Autonomous teaching method and device and storage medium

Abstract

The invention discloses an autonomous teaching method and device and a storage medium, and the method comprises the steps: obtaining teaching plan information, calling a preset teaching model, and determining a current teaching scheme according to the teaching plan information; teaching the student according to the current teaching scheme, and obtaining learning feedback information of the student in real time; calling a preset teaching model to update the current teaching scheme according to the learning feedback information; when teaching is carried out on students according to the current teaching scheme, teacher adjustment information is monitored in real time; and updating the preset teaching model when the teacher adjustment information is received. The current teaching scheme is adjusted by acquiring the learning feedback information of the student in real time, so that the learning experience and learning efficiency of the student are ensured; meanwhile, when teaching is carried out according to the current teaching scheme, teacher adjustment information is monitored in real time, the preset teaching model can carry out self-learning updating according to the teacher adjustment information, the model is further perfected, and teaching is better carried out.

Description

Technical Field

[0001] This application relates to the field of intelligent education technology, and particularly to an autonomous teaching method, device, and storage medium. Background Art

[0002] Driven by current artificial intelligence technology, the education field is moving towards a more personalized and intelligent development direction. Although the traditional intelligent education system can generate teaching plans and guide students under the drive of algorithms, this system focuses more on the imparting of content and the tracking of learning progress. However, students are not only affected by the difficulty of knowledge and learning progress during the learning process, but also the learning effect fluctuates due to factors such as mood swings and attention changes.

[0003] The traditional intelligent teaching system often cannot identify and adjust teaching content or progress in real time to cope with students' emotional changes, resulting in impaired learning experiences and learning efficiencies for students. Therefore, it is particularly important to propose a teaching method that can adjust teaching plans according to students' real-time emotions and learning states. Summary of the Invention

[0004] The following is an overview of the subject matter described in detail in this article. This overview is not intended to limit the scope of protection of the claims.

[0005] Embodiments of this application provide an autonomous teaching method, device, and storage medium that can update teaching plans in real time according to students' emotional changes, and can also perform self-learning on teachers' adjustments to update the model for better teaching.

[0006] In a first aspect, embodiments of this application provide an autonomous teaching method, the method including: Obtain teaching plan information, and call a preset teaching model to determine a current teaching plan according to the teaching plan information; Teach students according to the current teaching plan, and obtain the students' learning feedback information in real time; Call a preset teaching model to update the current teaching plan according to the learning feedback information, and loop through the above steps until the teaching ends; Among them, when teaching students according to the current teaching plan, listen for teacher adjustment information in real time; When receiving the teacher adjustment information, update the current teaching plan according to the teacher adjustment information and update the preset teaching model according to the learning feedback information, the current teaching plan, and the teacher adjustment information.

[0007] According to the autonomous teaching method provided by some feasible embodiments of this application, updating the preset teaching model according to the current teaching plan, the learning feedback information, and the teacher adjustment information includes: Determine the initial sample features according to the learning feedback information, and determine the first sample features according to the current teaching plan; Adjust the current teaching plan according to the teacher adjustment information, and generate an adjusted teaching plan. Determine the second sample features according to the adjusted teaching plan; Calculate a first loss value according to the initial sample features and the first sample features; Calculate a second loss value according to the initial sample features and the second sample features; Update the preset teaching model according to the first loss value, the second loss value, and the initial sample features.

[0008] According to the autonomous teaching method provided by some feasible embodiments of the present application, the learning feedback information includes emotion feedback information, progress feedback information, and interest feedback information. Obtaining the learning feedback information of the student includes: Obtain expression information and emotion voice information, and determine the emotion feedback information and interest feedback information according to at least one of the expression information and the emotion voice information; Obtain progress information, and determine the progress feedback information according to the progress information.

[0009] According to the autonomous teaching method provided by some feasible embodiments of the present application, determining the emotion feedback information and interest feedback information according to at least one of the expression information and the emotion voice information includes: Call a preset expression analysis neural network to obtain the micro-expression changes in the expression information; Match the micro-expression changes with their corresponding emotions, and determine the emotion feedback information and the interest feedback information according to the emotions corresponding to the micro-expression changes.

[0010] According to the autonomous teaching method provided by some feasible embodiments of the present application, determining the emotion feedback information and interest feedback information according to at least one of the expression information and the emotion voice information includes: Extract the speech content information and tone and speech rate information in the emotion voice information; Determine the emotion feedback information and the interest feedback information according to the speech content information and the tone and speech rate information.

[0011] According to the autonomous teaching method provided by some feasible embodiments of the present application, the method further includes: Generate incentive information according to the learning feedback information, and the incentive information is used to remind the student to adjust the learning state.

[0012] According to the autonomous teaching method provided by some feasible embodiments of the present application, the method further includes: Set a preset period; Obtain progress feedback information within each preset period, and generate a learning progress report.

[0013] In a second aspect, an embodiment of the present application provides an autonomous teaching device, which includes: A scheme determination module, configured to obtain teaching plan information, and call a preset teaching model to determine the current teaching scheme according to the teaching plan information; A teaching feedback module, configured to teach students according to the current teaching scheme, and obtain the learning feedback information of the students in real time; A scheme update module, configured to call a preset teaching model to update the current teaching scheme according to the learning feedback information, and loop through the above steps until the teaching ends; Wherein, when teaching the students according to the current teaching scheme, the teacher adjustment information is monitored in real time; When the teacher adjustment information is received, the current teaching scheme is updated according to the teacher adjustment information, and the preset teaching model is updated according to the learning feedback information, the current teaching scheme, and the teacher adjustment information.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, including: At least one processor; At least one memory, configured to store at least one program; When at least one of the at least one program is executed by at least one of the at least one processor, the method described in the first aspect of the embodiments of the present application is implemented.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program executable by a processor is stored, and when the computer program executable by the processor is executed by the processor, it is used to implement the method described in the first aspect of the embodiments of the present application.

[0016] The embodiments of the present application at least include the following beneficial effects: The autonomous teaching method provided by the embodiments of this application obtains teaching plan information, and invokes a preset teaching model to determine the current teaching plan according to the teaching plan information; teaches students according to the current teaching plan, and obtains the learning feedback information of the students in real time; invokes the preset teaching model to update the current teaching plan according to the learning feedback information, and loops to execute the above steps until the teaching ends; wherein, when teaching the students according to the current teaching plan, the teacher adjustment information is monitored in real time; when the teacher adjustment information is received, the current teaching plan is updated according to the teacher adjustment information, and the preset teaching model is updated according to the learning feedback information, the current teaching plan and the teacher adjustment information. By using the preset teaching model to formulate the current teaching plan according to the teaching plan information to teach students, and obtaining the learning feedback information of the students in real time to adjust the current teaching plan, the learning experience and learning efficiency of the students can be guaranteed; at the same time, when teaching according to the current teaching plan, the teacher adjustment information is monitored in real time, and the teacher can make adjustments through the teacher adjustment information when the current teaching plan generated by the preset teaching model is unreasonable, and the preset teaching model can perform self-learning and update according to the teacher adjustment information to further improve the model and better carry out teaching.

[0017] Other features and advantages of this application will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing this application. The objectives and other advantages of this application can be achieved and obtained by the structures specifically pointed out in the specification and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings are used to provide a further understanding of the technical solutions of this application, and constitute a part of the specification. Together with the embodiments of this application, they are used to explain the technical solutions of this application, and do not constitute a limitation to the technical solutions of this application.

[0019] Figure 1 It is a schematic diagram of the steps of an autonomous teaching method provided by the embodiments of this application; Figure 2 For the embodiments of this application Figure 1 It is a specific schematic diagram of the steps of step S120; Figure 3 It is a schematic diagram of the steps of an autonomous teaching method provided by the embodiments of this application; Figure 4 For the embodiments of this application Figure 3 It is a specific schematic diagram of the steps of step S220; Figure 5 It is a schematic diagram of the structure of an autonomous teaching device provided by the embodiments of this application; Figure 6 It is a schematic diagram of the structure of an electronic device provided by the embodiments of this application. Detailed implementation manners

[0020] The present application will be further described below in conjunction with the accompanying drawings of the specification and specific embodiments. The described embodiments should not be construed as limiting the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present application.

[0021] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0023] Before further elaborating on the embodiments of the present application, the nouns and terms involved in the embodiments of the present application are described. The nouns and terms involved in the embodiments of the present application are applicable to the following explanations.

[0024] Artificial Intelligence (AI) is a theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science. It attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a way similar to human intelligence. Artificial intelligence also studies the design principles and implementation methods of various intelligent machines to enable the machines to have the functions of perception, reasoning, and decision-making. Artificial intelligence technology is an interdisciplinary subject involving a wide range of fields, including both hardware-level technologies and software-level technologies. The basic technologies of artificial intelligence generally include, for example, sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, pre-trained model technology, operation / interaction systems, mechatronics, etc. Among them, the pre-trained model, also known as the large model or the basic model, can be widely applied to downstream tasks in various directions of artificial intelligence after fine-tuning. The software technologies of artificial intelligence mainly include several major directions such as computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0025] The self-learning mechanism is a method that allows the model to learn from unlabeled or partially labeled data through its own capabilities, with the aim of improving the generalization ability and robustness of the model. It mainly relies on semi-supervised learning and unsupervised learning methods. The self-learning mechanism includes: Self-supervised learning is an important part of the self-learning mechanism. Its core lies in training the model by designing auxiliary tasks to generate labels from unlabeled data. For example, in natural language processing, the model may be required to predict the missing words in a sentence; in computer vision, the model may be trained to identify specific parts of an image or the relationships between images. This method enables the model to learn rich feature representations without the need for manually labeled data.

[0026] Adaptive learning allows the model to dynamically adjust its own structure and parameters according to the characteristics of the input data. For example, in the full life cycle management of equipment, the model can dynamically adjust the prediction rules based on the real-time operating parameters of the equipment. This mechanism enables the model to better adapt to different scenarios and task requirements.

[0027] The self-learning mechanism has been widely applied in fields such as natural language processing, image recognition, and recommendation systems. By reducing the dependence on labeled data, the self-learning mechanism reduces the data annotation cost while improving the generalization ability and robustness of the model.

[0028] Driven by current artificial intelligence technologies, the education field is moving towards a more personalized and intelligent development direction. Although the traditional intelligent education system can generate teaching plans and guide students under the drive of algorithms, this system focuses more on the imparting of content and the tracking of learning progress. However, during the learning process, students are not only affected by the difficulty of knowledge and the learning progress, but also the learning effect fluctuates due to factors such as emotional fluctuations and changes in attention.

[0029] The traditional intelligent teaching system often fails to identify and adjust the teaching content or progress in real time to cope with students' emotional changes, resulting in the impairment of students' learning experience and learning efficiency. Therefore, it is particularly important to propose a teaching method that can adjust the teaching plan according to students' real-time emotions and learning status.

[0030] Based on this, the embodiments of this application provide an autonomous teaching method, device, and storage medium, which can update the teaching plan in real time according to students' emotional changes, and can also perform self-learning on the adjustments of teachers to update the model for better teaching.

[0031] Please refer to Figure 1 , which is a schematic diagram of the steps of an autonomous teaching method provided by the embodiments of this application. As Figure 1 shown, in the embodiments of this application, the steps of the autonomous teaching method may include but are not limited to steps S110 to S130.

[0032] Step S110: Obtain teaching plan information, and call a preset teaching model to determine the current teaching plan according to the teaching plan information.

[0033] In the embodiments of the present application, the teaching plan information may be teaching objectives, teaching content, teaching methods, evaluation methods, etc. formulated for each teaching cycle or each course unit. It may include but is not limited to the following: Teaching objectives: Knowledge points and skills that students should master during the learning process; Teaching content: Knowledge areas involved in teaching, teaching resources (such as textbooks, videos, cases, etc.); Teaching methods: Teaching strategies planned to be adopted (such as lecture-based, discussion-based, task-driven, etc.); Evaluation methods: Methods used to evaluate students' learning outcomes (such as exams, assignments, discussions, experiments, etc.); Progress arrangement: The teaching progress arrangement for each stage in the plan, usually including class hour allocation, duration of learning tasks, key content of each stage, etc.

[0034] It can be understood that the teaching plan information can be set according to the actual situation. The teaching plan information can be the teaching plan for one cycle or the teaching plans for multiple teaching cycles. The cycle duration of the teaching cycle can be planned according to weeks, days, months or the school semester. Teachers can use the same or different content as the teaching plan information, and can adopt one or more of the above content as the teaching plan information. The embodiments of the present application do not impose too many restrictions on the teaching plan information.

[0035] It should be noted that the preset teaching model provided in the embodiments of the present application can be composed of multiple sub-models. Exemplarily, in a feasible embodiment of the present application, the preset teaching model may include but is not limited to: Knowledge point planning sub-model, which is used to analyze the division of core and auxiliary knowledge points in the teaching plan information, automatically generate the priority ranking of knowledge points according to the teaching plan information, and can automatically adjust the ranking of knowledge points according to the learning progress of students; after determining the knowledge point priority according to the teaching plan information, the knowledge point planning sub-model outputs the knowledge point ranking.

[0036] Teaching strategy sub-model, which is used to determine the current teaching plan according to the teaching plan information and the knowledge point ranking output by the knowledge point planning sub-model. The teaching strategy sub-model can dynamically select the most suitable teaching methods and strategies to generate the current teaching plan. The teaching strategy sub-model can also modify and adjust the generated current teaching plan according to the feedback such as the emotional changes of students during the teaching process, so as to always maintain the learning efficiency of students and ensure the teaching quality.

[0037] The preset teaching model in the embodiments of the present application can be trained according to the commonly used training methods at present. Exemplarily, the preset teaching model can be trained through training schemes such as supervised learning, semi-supervised learning or unsupervised learning.

[0038] Step S120: Teach the students according to the current teaching plan, and obtain the students' learning feedback information in real time.

[0039] In the embodiments of the present application, when teaching the students according to the current teaching plan, the students will have fluctuations in learning effects due to factors such as emotional fluctuations and attention changes. Therefore, it is necessary to obtain the students' learning feedback information in real time. Thus, step S120 is executed in the embodiments of the present application.

[0040] It should be noted that in the embodiments of the present application, the learning feedback information may include but is not limited to: emotional feedback information, progress feedback information, and interest feedback information. Among them, the emotional feedback information represents the emotions of the students during teaching, the progress feedback information represents the learning progress of the students on the teaching content in the teaching plan, and the interest feedback information represents the students' interest in the teaching plan, such as Figure 2 As shown, in the embodiments of the present application, step S120 may specifically include but is not limited to steps S121 to S122: Step S121: Obtain the facial expression information and emotional voice information, and determine the emotional feedback information and interest feedback information according to at least one of the facial expression information and the emotional voice information.

[0041] It should be noted that, on the one hand, in the embodiments of the present application, the emotional feedback information and interest feedback information can be determined according to the facial expression information. It is obtained by analyzing the facial expression changes of the students. The facial expression information of the students during the teaching process is obtained in real time through a camera device. Then, the facial expression information is analyzed for facial expression analysis to determine the emotional feedback information and interest feedback information. Specifically, it may include but is not limited to the following steps: Call the preset facial expression analysis neural network to obtain the micro-expression changes in the facial expression information; Match the micro-expression changes with their corresponding emotions, and determine the emotional feedback information and interest feedback information according to the emotions corresponding to the micro-expression changes.

[0042] In the embodiments of the present application, the camera device may be a device capable of video recording or shooting, including but not limited to: cameras and video recorders. The facial expression information of the students during the teaching process is obtained in real time through the camera device. Then, computer vision technology (such as convolutional neural network) is used to identify the minute changes (micro-expression changes, such as the movements of eyebrows, eyes, corners of the mouth, etc.) on the faces of the students, and the emotional state can be accurately judged.

[0043] Specifically, in an embodiment of the present application, the facial images or video streams of students are collected in real time through a camera. In the original facial images, first, facial feature points are located through key point detection techniques (such as Dlib or OpenCV). These facial feature points usually include parts such as eyebrows, eyes, nose, mouth, etc.; then, the facial images or video streams are normalized to enhance the facial feature contrast and may be cropped to focus on the facial area for subsequent feature extraction; convolutional neural networks are used to extract features and recognize emotional feature learning: through convolutional neural networks, low-level and high-level features of the face are extracted. Low-level features can include facial contours, skin textures, etc., while high-level features can include subtle changes in facial expressions, such as the curvature of eyebrows, the opening degree of eyes, the upward angle of the corners of the mouth, etc.; features are extracted through multiple convolutional layers to obtain more abstract facial features, and the dimension of the feature map is reduced through pooling layers, thereby accelerating the calculation and avoiding overfitting; when the features are extracted, the facial features are mapped to corresponding emotion categories, such as "happy", "confused", "nervous", "relaxed", etc. through a fully connected layer (Fully Connected Layer). Usually, the softmax function is used to calculate the probability of each emotion, and the current emotional state of the student is judged according to the highest probability value, so as to determine the expression information of the student.

[0044] Based on the expression information, the emotional feedback information and interest feedback information of the student regarding the currently taught content can be determined. For example, when teaching, if the expression information of the student shows a happy and relaxed state for nearly 80% of the time, it can be determined that the emotional feedback information at this time is good, and the interest feedback information is that the interest is good.

[0045] On the other hand, in the embodiment of the present application, the emotional feedback information and interest feedback information can be determined according to the emotional speech information. The emotional speech information can be obtained by analyzing the content spoken by the student during teaching and can be achieved by using speech analysis and natural language processing (NLP) methods. Through speech analysis, features such as pitch, speech rate, volume, and duration of speech can be used, and through NLP, the text content in the emotional speech information can be analyzed to determine whether the student is anxious, nervous, excited, etc., so as to analyze and judge the emotion of the student. Specifically, it may include but is not limited to the following steps: Extract the speech content information and tone and speech rate information in the emotional speech information; Based on the speech content information and tone and speech rate information, determine the emotional feedback information and interest feedback information.

[0046] In the embodiments of the present application, by using speech analysis, it is possible to infer the characteristics of the emotional state of students by analyzing the tone and speech rate information (such as pitch, speech rate, volume, speech duration, etc.) in the emotional speech information, achieving the technical effect of determining emotional feedback information and interest feedback information. A convolutional neural network can be used to identify local patterns in the emotional speech information, such as sudden changes in frequency and pitch, and then judge the emotional state; alternatively, a recurrent neural network and a long short-term memory network (LSTM) can be used to process the time series data of the emotional speech information, capture the temporal features in the speech (such as changes in speech rate and pitch), and judge the emotional changes from them; or a convolutional neural network can be combined with a recurrent neural network or LSTM to more comprehensively extract the spatial and temporal information in the emotional speech information, improving the accuracy of emotion classification.

[0047] Exemplarily, in a feasible embodiment of the present application, a convolutional neural network is used for speech analysis to extract Mel-frequency cepstral coefficients (MFCCs), capture the timbre and voiceprint features of the speech, extract relevant features of the pitch by analyzing the frequency changes of the speech, and extract the changes in the student's speech rate and volume by calculating the number of speech units per second and the loudness value of the audio signal, and then analyze the emotion.

[0048] In the embodiments of the present application, the text content in the emotional speech information can also be analyzed through NLP to further analyze and judge the emotions of the students. First, the emotional speech information of the students is converted into processable text data through speech recognition. This process can process the audio signal through deep learning algorithms (such as recurrent neural networks, LSTMs, etc.) to identify the corresponding text of each speech segment; then, feature extraction is performed to analyze the emotions represented by what the students say.

[0049] Through step S121, the embodiments of the present application can obtain the facial expression information and emotional speech information of the students in real time during teaching to determine the emotional feedback information and interest feedback information.

[0050] Step S122: Obtain progress information and determine progress feedback information according to the progress information.

[0051] It can be understood that in the embodiments of the present application, the progress information during the teaching of the students is the progress of the students' learning, and the progress feedback information represents the speed of the students' learning progress. By determining the progress feedback information based on the progress information, it is possible to determine the speed of the students' learning according to the teaching plan and the progress made by the students within the planned time, thereby determining the progress feedback information.

[0052] Exemplarily, in an embodiment of the present application, the teaching plan is to complete the teaching of the content within one month. When teaching for half a month, assuming that the learning progress of the students should be 50%, however, the learning progress of student A is 40%. Therefore, the obtained progress information of student A corresponds to 40%, and the determined progress feedback information is that the progress is slow; assuming that the learning progress of student B is 50%, so the obtained progress information of student B corresponds to 50%, and the determined progress feedback information is that the progress is appropriate; assuming that the learning progress of student C is 60%, the obtained progress information of student C corresponds to 60%, and the determined progress feedback information is that the progress is fast.

[0053] After step S120, the learning feedback information of the students during teaching can be obtained in real time, so as to facilitate the adjustment of the subsequent teaching plan.

[0054] Step S130: Call a preset teaching model to update the current teaching plan according to the learning feedback information, and loop to execute steps S110 to S120 until the teaching ends.

[0055] In the embodiment of the present application, a preset teaching model is called to update the current teaching plan according to the learning feedback information. The presentation method of the teaching content can be dynamically adjusted according to the emotions of the students. For anxious students, the difficulty can be reduced and more demonstrations and guidance can be used; for tired students, short breaks or meditation time can be arranged to restore learning vitality; if the students are in a low mood, positive feedback, encouraging statements or interactive sessions can be automatically provided to motivate the students. If a student shows a decrease in interest in a certain part of the content, the attention of the student can be attracted by changing the type of learning resources (such as videos, charts, gamified tasks, etc.). For example, when the student's interest in text content decreases, the system can recommend image or video content to increase interactivity and improve the student's learning experience. At the same time, it will judge whether it is necessary to adjust the difficulty of the task according to the speed and accuracy of the student's completion of the task. For example, if a student progresses quickly in a certain task, the system can increase the difficulty and add more complex tasks; on the contrary, if a student progresses slowly, the system can adjust the task difficulty, add prompts or decompose the task.

[0056] It can be understood that in the embodiment of the present application, the emotion feedback information, progress feedback information and interest feedback information in the learning feedback information are intertwined. For example, the loss of interest of a student may lead to emotional fluctuations, and the emotional fluctuations will directly affect the learning progress of the student. Therefore, adjusting the current teaching plan according to the learning feedback information can ensure the learning experience and learning efficiency of the students.

[0057] It should be noted that with reference to Figure 3, in the embodiments of the present application, when teaching students according to the current teaching plan, there may still be unreasonableness in the adjustment of the preset teaching model for the current teaching plan. Therefore, the autonomous teaching method provided by the embodiments of the present application further includes steps S210 to S220: Step S210, monitor the teacher adjustment information in real time; In the embodiments of the present application, the teacher adjustment information is the information modified by the teacher for the current teaching plan. For example, when the teacher believes that the teaching content and teaching time in the current teaching plan are unreasonable, adjustments are made. At this time, the system can receive the teacher adjustment information to execute step S210.

[0058] Step S220, when receiving the teacher adjustment information, update the current teaching plan according to the teacher adjustment information and update the preset teaching model according to the learning feedback information, the current teaching plan and the teacher adjustment information.

[0059] It should be noted that with reference to Figure 4 , in the embodiments of the present application, step S220 may include but is not limited to steps S221 to S225: Step S221, determine the initial sample features according to the learning feedback information, and determine the first sample features according to the current teaching plan.

[0060] In the embodiments of the present application, the initial sample features are generated based on the learning feedback information of the students and are used to model the current learning state of the students. The learning feedback information includes emotion feedback information, interest feedback information, and progress feedback information. The specific acquisition steps of the learning feedback information can refer to the previous description and will not be elaborated here. Combine the emotion feedback information, interest feedback information, and progress feedback information into a comprehensive feature vector to represent the current learning state of the students. This initial sample feature vector will become the basis for subsequent model update and teaching plan adjustment.

[0061] The current teaching plan is generated based on the teaching plan information and the preset strategy of the preset teaching model. According to the current teaching plan, the corresponding first sample features are generated, and this feature vector describes the learning state of the students in different tasks and contents in the current teaching environment.

[0062] Generate the initial sample and the first sample features through step S221 to facilitate the subsequent calculation of the first loss value.

[0063] Step S222, adjust the current teaching plan according to the teacher adjustment information, generate an adjusted teaching plan, and determine the second sample features according to the adjusted teaching plan.

[0064] In the embodiments of the present application, since the current teaching plan is unreasonable, teacher adjustment information will be received. After the current teaching plan obtains the teacher adjustment information, it is necessary to adjust the current teaching plan according to the teacher adjustment information to obtain an adjusted teaching plan that meets the conditions, so as to determine the second sample feature based on the adjusted teaching plan. Based on the adjusted teaching plan, the system will recalculate the learning status of the students and generate a new feature vector (i.e., the second sample feature).

[0065] Step S223: Calculate a first loss value based on the initial sample feature and the first sample feature; Step S224: Calculate a second loss value based on the initial sample feature and the second sample feature; In the embodiments of the present application, according to the first sample feature and the second feature, the system calculates the loss value between the two feature vectors and uses the loss value to update the preset teaching model. Based on the initial sample feature, the difference between the first sample feature and the second sample feature is calculated respectively.

[0066] The first loss value can help the system identify the problems existing in the teaching plan and provide an intuitive feedback on the effectiveness of the current plan; the second loss value is used to evaluate whether the teacher's adjustment can have a positive impact and is a quantitative feedback on the effectiveness of the adjustment of the current teaching plan. By calculating the second loss value, the system can know that the adjustment made by the teacher is correct and incorporate this feedback into the future teaching plan generation and model optimization processes.

[0067] Step S225: Update the preset teaching model according to the first loss value, the second loss value, and the initial sample feature.

[0068] In the embodiments of the present application, after obtaining the first loss value and the second loss value, the preset teaching model will adjust the model parameters according to the difference between the second loss value and the first loss value until the difference between the first loss value and the second loss value is less than the preset loss threshold.

[0069] Exemplarily, in an embodiment of the present application, the system may update the preset teaching model through a backpropagation algorithm (such as gradient descent). By adjusting the parameters of the model, the system will optimize the teaching plan generation process and enhance its adaptability and personalization.

[0070] Through steps S221 to S225 in the embodiments of the present application, the preset teaching model can be continuously optimized through self-learning, gradually learn more effective teaching plan generation rules, and generate teaching plans more efficiently and accurately.

[0071] It should be noted that in the embodiments of the present application, the provided autonomous teaching method further includes: Generate incentive information according to the learning feedback information, and the incentive information is used to remind students to adjust their learning status.

[0072] In the embodiments of the present application, when a student has emotional fluctuations during teaching, the system generates corresponding incentive information according to the student's emotional fluctuations. For example, when a student is in a low mood, corresponding encouragement suggestions are generated to encourage the student and improve the student's learning enthusiasm.

[0073] Through the incentive information, the learning state of the student can be interfered and adjusted, so as to maintain the learning efficiency of the student.

[0074] It should be noted that in the embodiments of the present application, the autonomous teaching method further includes: Setting a preset period; Obtaining the progress feedback information within the period every time the preset period elapses, and generating a learning progress report.

[0075] In the embodiments of the present application, the preset period can be daily, weekly or monthly. The preset period is set according to the actual situation, and the present application does not make too many limitations on this.

[0076] Generating a learning progress report according to the progress feedback information every time the preset period elapses can help teachers and students understand the teaching progress, help teachers understand the learning situation of students, and at the same time help students grasp their own learning situation, so as to adjust the learning state.

[0077] Exemplarily, in a feasible embodiment of the present application, the preset period is weekly. Then, on Sunday of each week, the progress feedback information within that week is collected, and a corresponding learning progress report is generated according to the progress feedback information. The generated learning progress report can be viewed by students and teachers to help teachers understand the learning progress of students within that week and help students grasp the learning state.

[0078] Please refer to Figure 5 for the structural schematic diagram of an autonomous teaching device provided by the embodiments of the present application. As Figure 5 shown, the autonomous teaching device 500 provided by the embodiments of the present application includes: A scheme determination module 510, configured to obtain teaching plan information, and call a preset teaching model to determine the current teaching scheme according to the teaching plan information; A teaching feedback module 520, configured to teach students according to the current teaching scheme and obtain the learning feedback information of the students in real time; A scheme update module 530, configured to call a preset teaching model to update the current teaching scheme according to the learning feedback information, and cycle teaching until the teaching ends; Among them, when teaching students according to the current teaching scheme, the teacher adjustment information is monitored in real time; When receiving teacher adjustment information, update the current teaching plan according to the teacher adjustment information, and update the preset teaching model according to the learning feedback information, the current teaching plan, and the teacher adjustment information.

[0079] It should be noted that since the autonomous teaching device 500 in this embodiment can implement the autonomous teaching method in the previous embodiment, the autonomous teaching device 500 in this embodiment and the autonomous teaching method in the previous embodiment have the same technical principle and the same beneficial effects. To avoid repetition of content, it will not be elaborated here.

[0080] Refer to Figure 6 , this application embodiment also discloses an electronic device. The electronic device 600 includes: At least one processor 601; At least one memory 602, configured to store at least one program; When at least one program is executed by at least one processor 601, the autonomous teaching method as described above is implemented.

[0081] This application embodiment also discloses a computer-readable storage medium, in which a computer program executable by a processor is stored. When the computer program executable by the processor is executed by the processor, it is used to implement the autonomous teaching method as described above.

[0082] This application embodiment also discloses a computer program product, including a computer program or computer instructions. The computer program or computer instructions are stored in a computer-readable storage medium. The processor of the electronic device reads the computer program or computer instructions from the computer-readable storage medium, and the processor executes the computer program or computer instructions, so that the electronic device executes the autonomous teaching method as described above.

[0083] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of this application and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of this application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0084] It should be understood that in this application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects and indicates that three relationships can exist. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one (piece) of the following" or its similar expression refers to any combination of these items, including any combination of single item (piece) or plural items (pieces). For example, at least one (piece) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0085] In several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be an indirect coupling or communication connection through some interfaces, devices, or units, and can be in electrical, mechanical, or other forms.

[0086] In the embodiments of this application, the term "module" or "unit" refers to a computer program with a predetermined function or a part of a computer program, and works together with other related parts to achieve a predetermined goal, and can be fully or partially implemented by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Similarly, one processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of an overall module or unit that includes the function of the module or unit.

[0087] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0088] In addition, in each embodiment of this application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0089] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0090] Regarding the step numbers in the above method embodiments, they are only set for the convenience of elaboration and explanation, and no limitation is imposed on the order between the steps. The execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

Claims

1. An autonomous teaching method, characterized in that, The method includes: Obtaining teaching plan information, and calling a preset teaching model to determine a current teaching plan according to the teaching plan information; Teaching students according to the current teaching plan, and obtaining the learning feedback information of the students in real time; Calling a preset teaching model to update the current teaching plan according to the learning feedback information, and looping to execute the above steps until the teaching ends; Among them, when teaching the students according to the current teaching plan, the teacher adjustment information is monitored in real time; When receiving the teacher adjustment information, updating the current teaching plan according to the teacher adjustment information, and updating the preset teaching model according to the learning feedback information, the current teaching plan and the teacher adjustment information.

2. The method according to claim 1, wherein Updating the preset teaching model according to the current teaching plan, the learning feedback information and the teacher adjustment information includes: Determining initial sample features according to the learning feedback information, and determining first sample features according to the current teaching plan; Adjusting the current teaching plan according to the teacher adjustment information, and generating an adjusted teaching plan, and determining second sample features according to the adjusted teaching plan; Calculating a first loss value according to the initial sample features and the first sample features; Calculating a second loss value according to the initial sample features and the second sample features; Updating the preset teaching model according to the first loss value, the second loss value and the initial sample features.

3. The method according to claim 1, characterized in that The learning feedback information includes emotion feedback information, progress feedback information and interest feedback information. Obtaining the learning feedback information of the students includes: Obtaining expression information and emotion voice information, and determining the emotion feedback information and interest feedback information according to at least one of the expression information and the emotion voice information; Obtaining progress information, and determining the progress feedback information according to the progress information.

4. The method according to claim 3, wherein Determining the emotion feedback information and interest feedback information according to at least one of the expression information and the emotion voice information includes: Calling a preset expression analysis neural network to obtain the micro-expression changes in the expression information; Matching the micro-expression changes with their corresponding emotions, and determining the emotion feedback information and the interest feedback information according to the emotions corresponding to the micro-expression changes.

5. The method according to claim 3, characterized in that, Determining the emotion feedback information and interest feedback information according to at least one of the expression information and the emotion voice information includes: Extracting the speech content information and the tone and speech rate information in the emotion voice information; Determining the emotion feedback information and the interest feedback information according to the speech content information and the tone and speech rate information.

6. The method according to claim 1, characterized in that The method further includes: Generating incentive information according to the learning feedback information, and the incentive information is used to remind students to adjust their learning states.

7. The method according to claim 1, wherein The method further includes: Setting a preset period; Obtaining the progress feedback information within the period every other preset period, and generating a learning progress report.

8. An autonomous teaching device, characterized in that, The device includes: A scheme determination module, configured to obtain teaching plan information, and call a preset teaching model to determine a current teaching plan according to the teaching plan information; A teaching feedback module for teaching students according to the current teaching plan and obtaining the learning feedback information of the students in real time; A plan update module for calling a preset teaching model to update the current teaching plan according to the learning feedback information and looping through the teaching steps until the teaching ends; Among them, when teaching the students according to the current teaching plan, the teacher adjustment information is monitored in real time; When the teacher adjustment information is received, the current teaching plan is updated according to the teacher adjustment information, and the preset teaching model is updated according to the learning feedback information, the current teaching plan, and the teacher adjustment information.

9. An electronic device, characterized in that, It includes: At least one processor; At least one memory for storing at least one program; When at least one of the at least one program is executed by at least one of the at least one processor, the method described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that, Among them, there is a computer program executable by the processor, and when the computer program executable by the processor is executed by the processor, it is used to implement the method described in any one of claims 1 to 7.

Images