Intelligent supervision auxiliary learning system based on AI

Abstract

The invention discloses an AI-based intelligent supervision auxiliary learning system, which comprises thirteen modules such as a main control module, a fingerprint identification module, a visual identification module and a temperature and humidity module, and can realize eight functions based on software algorithm development. Comprising a system interaction control panel design function, an environment monitoring function, a countdown anti-addiction self-discipline lock function, a light control function, a sitting posture and humpback monitoring function, a WIFI communication and network clock function, an APP display storage and remote control function and a voice interaction function. The system provided by the invention can effectively assist in solving the problem that children widely have bad sitting posture habits and are addicted to mobile phones.

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence, and in particular relates to an AI-based intelligent supervision-assisted learning system. Background Art

[0002] In today's rapidly developing society, the importance of children's education is becoming increasingly prominent, and good study habits are the key to successful education. However, with the accelerated pace of modern life, many families face the problem of insufficient parental companionship, which leads to children easily developing bad study habits in the absence of supervision. Among them, hunchback and mobile phone addiction are two particularly prominent problems. Hunchback not only affects children's physical health, but may also affect their learning efficiency; while mobile phone addiction may lead to distraction and affect the quality of learning.

[0003] Faced with these challenges, researchers have been exploring effective solutions. At present, the development of artificial intelligence technology provides new possibilities for solving these problems. The present invention aims to assist children in developing good learning habits through technological innovation. Summary of the invention

[0004] In order to solve the above problems in the prior art, the present invention provides an AI-based intelligent supervision assisted learning system. By combining AI technology with the real environment, based on thirteen modules such as fingerprint recognition module, visual recognition module, temperature and humidity module, and based on software algorithm development, it realizes eight functions including system interactive control panel design and environmental monitoring function, thereby assisting in solving the widespread problems of children's bad sitting habits and addiction to mobile phones.

[0005] In a first aspect of the present invention, an AI-based intelligent supervision-assisted learning system is proposed, the system comprising:

[0006] The main control module is used to store, process and transmit the data and functions of each module;

[0007] Fingerprint recognition module, used by authorized users to unlock the mobile phone's self-discipline safety box;

[0008] The visual recognition module is used to monitor children's hunchback posture and realize intelligent monitoring based on the AI ​​model. Once an abnormality is found, a signal is sent to the main control, which then gives voice reminders through the voice module to correct bad sitting habits in time.

[0009] The screen display expansion board is used to provide an intuitive user interaction interface, display learning environment information, countdown and other prompts, and facilitate user operation;

[0010] The ambient light detection module is used to monitor the light intensity of the learning environment in real time. When the light intensity is too low, it sends information to the main control, which lights up the LED to increase the light intensity, protect children's eyesight and improve learning efficiency.

[0011] The sound intensity detection module is used to monitor the noise level of the learning environment in real time. When the noise intensity is too high, it sends information to the main control, which then sends it to the mobile phone APP via the WIFI module for reminder;

[0012] The temperature and humidity module is used to monitor the temperature and humidity of the learning environment in real time, and transmit the detection results to the main control and display them on the screen;

[0013] Voice interaction module, used for the main control to issue voice reminders to help children use system functions more conveniently;

[0014] Serial port expansion module is used to expand serial port resources, realize data transmission and communication with other modules, and provide system scalability;

[0015] WIFI module, used to realize network clock and communication with mobile phone App, parents can check their children's learning status through mobile phone App;

[0016] Self-designed expansion board, used to expand the input and output interfaces on the development board, and can also provide power to the main control on the expansion board;

[0017] Servo, a switch component used in autonomous mobile phone boxes, its simple control and output make it very easy to connect to the microcontroller system;

[0018] Light control module for adjustable ambient lighting.

[0019] As a further optimization of AI-based intelligent supervision-assisted learning system.

[0020] Preferably, the mobile phone self-discipline safety box is used to store mobile phones, cannot be opened within a set time, and is equipped with an emergency unlocking function. Parents can set a fingerprint password to perform forced fingerprint unlocking.

[0021] Preferably, the AI ​​intelligent model-based monitoring method in the visual recognition module is:

[0022] Step A100, constructing a hunchback posture dataset;

[0023] Step A200, designing a lightweight AI monitoring model;

[0024] Step A300, training a lightweight AI monitoring model based on a self-made data set;

[0025] Step A400: Input the image taken by the camera into the trained AI monitoring model in real time, and the model outputs the pixel coordinates and confidence of 17 key points;

[0026] Step A500, determine the sitting posture and transmit the determination result to the main control module.

[0027] Furthermore, the hunchback posture dataset is composed of hunchback posture pictures taken by oneself and pictures in public datasets.

[0028] Furthermore, the backbone network of the lightweight AI monitoring model is Yolov8-pose, on which the lightweight module C2f-GhostNetBottleNeckV2 is introduced to replace the original C2f module.

[0029] Furthermore, the sitting posture determination method is to implement the sitting posture detection logic according to the relative coordinates of the three key points (nose, left shoulder, right shoulder) returned by the model, and set whether to hunchback as a binary variable Z, and Z∈(0,1). Among them, 1 represents hunchback, and 0 represents no hunchback. According to the key point coordinates returned by the model, record the y-axis coordinate y of the nose tip (nose) nose and the y-axis coordinates of the shoulders left_sh With y right_sh , compare y nose The logarithm of the sum of the y-axis coordinates of the two shoulders, if y nose If it is greater than half of the logarithm of the sum of the y-axis coordinates of the two shoulders, it is considered a hunchback. The formula is as follows:

[0030]

[0031] The second aspect of the present invention proposes an AI-based intelligent supervision-assisted learning method, comprising the following steps:

[0032] Step S100, start the system and load the pre-trained AI monitoring model, and the system initializes the environmental data acquisition function;

[0033] Step S200, the system collects environment and user data through various modules;

[0034] Step S300, inputting environmental data and user data into the main control module;

[0035] Step S400, the main control module analyzes the input data, and the AI ​​monitoring model performs sitting posture monitoring;

[0036] Step S500, the main control module performs environment and user feedback;

[0037] Step S600, using the WIFI module, real-time storage and remote transmission control of the input data of the environment and the user and the feedback data of the main control module;

[0038] Step S700, when the user completes learning, the system will save the user data and close. All user data is encrypted to ensure user privacy.

[0039] As a further optimization of AI-based intelligent supervision-assisted learning methods.

[0040] Preferably, the environmental data includes: ambient light data, noise data, and humidity and temperature data.

[0041] Preferably, the user data includes: voice data, fingerprint data, and touch data.

[0042] Preferably, the main control module performs user feedback, returns the blocking status of the autonomous mobile phone box according to the user's fingerprint information; returns the touch screen display information according to the user's touch command; and returns voice reminder data according to the environmental data and the monitoring data of the AI ​​monitoring model.

[0043] Preferably, the real-time storage and remote transmission control of the data are implemented by: transmitting user information to the Alibaba Cloud server and obtaining APP instructions via WIFI; using AT instructions to connect to the NTP server; connecting to Alibaba Cloud via the MQTT protocol to realize APP data reading and data transmission, thereby realizing remote control.

[0044] Beneficial effects of the present invention:

[0045] (1) The present invention can realize a series of learning auxiliary functions including hunchback posture detection, anti-addiction mobile phone safety box, fingerprint unlocking, adaptive lighting adjustment, voice assistant, mobile phone App, noise detection, temperature and humidity detection, ambient light detection, etc. The realization of these functions effectively promotes the formation of good learning habits of children.

[0046] (2) The lightweight AI sitting posture monitoring model for children designed by the present invention can accurately detect and remind children to maintain a correct sitting posture, thereby preventing the formation of bad sitting habits such as hunchback.

[0047] (3) The present invention can realize two ways of controlling the mobile phone fuse box switch: touch screen and mobile phone APP. This function effectively restricts children's use of mobile phones, thereby reducing the risk of mobile phone addiction.

[0048] (4) The touch screen interactive panel of the present invention is simple and intuitive, and combined with visual highlights and voice and auditory feedback prompts, it allows children to conveniently use the entire system functions. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0050] Figure 1 This is a structural diagram of the overall hardware modules of an AI-based intelligent supervision-assisted learning system of the present invention;

[0051] Figure 2 This is an overall hardware schematic diagram of an AI-based intelligent supervision-assisted learning system of the present invention;

[0052] Figure 3 It is a system control diagram of an AI-based intelligent supervision-assisted learning system of the present invention;

[0053] Figure 4 It is the test result of the AI ​​monitoring model of the present invention on the COCO hunchback dataset;

[0054] Figure 5 These are some screen display interfaces of an AI-based intelligent supervision-assisted learning system of the present invention. DETAILED DESCRIPTION

[0055] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0056] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0057] like Figure 1 As shown, the first embodiment of the present invention is an AI-based intelligent supervision-assisted learning system, including the following parts:

[0058] The main control module is used to store, process and transmit the data and functions of each module;

[0059] In this embodiment, the HT32F52367 chip is selected as the main control module;

[0060] Fingerprint recognition module, used by authorized users to unlock the mobile phone's self-discipline safety box;

[0061] In this embodiment, the BMA92K222 component is selected as the fingerprint recognition module;

[0062] The visual recognition module is used to monitor children's hunchback posture and realize intelligent monitoring based on the AI ​​model. Once an abnormality is found, a signal is sent to the main control, which then gives voice reminders through the voice module to correct bad sitting habits in time.

[0063] In this embodiment, the K230 development board is used as the visual recognition module;

[0064] The screen display expansion board is used to provide an intuitive user interaction interface, display learning environment information, countdown and other prompts, and facilitate user operation;

[0065] In this embodiment, a 2.8-inch TFT-LCD display expansion board + a homemade expansion board + a BM53A367A development board are used to place the screen upright, making it convenient for users to view and operate the screen;

[0066] The ambient light detection module is used to monitor the light intensity of the learning environment in real time. When the light intensity is too low, it sends information to the main control, which lights up the LED to increase the light intensity, protect children's eyesight and improve learning efficiency.

[0067] In this embodiment, the BMS33M332 component is used to measure the ambient light;

[0068] The sound intensity detection module is used to monitor the noise level of the learning environment in real time. When the noise intensity is too high, it sends information to the main control, which then sends it to the mobile phone APP via the WIFI module for reminder;

[0069] In this embodiment, the decibel value of ambient noise is measured using the LM2904 component;

[0070] The temperature and humidity module is used to monitor the temperature and humidity of the learning environment in real time, and transmit the detection results to the main control and display them on the screen;

[0071] In this embodiment, the BME33M251 component is used to measure the ambient temperature and humidity values;

[0072] Voice interaction module, used for the main control to issue voice reminders to help children use system functions more conveniently;

[0073] In this embodiment, the speaker embedding position of the ASR PRO component is used to broadcast the system language function;

[0074] Serial port expansion module is used to expand serial port resources, realize data transmission and communication with other modules, and provide system scalability;

[0075] In this embodiment, the BMB22M210 component is used as a serial port expansion module;

[0076] WIFI module, used to realize network clock and communication with mobile phone App, parents can check their children's learning status through mobile phone App;

[0077] In this embodiment, the BMC81M001 chip is used to realize wireless signal transmission;

[0078] Self-designed expansion board, used to expand the input and output interfaces on the development board, and can also provide power to the main control on the expansion board;

[0079] In this embodiment, the side slots of the BM53A367A development board are used to connect the required data lines through debugging;

[0080] Servo, a switch component used in autonomous mobile phone boxes, its simple control and output make it very easy to connect to the microcontroller system;

[0081] In this embodiment, the Sg90 servo placement position is used and placed on the right side of the mobile phone autonomous box, which is firmly locked without affecting the insertion and removal of the mobile phone;

[0082] Light control module for adjustable ambient lighting.

[0083] Figure 2 The overall hardware schematic is shown.

[0084] It should be noted that the AI-based intelligent supervision-assisted learning system provided in the above embodiment is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be decomposed or combined. For example, the modules in the above embodiments can be combined into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps and are not regarded as improper limitations of the present invention.

[0085] like Figure 3 As shown, the second embodiment of the present invention is an AI-based intelligent supervision-assisted learning method, comprising the steps of:

[0086] Step S100, start the system and load the pre-trained AI monitoring model, and the system initializes the environmental data acquisition function;

[0087] Step S200, the system collects environment and user data through various modules;

[0088] Step S300, inputting environmental data and user data into the main control module;

[0089] Step S400, the main control module analyzes the input data, and the AI ​​monitoring model performs sitting posture monitoring;

[0090] Step S500, the main control module performs environment and user feedback;

[0091] Step S600, using the WIFI module, real-time storage and remote transmission control of the input data of the environment and the user and the feedback data of the main control module;

[0092] Step S700, when the user completes learning, the system will save the user data and close. All user data is encrypted to ensure user privacy.

[0093] like Figure 3 As shown, the present invention can realize eight functions including interactive control panel, environment monitoring, sitting posture hunchback monitoring, WIFI communication and network clock function.

[0094] In this embodiment, when training the AI ​​monitoring model, the data set used is: 552 pictures of hunchback posture obtained by shooting and 500 data from the public data set COCO keypoint track. The final hunchback posture data set consists of 1052 pictures. Figure 4 The test results of the AI ​​monitoring model on the COCO Hunchback dataset were shown;

[0095] Figure 5 It shows the interface information displayed on the screen when the system is in use.

[0096] An electronic device according to the third embodiment of the present invention comprises: at least one processor; and a memory communicatively connected to at least one of the processors; wherein the memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the above-mentioned AI-based intelligent supervised assisted learning system.

[0097] The terms "first", "second", etc. are used to distinguish similar objects rather than to describe or indicate a particular order or sequence.

[0098] The term "comprise" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus / device.

[0099] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. An AI-based intelligent supervision-assisted learning system, characterized in that: Contains the following modules: The main control module is used to store, process and transmit the data and functions of each module; Fingerprint recognition module, used by authorized users to unlock the mobile phone's self-discipline safety box; The visual recognition module is used to monitor children's hunchback posture and realize intelligent monitoring based on the AI ​​model. Once an abnormality is found, a signal is sent to the main control, which then gives voice reminders through the voice module to correct bad sitting habits in time. The screen display expansion board is used to provide an intuitive user interaction interface, display learning environment information, countdown and other prompts, and facilitate user operation; The ambient light detection module is used to monitor the light intensity of the learning environment in real time. When the light intensity is too low, it sends information to the main control, which lights up the LED to increase the light intensity, protect children's eyesight and improve learning efficiency. The sound intensity detection module is used to monitor the noise level of the learning environment in real time. When the noise intensity is too high, it sends information to the main control, which then sends it to the mobile phone APP via the WIFI module for reminder; The temperature and humidity module is used to monitor the temperature and humidity of the learning environment in real time, and transmit the detection results to the main control and display them on the screen; Voice interaction module, used for the main control to issue voice reminders to help children use system functions more conveniently; Serial port expansion module is used to expand serial port resources, realize data transmission and communication with other modules, and provide system scalability; WIFI module, used to realize network clock and communication with mobile phone App, parents can check their children's learning status through mobile phone App; Self-designed expansion board, used to expand the input and output interfaces on the development board, and can also provide power to the main control on the expansion board; Servo, a switch component used for autonomous mobile phone fuse box, its simple control and output make it very easy to connect to the microcontroller system; Light control module for adjustable ambient lighting.

2. The AI-based intelligent supervision-assisted learning system according to claim 1, characterized in that: The mobile phone self-discipline safety box in the steering gear is used to store mobile phones. It cannot be opened within a set time and is equipped with an emergency unlocking function. Parents can set a fingerprint password for forced fingerprint unlocking.

3. The AI-based intelligent supervision-assisted learning system according to claim 1, characterized in that: The AI ​​intelligent model-based monitoring method in the visual recognition module is: Step A100, constructing a hunchback posture dataset; Step A200, designing a lightweight AI monitoring model; Step A300, training a lightweight AI monitoring model based on a self-made data set; Step A400: Input the image taken by the camera into the trained AI monitoring model in real time, and the model outputs the pixel coordinates and confidence of 17 key points; Step A500, determine the sitting posture and transmit the determination result to the main control module.

4. The hunchback posture dataset according to step A100 in claim 3, characterized in that: It consists of self-taken hunchback posture pictures and pictures from public datasets.

5. The lightweight AI monitoring model according to step A200 in claim 3, characterized in that: The backbone network is Yolov8-pose, on which the lightweight module C2f-GhostNetBottleNeckV2 is introduced to replace the original C2f module.

6. The sitting posture determination method according to step A500 in claim 3, characterized in that: According to the relative coordinates of the three key points (nose, left shoulder, right shoulder) returned by the model, the sitting posture detection logic is implemented. Let whether the hunchback is a binary variable Z, and Z∈(0,1). Among them, 1 represents hunchback and 0 represents no hunchback. According to the key point coordinates returned by the model, record the y-axis coordinate y of the nose tip (nose) nose and the y-axis coordinates of the shoulders left_sh With y right_sh , compare y nose The logarithm of the sum of the y-axis coordinates of the two shoulders, if y nose If it is greater than half of the logarithm of the sum of the y-axis coordinates of the two shoulders, it is considered a hunchback. The formula is as follows:

7. An AI-based intelligent supervision-assisted learning method, characterized in that: The following steps are involved: Step S100, start the system and load the pre-trained AI monitoring model, and the system initializes the environmental data acquisition function; Step S200, the system collects environment and user data through various modules; Step S300, inputting environmental data and user data into the main control module; Step S400, the main control module analyzes the input data, and the AI ​​monitoring model performs sitting posture monitoring; Step S500, the main control module performs environment and user feedback; Step S600, using the WIFI module, real-time storage and remote transmission control of the input data of the environment and the user and the feedback data of the main control module; Step S700, when the user completes learning, the system will save the user data and close. All user data is encrypted to ensure user privacy.

8. The AI-based intelligent supervision-assisted learning method according to claim 7, characterized in that: The environmental data described in step S100 includes: ambient light data, noise data, and humidity and temperature data; The user data described in step S200 includes: voice data, fingerprint data, and touch data.

9. The AI-based intelligent supervision-assisted learning method according to claim 7, characterized in that The main control module described in step S500 performs user feedback, which is characterized in that the blocking status of the autonomous mobile phone box is returned according to the user's fingerprint information; the touch screen display information is returned according to the user's touch command; and the voice reminder data is returned according to the environmental data and the monitoring data of the AI ​​monitoring model.

10. The AI-based intelligent supervision-assisted learning method according to claim 7, characterized in that The real-time storage and remote transmission control of the data described in step S600 is characterized in that the implementation method is: transmitting user information to the Alibaba Cloud server and obtaining APP instructions via WIFI; using AT instructions to connect to the NTP server; connecting to Alibaba Cloud via the MQTT protocol to realize APP data reading and data transmission, and realize remote control.

Images