AI-based science popularization robot control system for teenagers

Abstract

This invention discloses an artificial intelligence-based control system for a science popularization robot for teenagers, belonging to the field of robotics technology. It includes: a navigation and obstacle avoidance module for autonomous navigation and obstacle avoidance control of the robot; a science acquisition module for acquiring real-time images of the objects to be popularized based on computer vision; and a science control terminal for processing, analyzing, and recognizing the real-time images of the objects based on computer vision, and for automatically controlling the objects based on the AI-based analysis and recognition results. This invention solves the problems of existing methods of science popularization for teenagers being monotonous, reliant on manual labor, and unable to effectively explain and intelligently control science, resulting in poor science popularization effects and reduced fun and participation in science education. This invention can effectively explain and intelligently control science for teenagers, improving the effectiveness of science popularization and enhancing the fun and participation in science education.

Description

Technical Field

[0001] This invention relates to the field of robotics technology, specifically to an artificial intelligence-based science popularization robot control system for teenagers. Background Technology

[0002] A robot is an intelligent machine that can work semi-autonomously or fully autonomously. Robots can perform tasks such as jobs or movement through programming and automatic control. With the development of artificial intelligence interaction technology, more and more robots are coming into people's view.

[0003] Chinese patent CN117666454A discloses an artificial intelligence-based children's programming robot and its control system, including a support base plate. A protective box is fixedly connected to the upper surface of the support base plate, a motherboard cover is fixedly connected to one side of the protective box, and a display panel is fixedly connected to the inside of the motherboard cover on the side away from the protective box. The patent employs a combined evaluation and analysis from three perspectives: power supply, drive, and execution, combined with an interference evaluation coefficient R, to ensure the robot's control effect and operational safety, while also improving the accuracy of the analysis results. Specifically, it performs operational risk monitoring analysis on the power supply data to ensure the robot's normal operation and control; it performs execution feedback analysis on the drive's status data to ensure the robot's execution performance; and it performs runaway risk assessment analysis by combining execution data from the execution end to ensure the robot's control effect. However, this patent has the following drawbacks:

[0004] Existing technologies rely on a single, manual approach to popularizing science among teenagers, failing to provide effective explanations and intelligent control. This results in poor science education outcomes and reduces the fun and engagement of science education. Summary of the Invention

[0005] The purpose of this invention is to provide an artificial intelligence-based science popularization robot control system for teenagers, which can effectively explain and intelligently control science popularization for teenagers, improve the effectiveness of science popularization for teenagers, enhance the fun and participation of science education, and solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] The AI-based science popularization robot control system for teenagers includes:

[0008] The navigation and obstacle avoidance module is used for autonomous navigation and obstacle avoidance control of the science popularization robot for teenagers.

[0009] The science popularization data acquisition module is used to acquire real-time images of items to be popularized based on computer vision.

[0010] The science popularization control terminal is used to process and analyze real-time images of items to be popularized based on computer vision, and to automatically control the items to be popularized based on the analysis and recognition results of the items to be popularized based on artificial intelligence.

[0011] Preferably, the navigation obstacle avoidance module includes:

[0012] The environmental acquisition unit is used to monitor and collect data on the surrounding environment of the youth science popularization robot in real time based on sensors, and to obtain environmental data of the youth science popularization robot.

[0013] The autonomous navigation unit is used to control the youth science popularization robot autonomously based on the surrounding environment data, enabling the youth science popularization robot to walk and avoid obstacles autonomously in various environments according to changes in the surrounding environment.

[0014] Preferably, the science popularization data collection module includes:

[0015] The object acquisition unit is used to monitor and acquire objects to be popularized in the environment around the youth science popularization robot in real time based on computer vision technology, and to obtain real-time images of the objects to be popularized based on computer vision.

[0016] The wireless transmission unit is used to transmit real-time images of the objects to be popularized based on computer vision to the popularization control terminal via a wireless network.

[0017] This includes establishing a data transmission link between the item collection unit and the science popularization control terminal;

[0018] The item collection unit sends a command to the science popularization control terminal requesting the establishment of a data transmission link;

[0019] After receiving the instruction from the item collection unit to establish a data transmission link, the science popularization control terminal checks the data transmission port of the item collection unit to determine whether the item collection unit is qualified to transmit data with the science popularization control terminal.

[0020] When the item collection unit is qualified to transmit data with the science popularization control terminal, the science popularization control terminal sends an instruction to the item collection unit to agree to establish a data transmission link. After receiving the instruction from the science popularization control terminal to agree to establish a data transmission link, the item collection unit establishes a data transmission link with the science popularization control terminal.

[0021] Once the data transmission link between the item acquisition unit and the science popularization control terminal is established, the item acquisition unit will transmit the real-time images of the items to be popularized based on computer vision to the science popularization control terminal, enabling the science popularization control terminal to analyze and control the real-time images of the items to be popularized based on computer vision.

[0022] Preferably, the science popularization control terminal includes:

[0023] The image processing module is used to process real-time images of the items to be popularized based on computer vision, and to determine the feature images of the items to be popularized based on computer vision.

[0024] The analysis and recognition module is used to analyze and recognize the feature images of the items to be popularized based on computer vision, and to determine the analysis and recognition results of the items to be popularized based on artificial intelligence.

[0025] The science popularization control module is used to automatically explain science popularization items and make intelligent recommendations based on human-computer interaction, based on the analysis and identification results of the items to be popularized using artificial intelligence.

[0026] The user interface module is used to visually display the human-computer interaction process and popular science learning content, and to control the youth popular science robot based on different functions and settings selected by the user.

[0027] Preferably, the image processing module includes:

[0028] The image denoising unit is used to denoise the real-time image of the science popularization item based on computer vision based on the median filter. The real-time image of the science popularization item based on computer vision is divided into blocks. For each pixel in each block, all pixels in its neighborhood are found, the median of the neighborhood pixels is calculated, and the median is used to replace the pixels in the original image to reduce the noise in the real-time image of the science popularization item based on computer vision.

[0029] The image adjustment unit is used to adjust the brightness and contrast of the real-time image of the scientific and technological items based on computer vision based on image segmentation technology, to keep the brightness of the real-time image of the scientific and technological items based on computer vision based on interpolation technology, and to automatically adjust the contrast of pixels in the real-time image of the scientific and technological items based on computer vision based on an adaptive adjustment method of global contrast and adjacent pixel relationship.

[0030] The feature extraction unit is used to extract features from real-time images of the scientifically relevant items based on computer vision using the principal component analysis method. It extracts useful features from the real-time images of the scientifically relevant items based on computer vision and determines the feature images of the scientifically relevant items based on computer vision.

[0031] Preferably, the image adjustment unit further includes:

[0032] The grayscale value acquisition module is used to extract the grayscale value of each pixel in the real-time image after contrast adjustment is completed based on the adaptive adjustment method.

[0033] The target pixel set acquisition module is used to extract pixels with gray values ​​not lower than a preset gray value threshold to form a target pixel set;

[0034] The grayscale value coefficient acquisition module is used to acquire the grayscale value coefficient by using the grayscale values ​​of the pixels before contrast adjustment and the grayscale values ​​after contrast adjustment of the pixels contained in the target pixel set.

[0035] The grayscale coefficient is obtained using the following formula:

[0036]

[0037] Where R represents the grayscale coefficient; n represents the number of pixels contained in the target pixel set; J xi J represents the grayscale value of the i-th pixel in the target pixel set before contrast adjustment; hi J represents the contrast-adjusted grayscale value corresponding to the i-th pixel in the target pixel set; y Indicates the preset grayscale threshold; J hmax J represents the maximum contrast-adjusted grayscale value corresponding to the pixels contained in the target pixel set; m This represents the maximum grayscale value of the pixels in the target pixel set before contrast adjustment.

[0038] The coefficient comparison module is used to compare the grayscale value coefficient with a preset coefficient threshold.

[0039] The secondary contrast adjustment module is used to perform secondary contrast adjustment on the real-time image when the grayscale value coefficient is lower than a preset coefficient threshold.

[0040] Preferably, the secondary contrast adjustment module includes:

[0041] The weight intensity value retrieval module is used to retrieve the weight intensity value of each pixel in the target pixel set in the adaptive adjustment method based on global contrast and neighbor pixel relationship;

[0042] The grayscale value retrieval module is used to retrieve the grayscale value before contrast adjustment and the grayscale value after contrast adjustment for each pixel in the target pixel set.

[0043] The grayscale value compensation coefficient acquisition module is used to obtain the grayscale value compensation coefficient corresponding to each pixel by combining the weight intensity value of each pixel in the adaptive adjustment method based on global contrast and adjacent pixel relationship with the grayscale value of each pixel before contrast adjustment and the grayscale value of each pixel after contrast adjustment.

[0044] The grayscale value compensation coefficient is obtained by the following formula:

[0045]

[0046] Among them, B i J represents the grayscale compensation coefficient corresponding to the i-th pixel in the target pixel set; xi J represents the grayscale value of the i-th pixel in the target pixel set before contrast adjustment; hi w represents the contrast-adjusted grayscale value corresponding to the i-th pixel in the target pixel set. i w represents the weight intensity value corresponding to the i-th pixel in the target pixel set. p This represents the average weight intensity value of n pixels in the target pixel set;

[0047] The grayscale adjustment module is used to adjust the grayscale value of each pixel using the grayscale compensation coefficient of each pixel.

[0048] The adjusted grayscale value of each pixel is obtained using the following formula:

[0049] J ti = (1+B) i )·J hi

[0050] Among them, J ti B represents the adjusted grayscale value corresponding to the i-th pixel in the target pixel set; i J represents the grayscale compensation coefficient corresponding to the i-th pixel in the target pixel set; hi This represents the contrast-adjusted grayscale value corresponding to the i-th pixel in the target pixel set.

[0051] Preferably, the analysis and identification module includes:

[0052] The model training unit is used to train an artificial intelligence-based model for analyzing and recognizing scientifically relevant items based on deep learning technology.

[0053] This involves collecting historical images of items to be popularized, dividing these images into training and testing sets.

[0054] Based on the training set, the deep learning model is trained to enable the deep learning model to autonomously learn the process of analyzing and recognizing items to be popularized, identify the content of items to be popularized, and determine the artificial intelligence-based analysis and recognition model for items to be popularized.

[0055] Based on the test set, the performance of the AI-based analysis and recognition model for popular science items is tested to determine whether the model can achieve the expected effect of recognizing the content of popular science items. Based on the performance test results, the parameters of the AI-based analysis and recognition model for popular science items are adjusted and the structure is optimized to determine the optimal model.

[0056] The analysis and recognition unit is used to analyze and recognize the feature images of the science popularization items based on computer vision according to the optimal AI-based science popularization item analysis and recognition model.

[0057] Specifically, the optimal AI-based model for analyzing and recognizing science-related items is deployed in the actual environment for analyzing and recognizing science-related items. The feature images of the science-related items based on computer vision are input into the optimal AI-based model for analyzing and recognizing science-related items. The AI-based model is then used to analyze and recognize the feature images of the science-related items based on computer vision, and the results of the AI-based analysis and recognition of science-related items are determined.

[0058] Preferably, the science popularization control module includes:

[0059] The science popularization explanation unit is used to automatically explain the science popularization items based on the analysis and identification results of the items to be popularized using artificial intelligence, so that teenagers can understand science knowledge;

[0060] The human-computer interaction unit is used to enable the science popularization robot for teenagers to understand the user's voice commands based on natural language processing technology, and to interact with the user through voice feedback during the science popularization process;

[0061] The intelligent recommendation unit is used to intelligently recommend subsequent science learning content to users based on human-computer interaction feedback, including performing preset scientific experiments and providing science exhibitions to users through demonstrations and explanations.

[0062] Preferably, the user interface module includes:

[0063] The interface display unit is used to visually showcase the human-computer interaction process and popular science learning content. It uses brightly colored icons and animations to attract the attention of teenagers, while providing a variety of interactive methods to enhance user engagement.

[0064] The function setting unit allows users to select different functions and settings. It includes buttons and menus to control the youth science popularization robot based on the different functions and settings selected by the user.

[0065] Compared with the prior art, the beneficial effects of the present invention are:

[0066] 1. This invention uses sensors to monitor and collect data on the surrounding environment of a science popularization robot for teenagers in real time, obtains environmental data of the surrounding environment of the science popularization robot for teenagers, and performs autonomous navigation control on the science popularization robot for teenagers based on the environmental data of the surrounding environment, so that the science popularization robot for teenagers can walk and avoid obstacles autonomously in various environments according to changes in the surrounding environment.

[0067] 2. This invention uses computer vision technology to monitor and collect real-time images of objects to be educated in the environment surrounding the science popularization robot for teenagers. It acquires real-time images of these objects based on computer vision, processes them to determine their feature images, and then analyzes and identifies these feature images using an optimal artificial intelligence-based object analysis and recognition model. Based on this analysis and recognition result, it provides automated science popularization explanations and intelligent recommendations for the objects through human-computer interaction. This allows for effective explanations and intelligent control of science popularization for teenagers, enhancing the effectiveness of science popularization and increasing the fun and participation in science education. Attached Figure Description

[0068] Figure 1 This is a block diagram of the AI-based science popularization robot control system for teenagers according to the present invention. Detailed Implementation

[0069] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0070] To address the current issues of reliance on manual methods in science education for teenagers, which hinders effective explanation and intelligent control, resulting in poor educational outcomes and reduced engagement and enjoyment, please refer to [link to relevant information]. Figure 1 This embodiment provides the following technical solution:

[0071] The AI-based control system for science popularization robots for teenagers includes: a navigation and obstacle avoidance module, a science popularization data collection module, and a science popularization control terminal.

[0072] It should be noted that the navigation and obstacle avoidance module enables the youth science popularization robot to navigate and avoid obstacles autonomously; the science popularization acquisition module collects real-time images of the objects to be popularized based on computer vision; and the science popularization control terminal processes, analyzes, and identifies the real-time images of the objects to be popularized based on computer vision, and automatically controls the objects to be popularized based on the analysis and identification results of the objects to be popularized based on artificial intelligence. This allows for effective explanation and intelligent control of science popularization for teenagers, which can improve the effectiveness of science popularization for teenagers and enhance the fun and participation of science education.

[0073] In this embodiment, the navigation obstacle avoidance module includes:

[0074] The environmental acquisition unit is used to monitor and collect data on the surrounding environment of the youth science popularization robot in real time based on sensors, and to obtain environmental data of the youth science popularization robot.

[0075] The autonomous navigation unit is used to control the youth science popularization robot autonomously based on the surrounding environment data, enabling the youth science popularization robot to walk and avoid obstacles autonomously in various environments according to changes in the surrounding environment.

[0076] In this embodiment, the science popularization data collection module includes:

[0077] The object acquisition unit is used to monitor and acquire objects to be popularized in the environment around the youth science popularization robot in real time based on computer vision technology, and to obtain real-time images of the objects to be popularized based on computer vision.

[0078] The wireless transmission unit is used to transmit real-time images of the objects to be popularized based on computer vision to the popularization control terminal via a wireless network.

[0079] This includes establishing a data transmission link between the item collection unit and the science popularization control terminal;

[0080] The item collection unit sends a command to the science popularization control terminal requesting the establishment of a data transmission link;

[0081] After receiving the instruction from the item collection unit to establish a data transmission link, the science popularization control terminal checks the data transmission port of the item collection unit to determine whether the item collection unit is qualified to transmit data with the science popularization control terminal.

[0082] When the item collection unit is qualified to transmit data with the science popularization control terminal, the science popularization control terminal sends an instruction to the item collection unit to agree to establish a data transmission link. After receiving the instruction from the science popularization control terminal to agree to establish a data transmission link, the item collection unit establishes a data transmission link with the science popularization control terminal.

[0083] Once the data transmission link between the item acquisition unit and the science popularization control terminal is established, the item acquisition unit will transmit the real-time images of the items to be popularized based on computer vision to the science popularization control terminal, enabling the science popularization control terminal to analyze and control the real-time images of the items to be popularized based on computer vision.

[0084] In this embodiment, the science popularization control terminal includes: an image processing module, an analysis and recognition module, a science popularization control module, and a user interface module.

[0085] It should be noted that the image processing module processes real-time images of the items to be popularized based on computer vision to determine the characteristic images of the items; the analysis and recognition module analyzes and recognizes the characteristic images of the items to be popularized based on computer vision to determine the analysis and recognition results of the items to be popularized based on artificial intelligence; the science popularization control module provides automated science popularization explanations and intelligent recommendations for the items to be popularized based on the analysis and recognition results of the items to be popularized based on artificial intelligence; and the user interface module displays the human-computer interaction process and science popularization learning content in a visual form, and controls the science popularization robot for teenagers based on different functions and settings selected by the user.

[0086] In this embodiment, the image processing module includes:

[0087] The image denoising unit is used to denoise the real-time image of the science popularization item based on computer vision based on the median filter. The real-time image of the science popularization item based on computer vision is divided into blocks. For each pixel in each block, all pixels in its neighborhood are found, the median of the neighborhood pixels is calculated, and the median is used to replace the pixels in the original image to reduce the noise in the real-time image of the science popularization item based on computer vision.

[0088] The image adjustment unit is used to adjust the brightness and contrast of the real-time image of the scientific and technological items based on computer vision based on image segmentation technology, to keep the brightness of the real-time image of the scientific and technological items based on computer vision based on interpolation technology, and to automatically adjust the contrast of pixels in the real-time image of the scientific and technological items based on computer vision based on an adaptive adjustment method of global contrast and adjacent pixel relationship.

[0089] The feature extraction unit is used to extract features from real-time images of the scientifically relevant items based on computer vision using the principal component analysis method. It extracts useful features from the real-time images of the scientifically relevant items based on computer vision and determines the feature images of the scientifically relevant items based on computer vision.

[0090] Specifically, the image adjustment unit further includes:

[0091] The grayscale value acquisition module is used to extract the grayscale value of each pixel in the real-time image after contrast adjustment is completed based on the adaptive adjustment method.

[0092] The target pixel set acquisition module is used to extract pixels with gray values ​​not lower than a preset gray value threshold to form a target pixel set;

[0093] The grayscale value coefficient acquisition module is used to acquire the grayscale value coefficient by using the grayscale values ​​of the pixels before contrast adjustment and the grayscale values ​​after contrast adjustment of the pixels contained in the target pixel set.

[0094] The grayscale coefficient is obtained using the following formula:

[0095]

[0096] Where R represents the grayscale coefficient; n represents the number of pixels contained in the target pixel set; J xi J represents the grayscale value of the i-th pixel in the target pixel set before contrast adjustment; hi J represents the contrast-adjusted grayscale value corresponding to the i-th pixel in the target pixel set; y Indicates the preset grayscale threshold; J hmax J represents the maximum contrast-adjusted grayscale value corresponding to the pixels contained in the target pixel set; m This represents the maximum grayscale value of the pixels in the target pixel set before contrast adjustment.

[0097] The coefficient comparison module is used to compare the grayscale value coefficient with a preset coefficient threshold.

[0098] The secondary contrast adjustment module is used to perform secondary contrast adjustment on the real-time image when the grayscale value coefficient is lower than a preset coefficient threshold.

[0099] The technical effects of the above solution are as follows: The grayscale value acquisition module can accurately extract the grayscale value of each pixel in the real-time image after contrast adjustment, providing basic data for subsequent processing. The target pixel set acquisition module can filter out pixels with higher grayscale values; these pixels often contain important information or features in the image, helping to more accurately evaluate the effect of contrast adjustment. The grayscale value coefficient acquisition module uses the grayscale values ​​before and after contrast adjustment to calculate the grayscale value coefficient using a specific formula. This coefficient reflects the degree of influence of contrast adjustment on the image's grayscale distribution. This coefficient not only considers the grayscale value changes of pixels in the target pixel set but also introduces a preset grayscale threshold, the maximum grayscale value after contrast adjustment, and the maximum grayscale value before adjustment, thus providing a more comprehensive evaluation of the contrast adjustment effect. The coefficient comparison module compares the calculated grayscale value coefficient with the preset coefficient threshold, achieving automatic evaluation of the contrast adjustment effect. When the grayscale value coefficient is lower than the preset coefficient threshold, the secondary contrast adjustment module performs a secondary adjustment on the real-time image to ensure that the image contrast reaches the desired effect. This adaptive adjustment mechanism helps improve the flexibility and accuracy of image processing. The above technical solution enables precise control and optimization of image contrast, thereby improving the overall visual effect of the image. Especially when processing low-contrast images, this solution can significantly enhance image clarity and detail, making the information in the image easier to identify and interpret.

[0100] In summary, this technical solution achieves precise control and optimization of image contrast through accurate extraction of grayscale values, quantitative analysis of grayscale value changes, and an adaptive contrast adjustment mechanism, thereby improving the accuracy and flexibility of image processing.

[0101] Specifically, the secondary contrast adjustment module includes:

[0102] The weight intensity value retrieval module is used to retrieve the weight intensity value of each pixel in the target pixel set in the adaptive adjustment method based on global contrast and neighbor pixel relationship;

[0103] The grayscale value retrieval module is used to retrieve the grayscale value before contrast adjustment and the grayscale value after contrast adjustment for each pixel in the target pixel set.

[0104] The grayscale value compensation coefficient acquisition module is used to obtain the grayscale value compensation coefficient corresponding to each pixel by combining the weight intensity value of each pixel in the adaptive adjustment method based on global contrast and adjacent pixel relationship with the grayscale value of each pixel before contrast adjustment and the grayscale value of each pixel after contrast adjustment.

[0105] The grayscale value compensation coefficient is obtained by the following formula:

[0106]

[0107] Among them, B i J represents the grayscale compensation coefficient corresponding to the i-th pixel in the target pixel set; xi J represents the grayscale value of the i-th pixel in the target pixel set before contrast adjustment; hi w represents the contrast-adjusted grayscale value corresponding to the i-th pixel in the target pixel set. i w represents the weight intensity value corresponding to the i-th pixel in the target pixel set. p This represents the average weight intensity value of n pixels in the target pixel set;

[0108] The grayscale adjustment module is used to adjust the grayscale value of each pixel using the grayscale compensation coefficient of each pixel.

[0109] The adjusted grayscale value of each pixel is obtained using the following formula:

[0110] J ti = (1+B) i )·J hi

[0111] Among them, J ti B represents the adjusted grayscale value corresponding to the i-th pixel in the target pixel set; i J represents the grayscale compensation coefficient corresponding to the i-th pixel in the target pixel set; hi This represents the contrast-adjusted grayscale value corresponding to the i-th pixel in the target pixel set.

[0112] The technical effects of the above solution are as follows: The weight intensity value retrieval module can obtain the weight intensity value of each pixel in the target pixel set using an adaptive adjustment method based on global contrast and neighboring pixel relationships. These weight intensity values ​​reflect the importance and influence range of each pixel in the image, providing a basis for subsequent grayscale value compensation. The grayscale value compensation coefficient acquisition module uses these weight intensity values ​​and the grayscale values ​​before and after contrast adjustment to calculate the grayscale value compensation coefficient corresponding to each pixel. This step enables fine-grained adjustment of different regions and pixels in the image, helping to improve the visual effect of the image. The calculation of the grayscale value compensation coefficient considers global contrast and neighboring pixel relationships, ensuring that the adjusted image not only has better contrast but also maintains image details and features. This adaptive optimization mechanism makes image processing more flexible and accurate. Through the grayscale value adjustment module, the grayscale value of each pixel is adjusted using the calculated grayscale value compensation coefficient, achieving further optimization of image contrast. This adjustment method can be adjusted according to the specific situation of the image, avoiding image distortion or loss of detail that may occur with traditional contrast adjustment methods. The aforementioned technical solution significantly improves image quality through refined contrast adjustment and adaptive optimization. The adjusted image exhibits better contrast, sharpness, and detail, making the information within the image easier to identify and interpret. Particularly when processing low-contrast or complex background images, this solution significantly enhances the visual effect, providing a more favorable foundation for subsequent image analysis and processing. Because this solution employs an adaptive adjustment method based on global contrast and the relationship between adjacent pixels, and can compensate for grayscale values ​​according to the weight intensity of each pixel, it offers high flexibility. This allows the solution to adapt to different types of images and various application scenarios, meeting diverse user needs.

[0113] In summary, the above technical solutions achieve precise control and optimization of image contrast through refined contrast adjustment and adaptive optimization mechanisms, thereby improving image quality and visual effects, and enhancing the flexibility of image processing.

[0114] In this embodiment, the analysis and identification module includes:

[0115] The model training unit is used to train an artificial intelligence-based model for analyzing and recognizing scientifically relevant items based on deep learning technology.

[0116] This involves collecting historical images of items to be popularized, dividing these images into training and testing sets.

[0117] Based on the training set, the deep learning model is trained to enable the deep learning model to autonomously learn the process of analyzing and recognizing items to be popularized, identify the content of items to be popularized, and determine the artificial intelligence-based analysis and recognition model for items to be popularized.

[0118] Based on the test set, the performance of the AI-based analysis and recognition model for popular science items is tested to determine whether the model can achieve the expected effect of recognizing the content of popular science items. Based on the performance test results, the parameters of the AI-based analysis and recognition model for popular science items are adjusted and the structure is optimized to determine the optimal model.

[0119] The analysis and recognition unit is used to analyze and recognize the feature images of the science popularization items based on computer vision according to the optimal AI-based science popularization item analysis and recognition model.

[0120] Specifically, the optimal AI-based model for analyzing and recognizing science-related items is deployed in the actual environment for analyzing and recognizing science-related items. The feature images of the science-related items based on computer vision are input into the optimal AI-based model for analyzing and recognizing science-related items. The AI-based model is then used to analyze and recognize the feature images of the science-related items based on computer vision, and the results of the AI-based analysis and recognition of science-related items are determined.

[0121] In this embodiment, the science popularization control module includes:

[0122] The science popularization explanation unit is used to automatically explain the science popularization items based on the analysis and identification results of the items to be popularized using artificial intelligence, so that teenagers can understand science knowledge;

[0123] The human-computer interaction unit is used to enable the science popularization robot for teenagers to understand the user's voice commands based on natural language processing technology, and to interact with the user through voice feedback during the science popularization process, thereby enhancing the fun of learning;

[0124] The intelligent recommendation unit is used to intelligently recommend subsequent science learning content to users based on human-computer interaction feedback, including performing preset scientific experiments and providing science exhibitions to users through demonstrations and explanations.

[0125] In this embodiment, the user interface module includes:

[0126] The interface display unit is used to visually showcase the human-computer interaction process and popular science learning content. It uses brightly colored icons and animations to attract the attention of teenagers, while providing a variety of interactive methods to enhance user engagement.

[0127] The function setting unit allows users to select different functions and settings. It includes buttons and menus to control the youth science popularization robot based on the different functions and settings selected by the user.

[0128] In summary, by using AI-based analysis and identification results of items to be popularized, and by providing automated explanations and intelligent recommendations through human-computer interaction, science popularization for teenagers can be effectively explained and intelligently controlled, thereby improving the effectiveness of science popularization and enhancing the fun and participation of science education.

[0129] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0130] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A science popularization robot control system for teenagers based on artificial intelligence, characterized in that, include: The navigation and obstacle avoidance module is used for autonomous navigation and obstacle avoidance control of the science popularization robot for teenagers. The science popularization data acquisition module is used to acquire real-time images of items to be popularized based on computer vision. The science popularization control terminal is used to process and analyze real-time images of items to be popularized based on computer vision, and to automatically control the items to be popularized based on the analysis and recognition results of the items to be popularized based on artificial intelligence. The science popularization control terminal includes: The image processing module is used to process real-time images of the items to be popularized based on computer vision, and to determine the feature images of the items to be popularized based on computer vision. The image processing module includes: The image adjustment unit is used to adjust the brightness and contrast of the real-time image of the scientific and technological items based on computer vision based on image segmentation technology, to keep the brightness of the real-time image of the scientific and technological items based on computer vision based on interpolation technology, and to automatically adjust the contrast of pixels in the real-time image of the scientific and technological items based on computer vision based on an adaptive adjustment method of global contrast and adjacent pixel relationship. The image adjustment unit includes: The grayscale value acquisition module is used to extract the grayscale value of each pixel in the real-time image after contrast adjustment is completed based on the adaptive adjustment method. The target pixel set acquisition module is used to extract pixels with gray values ​​not lower than a preset gray value threshold to form a target pixel set; The grayscale value coefficient acquisition module is used to acquire the grayscale value coefficient by using the grayscale values ​​of the pixels before contrast adjustment and the grayscale values ​​after contrast adjustment of the pixels contained in the target pixel set. The grayscale coefficient is obtained using the following formula: Where R represents the grayscale coefficient; n represents the number of pixels contained in the target pixel set; J xi J represents the grayscale value of the i-th pixel in the target pixel set before contrast adjustment; hi J represents the contrast-adjusted grayscale value corresponding to the i-th pixel in the target pixel set; y Indicates the preset grayscale threshold; J hmax J represents the maximum contrast-adjusted grayscale value corresponding to the pixels contained in the target pixel set; m This represents the maximum grayscale value of the pixels in the target pixel set before contrast adjustment. The coefficient comparison module is used to compare the grayscale value coefficient with a preset coefficient threshold. The secondary contrast adjustment module is used to perform secondary contrast adjustment on the real-time image when the grayscale value coefficient is lower than a preset coefficient threshold.

2. The artificial intelligence-based science popularization robot control system for teenagers as described in claim 1, characterized in that, The navigation obstacle avoidance module includes: The environmental acquisition unit is used to monitor and collect data on the surrounding environment of the youth science popularization robot in real time based on sensors, and to obtain environmental data of the youth science popularization robot. The autonomous navigation unit is used to control the youth science popularization robot autonomously based on the surrounding environment data, enabling the youth science popularization robot to walk and avoid obstacles autonomously in various environments according to changes in the surrounding environment.

3. The artificial intelligence-based science popularization robot control system for teenagers as described in claim 2, characterized in that, The science popularization data collection module includes: The object acquisition unit is used to monitor and acquire objects to be popularized in the environment around the youth science popularization robot in real time based on computer vision technology, and to obtain real-time images of the objects to be popularized based on computer vision. The wireless transmission unit is used to transmit real-time images of the objects to be popularized based on computer vision to the popularization control terminal via a wireless network. This includes establishing a data transmission link between the item collection unit and the science popularization control terminal; The item collection unit sends a command to the science popularization control terminal requesting the establishment of a data transmission link; After receiving the instruction from the item collection unit to establish a data transmission link, the science popularization control terminal checks the data transmission port of the item collection unit to determine whether the item collection unit is qualified to transmit data with the science popularization control terminal. When the item collection unit is qualified to transmit data with the science popularization control terminal, the science popularization control terminal sends an instruction to the item collection unit to agree to establish a data transmission link. After receiving the instruction from the science popularization control terminal to agree to establish a data transmission link, the item collection unit establishes a data transmission link with the science popularization control terminal. Once the data transmission link between the item acquisition unit and the science popularization control terminal is established, the item acquisition unit will transmit the real-time images of the items to be popularized based on computer vision to the science popularization control terminal, enabling the science popularization control terminal to analyze and control the real-time images of the items to be popularized based on computer vision.

4. The artificial intelligence-based science popularization robot control system for teenagers as described in claim 3, characterized in that, The science popularization control terminal also includes: The analysis and recognition module is used to analyze and recognize the feature images of the items to be popularized based on computer vision, and to determine the analysis and recognition results of the items to be popularized based on artificial intelligence. The science popularization control module is used to automatically explain science popularization items and make intelligent recommendations based on human-computer interaction, based on the analysis and identification results of the items to be popularized using artificial intelligence. The user interface module is used to visually display the human-computer interaction process and popular science learning content, and to control the youth popular science robot based on different functions and settings selected by the user.

5. The artificial intelligence-based science popularization robot control system for teenagers as described in claim 4, characterized in that, The image processing module further includes: The image denoising unit is used to denoise the real-time image of the science popularization item based on computer vision based on the median filter. The real-time image of the science popularization item based on computer vision is divided into blocks. For each pixel in each block, all pixels in its neighborhood are found, the median of the neighborhood pixels is calculated, and the median is used to replace the pixels in the original image to reduce the noise in the real-time image of the science popularization item based on computer vision. The feature extraction unit is used to extract features from real-time images of the scientifically relevant items based on computer vision using the principal component analysis method. It extracts useful features from the real-time images of the scientifically relevant items based on computer vision and determines the feature images of the scientifically relevant items based on computer vision.

6. The artificial intelligence-based science popularization robot control system for teenagers as described in claim 5, characterized in that, The secondary contrast adjustment module includes: The weight intensity value retrieval module is used to retrieve the weight intensity value of each pixel in the target pixel set in the adaptive adjustment method based on global contrast and neighbor pixel relationship; The grayscale value retrieval module is used to retrieve the grayscale value before contrast adjustment and the grayscale value after contrast adjustment for each pixel in the target pixel set. The grayscale value compensation coefficient acquisition module is used to obtain the grayscale value compensation coefficient corresponding to each pixel by combining the weight intensity value of each pixel in the adaptive adjustment method based on global contrast and adjacent pixel relationship with the grayscale value of each pixel before contrast adjustment and the grayscale value of each pixel after contrast adjustment. The grayscale value compensation coefficient is obtained by the following formula: Among them, B i J represents the grayscale compensation coefficient corresponding to the i-th pixel in the target pixel set; xi J represents the grayscale value of the i-th pixel in the target pixel set before contrast adjustment; hi w represents the contrast-adjusted grayscale value corresponding to the i-th pixel in the target pixel set. i w represents the weight intensity value corresponding to the i-th pixel in the target pixel set. p This represents the average weight intensity value of n pixels in the target pixel set; The grayscale adjustment module is used to adjust the grayscale value of each pixel using the grayscale compensation coefficient of each pixel. The adjusted grayscale value of each pixel is obtained using the following formula: J ti =(1+B i )·J hi Among them, J ti B represents the adjusted grayscale value corresponding to the i-th pixel in the target pixel set; i J represents the grayscale compensation coefficient corresponding to the i-th pixel in the target pixel set; hi This represents the contrast-adjusted grayscale value corresponding to the i-th pixel in the target pixel set.

7. The artificial intelligence-based science popularization robot control system for teenagers as described in claim 5, characterized in that, The analysis and identification module includes: The model training unit is used to train an artificial intelligence-based model for analyzing and recognizing scientifically relevant items based on deep learning technology. This involves collecting historical images of items to be popularized, dividing these images into training and testing sets. Based on the training set, the deep learning model is trained to enable the deep learning model to autonomously learn the process of analyzing and recognizing items to be popularized, identify the content of items to be popularized, and determine the artificial intelligence-based analysis and recognition model for items to be popularized. Based on the test set, the performance of the AI-based analysis and recognition model for popular science items is tested to determine whether the model can achieve the expected effect of recognizing the content of popular science items. Based on the performance test results, the parameters of the AI-based analysis and recognition model for popular science items are adjusted and the structure is optimized to determine the optimal model. The analysis and recognition unit is used to analyze and recognize the feature images of the science popularization items based on computer vision according to the optimal AI-based science popularization item analysis and recognition model. Specifically, the optimal AI-based model for analyzing and recognizing science-related items is deployed in the actual environment for analyzing and recognizing science-related items. The feature images of the science-related items based on computer vision are input into the optimal AI-based model for analyzing and recognizing science-related items. The AI-based model is then used to analyze and recognize the feature images of the science-related items based on computer vision, and the results of the AI-based analysis and recognition of science-related items are determined.

8. The artificial intelligence-based science popularization robot control system for teenagers as described in claim 7, characterized in that, The science popularization control module includes: The science popularization explanation unit is used to automatically explain the science popularization items based on the analysis and identification results of the items to be popularized using artificial intelligence, so that teenagers can understand science knowledge; The human-computer interaction unit is used to enable the science popularization robot for teenagers to understand the user's voice commands based on natural language processing technology, and to interact with the user through voice feedback during the science popularization process; The intelligent recommendation unit is used to intelligently recommend subsequent science learning content to users based on human-computer interaction feedback, including performing preset scientific experiments and providing science exhibitions to users through demonstrations and explanations.

9. The artificial intelligence-based science popularization robot control system for teenagers as described in claim 8, characterized in that, The user interface module includes: The interface display unit is used to visually showcase the human-computer interaction process and popular science learning content. It uses brightly colored icons and animations to attract the attention of teenagers, while providing a variety of interactive methods to enhance user engagement. The function setting unit allows users to select different functions and settings. It includes buttons and menus to control the youth science popularization robot based on the different functions and settings selected by the user.

Images