0017] The first performance feature and the second performance feature are input into a preset learning efficiency prediction model, and the first performance feature and the second performance feature are transformed and predicted according to the learning efficiency prediction model to obtain the efficiency value of the student's learning efficiency.

[0018] The learning efficiency prediction model is obtained by training the model to be trained based on the feature training samples, the conversion performance labels of the feature training samples, and the time labels of the key events in the course of the feature training samples.

[0019] For example, the step of performing transformation prediction processing on the first performance feature and the second performance feature respectively according to the learning efficiency prediction model to obtain the efficiency value of the student's learning efficiency includes:

[0020] According to the learning efficiency prediction model, the first performance feature and the second performance feature are classified into events, and based on the classification results and preset event weights, the first performance feature and the second performance feature are respectively transformed and predicted to obtain the efficiency value of the student's learning efficiency.

[0021] For example, the step of adjusting the difficulty of the course being studied by the student in real time when the efficiency value differs from a preset threshold by a preset difference value includes:

[0022] When the efficiency value differs from the preset threshold by more than a preset difference, the course learning record corresponding to the course learned by the student and the course information of the course learned by the student are obtained.

[0023] The difficulty of the courses studied by the students is adjusted in real time based on the course learning records, the course information, and the preset difficulty adjustment rules.

[0024] For example, the step of adjusting the difficulty of the course being studied by the student in real time based on the course learning record, the course information, and the preset difficulty adjustment rules includes:

[0025] Based on the course learning records and the course information, determine the total number of unlearned courses currently held by the student;

[0026] Based on the remaining total amount and the preset difficulty adjustment rules, the difficulty of the courses learned by the students is initially adjusted, and the courses corresponding to the adjusted difficulty are retrieved, and the total amount of courses to be learned after the adjustment is calculated.

[0027] If the total amount of learning to be completed is greater than the preset learning amount, the difficulty of the courses learned by the student is readjusted, and the process returns to the step of retrieving the course corresponding to the adjusted difficulty and calculating the total amount of learning to be completed for the adjusted course, until the total amount of learning to be completed is less than or equal to the preset learning amount.

[0028] For example, to achieve the above objectives, this application also provides an intelligent teaching system, which includes a teaching device, a monitoring device, and a prediction device:

[0029] The monitoring device is used to acquire the student's performance characteristics while learning the course;

[0030] The prediction device is used to predict the efficiency value of the student's learning efficiency based on the state performance characteristics.

[0031] The teaching device is used to adjust the difficulty of the course being learned by the student in real time when the difference between the efficiency value and the preset threshold is greater than a preset difference; to retrieve test questions corresponding to the course with adjusted difficulty based on the adjusted difficulty, and to release test questions during the teaching process according to the real-time playback progress of the course with adjusted difficulty, so that the student can test their learning progress in real time; and to adjust the difficulty of the course being learned by the student in real time based on the student's completion of the test questions.

[0032] For example, to achieve the above objectives, this application also provides an intelligent teaching device, the device comprising:

[0033] The acquisition module is used to acquire the status and performance characteristics of students while learning courses;

[0034] The prediction module is used to predict the learning efficiency value of the student based on the state performance characteristics, and adjust the difficulty of the course being studied by the student in real time when the difference between the efficiency value and the preset threshold is greater than the preset difference.

[0035] The testing module is used to retrieve test questions corresponding to the adjusted course difficulty, and to release test questions during the teaching process according to the real-time playback progress of the adjusted course, so that students can test their learning progress in real time.

[0036] The adjustment module is used to adjust the difficulty of the courses studied by the students in real time based on their performance on the test questions.

[0037] For example, to achieve the above objectives, this application also provides an intelligent teaching device, the device comprising: a memory, a processor, and an intelligent teaching program stored in the memory and executable on the processor, the intelligent teaching program being configured to implement the steps of the intelligent teaching method as described above.

[0038] For example, to achieve the above objectives, this application also provides a computer-readable storage medium storing an intelligent teaching program, which, when executed by a processor, implements the steps of the intelligent teaching method as described above.

[0039] Compared to related technologies where current intelligent education systems cannot recommend switching to more suitable courses in real time when users encounter difficult lessons or experience poor learning outcomes, leading to a poor user experience, this application addresses this issue by acquiring the student's performance characteristics during course learning; predicting the student's learning efficiency based on these characteristics; adjusting the difficulty of the course in real time when the efficiency value differs from a preset threshold by more than a preset difference; retrieving test questions corresponding to the adjusted course; and releasing tests during the teaching process based on the real-time playback progress of the adjusted course. The system provides students with real-time test questions to assess their learning progress. Based on the students' performance on these test questions, the system adjusts the difficulty of the courses in real time. In other words, by acquiring students' performance characteristics, the system predicts their learning efficiency and adjusts the difficulty of the courses accordingly. Test questions are also released in real-time, and the difficulty of the courses is adjusted synchronously after the students complete the tests. This allows for continuous and dynamic adjustment of course difficulty based on students' status and test performance during the learning process, adapting to different students' learning abilities and improving the user experience when using the intelligent teaching system. Attached Figure Description

[0040] Figure 1 This is a flowchart illustrating the first embodiment of the intelligent teaching method of this application;

[0041] Figure 2 This is a detailed flowchart of step S120 in the first embodiment of the intelligent teaching method of this application;

[0042] Figure 3 This is another detailed flowchart of step S120 in the first embodiment of the intelligent teaching method of this application;

[0043] Figure 4 This is a schematic diagram of the hardware operating environment involved in the embodiments of this application.

[0044] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0045] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0046] This application provides an intelligent teaching method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the intelligent teaching method of this application.

[0047] This application provides embodiments of an intelligent teaching method. It should be noted that although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order. For ease of description, the following omits the description of the various steps of the intelligent teaching method, which includes:

[0048] Step S110: Obtain the student's performance characteristics during the course;

[0049] In this embodiment, the student's state performance characteristics during the course are obtained. These state performance characteristics mainly include the student's reactions during the course, including actions and expressions. For example, the student may show a puzzled expression or a smiling expression when learning new knowledge, or the student may nod or shake their head during the course.

[0050] The acquisition process is mainly carried out through corresponding monitoring devices, such as the camera equipped on the terminal used by the student when learning the course. It should be noted that before acquiring the student's status behavior characteristics, confirmation will be made with the student first. Only after the student agrees to the collection of the student's status behavior characteristics can the monitoring device be controlled to acquire the corresponding status behavior characteristics. In this embodiment, the following are the implementation schemes after the student has given consent.

[0051] For example, the state performance characteristics include a first performance characteristic and a second performance characteristic, and the step of obtaining the student's state performance characteristics while learning the course includes:

[0052] Step a: Obtain the facial expression features of the trainee, as well as the movement features of the trainee;

[0053] Step b: Determine the facial expression features and the motion features according to the time when they change;

[0054] In this embodiment, after obtaining the facial expression features and movement features of the trainee, the current time will be recorded accordingly. This time is a natural time, such as 1:40 pm or 10:31 am, etc., and there is no specific limitation.

[0055] This moment corresponds to the moment when facial expression and movement characteristics change. For example, a student suddenly starts to frown from a relatively calm expression, or a student's frowning expression suddenly changes to an expression of sudden realization, or a student changes from a static state to a nodding state, etc.

[0056] In this context, the moment corresponds to additional information about facial expression features and movement features, meaning that each of the above features is assigned a corresponding moment.

[0057] Step c: If the time matches the preset course question time, then the facial expression features and the action features are used as the first performance features;

[0058] Step d: If the time does not match the preset course question time, then the facial expression features and the action features are used as the second performance features.

[0059] In this embodiment, during course recording, the time of each questioning segment in the course is pre-marked. The course content corresponding to this time is only the process of the teacher asking questions to the students. Since this process will cause students to interact with it subconsciously, for example, students will nod or shake their heads according to the questions asked by the teacher, the action features and facial expression features corresponding to this moment need to be analyzed in detail, while the action features and facial expression features at other moments are analyzed in a secondary manner.

[0060] Therefore, after determining the time of facial expression and action features, the time is matched with the preset course question time. If the two times coincide, the facial expression and action features corresponding to that time are taken as the first performance feature. If the two times do not coincide, the facial expression and action features corresponding to that time are taken as the second performance feature.

[0061] The preset question time for the course is a pre-marked time node of the entire recorded broadcast time. When the student plays the course video, the playback time is recorded when the video reaches the pre-marked time node. The time corresponding to the feature is then matched with the playback time to determine whether the two overlap.

[0062] Step S120: Based on the state performance characteristics, predict the learning efficiency value of the student; when the difference between the efficiency value and the preset threshold is greater than the preset difference, adjust the difficulty of the course being studied by the student in real time.

[0063] In this embodiment, the efficiency value of the student's learning efficiency is predicted based on the state performance characteristics. In the prediction process, the first performance characteristics and the second performance characteristics are converted into corresponding learning efficiency values, and the efficiency values ​​corresponding to the first performance characteristics and the second performance characteristics are summarized using specific weights to obtain the efficiency value of the predicted learning efficiency of the student. The weight of the first performance characteristics is greater than the weight of the second performance characteristics.

[0064] In this embodiment, when the difference between the efficiency value and the preset threshold is greater than the preset difference, it is necessary to adjust the difficulty of the course being studied by the student in real time, for example, by increasing or decreasing the difficulty of the course.

[0065] The preset threshold corresponds to the difficulty of the course. For example, if the course is of beginner difficulty, the preset threshold for beginner difficulty is relatively high and can be set to 80. If the course is of intermediate difficulty, the preset threshold for intermediate difficulty is relatively low and can be set to 70. If the course is of advanced difficulty, the preset threshold for advanced difficulty is the lowest and can be set to 60.

[0066] In this process, when pre-recording instructional videos, for the same course, content at different difficulty levels is recorded.

[0067] When the efficiency value is greater than the preset threshold, and the difference between the efficiency value and the preset threshold is greater than the preset difference, the student's current course can be switched to a more difficult course, up to the highest difficulty course.

[0068] When the efficiency value is less than the preset threshold, and the difference between the efficiency value and the preset threshold is less than the preset difference, the student's current course can be switched to a more difficult course, up to the lowest difficulty course.

[0069] The preset difference can be understood as a preset deviation value, such as 3 or 5. Taking 5 as an example, when a student is currently learning an intermediate level course, the preset threshold is 70 and the preset difference is 5. When the efficiency value is greater than 75, the difficulty of the course can be increased. When the efficiency value is less than 65, the difficulty of the course can be decreased. When the sum of the efficiency value, the preset threshold, and the preset difference is equal, the difficulty of the course remains unchanged.

[0070] Step S130: Based on the adjusted difficulty of the course, retrieve the test questions corresponding to the adjusted difficulty of the course, and during the teaching process, release the test questions according to the real-time playback progress of the adjusted difficulty of the course so that the students can test their learning progress in real time.

[0071] In this embodiment, corresponding test questions are scheduled according to the course with adjusted difficulty, and test questions are released during the teaching process according to the real-time playback progress of the course with adjusted difficulty, so that students can test their learning progress in real time.

[0072] The real-time playback progress of the course after the difficulty adjustment is selected based on the playback time of the course after the difficulty adjustment, and the timing of releasing test questions is determined accordingly. For example, after the course difficulty is adjusted, a test question is released every twenty minutes of playback.

[0073] This test question is used to assess the student's current learning progress, such as their understanding of the knowledge points covered in the past twenty minutes.

[0074] Step S140: Adjust the difficulty of the course being studied by the student in real time based on the student's performance on the test questions.

[0075] Based on the students' performance on the test questions, the difficulty of the courses they are learning is adjusted in real time. For example, after increasing the difficulty of the course, a test question is used to determine whether the students are suitable for the current level of difficulty. If not, the difficulty of the course is further adjusted. For example, after the difficulty of the course is increased, a test question is released. If the students complete the test question with a passing score or above, the difficulty of the course remains unchanged. If they fail, the difficulty of the course is reduced. Or, for example, after the difficulty of the course is reduced, if the students complete the test question with a score of 90 or above, the difficulty of the course is increased.

[0076] Compared to related technologies where current intelligent education systems cannot recommend switching to more suitable courses in real time when users encounter difficult lessons or experience poor learning outcomes, leading to a poor user experience, this application addresses this issue by acquiring the student's performance characteristics during course learning; predicting the student's learning efficiency based on these characteristics; adjusting the difficulty of the course in real time when the efficiency value differs from a preset threshold by more than a preset difference; retrieving test questions corresponding to the adjusted course; and releasing tests during the teaching process based on the real-time playback progress of the adjusted course. The system provides students with real-time test questions to assess their learning progress. Based on the students' performance on these test questions, the system adjusts the difficulty of the courses in real time. In other words, by acquiring students' performance characteristics, the system predicts their learning efficiency and adjusts the difficulty of the courses accordingly. Test questions are also released in real-time, and the difficulty of the courses is adjusted synchronously after the students complete the tests. This allows for continuous and dynamic adjustment of course difficulty based on students' status and test performance during the learning process, adapting to different students' learning abilities and improving the user experience when using the intelligent teaching system.

[0077] Exemplary, according to the first embodiment of the intelligent teaching method of this application described above, another embodiment is proposed, in which reference is made to... Figure 2 The step of predicting the learning efficiency value of the student based on the state performance characteristics includes:

[0078] Step S210: Input the first performance feature and the second performance feature into a preset learning efficiency prediction model, and perform transformation prediction processing on the first performance feature and the second performance feature respectively according to the learning efficiency prediction model to obtain the efficiency value of the student's learning efficiency.

[0079] The learning efficiency prediction model is obtained by training the model to be trained based on the feature training samples, the conversion performance labels of the feature training samples, and the time labels of the key events in the course of the feature training samples.

[0080] For example, the step of performing transformation prediction processing on the first performance feature and the second performance feature respectively according to the learning efficiency prediction model to obtain the efficiency value of the student's learning efficiency includes:

[0081] Step e: Based on the learning efficiency prediction model, classify the first performance feature and the second performance feature into events, and based on the classification results and preset event weights, perform transformation prediction processing on the first performance feature and the second performance feature respectively to obtain the efficiency value of the student's learning efficiency.

[0082] In this embodiment, the first performance feature and the second performance feature are input into a preset learning efficiency prediction model, and then the first performance feature and the second performance feature are transformed and predicted according to the learning efficiency prediction model to obtain the efficiency value of the student's learning efficiency.

[0083] The learning efficiency prediction model is obtained by training the model to be trained based on the feature training samples, the conversion performance labels of the feature training samples, and the time labels of the key events in the course of the feature training samples.

[0084] In converting the first and second performance characteristics into efficiency values, the algorithm primarily relies on the corresponding conversion performance tags and event tags for key time points in the course. These time tags correspond to the time tags of key knowledge points covered in the course, essentially functioning as an event classification algorithm. Based on these time tags, the first and second performance characteristics are categorized. If the first and second performance characteristics correspond to the time of key knowledge points, their corresponding weights are increased. Otherwise, normal weights are used. In other words, the time tags of key course events influence the weights of the first and second performance characteristics in their corresponding conversion efficiency values, thereby making the obtained efficiency values ​​more accurate.

[0085] Before using the pre-defined learning efficiency prediction model, a corresponding training process is required, which is as follows:

[0086] The process involves: acquiring feature training samples, efficiency value labels of the feature training samples, and time labels of the feature training samples; determining preset event weights with the time labels based on the feature training samples, efficiency value labels of the feature training samples, and time labels of the feature training samples; iteratively training a preset model to be trained based on the feature training samples, conversion performance labels of the feature training samples, and the preset event weights to obtain a learning efficiency prediction model that meets accuracy requirements; inputting the feature training samples and the preset event weights into the model to be trained to obtain a predicted efficiency value; calculating the difference between the predicted efficiency value and the efficiency value labels of the feature training samples to obtain an error result; determining whether the error result meets the error standard indicated by a preset error threshold range based on the error result; if the error result does not meet the error standard indicated by the preset error threshold range, returning to the step of inputting the feature training samples and the preset event weights into the model to be trained to obtain a predicted efficiency value, and stopping training until the training error result meets the error standard indicated by the preset error threshold range, thus obtaining the learning efficiency prediction model.

[0087] In this embodiment, the first performance feature and the second performance feature are input into a preset learning efficiency prediction model, and the first performance feature and the second performance feature are converted and predicted according to the learning efficiency prediction model to obtain the efficiency value of the student's learning efficiency. The learning efficiency prediction model is obtained by training a model to be trained based on feature training samples, the conversion performance labels of the feature training samples, and the time labels of the key events of the course in the feature training samples. By setting the learning efficiency prediction model with the time labels of the key events of the course, the efficiency value of the student can be accurately predicted, thereby ensuring the accuracy of subsequent adjustments to the course difficulty.

[0088] Exemplary, according to the first embodiment of the intelligent teaching method of this application described above, another embodiment is proposed, in which reference is made to... Figure 3 The step of adjusting the difficulty of the course being studied by the student in real time when the efficiency value differs from the preset threshold by a preset difference value further includes:

[0089] Step S310: When the efficiency value differs from the preset threshold by more than a preset difference, obtain the course learning record corresponding to the course learned by the student, and the course information of the course learned by the student.

[0090] In the above embodiments, the difficulty of the course being studied by the student will be adjusted in real time based on the student's performance on the test questions. For example, after increasing the difficulty of the course, the test questions will be used to determine whether the student is suitable for the current level of difficulty. If not, the difficulty of the course will be further adjusted.

[0091] In this embodiment, in addition to the adjustment method based on the completion of test questions, it also includes, based on relevant course information, when the difference between the efficiency value and the preset threshold is greater than a preset difference, obtaining the course learning record corresponding to the course learned by the student, as well as the course information of the course learned by the student, and adjusting the difficulty of the course accordingly based on the course learning record and the course information.

[0092] The course learning record includes the student's completion status of the course, including at least the viewing progress of the corresponding course videos, such as whether the student has watched 30% of the corresponding course videos, the completion status of the corresponding course exercises, such as whether the student has not mastered certain knowledge points of the course well (judging whether the student has mastered the knowledge points by the accuracy of the exercises), and the difficulty level of the courses the student has taken, such as whether the student has taken three beginner-level courses, five intermediate-level courses, and one advanced-level course.

[0093] The course information includes the total number of videos in the course, for example, a course consists of 10 videos, which are considered 10 lessons. It also includes the number of lessons that the student has not yet studied, for example, a course has a total of 10 lessons, and the student has studied 5 lessons. When the difficulty of the course is adjusted later, it may be adjusted accordingly due to the difficulty of the course, which is also important information.

[0094] Step S320: Adjust the difficulty of the course being studied by the student in real time based on the course learning record, the course information, and the preset difficulty adjustment rules.

[0095] In this embodiment, the difficulty of the courses learned by students is adjusted in real time based on course learning records, course information, and preset difficulty adjustment rules.

[0096] For example, the step of adjusting the difficulty of the course being studied by the student in real time based on the course learning record, the course information, and the preset difficulty adjustment rules includes:

[0097] Step f: Based on the course learning records and the course information, determine the total number of unlearned courses currently held by the student;

[0098] Based on course learning records and course information, the total amount of unlearned courses currently available to a student can be determined. This total amount includes the number of remaining lessons and the unplayed portion of the current lesson of the currently attended course. For example, if a student is watching a video of a lesson and detects that the course difficulty needs to be adjusted, then half of the unadjusted lesson remains unplayed and needs to be combined with other lessons of corresponding difficulty levels.

[0099] When reducing the difficulty of a course, the remaining half of the lesson that was not played can be played as advanced content at the end. When increasing the difficulty of a course, the remaining half of the lesson that was not played can be played as initial content, with key points extracted and played quickly.

[0100] In summary, when adjusting course difficulty, all course content can be played simultaneously, ensuring that students learn all the course content. Specifically, when adjusting the difficulty of a student's course in real time based on the course learning record, course information, and preset difficulty adjustment rules, courses of different difficulty levels will be merged. Unlike adjusting course difficulty based on test questions, this embodiment selects and merges courses of different difficulties to adapt to the current student's learning progress, improving the student's user experience. In contrast, when adjusting course difficulty based on test questions, the course is simply converted to the corresponding difficulty level without merging the courses.

[0101] Step g: Based on the remaining total amount and the preset difficulty adjustment rules, make an initial adjustment to the difficulty of the courses learned by the students, retrieve the courses corresponding to the adjusted difficulty, and calculate the total amount of courses to be learned after the adjustment.

[0102] In this embodiment, the difficulty of the courses learned by students is initially adjusted according to the remaining total amount and the preset difficulty adjustment rules. The course before adjustment is referred to as A, and the course after adjustment is referred to as B. Taking the example that the difficulty of course A is greater than that of course B, the courses A and B are merged. The content of course A is merged with the advanced difficulty content of the overall course. If the difficulty of course A is less than that of course B, then the opposite is true. The content of course B is merged with the advanced difficulty content of course A.

[0103] After the courses are integrated, the total amount of material to be learned in the overall courses is calculated.

[0104] The preset difficulty adjustment rule involves merging courses and using the more difficult content from the two courses as the advanced difficulty content, thereby lowering the learning threshold for students and improving their learning outcomes and user experience.

[0105] Step h: If the total amount to be learned is greater than the preset learning amount, then the difficulty of the courses learned by the student is readjusted, and the steps of retrieving the courses corresponding to the adjusted difficulty and calculating the total amount to be learned of the adjusted courses are repeated until the total amount to be learned is less than or equal to the preset learning amount.

[0106] If the calculated amount of learning to be done after integrating the learning courses is too large, it will put a certain burden on the students. Therefore, it is necessary to judge the total amount of learning to be done. If it is greater than the preset learning amount, the difficulty of the course needs to be readjusted, and the advanced difficulty courses in the integrated course can be adaptively removed.

[0107] The preset learning volume can be set according to the actual situation. This preset learning volume is a dynamically adjustable value. Its size is determined by multiplying the total amount of unlearned courses remaining by a fixed ratio, thereby ensuring that the total amount of courses to be learned after the adjustment of the course difficulty will not burden the students.

[0108] It should be noted that, to implement the above solution, the course videos need to be pre-processed accordingly. For example, course videos of three difficulty levels are recorded simultaneously, and the time for the Q&A session is marked in each video, as well as the nodes corresponding to different knowledge points in each video. For example, the first ten minutes of the course video may represent one knowledge point, and the last ten minutes may represent another knowledge point. When merging the courses, knowledge points corresponding to different difficulty levels will be extracted, extracted from different videos, and then merged. When the total amount of learning is too large, the videos corresponding to some knowledge points can be removed to avoid the total amount being too large.

[0109] In this embodiment, when the difference between the efficiency value and the preset threshold is greater than a preset difference, the course learning record corresponding to the course learned by the student and the course information of the course learned by the student are obtained; according to the course learning record, the course information and the preset difficulty adjustment rules, the difficulty of the course learned by the student is adjusted in real time, so as to realize the dynamic adjustment of the course difficulty when the student watches the course video to adapt to the learning situation of different students.

[0110] Furthermore, this application also provides an intelligent teaching system, which includes a teaching device, a monitoring device, and a prediction device.

[0111] The monitoring device is used to acquire the student's performance characteristics while learning the course;

[0112] The prediction device is used to predict the efficiency value of the student's learning efficiency based on the state performance characteristics.

[0113] The teaching device is used to adjust the difficulty of the course being learned by the student in real time when the difference between the efficiency value and the preset threshold is greater than a preset difference; to retrieve test questions corresponding to the course with adjusted difficulty based on the adjusted difficulty, and to release test questions during the teaching process according to the real-time playback progress of the course with adjusted difficulty, so that the student can test their learning progress in real time; and to adjust the difficulty of the course being learned by the student in real time based on the student's completion of the test questions.

[0114] In addition, this application also provides an intelligent teaching device, which includes:

[0115] The acquisition module is used to acquire the status and performance characteristics of students while learning courses;

[0116] The prediction module is used to predict the learning efficiency value of the student based on the state performance characteristics, and adjust the difficulty of the course being studied by the student in real time when the difference between the efficiency value and the preset threshold is greater than the preset difference.

[0117] The testing module is used to retrieve test questions corresponding to the adjusted course difficulty, and to release test questions during the teaching process according to the real-time playback progress of the adjusted course, so that students can test their learning progress in real time.

[0118] The adjustment module is used to adjust the difficulty of the courses studied by the students in real time based on their performance on the test questions.

[0119] For example, the acquisition module includes:

[0120] The first acquisition submodule is used to acquire the facial expression features of the trainee and the action features of the trainee;

[0121] A determination submodule is used to determine the facial expression features and the motion features according to the time when they change;

[0122] The first judgment submodule is used to take the facial expression features and the action features as the first performance features if the time matches the preset course question time.

[0123] The second judgment submodule is used to take the facial expression features and the action features as the second performance features if the time does not match the preset course question time.

[0124] For example, the prediction module includes:

[0125] The prediction submodule is used to input the first performance feature and the second performance feature into a preset learning efficiency prediction model, and perform conversion prediction processing on the first performance feature and the second performance feature respectively according to the learning efficiency prediction model to obtain the efficiency value of the student's learning efficiency; wherein, the learning efficiency prediction model is obtained by training the model to be trained based on the feature training samples, the conversion performance labels of the feature training samples, and the time labels of the course key events of the feature training samples.

[0126] For example, the prediction submodule includes:

[0127] The prediction unit is used to classify the first performance feature and the second performance feature into events according to the learning efficiency prediction model, and to perform transformation prediction processing on the first performance feature and the second performance feature respectively according to the classification results and preset event weights, so as to obtain the efficiency value of the student's learning efficiency.

[0128] For example, the prediction module further includes:

[0129] The second acquisition submodule is used to acquire the course learning record corresponding to the course learned by the student and the course information of the course learned by the student when the difference between the efficiency value and the preset threshold is greater than the preset difference.

[0130] The adjustment submodule is used to adjust the difficulty of the courses studied by the students in real time based on the course learning records, the course information, and the preset difficulty adjustment rules.

[0131] For example, the adjustment submodule includes:

[0132] The determining unit is used to determine the total number of unlearned courses remaining for the student based on the course learning records and the course information.

[0133] The adjustment unit is used to initially adjust the difficulty of the courses learned by the students according to the remaining total amount and the preset difficulty adjustment rules, retrieve the courses corresponding to the adjusted difficulty, and calculate the total amount of the adjusted courses to be learned.

[0134] The judgment unit is used to readjust the difficulty of the courses learned by the student if the total amount to be learned is greater than the preset learning amount, and return to the steps of retrieving the course corresponding to the adjusted difficulty and calculating the total amount to be learned of the adjusted course, until the total amount to be learned is less than or equal to the preset learning amount.

[0135] The specific implementation of the intelligent teaching device in this application is basically the same as the embodiments of the intelligent teaching method described above, and will not be repeated here.

[0136] In addition, this application also provides an intelligent teaching device. For example... Figure 4 As shown, Figure 4 This is a schematic diagram of the hardware operating environment involved in the embodiments of this application.

[0137] For example, Figure 4 This can be a structural diagram of the hardware operating environment of intelligent teaching equipment.

[0138] like Figure 4 As shown, the intelligent teaching device may include a processor 401, a communication interface 402, a memory 403, and a communication bus 404. The processor 401, the communication interface 402, and the memory 403 communicate with each other through the communication bus 404. The memory 403 is used to store computer programs. When the processor 401 executes the program stored in the memory 403, it implements the steps of the intelligent teaching method.

[0139] The communication bus 404 mentioned in the aforementioned intelligent teaching equipment can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus 404 can be divided into an address bus, a data bus, and a control bus, etc. For ease of illustration, it is represented by only one thick line in the figure, but this does not indicate that there is only one bus or one type of bus.

[0140] Communication interface 402 is used for communication between the above-mentioned intelligent teaching equipment and other devices.

[0141] The memory 403 may include random access memory (RMD) or non-volatile memory (NM), such as at least one disk storage device. Optionally, the memory 403 may also be at least one storage device located remotely from the aforementioned processor 401.

[0142] The processor 401 mentioned above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0143] The specific implementation method of the intelligent teaching device in this application is basically the same as the embodiments of the intelligent teaching method described above, and will not be repeated here.

[0144] Furthermore, embodiments of this application also propose a computer-readable storage medium storing an intelligent teaching program, which, when executed by a processor, implements the steps of the intelligent teaching method described above.

[0145] The specific implementation of the computer-readable storage medium in this application is basically the same as the embodiments of the above-described intelligent teaching method, and will not be repeated here.

[0146] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0147] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0148] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0149] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. An intelligent teaching method, characterized in that, The intelligent teaching method includes the following steps: To obtain the characteristics of students' performance status while learning courses; Based on the aforementioned performance characteristics, the learning efficiency of the student is predicted. When the difference between the efficiency value and a preset threshold is greater than a preset difference, the difficulty of the course being studied by the student is adjusted in real time. The difficulty of the course refers to video content of the same course at different difficulty levels. The step of adjusting the difficulty of the course being studied by the student in real time when the efficiency value differs from a preset threshold by a preset difference includes: When the efficiency value differs from the preset threshold by more than a preset difference, the course learning record corresponding to the course learned by the student and the course information of the course learned by the student are obtained. Based on the course learning records, course information, and preset difficulty adjustment rules, the difficulty of the courses learned by the students is adjusted in real time. If the students have not finished learning the current course when the adjustment is made, courses of different difficulties are selected and combined accordingly based on the adjusted difficulty. Based on the adjusted difficulty of the course, retrieve the corresponding test questions and, during the teaching process, release the test questions according to the real-time playback progress of the adjusted difficulty of the course so that the students can test their learning progress in real time. The difficulty of the courses studied by the students is adjusted in real time based on their performance on the test questions.

2. The intelligent teaching method as described in claim 1, characterized in that, The state performance characteristics include a first performance characteristic and a second performance characteristic. The step of obtaining the student's state performance characteristics while learning the course includes: Acquire the facial expression features of the trainees, as well as the movement features of the trainees; Determine the facial expression features and the motion features according to the time when they change; If the time specified matches the preset question time in the course, then the facial expression features and the action features will be used as the first performance features. If the time specified does not match the preset questioning time for the course, then the facial expression features and the action features will be used as the second performance features.

3. The intelligent teaching method as described in claim 2, characterized in that, The step of predicting the learning efficiency value of the student based on the state performance characteristics includes: The first performance feature and the second performance feature are input into a preset learning efficiency prediction model, and the first performance feature and the second performance feature are transformed and predicted according to the learning efficiency prediction model to obtain the efficiency value of the student's learning efficiency. The learning efficiency prediction model is obtained by training the model to be trained based on the feature training samples, the conversion performance labels of the feature training samples, and the time labels of the key events in the course of the feature training samples.

4. The intelligent teaching method as described in claim 3, characterized in that, The step of performing transformation prediction processing on the first performance feature and the second performance feature respectively according to the learning efficiency prediction model to obtain the efficiency value of the student's learning efficiency includes: According to the learning efficiency prediction model, the first performance feature and the second performance feature are classified into events, and based on the classification results and preset event weights, the first performance feature and the second performance feature are respectively transformed and predicted to obtain the efficiency value of the student's learning efficiency.

5. The intelligent teaching method as described in claim 1, characterized in that, The step of adjusting the difficulty of the course being studied by the student in real time based on the course learning record, the course information, and the preset difficulty adjustment rules includes: Based on the course learning records and the course information, determine the total number of unlearned courses currently held by the student; Based on the remaining total amount and the preset difficulty adjustment rules, the difficulty of the courses learned by the students is initially adjusted, and the courses corresponding to the adjusted difficulty are retrieved, and the total amount of courses to be learned after the adjustment is calculated. If the total amount of learning to be completed is greater than the preset learning amount, the difficulty of the courses learned by the student is readjusted, and the process returns to the step of retrieving the course corresponding to the adjusted difficulty and calculating the total amount of learning to be completed for the adjusted course, until the total amount of learning to be completed is less than or equal to the preset learning amount.

6. An intelligent teaching system, characterized in that, The intelligent teaching system includes teaching devices, monitoring devices, and prediction devices. The monitoring device is used to acquire the student's performance characteristics while learning the course; The prediction device is used to predict the efficiency value of the student's learning efficiency based on the state performance characteristics. The teaching device is used to adjust the difficulty of the course being studied by the student in real time when the difference between the efficiency value and the preset threshold is greater than a preset difference. Based on the adjusted difficulty of the course, test questions corresponding to the adjusted difficulty are retrieved. During the teaching process, test questions are released according to the real-time playback progress of the adjusted difficulty course, allowing students to test their learning progress in real time. The difficulty of the course being studied by the student is adjusted in real time based on the student's completion of the test questions. The difficulty of the course consists of video content of the same course at different difficulty levels. The step of adjusting the difficulty of the course being studied in real time when the efficiency value differs from a preset threshold by more than a preset difference includes: when the efficiency value differs from the preset threshold by more than a preset difference, obtaining the course learning record corresponding to the student's course and the course information of the student's course; adjusting the difficulty of the course being studied in real time based on the course learning record, the course information, and preset difficulty adjustment rules; if the student has not finished studying the current course at the time of adjustment, courses of different difficulties are selected and integrated accordingly based on the adjusted difficulty.

7. An intelligent teaching device, characterized in that, The intelligent teaching device includes: The acquisition module is used to acquire the status and performance characteristics of students while learning courses; The prediction module is used to predict the learning efficiency value of the student based on the state performance characteristics. When the difference between the efficiency value and the preset threshold is greater than the preset difference, the difficulty of the course being learned by the student is adjusted in real time. The difficulty of the course refers to video content of the same course at different difficulty levels. The second acquisition submodule is used to acquire the course learning record corresponding to the course learned by the student and the course information of the course learned by the student when the difference between the efficiency value and the preset threshold is greater than the preset difference. The adjustment submodule is used to adjust the difficulty of the courses learned by the students in real time based on the course learning records, the course information and the preset difficulty adjustment rules. If the students have not finished learning the current course when the adjustment is made, courses of different difficulties will be selected and combined accordingly based on the adjusted difficulty. The testing module is used to retrieve test questions corresponding to the adjusted course difficulty, and to release test questions during the teaching process according to the real-time playback progress of the adjusted course, so that students can test their learning progress in real time. The adjustment module is used to adjust the difficulty of the courses studied by the students in real time based on their performance on the test questions.

8. An intelligent teaching device, characterized in that, The device includes: a memory, a processor, and an intelligent teaching program stored in the memory and executable on the processor, the intelligent teaching program being configured to implement the steps of the intelligent teaching method as described in any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an intelligent teaching program, which, when executed by a processor, implements the steps of the intelligent teaching method as described in any one of claims 1 to 5.

Images