Child learning interaction system and method based on AI deep learning

Abstract

The invention relates to the technical field of artificial intelligence, and discloses a children learning interaction system and method based on AI deep learning, and the system comprises a learning state sensing module, a learning mode switching module, a deep learning evaluation module, a learning content dynamic adjustment module, and an artificial intelligence positioning module. The learning duration of the child user is recorded through a built-in timer of the learning system, the learning duration is analyzed to perceive the learning state, learning mode adaptation is carried out according to the perceived result of the learning state, learning mode automatic switching operation is carried out, and the learning progress and the learning effect of the child user are monitored in real time. And deep learning evaluation is performed based on the monitoring result, the learning content of the learning system is dynamically adjusted based on the deep evaluation result, and the system takes the child user as the center and realizes personalized customization of the learning content and intelligent management of the learning process through the AI deep learning technology.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and more specifically to a children's learning interaction system and method based on AI deep learning. Background Art

[0002] With the rapid development of artificial intelligence and deep learning technologies, the field of education is undergoing a profound transformation. Traditional education models often cannot meet the personalized learning needs of children, and children's learning interactive systems based on AI deep learning have emerged. This system uses intelligent technology to provide children with personalized learning experiences, monitor learning progress in real time, optimize learning paths, and enhance learning interactivity. AI technology can process and analyze massive learning data, provide support for personalized learning, and provide intelligent recommendations.

[0003] Deep learning algorithms can recommend appropriate learning content and paths based on children's learning behavior and historical data. However, existing children's learning interaction systems still have some shortcomings. For example, the perception of children's learning status is not accurate enough, the switching of learning modes is not smart enough, the adjustment of learning content is not timely enough, and the positioning of learning paths is not accurate enough. These problems limit the effectiveness and practicality of children's learning interaction systems and affect children's learning experience and results. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a children's learning interaction system based on AI deep learning to solve the problems existing in the above-mentioned background technology.

[0005] The present invention provides the following technical solution: a children's learning interactive system based on AI deep learning, comprising: a learning state perception module, a learning mode switching module, a deep learning evaluation module, a learning content dynamic adjustment module, and an artificial intelligence positioning module; The learning status perception module includes a learning time recording unit and a learning time analysis unit, which records the learning time of the child user through the built-in timer of the learning system and analyzes the learning time to perceive the learning status; The learning mode switching module adapts the learning mode according to the perception result of the learning state, performs an automatic learning mode switching operation, and transmits the adapted learning mode to the deep learning evaluation module; The deep learning evaluation module monitors the learning progress and learning effect of the child user in real time based on the adapted learning mode transmitted by the learning mode switching module, performs deep learning evaluation based on the monitoring results, and transmits the deep learning evaluation results to the learning content dynamic adjustment module and the artificial intelligence positioning module respectively; The learning content dynamic adjustment module dynamically adjusts the learning content of the learning system based on the depth evaluation results transmitted by the deep learning evaluation module; The artificial intelligence positioning module performs intelligent positioning analysis on the learning path of the child user based on the depth evaluation results transmitted by the deep learning evaluation module.

[0006] Preferably, in the learning environment perception module, a built-in timer automatically starts after the child user logs into the system and stops when the child user logs out or pauses learning; The specific contents of analyzing learning time and perceiving learning status are as follows: The total learning time is divided into learning time periods according to the number of times the child user quits or pauses learning. The total number of time periods represents the number of times the child user quits or pauses learning, n, where i=1, 2, 3, ..., n, where i represents the number of the learning time period; The learning status is evaluated based on the completion of learning tasks in different learning time periods and the learning time in different learning time periods. The calculation formula is: ,in represents the output value of the learning state evaluation, e represents a natural constant, represents the degree of completion of the learning task in the i-th time period, Indicates the degree of completion of the learning task in the i-1th time period, Indicates the learning time in the i-th time period.

[0007] Preferably, in the learning mode switching module, the learning mode is adapted based on the perception results of the learning state, and the specific content of the automatic switching operation of the learning mode is: comparing the total learning time with the preset learning mode switching time threshold, and comparing the output value of the learning state evaluation with the preset learning mode switching state threshold. If the total learning time is greater than or equal to the preset learning mode switching time threshold and the output value of the learning state evaluation is greater than or equal to the preset learning mode switching state threshold, switch to the entertainment learning mode; otherwise, switch to the focus learning mode.

[0008] Preferably, in the deep learning evaluation module, the specific contents of the deep learning evaluation based on the monitoring results are as follows: Based on the adapted learning mode transmitted by the learning mode switching module, the learning progress of the child user is monitored in real time to calculate the learning progress stability index of the child user; Based on the adapted learning mode transmitted by the learning mode switching module, the learning effect of the child user is monitored in real time to calculate the learning effect stability index of the child user; Conduct in-depth learning assessments on child users based on their learning progress and the weight of their learning outcomes.

[0009] Preferably, the specific content of real-time monitoring of the learning progress of the child user based on the adapted learning mode transmitted by the learning mode switching module is as follows: The daily historical data in the interactive system perception terminal is used to calculate the task completion rate of the child user on that day. The calculation formula is: ,in Indicates the task completion rate of child users on that day, Indicates the number of tasks completed by child users on that day. Indicates the total number of tasks that child users need to complete on that day; The average task completion rate of child users within a five-day period was analyzed. The learning progress stability index of child users was calculated based on the task completion rate of child users on that day and the average task completion rate of child users within a period. The calculation formula is: ,in Indicates the learning progress stability index of child users. Indicates the task completion rate of child users on that day, Indicates the average task completion rate of child users in a cycle, A constant that represents the influence of the learning progress stability index of child users.

[0010] Preferably, the calculation formula for real-time monitoring of the learning effect of the child user based on the adapted learning mode transmitted by the learning mode switching module is: ,in Indicates the learning effect stability index of child users, Indicates the number of tasks completed by child users on that day. Indicates the number of tasks correctly completed by child users on that day. Indicates the current score of the child user. Indicates the historical scores of child users. Indicates the time a child user can concentrate on a given day. Indicates the total learning time of the child user on the day. Represents a natural constant.

[0011] Preferably, the calculation formula for evaluating the child user's deep learning based on the child user's learning progress and the weight of the child user's learning effect is: ,in represents the child user deep learning evaluation index, represents a natural constant, Indicates the learning progress stability index of child users. Indicates the proportion of child users’ learning progress in deep learning evaluation, Indicates the learning effect stability index of child users, Indicates the proportion of child users’ learning effects in deep learning evaluation.

[0012] Preferably, in the learning content dynamic adjustment module, the child user's deep learning evaluation index is compared with a preset deep learning evaluation threshold. If the child user's deep learning evaluation index is greater than or equal to the preset deep learning evaluation threshold, the user's deep learning is judged to be qualified, and the learning content is dynamically adjusted to increase interactive entertainment activities. Otherwise, the user's deep learning is judged to be unqualified, and the learning content is dynamically adjusted to increase focused learning activities.

[0013] Preferably, the artificial intelligence positioning module tracks the movement trajectory of child users in the learning space in real time, and provides terminal users with an analysis report on children's learning habits and preferences in combination with the child user's deep learning evaluation index.

[0014] A children's learning interaction method based on AI deep learning, comprising the following steps: Step S01: Recording the learning time of the child user through the built-in timer of the learning system, and analyzing the learning time to perceive the learning status; Step S02: adapting the learning mode according to the perception result of the learning state, and performing an automatic switching operation of the learning mode; Step S03: Monitor the learning progress and learning effect of the child user in real time, and conduct a deep learning evaluation based on the monitoring results; Step S04: Dynamically adjust the learning content of the learning system based on the depth evaluation results; Step S05: Perform intelligent positioning analysis on the child user's learning path based on the in-depth evaluation results.

[0015] Technical effects and advantages of the present invention: The present invention is equipped with a learning status perception module, a learning mode switching module, a deep learning evaluation module, a learning content dynamic adjustment module, and an artificial intelligence positioning module. The learning system records the learning time of the child user through a built-in timer, analyzes the learning time to perceive the learning status, adapts the learning mode based on the perception result of the learning status, and performs automatic switching of the learning mode. Through the automatic switching of the learning mode, the system can adjust the learning process and learning resources in real time according to the learning status and needs of the child user. The automated learning process optimization reduces manual intervention and improves learning efficiency and learning experience. Real-time monitoring of child users' learning progress and learning outcomes, in-depth learning evaluation based on the monitoring results, and dynamic adjustment of the learning content of the learning system based on the in-depth evaluation results will help identify weak links in learning and provide a strong basis for subsequent adjustments to learning content. By dynamically adjusting learning content, it ensures that child users get the maximum learning benefits in the shortest time. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a structural diagram of a children's learning interaction system based on AI deep learning.

[0017] Figure 2 This is a flowchart of an interactive method for children's learning based on AI deep learning. DETAILED DESCRIPTION

[0018] The technical solutions of the present invention will be clearly and completely described below in conjunction with the drawings in the present invention. In addition, the forms of the various structures described in the following embodiments are merely examples. The children's learning interactive system and method based on AI deep learning involved in the present invention are not limited to the various structures described in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0019] like Figure 1 As shown, the present invention provides a children's learning interactive system based on AI deep learning, including: a learning state perception module, a learning mode switching module, a deep learning evaluation module, a learning content dynamic adjustment module, and an artificial intelligence positioning module; The learning status perception module includes a learning time recording unit and a learning time analysis unit. It records the learning time of the child user through the built-in timer of the learning system, analyzes the learning time, perceives the learning status, and obtains a learning status evaluation value. The learning status evaluation value provides data support for subsequent learning mode switching; The learning mode switching module adapts the learning mode according to the perception results of the learning state, performs automatic learning mode switching operations, and transmits the adapted learning mode to the deep learning evaluation module. The learning modes include entertainment learning mode and focus learning mode. When switching to entertainment learning mode, the system stimulates the learning interest of child users through interactive games or interesting questions and answers; when switching to focus learning mode, the system ensures the learning time of child users; The deep learning evaluation module monitors the learning progress and learning effect of the child user in real time based on the adapted learning mode transmitted by the learning mode switching module, performs deep learning evaluation based on the monitoring results, and transmits the deep learning evaluation results to the learning content dynamic adjustment module and the artificial intelligence positioning module respectively; The learning content dynamic adjustment module dynamically adjusts the learning content of the learning system based on the depth evaluation results transmitted by the deep learning evaluation module; The artificial intelligence positioning module performs intelligent positioning analysis on the learning path of the child user based on the depth evaluation results transmitted by the deep learning evaluation module.

[0020] In this embodiment, it should be specifically noted that in the learning environment perception module, a built-in timer automatically starts after the child user logs into the system and stops when the child user logs out or pauses learning; The specific contents of analyzing learning time and perceiving learning status are as follows: The total learning time is divided into learning time periods according to the number of times the child user quits or pauses learning. The total number of time periods represents the number of times the child user quits or pauses learning, n, where i=1, 2, 3, ..., n, where i represents the number of the learning time period; The learning status is evaluated based on the completion of learning tasks in different learning time periods and the learning time in different learning time periods. The calculation formula is: ,in represents the output value of the learning state evaluation, e represents a natural constant, represents the degree of completion of the learning task in the i-th time period, Indicates the degree of completion of the learning task in the i-1th time period, Indicates the learning time in the i-th time period.

[0021] In this embodiment, it should be specifically explained that, in the learning mode switching module, the learning mode is adapted according to the perception result of the learning state, and the specific content of the automatic learning mode switching operation is as follows: the total learning time is compared with the preset learning mode switching time threshold, and the output value of the learning state evaluation is compared with the preset learning mode switching state threshold; if the total learning time is greater than or equal to the preset learning mode switching time threshold and the output value of the learning state evaluation is greater than or equal to the preset learning mode switching state threshold, the mode is switched to the entertainment learning mode; otherwise, the mode is switched to the focus learning mode; In the aforementioned entertainment learning mode, the system has built-in rich and diverse gamified learning resources and interactive elements, such as educational games, role-playing games, and knowledge quizzes, aiming to stimulate children's interest in learning, enabling them to master knowledge in a relaxed and enjoyable atmosphere while also cultivating their independent learning and problem-solving abilities. In the focused learning mode, the system provides a structured learning path and strict learning task management. By setting clear learning goals and time limits, it guides child users to concentrate their attention and complete learning tasks efficiently. In this mode, the system will reduce interference factors, such as blocking irrelevant notifications and restricting access to entertainment applications, to ensure that child users can devote themselves to learning.

[0022] In this embodiment, it should be specifically explained that the specific content of the deep learning evaluation based on the monitoring results in the deep learning evaluation module is as follows: Based on the adapted learning mode transmitted by the learning mode switching module, the learning progress of the child user is monitored in real time to calculate the learning progress stability index of the child user; Based on the adapted learning mode transmitted by the learning mode switching module, the learning effect of the child user is monitored in real time to calculate the learning effect stability index of the child user; Conduct in-depth learning assessments on child users based on their learning progress and the weight of their learning outcomes.

[0023] In this embodiment, it should be specifically explained that the specific content of the real-time monitoring of the learning progress of the child user based on the adapted learning mode transmitted by the learning mode switching module is as follows: The daily historical data in the interactive system perception terminal is used to calculate the task completion rate of the child user on that day. The calculation formula is: ,in Indicates the task completion rate of child users on that day, Indicates the number of tasks completed by child users on that day. Indicates the total number of tasks that child users need to complete on that day; The average task completion rate of child users within a five-day period was analyzed. The learning progress stability index of child users was calculated based on the task completion rate of child users on that day and the average task completion rate of child users within a period. The calculation formula is: ,in Indicates the learning progress stability index of child users. Indicates the task completion rate of child users on that day, It represents the average task completion rate of child users in a period, which is the mean of the task completion rate of child users in a period. A constant that represents the influence of the learning progress stability index of child users.

[0024] In this embodiment, it should be specifically explained that the calculation formula for real-time monitoring of the learning effect of the child user based on the adapted learning mode transmitted by the learning mode switching module is: ,in Indicates the learning effect stability index of child users, Indicates the number of tasks completed by child users on that day. Indicates the number of tasks correctly completed by child users on that day. The ratio of the number of tasks correctly completed by child users on that day to the number of tasks completed by child users on that day indicates the task accuracy rate of child users on that day. Indicates the current score of the child user. Indicates the historical scores of the child user. The ratio of the difference between the current score and the historical score of the child user to the historical score of the child user represents the learning progress rate of the child user. Indicates the time a child user can concentrate on a given day. Indicates the total learning time of a child user on that day. The ratio of the child user's concentration time to the total learning time on that day indicates the child user's learning concentration. Represents a natural constant, among which the task accuracy rate of child users, the learning progress rate of child users and the learning concentration of child users are all important influencing factors of the learning effect stability index of child users.

[0025] In this embodiment, it should be specifically explained that the calculation formula for evaluating the child user's deep learning based on the child user's learning progress and the weight of the child user's learning effect is: ,in represents the child user deep learning evaluation index, represents a natural constant, Indicates the learning progress stability index of child users. Indicates the proportion of child users’ learning progress in deep learning evaluation, Indicates the learning effect stability index of child users, Indicates the proportion of child users’ learning effects in deep learning evaluation.

[0026] In this embodiment, it should be specifically explained that in the learning content dynamic adjustment module, the child user's deep learning evaluation index is compared with the preset deep learning evaluation threshold. If the child user's deep learning evaluation index is greater than or equal to the preset deep learning evaluation threshold, the user's deep learning is judged to be qualified, and the learning content is dynamically adjusted to increase interactive entertainment activities. Otherwise, if the child user's deep learning evaluation index is less than the preset deep learning evaluation threshold, the user's deep learning is judged to be unqualified, and the learning content is dynamically adjusted to increase focused learning activities.

[0027] In this embodiment, it should be specifically explained that the artificial intelligence positioning module tracks the movement trajectory of child users in the learning space in real time, and provides terminal users with an analysis report on children's learning habits and preferences in combination with the child user's deep learning evaluation index.

[0028] like Figure 2 As shown, in this embodiment, it should be specifically explained that a children's learning interaction method based on AI deep learning includes the following steps: Step S01: Recording the learning time of the child user through the built-in timer of the learning system, and analyzing the learning time to perceive the learning status; Step S02: adapting the learning mode according to the perception result of the learning state, and performing an automatic switching operation of the learning mode; Step S03: Monitor the learning progress and learning effect of the child user in real time, and conduct a deep learning evaluation based on the monitoring results; Step S04: Dynamically adjust the learning content of the learning system based on the depth evaluation results; Step S05: Perform intelligent positioning analysis on the child user's learning path based on the in-depth evaluation results.

[0029] In this embodiment, it should be specifically explained that the main difference between this embodiment and the prior art is that this embodiment is provided with a learning status perception module, a learning mode switching module, a deep learning evaluation module, a learning content dynamic adjustment module, and an artificial intelligence positioning module. The learning time of the child user is recorded by a built-in timer of the learning system, and the learning status is perceived by analyzing the learning time. The learning mode is adapted based on the perception result of the learning status, and the learning mode is automatically switched. Through the automatic switching operation of the learning mode, the system can adjust the learning process and learning resources in real time according to the learning status and needs of the child user. The automated learning process optimization reduces manual intervention and improves learning efficiency and learning experience. Real-time monitoring of child users' learning progress and learning outcomes, in-depth learning evaluation based on the monitoring results, and dynamic adjustment of the learning content of the learning system based on the in-depth evaluation results will help identify weak links in learning and provide a strong basis for subsequent adjustments to learning content. By dynamically adjusting learning content, it ensures that child users get the maximum learning benefits in the shortest time.

[0030] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0031] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A children's learning interactive system based on AI deep learning, characterized by: include: Learning status perception module, learning mode switching module, deep learning evaluation module, learning content dynamic adjustment module, and artificial intelligence positioning module; The learning status perception module includes a learning time recording unit and a learning time analysis unit, which records the learning time of the child user through the built-in timer of the learning system and analyzes the learning time to perceive the learning status; The learning mode switching module adapts the learning mode according to the perception result of the learning state, performs an automatic learning mode switching operation, and transmits the adapted learning mode to the deep learning evaluation module; The deep learning evaluation module monitors the learning progress and learning effect of the child user in real time based on the adapted learning mode transmitted by the learning mode switching module, performs deep learning evaluation based on the monitoring results, and transmits the deep learning evaluation results to the learning content dynamic adjustment module and the artificial intelligence positioning module respectively; The learning content dynamic adjustment module dynamically adjusts the learning content of the learning system based on the depth evaluation results transmitted by the deep learning evaluation module; The artificial intelligence positioning module performs intelligent positioning analysis on the learning path of the child user based on the depth evaluation results transmitted by the deep learning evaluation module.

2. The children's learning interactive system based on AI deep learning according to claim 1, characterized in that: In the learning environment perception module, a built-in timer automatically starts after the child user logs into the system and stops when the child user logs out or pauses learning; The specific contents of analyzing learning time and perceiving learning status are as follows: The total learning time is divided into learning time periods according to the number of times the child user quits or pauses learning. The total number of time periods represents the number of times the child user quits or pauses learning, n, where i=1, 2, 3, ..., n, where i represents the number of the learning time period; The learning status is evaluated based on the completion of learning tasks in different learning time periods and the learning time in different learning time periods. The calculation formula is: ,in represents the output value of the learning state evaluation, e represents a natural constant, represents the degree of completion of the learning task in the i-th time period, Indicates the degree of completion of the learning task in the i-1th time period, Indicates the learning time in the i-th time period.

3. The children's learning interactive system based on AI deep learning according to claim 1, characterized in that: In the learning mode switching module, the learning mode is adapted according to the perception results of the learning state, and the specific content of the automatic switching operation of the learning mode is: comparing the total learning time with the preset learning mode switching time threshold, and comparing the output value of the learning state evaluation with the preset learning mode switching state threshold. If the total learning time is greater than or equal to the preset learning mode switching time threshold and the output value of the learning state evaluation is greater than or equal to the preset learning mode switching state threshold, switch to the entertainment learning mode; otherwise, switch to the focus learning mode.

4. The children's learning interactive system based on AI deep learning according to claim 1, characterized in that: In the deep learning evaluation module, the specific contents of the deep learning evaluation based on the monitoring results are as follows: Based on the adapted learning mode transmitted by the learning mode switching module, the learning progress of the child user is monitored in real time to calculate the learning progress stability index of the child user; Based on the adapted learning mode transmitted by the learning mode switching module, the learning effect of the child user is monitored in real time to calculate the learning effect stability index of the child user; Conduct in-depth learning assessments on child users based on their learning progress and the weight of their learning outcomes.

5. The children's learning interactive system based on AI deep learning according to claim 4, characterized in that: The specific contents of real-time monitoring of the learning progress of the child user based on the adapted learning mode transmitted by the learning mode switching module are as follows: The daily historical data in the interactive system perception terminal is used to calculate the task completion rate of the child user on that day. The calculation formula is: ,in Indicates the task completion rate of child users on that day, Indicates the number of tasks completed by child users on that day. Indicates the total number of tasks that child users need to complete on that day; The average task completion rate of child users within a five-day period was analyzed. The learning progress stability index of child users was calculated based on the task completion rate of child users on that day and the average task completion rate of child users within a period. The calculation formula is: ,in Indicates the learning progress stability index of child users. Indicates the task completion rate of child users on that day, Indicates the average task completion rate of child users in a cycle, A constant that represents the influence of the learning progress stability index of child users.

6. The children's learning interactive system based on AI deep learning according to claim 4, characterized in that: The calculation formula for real-time monitoring of the learning effect of the child user based on the adapted learning mode transmitted by the learning mode switching module is: ,in Indicates the learning effect stability index of child users, Indicates the number of tasks completed by child users on that day. Indicates the number of tasks correctly completed by child users on that day. Indicates the current score of the child user. Indicates the historical scores of child users. Indicates the time a child user can concentrate on a given day. Indicates the total learning time of the child user on the day. Represents a natural constant.

7. The children's learning interactive system based on AI deep learning according to claim 4, characterized in that: The calculation formula for evaluating the deep learning of child users based on the learning progress of the child users and the weight of the learning effect of the child users is: ,in represents the child user deep learning evaluation index, represents a natural constant, Indicates the learning progress stability index of child users. Indicates the proportion of child users’ learning progress in deep learning evaluation, Indicates the learning effect stability index of child users, Indicates the proportion of child users’ learning effects in deep learning evaluation.

8. The children's learning interactive system based on AI deep learning according to claim 1, characterized in that: In the learning content dynamic adjustment module, the child user's deep learning evaluation index is compared with a preset deep learning evaluation threshold. If the child user's deep learning evaluation index is greater than or equal to the preset deep learning evaluation threshold, the user's deep learning is judged to be qualified, and the learning content is dynamically adjusted to increase interactive entertainment activities. Otherwise, the user's deep learning is judged to be unqualified, and the learning content is dynamically adjusted to increase focused learning activities.

9. The children's learning interactive system based on AI deep learning according to claim 1, characterized in that: The artificial intelligence positioning module tracks the movement trajectory of child users in the learning space in real time, and combines the child user's deep learning evaluation index to provide end users with an analysis report on children's learning habits and preferences.

10. A children's learning interaction method based on AI deep learning, used to use the children's learning interaction system based on AI deep learning according to any one of claims 1 to 9, characterized in that: The following steps are involved: Step S01: Recording the learning time of the child user through the built-in timer of the learning system, and analyzing the learning time to perceive the learning status; Step S02: adapting the learning mode according to the perception result of the learning state, and performing an automatic switching operation of the learning mode; Step S03: Monitor the learning progress and learning effect of the child user in real time, and conduct a deep learning evaluation based on the monitoring results; Step S04: Dynamically adjust the learning content of the learning system based on the depth evaluation results; Step S05: Perform intelligent positioning analysis on the child user's learning path based on the in-depth evaluation results.

Images