Child learning desk sitting posture correction management method and system based on image recognition

Abstract

The invention relates to the field of child learning desk sitting posture correction, and discloses a child learning desk sitting posture correction management method and system based on image recognition, and the method comprises the steps: obtaining a body posture image when a child uses a child learning desk, and determining a posture detection point and a desktop position in the body posture image through image recognition, the body posture of the child is determined according to the posture detection points; when the body posture of the child and the desktop position meet a first posture condition, sitting posture monitoring suggestion information of the child is determined based on a standard sitting posture model and the body posture of the child; and when the body posture of the child and the desktop position meet a second posture condition, determining a height adjustment value of the child learning desk based on the body posture of the child and the desktop position, and sending prompt information for prompting to adjust the desktop height according to the height adjustment value. The sitting posture of the child and the height of the table top can be comprehensively monitored and managed.

Description

Technical Field

[0001] The present application relates to the technical field of sitting posture correction for children's study desks. More specifically, it relates to a sitting posture correction management method and system for children's study desks based on image recognition. Background Art

[0002] When the existing children's study desks manage the sitting posture, they generally monitor the sitting posture of children after the desktop height adjustment is completed. This sitting posture monitoring method can only perform single management of the sitting posture at a fixed desktop height, resulting in insufficient monitoring and auxiliary functions for children's sitting postures and low intelligence in monitoring children's postures. It can be seen that the existing sitting posture management methods for children's study desks cannot meet the needs of children's sitting postures being adapted to the desktop height, and cannot provide comprehensive posture management support for children, resulting in poor management effects on children's body postures during learning.

[0003] For example, Patent CN114973423B (Application No.: CN202210894420.3) provides a warning method for sitting posture monitoring of children's study desks. The method includes: obtaining multiple frames of front images and their corresponding posture images, obtaining a standard posture image, obtaining abnormal posture images with posture changes in the posture images, determining the abnormal areas in the abnormal posture images, the human body parts where they are located, and the standard areas corresponding to the abnormal areas in the standard posture image, calculating the offset angle and offset distance of the pixel points in the abnormal areas and obtaining the sitting posture abnormality degree of the abnormal posture image, obtaining two adjacent frames of abnormal areas with the same human body parts, and calculating the comprehensive similarity of the abnormal areas corresponding to the two adjacent frames of abnormal posture images, accumulating the sitting posture abnormality degree of the abnormal areas according to the comprehensive similarity to obtain the final abnormality degree, and determining the abnormal sitting posture and giving a warning according to the final abnormality degree. The method in Patent CN114973423B cannot comprehensively monitor and manage the sitting postures of children and the height of the desktop. Summary of the Invention

[0004] The purpose of the present application is to provide a sitting posture correction management method and system for children's study desks based on image recognition, which solves the technical problem of not being able to comprehensively monitor and manage the sitting postures of children and the height of the desktop, and achieves the technical effect of comprehensively monitoring and managing the sitting postures of children and the height of the desktop.

[0005] A method for correcting and managing a child's sitting posture based on image recognition provided by an embodiment of the present application, the method includes: obtaining a body posture image of a child when using a child's study desk, determining posture detection points and a desktop position in the body posture image through image recognition, and determining the child's body posture according to the posture detection points; when the child's body posture and the desktop position meet the first posture condition, determining sitting posture monitoring suggestion information based on a standard sitting posture model and the child's body posture, and sending a prompt information for prompting to correct the child's sitting posture according to the sitting posture monitoring suggestion information; when the child's body posture and the desktop position meet the second posture condition, determining a height adjustment value of the child's study desk based on the child's body posture and the desktop position, and sending a prompt information for prompting to adjust the desktop height according to the height adjustment value.

[0006] In a possible implementation manner, the first posture condition includes: the first distance between the shoulder detection point in the child's body posture and the desktop is within a preset first distance range, and the child's sitting posture does not conform to the standard sitting posture model; the second posture condition includes: the first distance between the shoulder detection point in the child's body posture and the desktop is not within the preset first distance range, and the child's sitting posture does not conform to the standard sitting posture model; determining the height adjustment value of the child's study desk based on the child's body posture and the desktop position includes: determining the average height of the left shoulder detection point and the right shoulder detection point of the child's body posture as the shoulder detection point, determining the height difference between the shoulder detection point and the desktop, and determining the difference between the height difference and the preset height difference as the height adjustment value.

[0007] In another possible implementation manner, the method further includes: obtaining the sequential height difference between the shoulder detection point and the desktop and the sequential second distance between the child's eye detection point and the book on the desktop within the first historical time period; when the height differences at multiple moments in the sequential height difference decrease in sequence and the second distances at multiple moments in the sequential second distance decrease in sequence, sending a prompt information for tilting the side of the desktop away from the child upward; when the height differences at multiple moments in the sequential height difference increase in sequence and the second distances at multiple moments in the sequential second distance increase in sequence, sending a prompt information for tilting the side of the desktop away from the child downward.

[0008] In another possible implementation manner, the method further includes: when the height differences at multiple moments in the sequential height difference increase in sequence and the second distances at multiple moments in the sequential second distance decrease in sequence, sending a prompt information for adjusting the desktop height downward and tilting the side of the desktop away from the child upward; when the height differences at multiple moments in the sequential height difference decrease in sequence and the second distances at multiple moments in the sequential second distance increase in sequence, sending a prompt information for adjusting the desktop height upward and tilting the side of the desktop away from the child downward.

[0009] In another possible implementation, the method further includes: determining a child's learning posture based on the posture detection points; wherein, the child's learning posture includes a writing state and a drawing state; when the child's learning posture is in the drawing state, the height differences at multiple moments in the time-sequential height difference increase successively, and the second distances at multiple moments in the time-sequential second distance decrease successively, a prompt message for downward adjusting the desktop height and upward tilting the side of the desktop away from the child is issued; when the child's learning posture is in the writing state, the height differences at multiple moments in the time-sequential height difference decrease successively, and the second distances at multiple moments in the time-sequential second distance increase successively, a prompt message for upward adjusting the desktop height and downward tilting the side of the desktop away from the child is issued.

[0010] In another possible implementation, the method further includes: obtaining the time-sequential height difference between the shoulder detection point and the desktop within a second historical period, and the time-sequential second distance between the child's eye detection point and the book on the desktop; wherein, the duration of the second historical period is 3 to 10 times the duration of the first historical period; when the height differences at multiple moments in the time-sequential height difference remain stable, and the second distances at multiple moments in the time-sequential second distance decrease or increase successively, or when the second distances at multiple moments in the time-sequential second distance remain stable, and the height differences at multiple moments in the time-sequential height difference decrease or increase successively, based on the standard sitting posture model and the child's body posture, determine the sitting posture monitoring advice information for the child, and issue a prompt message for prompting the correction of the child's sitting posture according to the sitting posture monitoring advice information.

[0011] In another possible implementation, the method further includes: obtaining a seat pressure value for monitoring the pressure on the seat, and obtaining the time-sequential height difference between the shoulder detection point and the desktop within a second historical period, and the time-sequential second distance between the child's eye detection point and the book on the desktop; wherein, the duration of the second historical period is 3 to 10 times the duration of the first historical period; when the seat pressure value is greater than or equal to a preset seat pressure value, and when the height differences at multiple moments in the time-sequential height difference remain stable, and the second distances at multiple moments in the time-sequential second distance decrease or increase successively, or when the second distances at multiple moments in the time-sequential second distance remain stable, and the height differences at multiple moments in the time-sequential height difference decrease or increase successively, based on the standard sitting posture model and the child's body posture, determine the sitting posture monitoring advice information for the child, determine the seat height adjustment value and the desktop height adjustment value according to the sitting posture monitoring advice information, and adjust the seat height according to the seat height adjustment value and adjust the desktop height according to the desktop height adjustment value.

[0012] In another possible implementation, the method further includes: when the seat pressure value is greater than or equal to a preset seat pressure value, and when the height differences at multiple moments in the sequential height difference remain stable and the second distances at multiple moments in the sequential second distance decrease or increase in sequence, or when the second distances at multiple moments in the sequential second distance remain stable and the height differences at multiple moments in the sequential height difference decrease or increase in sequence, raise the desktop height to the standing position height and send a standing prompt message for prompting the adjustment of the child to the standing position.

[0013] In another possible implementation, the method further includes: obtaining the lateral swing times and lateral swing angles of the shoulder detection points of the child within a third historical time period. When the lateral swing times are less than a preset lateral swing times and the lateral swing angles are less than a preset lateral swing angle, obtain the sequential height difference between the shoulder detection point and the desktop and the sequential second distance between the eye detection point of the child and the book on the desktop within a first historical time period; wherein, the first historical time period is a subsequent time period connected in time to the third historical time period.

[0014] In another possible implementation, the method further includes: obtaining an activity habit adjustment factor set by the user, multiplying the preset lateral swing times by the activity habit adjustment factor to obtain adjusted lateral swing times, and multiplying the preset lateral swing angle by the activity habit adjustment factor to obtain adjusted lateral swing angles; when the lateral swing times are less than the adjusted lateral swing times and the lateral swing angles are less than the adjusted lateral swing angles, obtain the sequential height difference between the shoulder detection point and the desktop and the sequential second distance between the eye detection point of the child and the book on the desktop within a first historical time period.

[0015] The embodiment of the present application further provides an image recognition-based children's study desk sitting posture correction management system, including a unit for executing the method described in any one of the above.

[0016] The embodiment of the present application further provides an image recognition-based children's study desk sitting posture correction management system, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method described in any one of the above is implemented.

[0017] The embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the above is implemented.

[0018] The embodiment of the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the method described in any one of the above are implemented.

[0019] The beneficial effects of the embodiments of the present application compared with the prior art are as follows:

[0020] The embodiments of the present application provide a method for correcting and managing the sitting posture of a children's study desk based on image recognition. The method includes: obtaining a body posture image of a child using the children's study desk, determining posture detection points and desktop positions in the body posture image through image recognition, and determining the child's body posture based on the posture detection points; when the child's body posture and desktop position meet the first posture condition, determining sitting posture monitoring suggestion information based on a standard sitting posture model and the child's body posture, and sending a prompt message for prompting the correction of the child's sitting posture according to the sitting posture monitoring suggestion information; when the child's body posture and desktop position meet the second posture condition, determining a height adjustment value of the children's study desk based on the child's body posture and desktop position, and sending a prompt message for prompting the adjustment of the desktop height according to the height adjustment value. The method in the embodiments of the present application can comprehensively monitor the child's sitting posture in combination with the height of the children's study desk and the child's sitting posture, and improves the use effect of the children's study desk with adjustable height. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1 It is a flowchart of a method for correcting and managing the sitting posture of a children's study desk based on image recognition provided by the embodiments of the present application;

[0023] Figure 2 It is a schematic diagram of the usage scenario of a method for correcting and managing the sitting posture of a children's study desk based on image recognition provided by the embodiments of the present application;

[0024] Figure 3 It is a flowchart of another method for correcting and managing the sitting posture of a children's study desk based on image recognition provided by the embodiments of the present application;

[0025] Figure 4 It is a working schematic diagram of a method for correcting and managing the sitting posture of a children's study desk based on image recognition provided by the embodiments of the present application;

[0026] Figure 5 It is a schematic diagram of the logical structure of a system for correcting and managing the sitting posture of a children's study desk based on image recognition provided by the embodiments of the present application;

[0027] Figure 6Schematic diagram of the physical structure of a children's study desk sitting posture correction management system provided by an embodiment of the present application. Detailed implementation manners

[0028] It should be understood that when used in the specification and appended claims of the present application, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0029] It should also be understood that the term "and / or" used in the specification and appended claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0030] As used in the specification and appended claims of the present application, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" depending on the context. Similarly, the phrase "if determined" or "if detecting [the described condition or event]" can be interpreted as meaning "once determined", "in response to determining", "once detecting [the described condition or event]", or "in response to detecting [the described condition or event]" depending on the context.

[0031] In addition, in the description of the specification and appended claims of the present application, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0032] The reference to "one embodiment" or "some embodiments" or the like described in the specification of the present application means that a specific feature, structure or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, the statements "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0033] The existing sitting posture monitoring methods for children's study desks cannot comprehensively monitor and manage the sitting postures of children and the heights of the desktops.

[0034] For the above reasons, the embodiments of the present application provide a method for correcting and managing sitting postures of children's study desks based on image recognition. The method includes: obtaining a body posture image of a child when using a children's study desk, determining posture detection points and desktop positions in the body posture image through image recognition, and determining the child's body posture according to the posture detection points; when the child's body posture and desktop position meet the first posture condition, determining sitting posture monitoring suggestion information based on a standard sitting posture model and the child's body posture, and sending a prompt message for prompting the correction of the child's sitting posture according to the sitting posture monitoring suggestion information; when the child's body posture and desktop position meet the second posture condition, determining a height adjustment value of the children's study desk based on the child's body posture and desktop position, and sending a prompt message for prompting the adjustment of the desktop height according to the height adjustment value. The method in the embodiments of the present application can comprehensively monitor the sitting posture of children in combination with the height of the children's study desk and the sitting posture of children, improving the use effect of the height-adjustable children's study desk.

[0035] In some scenarios, a method for correcting and managing sitting postures of children's study desks based on image recognition in the embodiments of the present application can be applied to height-adjustable children's study desks, which can comprehensively monitor the sitting posture of children in combination with the height of the children's study desk and the sitting posture of children, and can improve the use effect of the height-adjustable children's study desk.

[0036] The following specifically describes a method for correcting and managing sitting postures of children's study desks based on image recognition provided by the embodiments of the present application with specific examples.

[0037] Figure 1 It is a flowchart of a method for correcting and managing sitting postures of children's study desks based on image recognition provided by the embodiments of the present application. The method includes S110 to S120, and the following specifically describes S110 to S120.

[0038] S110. Obtain a body posture image of a child when using a children's study desk, determine posture detection points and desktop positions in the body posture image through image recognition, and determine the child's body posture according to the posture detection points.

[0039] When using a height-adjustable children's study desk, existing sitting posture monitoring methods are difficult to accurately monitor the sitting posture of children, and are also difficult to accurately monitor the height of the children's study desk and the sitting posture of children.

[0040] Figure 2 It is a schematic diagram of the usage scenario of a method for correcting and managing sitting postures of children's study desks based on image recognition provided by the embodiments of the present application, as Figure 2As shown, the method in the embodiment of the present application can be applied to a children's learning desk 1. The children's learning desk 1 includes a desktop 11 and an image acquisition component 12. The desktop 11 is used to carry out children's learning, and the height of the desktop 11 can be adjusted. The image acquisition component 12 is used to acquire images of children and monitor the sitting postures of children, so as to monitor the learning status of children.

[0041] When the method in the embodiment of the present application is used, it is possible to first obtain the body posture image of a child when using the children's learning desk. The body posture image includes images of parts such as the child's body trunk, arms, and head. Furthermore, the sitting posture of the child can be monitored in real time according to the body posture image.

[0042] When monitoring the sitting posture of a child, the posture detection points in the body posture image can be determined through image recognition. The posture detection points are the feature points in the recognition of the child's sitting posture. Furthermore, the body posture of the child can be recognized through the posture detection points, so as to realize the recognition of the child's posture.

[0043] Exemplarily, when determining the posture detection points in the body posture image through image recognition, it can be achieved through deep learning object detection and human key point detection methods. Specifically, it can be achieved through YOLO (You Only Look Once) or SSD (Single Shot MultiBox Detector). YOLO and SSD are two common object detection algorithms. YOLO converts the object detection task into a regression problem of a single forward pass, achieving a high detection speed and accuracy; while SSD achieves a good balance between accuracy and speed by introducing multi-scale features and default bounding boxes. When working, it is possible to collect image and video data of the child's learning process, detect human key points based on YOLO or SSD using the CNN method, and conduct quantitative analysis using indicators such as confusion matrix, accuracy, and recall rate.

[0044] When monitoring the sitting posture of a child, it is also possible to determine the desktop position through image recognition. The desktop position includes the height information of the desktop. Furthermore, it is possible to determine whether the desktop height needs to be adjusted based on the height information of the desktop.

[0045] Exemplarily, when determining the desktop position through image recognition, the height information of the desktop can be determined by determining the relative relationship between the desktop position and the child's sitting posture through image recognition, so as to accurately recognize the height position of the children's learning desk.

[0046] Exemplarily, when determining the posture detection points in the body posture image through image recognition, the body image of the child can be detected by a camera, and 11 bone points of the child's body can be recognized through image recognition, so as to detect the sitting posture of the child according to the 11 bone points.

[0047] S120. When the body posture and desktop position of the child meet the first posture condition, determine the sitting posture monitoring advice information based on the standard sitting posture model and the child's body posture, and send a prompt message for prompting the correction of the child's sitting posture according to the sitting posture monitoring advice information. When the body posture and desktop position of the child meet the second posture condition, determine the height adjustment value of the child's study desk based on the child's body posture and desktop position, and send a prompt message for prompting the adjustment of the desktop height according to the height adjustment value.

[0048] When monitoring the child's sitting posture, it can be detected whether the child's body posture and desktop position meet the requirements of the standard sitting posture and whether the desktop height meets the requirements of the desktop height through the first posture condition. When the body posture and desktop position of the child meet the first posture condition, it indicates that attention needs to be focused on adjusting the child's sitting posture. Furthermore, the sitting posture monitoring advice information for the child can be determined based on the standard sitting posture model and the child's body posture, and a prompt message for prompting the correction of the child's sitting posture can be sent according to the sitting posture monitoring advice information to prompt the child to adjust the sitting posture.

[0049] When monitoring the child's sitting posture, it can also be detected whether the child's body posture and desktop position meet the requirements of the standard sitting posture and whether the desktop height meets the requirements of the desktop height through the second posture condition. When the body posture and desktop position of the child meet the second posture condition, it indicates that attention needs to be focused on adjusting the desktop height. The height adjustment value of the child's study desk can be determined based on the child's body posture and desktop position, and a prompt message for prompting the adjustment of the desktop height can be sent according to the height adjustment value to prompt the adjustment of the desktop height.

[0050] After adjusting the desktop height, the sitting posture of the child can be further detected according to the first posture condition to achieve the accurate adjustment of the child's sitting posture.

[0051] The beneficial effect of the above implementation method is that it is detected whether the child's body posture and desktop position meet the requirements of the standard sitting posture and whether the desktop height meets the requirements of the desktop height through the first posture condition. When attention needs to be focused on adjusting the child's sitting posture, the sitting posture monitoring advice information for the child is determined based on the standard sitting posture model and the child's body posture, ensuring the accuracy of the adjustment of the child's sitting posture.

[0052] The beneficial effect of the above implementation method is also that it is detected whether the child's body posture and desktop position meet the requirements of the standard sitting posture and whether the desktop height meets the requirements of the desktop height through the second posture condition. When attention needs to be focused on adjusting the desktop height, the height adjustment value of the child's study desk is determined based on the child's body posture and desktop position, realizing the adjustment of the height of the child's study desk and improving the accuracy of the adjustment of the height of the child's study desk.

[0053] In some implementations, the first posture condition includes: the first distance between the shoulder detection point in the child's body posture and the desktop is within a preset first distance range, and the child's sitting posture does not conform to the standard sitting posture model.

[0054] When detecting the child's sitting posture, the first distance between the shoulder detection point in the child's body posture and the desktop can be detected, and whether the height of the desktop is appropriate can be judged based on the child's sitting posture combined with the first distance.

[0055] During detection, the first posture condition can include that the first distance between the shoulder detection point in the child's body posture and the desktop is within a preset first distance range, and the child's sitting posture does not conform to the standard sitting posture model. The first distance within the preset first distance range indicates that the height of the desktop is appropriate, and the child's sitting posture not conforming to the standard sitting posture model indicates that the child's sitting posture is not standard enough. Furthermore, it can be judged that at this time, the child's sitting posture needs to be adjusted, rather than the height of the child's study desk.

[0056] Exemplarily, the shoulder monitoring point can be the highest point of the shoulder detected by image recognition.

[0057] Exemplarily, when judging whether the child's sitting posture conforms to the standard sitting posture model, it can be realized by an unhealthy sitting posture detection method based on deep learning object detection and human key point detection. Specifically, images and video data of the child's learning process can be collected, and the human key points can be detected by using the method of CNN based on YOLO or SSD, and quantitative analysis can be carried out by using indicators such as confusion matrix, accuracy, and recall rate to realize the detection of unhealthy sitting postures.

[0058] In some implementations, the second posture condition includes: the first distance between the shoulder detection point in the child's body posture and the desktop is not within a preset first distance range, and the child's sitting posture does not conform to the standard sitting posture model.

[0059] After detecting the first distance between the shoulder detection point in the child's body posture and the desktop, the second posture condition can be set to include: the first distance between the shoulder detection point in the child's body posture and the desktop is not within a preset first distance range, and the child's sitting posture does not conform to the standard sitting posture model. The first distance not within the preset first distance range indicates that the height of the desktop is not appropriate. At this time, the child's sitting posture not conforming to the standard sitting posture model indicates that the child's sitting posture may not be standard due to the inappropriate height of the desktop. Furthermore, it can be judged that the height of the desktop needs to be adjusted.

[0060] Exemplarily, the standard sitting posture model can be the relative position information of each posture monitoring point of the child's sitting posture stored in advance.

[0061] In some implementations, determining the height adjustment value of a children's study desk based on the body posture and desktop position of a child includes: determining the average height of the left shoulder detection point and the right shoulder detection point of the child's body posture as the shoulder detection point, determining the height difference between the shoulder detection point and the desktop, and determining the difference between the height difference and a preset height difference as the height adjustment value.

[0062] When adjusting the desktop height in the method of the embodiments of the present application, when determining the height adjustment value of the children's study desk based on the body posture and desktop position of the child, the average height of the left shoulder detection point and the right shoulder detection point of the child's body posture can be first determined as the shoulder detection point, so as to accurately locate the height of the child's shoulders.

[0063] After obtaining the shoulder detection point, the height difference between the shoulder detection point and the desktop can be determined, and the difference between the height difference and a preset height difference can be determined as the height adjustment value. The preset height difference is the standard value of the preset height between the shoulder detection point and the desktop.

[0064] Exemplarily, when determining the height difference between the shoulder detection point and the desktop, the height difference between the shoulder detection point and the desktop can be calculated by using a camera with depth information (such as an RGB-D camera) in combination with a height calculation algorithm.

[0065] Exemplarily, when determining the height difference between the shoulder detection point and the desktop, a general camera that uses a deep learning model to estimate depth in combination with a distance calculation algorithm can also be used to calculate the height difference between the shoulder detection point and the desktop.

[0066] The beneficial effect of the above implementation is that by determining whether the first distance between the shoulder detection point in the child's body posture and the desktop is within a preset first distance range, and combining whether the child's sitting posture does not conform to the standard sitting posture model to judge whether the height of the desktop is appropriate, the accuracy of judging the desktop height is ensured, and false detection is avoided.

[0067] The beneficial effect of the above implementation is also that when the first distance between the shoulder detection point in the child's body posture and the desktop is not within the preset first distance range, and the child's sitting posture does not conform to the standard sitting posture model, the desktop height can be first adjusted to facilitate the adjustment of the child's sitting posture after the desktop height adjustment is completed, improving the scientificity of adjusting the child's sitting posture.

[0068] The beneficial effect of the above implementation is also that by determining the height difference between the shoulder detection point and the desktop, and determining the difference between the height difference and the preset height difference, the accuracy of the relative position between the shoulder heights in the child's sitting posture and the desktop height is ensured, and the scientificity of adjusting the desktop height is improved.

[0069] The beneficial effect of the above implementation is also that the average height of the left shoulder detection point and the right shoulder detection point of the child's body posture is used as the shoulder detection point, which ensures the accuracy of the shoulder position detection and can avoid the errors caused by using the left shoulder detection point and the right shoulder detection point alone as the monitoring points.

[0070] Figure 3 The flowchart of another method for correcting and managing the sitting posture of a children's study desk based on image recognition provided by an embodiment of the present application is shown in Figure 3 As shown, the above method further includes S210 to S220, and the following is a specific description of S210 to S220.

[0071] S210. Obtain the time-sequential height difference between the shoulder detection point and the desktop within the first historical time period, and the time-sequential second distance between the eye detection point of the child and the book on the desktop.

[0072] When detecting the sitting posture of a child, the sitting posture of the child can be continuously monitored over time to improve the accuracy of sitting posture monitoring. In an embodiment of the present application, the time-sequential height difference between the shoulder detection point and the desktop within the first historical time period, and the time-sequential second distance between the eye detection point of the child and the book on the desktop can be obtained. The shoulder detection point corresponds to the shoulder position of the child, and the eye detection point corresponds to the eye position of the child. The time-sequential height difference represents the change in the distance between the shoulder monitoring point of the child on the children's study desk and the desktop, and the time-sequential second distance represents the change in the distance from the child's eye to the book during the reading process on the children's study desk. The time-sequential second distance can reflect whether the sitting posture of the child during the reading process is standard.

[0073] Figure 4 The working schematic diagram of a method for correcting and managing the sitting posture of a children's study desk based on image recognition provided by an embodiment of the present application is shown in Figure 4 As shown, the height difference between the detected shoulder detection point and the desktop can be the height difference H, and the second distance between the detected eye detection point of the child and the book 111 on the desktop can be the second distance L.

[0074] Exemplarily, when obtaining the time-sequential height difference between the shoulder detection point and the desktop within the first historical time period, the height difference between the shoulder detection point and the desktop can be determined at multiple time points evenly distributed within the first historical time period as the time-sequential height difference.

[0075] Exemplarily, when obtaining the time-sequential second distance between the eye detection point of the child and the book on the desktop, the second distance between the eye detection point and the book on the desktop can be determined at multiple time points evenly distributed within the first historical time period as the time-sequential second distance.

[0076] Exemplarily, when obtaining the second distance in time series between the eye detection point of the child and the book on the desktop, the distance between the eye detection point of the child and the center position of the book on the desktop can be detected as the second distance at each moment.

[0077] Exemplarily, the first historical time period can be a continuous historical time period traced back from the current moment, and the length of the first historical time period can be 5 minutes, 10 minutes, or 15 minutes.

[0078] S220. When the height differences at multiple moments in the height difference in time series decrease successively, and the second distances at multiple moments in the second distance in time series decrease successively, a prompt message for tilting the side of the desktop away from the child upward is sent. When the height differences at multiple moments in the height difference in time series increase successively, and the second distances at multiple moments in the second distance in time series increase successively, a prompt message for tilting the side of the desktop away from the child downward is sent.

[0079] When performing sitting posture detection, when the height differences at multiple moments in the height difference in time series decrease successively, and the second distances at multiple moments in the second distance in time series decrease successively, it indicates that in the current state, it may be due to the too small tilt angle of the desktop, resulting in the child's shoulders gradually approaching the desktop and the child's eyes gradually approaching the book on the desktop during the use of the children's study table.

[0080] When the child's shoulders gradually approach the desktop and the child's eyes gradually approach the book on the desktop during the use process, in order to adjust the child's sitting posture to the standard sitting posture, a prompt message for tilting the side of the desktop away from the child upward can be sent to increase the tilt angle of the desktop, so as to adjust the tilt angle of the desktop to adapt to the child's sitting posture, avoid the child's shoulders approaching the desktop, and avoid the child's eyes approaching the book on the desktop.

[0081] As Figure 4 shown, the side of the desktop away from the child can be the side where the A direction of the desktop is located.

[0082] Exemplarily, when sending a prompt message for tilting the side of the desktop away from the child upward, the side of the desktop away from the child can be tilted upward according to the unit angle prompt.

[0083] When performing sitting posture detection, when the height differences at multiple moments in the height difference in time series increase successively, and the second distances at multiple moments in the second distance in time series increase successively, it indicates that in the current state, it may be due to the too large tilt angle of the desktop, resulting in the child's shoulders gradually moving away from the desktop and the child's eyes gradually moving away from the book on the desktop during the use of the children's study table.

[0084] When the child's shoulders gradually move away from the tabletop and the child's eyes gradually move away from the book on the tabletop during the use of the children's study table, a prompt message for tilting the side of the tabletop away from the child downward can be sent to reduce the tilt angle of the tabletop, so as to increase the distance between the child's eyes and the book on the tabletop, and adjust the distance between the child's eyes and the book on the tabletop to an appropriate value.

[0085] The beneficial effect of the above implementation method is that it can detect the state where the child's shoulders gradually move closer to the tabletop and the child's eyes gradually move closer to the book on the tabletop during the use of the children's study table, and prompt the side of the tabletop away from the child to tilt upward, so as to achieve scientific adjustment of the tilt angle of the tabletop and improve the scientificity of adjusting the tabletop posture and the child's sitting posture.

[0086] The beneficial effect of the above implementation method is also that it can detect the state where the child's shoulders gradually move away from the tabletop and the child's eyes gradually move away from the book on the tabletop during the use of the children's study table, and prompt the side of the tabletop away from the child to tilt downward, so as to achieve scientific adjustment of the tilt angle of the tabletop and improve the scientificity of adjusting the tabletop posture and the child's sitting posture.

[0087] In some implementation methods, the above method further includes: when the height differences at multiple moments in the chronological height difference increase in sequence and the second distances at multiple moments in the chronological second distance decrease in sequence, a prompt message for downward adjusting the tabletop height and tilting the side of the tabletop away from the child upward is sent. When the height differences at multiple moments in the chronological height difference decrease in sequence and the second distances at multiple moments in the chronological second distance increase in sequence, a prompt message for upward adjusting the tabletop height and tilting the side of the tabletop away from the child downward is sent.

[0088] When monitoring the child's sitting posture, when the height differences at multiple moments in the chronological height difference increase in sequence and the second distances at multiple moments in the chronological second distance decrease in sequence, it indicates that in the current state, it may be due to the excessive height of the tabletop that the child's shoulders gradually move away from the tabletop, and the excessive distance between the child's eyes and the book on the tabletop that the child's eyes gradually move closer to the book on the tabletop.

[0089] When the excessive height of the tabletop causes the child's shoulders to gradually move away from the tabletop and the excessive distance between the child's eyes and the book on the tabletop causes the child's eyes to gradually move closer to the book on the tabletop, a prompt message for downward adjusting the tabletop height and tilting the side of the tabletop away from the child upward can be sent to reduce the height of the tabletop and increase the tilt angle of the tabletop, so as to achieve scientific adjustment of the height and tilt angle of the tabletop.

[0090] When monitoring a child's sitting posture, when the height differences at multiple moments in the chronological height difference decrease in sequence, and the second distances at multiple moments in the chronological second distance increase in sequence, it indicates that in the current state, the height of the desktop may be too small, causing the child's shoulders to gradually approach the desktop, and the distance between the child's eyes and the book on the desktop is too small, causing the child's eyes to gradually move away from the book on the desktop.

[0091] When the height of the desktop is too small, causing the child's shoulders to gradually approach the desktop, and the distance between the child's eyes and the book on the desktop is too small, causing the child's eyes to gradually move away from the book on the desktop, a prompt message can be sent to adjust the height of the desktop upward and tilt the side of the desktop away from the child downward to increase the height of the desktop and reduce the tilt angle of the desktop, so as to achieve scientific adjustment of the height and tilt angle of the desktop.

[0092] The beneficial effect of the above implementation method is that it can monitor the state where the height of the desktop is too large, causing the child's shoulders to gradually move away from the desktop, and the distance between the child's eyes and the book on the desktop is too large, causing the child's eyes to gradually approach the book on the desktop, and can make corresponding adjustments to the height and tilt angle of the desktop, improving the accuracy of monitoring the state of the desktop and the child's sitting posture.

[0093] The beneficial effect of the above implementation method is also that it can monitor the state where the height of the desktop is too small, causing the child's shoulders to gradually approach the desktop, and the distance between the child's eyes and the book on the desktop is too small, causing the child's eyes to gradually move away from the book on the desktop, and can make corresponding adjustments to the height and tilt angle of the desktop, improving the accuracy of monitoring the state of the desktop and the child's sitting posture.

[0094] In some implementation methods, the above method further includes S230 to S240, and the following is a specific description of S230 to S240.

[0095] S230. Determine the child's learning posture according to the posture detection points. Among them, the child's learning posture includes a writing state and a drawing state.

[0096] In the embodiment of the present application, in order to further improve the monitoring effect of the child's learning posture, the child's learning posture can be determined according to the posture detection points. The child's learning posture includes a writing state and a drawing state, and the writing state and the drawing state have different posture requirements for the posture of the learning desk.

[0097] S240. When the child's learning posture is in the painting state, and the height differences at multiple moments in the sequential height difference increase successively, and the second distances at multiple moments in the sequential second distance decrease successively, a prompt message for downward adjusting the desktop height and upward tilting the side of the desktop away from the child is issued. When the child's learning posture is in the writing state, and the height differences at multiple moments in the sequential height difference decrease successively, and the second distances at multiple moments in the sequential second distance increase successively, a prompt message for upward adjusting the desktop height and downward tilting the side of the desktop away from the child is issued.

[0098] After obtaining the child's learning posture, when the child's learning posture is in the painting state, and the height differences at multiple moments in the sequential height difference increase successively, and the second distances at multiple moments in the sequential second distance decrease successively, it indicates that in the current state, it may be due to the excessive height of the desktop that the child's shoulders gradually move away from the desktop, and the distance between the child's eyes and the book on the desktop is too large, resulting in the child's eyes gradually approaching the book on the desktop. A prompt message for downward adjusting the desktop height and upward tilting the side of the desktop away from the child can be issued to improve the comfort of the child in the painting state and the learning effect of the child in the painting state.

[0099] After obtaining the child's learning posture, when the child's learning posture is in the writing state, and the height differences at multiple moments in the sequential height difference decrease successively, and the second distances at multiple moments in the sequential second distance increase successively, it indicates that in the current state, it may be due to the too small height of the desktop that the child's shoulders gradually approach the desktop, and the distance between the child's eyes and the book on the desktop is too small, resulting in the child's eyes gradually moving away from the book on the desktop. A prompt message for upward adjusting the desktop height and downward tilting the side of the desktop away from the child can be issued to improve the comfort of the child in the writing state and the learning effect of the child in the writing state.

[0100] The beneficial effect of the above implementation method is to determine the child's learning posture based on the posture detection points. The child's learning posture includes the writing state and the painting state. Then, by combining the child's learning posture to adjust the state of the study table, it can improve the comfort of the child in the painting state and the learning effect of the child in the painting state; and it can also improve the comfort of the child in the writing state and the learning effect of the child in the writing state.

[0101] In some implementation methods, the above method further includes S310 to S320, which will be specifically described below.

[0102] S310. Obtain the sequential height difference between the shoulder detection point and the desktop and the sequential second distance between the eye detection point of the child and the book on the desktop within the second historical time period. The duration of the second historical time period is 3 to 10 times the duration of the first historical time period.

[0103] When monitoring the sitting posture of a child, it is also possible to obtain the sequential height difference between the shoulder detection point and the desktop and the sequential second distance between the eye detection point of the child and the book on the desktop within the second historical time period. The duration of the second historical time period is 3 to 10 times the duration of the first historical time period. Furthermore, the sitting posture of the child can be monitored based on the sequential height difference between the shoulder detection point and the desktop and the sequential second distance between the eye detection point of the child and the book on the desktop within a longer time period.

[0104] Exemplarily, the second historical time period can be 30 min, 45 min, or 60 min.

[0105] S320. When the height differences at multiple moments in the sequential height difference remain stable and the second distances at multiple moments in the sequential second distance decrease or increase in sequence, or when the second distances at multiple moments in the sequential second distance remain stable and the height differences at multiple moments in the sequential height difference decrease or increase in sequence, determine the sitting posture monitoring advice information based on the standard sitting posture model and the body posture of the child, and send a prompt message for prompting the correction of the child's sitting posture according to the sitting posture monitoring advice information.

[0106] After obtaining the sequential height difference between the shoulder detection point and the desktop and the sequential second distance between the eye detection point of the child and the book on the desktop within the second historical time period, when the height differences at multiple moments in the sequential height difference remain stable and the second distances at multiple moments in the sequential second distance decrease or increase in sequence, it indicates that the shoulder height of the child is relatively stable within the second time period, and the distance from the child's eyes to the book on the desktop gradually decreases or increases within the second time period. It can be judged from the shoulder height of the child that the sitting posture is relatively stable. At this time, a prompt can be sent to correct the child's sitting posture.

[0107] After obtaining the sequential height difference between the shoulder detection point and the desktop and the sequential second distance between the eye detection point of the child and the book on the desktop within the second historical time period, when the second distances at multiple moments in the sequential second distance remain stable and the height differences at multiple moments in the sequential height difference decrease or increase in sequence, it indicates that the shoulder height of the child gradually decreases or increases within the second time period, and the distance from the child's eyes to the book on the desktop is relatively stable within the second time period. It can be judged from the distance from the child's eyes to the book on the desktop that the sitting posture is relatively stable. At this time, a prompt can be sent to correct the child's sitting posture.

[0108] When correcting the sitting posture prompt for children, the sitting posture monitoring advice information for children can be determined based on the standard sitting posture model and the body posture of the children, and prompt information for prompting the correction of the sitting posture of children can be issued according to the sitting posture monitoring advice information, so as to realize the correction of the sitting posture of children.

[0109] The beneficial effect of the above implementation method is that the sitting posture of children is monitored in the second time period. The shoulder height of children is relatively stable in the second time period, and the distance from the eyes of children to the book on the desktop gradually decreases or increases in the second time period. It is possible to prompt the correction of the sitting posture of children when it is judged that the sitting posture of children is relatively stable from the shoulder height, ensuring the reliability of the correction of the sitting posture of children.

[0110] The beneficial effect of the above implementation method is also that when the shoulder height of children gradually decreases or increases in the second time period and the distance from the eyes of children to the book on the desktop is relatively stable in the second time period, it is possible to prompt the correction of the sitting posture of children when the distance from the eyes of children to the book on the desktop is relatively stable, ensuring the reliability of the correction of the sitting posture of children.

[0111] The beneficial effect of the above implementation method is also that the second time period is longer than the first time period. After the height and tilt angle of the desktop are adjusted, the sitting posture of children can be monitored in a longer time period, the full-time monitoring of the sitting posture of children can be realized, and the accuracy of the monitoring of the sitting posture of children is improved.

[0112] In some implementation methods, the above method further includes S330 to S340, and S330 to S340 will be specifically described below.

[0113] S330. Obtain the seat pressure value for monitoring the pressure on the seat, and obtain the sequential height difference between the shoulder detection point and the desktop and the sequential second distance between the eye detection point of the child and the book on the desktop in the second historical time period. The duration of the second historical time period is 3 to 10 times the duration of the first historical time period.

[0114] When detecting the sitting posture of children, the seat pressure value for monitoring the pressure on the seat can be obtained, and then it can be judged whether there is a child on the seat through the seat pressure value, and then the accuracy of the monitoring of the sitting posture of children can be improved according to whether there is a child on the seat.

[0115] Exemplarily, the pressure for monitoring the pressure on the seat can be detected by a pressure sensor installed on the seat.

[0116] When monitoring a child's sitting posture, the sequential height difference between the shoulder detection point and the desktop within a second historical time period and the sequential second distance between the child's eye detection point and the book on the desktop can be obtained. Furthermore, the child's sitting posture can be monitored based on the sequential height difference between the shoulder detection point and the desktop and the sequential second distance between the child's eye detection point and the book on the desktop over a longer time period.

[0117] S340. When the seat pressure value is greater than or equal to the preset seat pressure value, and when the height differences at multiple moments in the sequential height difference are stable and the second distances at multiple moments in the sequential second distance decrease or increase in sequence, or when the second distances at multiple moments in the sequential second distance are stable and the height differences at multiple moments in the sequential height difference decrease or increase in sequence, determine the sitting posture monitoring advice information for the child based on the standard sitting posture model and the child's body posture, determine the seat height adjustment value and the desktop height adjustment value according to the sitting posture monitoring advice information, and adjust the seat height according to the seat height adjustment value and adjust the desktop height according to the desktop height adjustment value.

[0118] When it is detected that the seat pressure value is greater than or equal to the preset seat pressure value, it indicates that there is a child sitting on the seat and studying. At this time, after obtaining the sequential height difference between the shoulder detection point and the desktop within a second historical time period and the sequential second distance between the child's eye detection point and the book on the desktop, when the height differences at multiple moments in the sequential height difference are stable and the second distances at multiple moments in the sequential second distance decrease or increase in sequence, it indicates that the child's shoulder height is relatively stable within the second time period, and the distance from the child's eyes to the book on the desktop gradually decreases or increases within the second time period. It can be judged that the child's sitting posture is relatively stable from the perspective of the child's shoulder height. At this time, a prompt can be given to correct the child's sitting posture.

[0119] When it is detected that the seat pressure value is greater than or equal to the preset seat pressure value, it indicates that there is a child sitting on the seat and studying. At this time, after obtaining the sequential height difference between the shoulder detection point and the desktop within a second historical time period and the sequential second distance between the child's eye detection point and the book on the desktop, when the second distances at multiple moments in the sequential second distance are stable and the height differences at multiple moments in the sequential height difference decrease or increase in sequence, it indicates that the child's shoulder height gradually decreases or increases within the second time period, and the distance from the child's eyes to the book on the desktop is relatively stable within the second time period. It can be judged that the child's sitting posture is relatively stable from the perspective of the distance from the child's eyes to the book on the desktop. At this time, a prompt can be given to correct the child's sitting posture.

[0120] Similarly, when correcting the sitting posture prompt for children, the sitting posture monitoring advice information for children can be determined based on the standard sitting posture model and the body posture of the children, and a prompt information for prompting the correction of the sitting posture of the children can be issued according to the sitting posture monitoring advice information, so as to realize the correction of the sitting posture of the children.

[0121] The beneficial effect of the above implementation method is that the accuracy of monitoring the sitting posture of children is improved according to whether there is a child on the seat, and the accuracy of detecting the sitting posture of children is further improved, and the linkage of the study table, the seat, and the sitting posture monitoring system can be realized, further improving the effect of monitoring the learning posture of children.

[0122] In some implementation methods, the above method further includes: when the seat pressure value is greater than or equal to the preset seat pressure value, and when the height differences at multiple moments in the time-sequence height difference remain stable, and the second distances at multiple moments in the time-sequence second distance decrease or increase in sequence, or when the second distances at multiple moments in the time-sequence second distance remain stable, and the height differences at multiple moments in the time-sequence height difference decrease or increase in sequence, raise the desktop height to the standing height, and issue a standing prompt information for prompting the child to adjust to the standing posture.

[0123] When it is monitored that the seat pressure value is greater than or equal to the preset seat pressure value, it indicates that there is a child learning on the seat. When the height differences at multiple moments in the time-sequence height difference remain stable, and the second distances at multiple moments in the time-sequence second distance decrease or increase in sequence, it indicates that the shoulder height of the child is relatively stable in the second time period, and the distance from the eyes of the child to the book on the desktop gradually decreases or increases in the second time period. It can be judged from the shoulder height of the child that the sitting posture is relatively stable. At this time, the desktop height can be raised to the standing height, and a standing prompt information for prompting the child to adjust to the standing posture can be issued, so that when the distance from the eyes of the child to the book on the desktop gradually decreases or increases after the child has studied with a relatively stable sitting posture for a long time, the child is prompted to adjust to the standing posture, realizing the dynamic adjustment of the learning posture of the child.

[0124] When the second distances at multiple moments in the time-sequence second distance remain stable, and the height differences at multiple moments in the time-sequence height difference decrease or increase in sequence, it indicates that the shoulder height of the child gradually decreases or increases in the second time period, and the distance from the eyes of the child to the book on the desktop is relatively stable. It can be judged from the distance from the eyes of the child to the book on the desktop that the sitting posture is relatively stable. At this time, the desktop height can be raised to the standing height, and a standing prompt information for prompting the child to adjust to the standing posture can be issued, so that when the sitting posture of the child is relatively stable for a long time and the shoulder height gradually decreases or increases, the child is prompted to adjust to the standing posture, realizing the dynamic adjustment of the learning posture of the child.

[0125] The beneficial effects of the above implementation method are as follows: by adding a gravity sensing function to the chair, the height of the study desk can be automatically adjusted, achieving the linkage of the study desk, the seat, and the sitting posture monitoring system, and improving the monitoring effect of the study desk, the seat, and the sitting posture monitoring system on children's sitting postures.

[0126] The beneficial effects of the above implementation method are also as follows: when the distance between the child's eyes and the book on the desktop gradually decreases or increases after a long period of stable sitting learning, or when the child's sitting posture is stable for a long time and the shoulder height gradually decreases or increases, it is prompted to adjust the child to a standing posture, realizing the dynamic adjustment of the child's learning posture and improving the protection effect on the child's vision.

[0127] In some implementation methods, the above method further includes: obtaining the lateral swing times and lateral swing angles of the child's shoulder detection points in the third historical time period. When the lateral swing times are less than the preset lateral swing times and the lateral swing angles are less than the preset lateral swing angles, obtain the sequential height difference between the shoulder detection point and the desktop and the sequential second distance between the child's eye detection point and the book on the desktop in the first historical time period. Here, the first historical time period is the subsequent time period connected to the third historical time period in time.

[0128] When monitoring the child's sitting posture, the lateral swing times and lateral swing angles of the child's shoulder detection points in the third historical time period can be obtained. The lateral swing times and lateral swing angles of the shoulder detection points characterize the stability of the child's shoulders, and thus the stability of the child's sitting posture can be monitored through the stability of the child's shoulders.

[0129] Exemplarily, when detecting the lateral swing times and lateral swing angles of the shoulder detection points, the position of the child's shoulder monitoring points can be detected by combining the image detected by the depth camera with the image recognition algorithm.

[0130] After obtaining the lateral swing times and lateral swing angles of the child's shoulder detection points in the third historical time period, when the lateral swing times are less than the preset lateral swing times and the lateral swing angles are less than the preset lateral swing angles, it indicates that the swing amplitude and swing times of the child's shoulders in the third historical time period are small, and it can be judged that the child's sitting posture is relatively stable in the third historical time period.

[0131] Exemplarily, the duration of the third historical time period can be 3 minutes, the preset lateral swing times can be 5 times, and the lateral swing angle can be 60 degrees.

[0132] When the sitting posture of the child is relatively stable during the third historical time period, the sequential height difference between the shoulder detection point and the desktop and the sequential second distance between the eye detection point of the child and the book on the desktop during the first historical time period can be obtained. The first historical time period is the subsequent time period connected to the third historical time period in time. Furthermore, the sitting posture of the child can be monitored based on the sitting posture of the child during the first historical time period.

[0133] The beneficial effect of the above implementation method is that the stability of the child's sitting posture is monitored through the stability of the child's shoulders. Furthermore, the subsequent first historical time period is determined when the child's sitting posture is in a relatively stable state, and the sequential height difference between the shoulder detection point and the desktop and the sequential second distance between the eye detection point of the child and the book on the desktop during the first historical time period are used to detect the child's sitting posture, improving the stability of the child's sitting posture detection.

[0134] The beneficial effect of the above implementation method is also that the stability of the child's shoulders is detected through the number of lateral swings and the lateral swing angle of the child's shoulder detection point, enabling accurate detection of the stability of the child's sitting posture and improving the reliability of the detection of the stability of the child's sitting posture.

[0135] In some implementation methods, the above method further includes S410 to S420. The following is a specific description of S410 to S420.

[0136] S410. Obtain the activity habit adjustment factor set by the user, multiply the preset number of lateral swings by the activity habit adjustment factor to obtain the adjusted number of lateral swings, and multiply the preset lateral swing angle by the activity habit adjustment factor to obtain the adjusted lateral swing angle.

[0137] Since different children have different activity habits and activity frequencies, the preset number of lateral swings and the preset lateral swing angle for monitoring the sitting posture stability of children can be adjusted based on the user's settings to improve the stability of detecting the sitting posture of children.

[0138] When adjusting the preset number of lateral swings and the preset lateral swing angle, the activity habit adjustment factor set by the user can be obtained, multiply the preset number of lateral swings by the activity habit adjustment factor to obtain the adjusted number of lateral swings, and multiply the preset lateral swing angle by the activity habit adjustment factor to obtain the adjusted lateral swing angle, so as to realize the adjustment of the preset number of lateral swings and the preset lateral swing angle.

[0139] Exemplarily, the activity habit adjustment factor can be set through the user operation button.

[0140] S420. When the number of lateral swings is less than the adjusted number of lateral swings and the lateral swing angle is less than the adjusted lateral swing angle, obtain the sequential height difference between the shoulder detection point and the desktop within the first historical time period, and the sequential second distance between the child's eye detection point and the book on the desktop.

[0141] After adjusting the preset number of lateral swings and the preset lateral swing angle, when the number of lateral swings is less than the adjusted number of lateral swings and the lateral swing angle is less than the adjusted lateral swing angle, it indicates that the child's sitting posture is relatively stable. At this time, the sequential height difference between the shoulder detection point and the desktop within the first historical time period, and the sequential second distance between the child's eye detection point and the book on the desktop can be obtained.

[0142] The beneficial effect of the above implementation method is that users can adjust the preset number of lateral swings and the preset lateral swing angle according to the child's activity habits and activity frequencies, improving the adaptability of correcting the sitting postures of different children and being able to improve the personalization degree of correcting the child's sitting posture.

[0143] The embodiment of the present application also provides an image recognition-based sitting posture correction management system for children's study desks, including a unit for executing the method described in any one of the above.

[0144] Figure 5 It is a schematic logical structure diagram of an image recognition-based sitting posture correction management system for children's study desks provided by an embodiment of the present application. As Figure 5 shown, the system 2 of this embodiment includes a processing unit 21, a storage unit 22, and a transceiver unit 23. The processing unit 21 is used to process data, the storage unit 22 is used to store data, and the transceiver unit 23 is used to send and receive data. The processing unit 21, the storage unit 22, and the transceiver unit 23 cooperate with each other to implement the above method. The beneficial effects of the embodiment of the present application have been described in the above method and will not be elaborated here.

[0145] The embodiment of the present application also provides an image recognition-based sitting posture correction management system for children's study desks, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method described in any one of the above.

[0146] Figure 6 It is a schematic physical structure diagram of an image recognition-based sitting posture correction management system for children's study desks provided by an embodiment of the present application. As Figure 6 shown, the system 3 of this embodiment includes: at least one processor 30( Figure 6Only one processor 30), a memory 31, and a computer program 32 stored in the memory 31 and executable on the at least one processor 30 are shown. When the processor 30 executes the computer program 32, the steps in any of the above method embodiments are implemented. The beneficial effects of the embodiments of the present application have been described in the above methods and will not be elaborated here.

[0147] It should be noted that for the content such as information interaction and execution process between the above devices / units, since it is based on the same concept as the method embodiments of the present application, for its specific functions and the technical effects brought, reference can be specifically made to the method embodiment part and will not be elaborated here.

[0148] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiments and will not be elaborated here.

[0149] The embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments can be implemented.

[0150] The embodiments of the present application provide a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal is enabled to execute the steps in any of the above method embodiments.

[0151] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of this application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the photographing device / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0152] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0153] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed in this document can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0154] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0155] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0156] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for correcting sitting posture of children's study desks based on image recognition, characterized in that: The method comprises: Obtaining a body posture image of a child when using a child study table, determining a posture detection point and a tabletop position in the body posture image through image recognition, and determining the child's body posture based on the posture detection point; When the child's body posture and desk position meet the first posture condition, the child's sitting posture monitoring suggestion information is determined based on the standard sitting posture model and the child's body posture, and prompt information for correcting the child's sitting posture is issued according to the sitting posture monitoring suggestion information; when the child's body posture and desk position meet the second posture condition, the height adjustment value of the child's study table is determined based on the child's body posture and desk position, and prompt information for adjusting the desk height is issued according to the height adjustment value.

2. The method according to claim 1, characterized in that The first posture conditions include: A first distance between a shoulder detection point and a desktop in the child's body posture is within a preset first distance range, and the child's sitting posture does not conform to a standard sitting posture model; The second posture conditions include: The first distance between the shoulder detection point and the desktop in the child's body posture is not within the preset first distance range, and the child's sitting posture does not conform to the standard sitting posture model; Determine the height adjustment value of the children's study table based on the child's body posture and desktop position, including: Determine the average height of the left shoulder detection point and the right shoulder detection point of the child's body posture as the shoulder detection point, determine the height difference between the shoulder detection point and the desktop, and determine the difference between the height difference and the preset height difference as the height adjustment value.

3. The method according to claim 2, characterized in that The method further comprises: Obtaining a time-series height difference between a shoulder detection point and a desktop, and a time-series second distance between an eye detection point of a child and a book on the desktop within a first historical time period; When the height difference values ​​at multiple moments in the time series height difference values ​​decrease successively, and the second distances at multiple moments in the time series second distances decrease successively, a prompt message is issued to tilt the side of the desktop away from the child upward; when the height difference values ​​at multiple moments in the time series height difference values ​​increase successively, and the second distances at multiple moments in the time series second distances increase successively, a prompt message is issued to tilt the side of the desktop away from the child downward.

4. The method according to claim 3, characterized in that The method further comprises: When the height difference values ​​at multiple moments in the time series height difference increase successively, and the second distances at multiple moments in the time series second distance decrease successively, a prompt message is issued to adjust the height of the desktop downward and tilt the side of the desktop away from the child upward; when the height difference values ​​at multiple moments in the time series height difference decrease successively, and the second distances at multiple moments in the time series second distance increase successively, a prompt message is issued to adjust the height of the desktop upward and tilt the side of the desktop away from the child downward.

5. The method according to claim 4, characterized in that The method further comprises: Determine the child's learning posture according to the posture detection points; wherein the child's learning posture includes a writing state and a drawing state; When the child's learning posture is in a drawing state, the height difference values ​​at multiple moments in the temporal height difference increase successively, and the second distances at multiple moments in the temporal second distance decrease successively, a prompt message is issued to adjust the height of the desktop downward and tilt the side of the desktop away from the child upward; when the child's learning posture is in a writing state, the height difference values ​​at multiple moments in the temporal height difference decrease successively, and the second distances at multiple moments in the temporal second distance increase successively, a prompt message is issued to adjust the height of the desktop upward and tilt the side of the desktop away from the child downward.

6. The method according to claim 5, characterized in that The method further comprises: Obtaining a time-series height difference between a shoulder detection point and a desktop, and a time-series second distance between an eye detection point of a child and a book on the desktop in a second historical time period; wherein the duration of the second historical time period is 3 to 10 times the duration of the first historical time period; When the height difference at multiple moments in the time series height difference remains stable and the second distance at multiple moments in the time series second distance decreases or increases successively, or when the second distance at multiple moments in the time series second distance remains stable and the height difference at multiple moments in the time series height difference decreases or increases successively, the child's sitting posture monitoring suggestion information is determined based on the standard sitting posture model and the child's body posture, and prompt information for correcting the child's sitting posture is issued according to the sitting posture monitoring suggestion information.

7. The method according to claim 6, characterized in that The method further comprises: Acquire a seat pressure value for monitoring the pressure on the seat, and acquire a time-series height difference between a shoulder detection point and a desktop, and a time-series second distance between an eye detection point of the child and a book on the desktop in a second historical time period; wherein the duration of the second historical time period is 3 to 10 times the duration of the first historical time period; When the seat pressure value is greater than or equal to the preset seat pressure value, and when the height difference values ​​at multiple moments in the time series height difference value remain stable and the second distances at multiple moments in the time series second distance value decrease or increase successively, or when the second distances at multiple moments in the time series second distance value remain stable and the height difference values ​​at multiple moments in the time series height difference value decrease or increase successively, the child's sitting posture monitoring recommendation information is determined based on the standard sitting posture model and the child's body posture, the seat height adjustment value and the table height adjustment value are determined according to the sitting posture monitoring recommendation information, and the seat height is adjusted according to the seat height adjustment value, and the table height is adjusted according to the table height adjustment value.

8. The method according to claim 7, characterized in that The method further comprises: When the seat pressure value is greater than or equal to the preset seat pressure value, and when the height difference at multiple moments in the time series height difference value remains stable and the second distance at multiple moments in the time series second distance value decreases or increases successively, or when the second distance at multiple moments in the time series second distance value remains stable and the height difference at multiple moments in the time series height difference value decreases or increases successively, the table top height is raised to the standing height, and a standing prompt message is issued to prompt the child to adjust to a standing position.

9. The method according to claim 8, characterized in that The method further comprises: The number of lateral swings and the lateral swing angle of the child's shoulder detection point in the third historical time period are obtained. When the number of lateral swings is less than the preset number of lateral swings and the lateral swing angle is less than the preset lateral swing angle, the temporal height difference between the shoulder detection point and the desktop in the first historical time period and the temporal second distance between the child's eye detection point and the book on the desktop are obtained; wherein the first historical time period is a subsequent time period connected in time to the third historical time period.

10. A children's study table sitting posture correction management system based on image recognition, characterized in that: Comprising means for performing the method according to any one of claims 1 to 9.

Images