Method, device and electronic equipment for correcting reading posture of adolescents and children

Abstract

The present invention provides a method, device and electronic device for correcting the reading posture of adolescents and children. The method comprises: inputting the to-be-tested reading data of adolescents and children into a preset body shape prediction module of a preset reading posture correction model to obtain the current body shape data of adolescents and children; inputting the current body shape data and the to-be-tested reading data into a preset body shape-posture recognition module of a preset reading posture correction model to obtain the current reading posture data of adolescents and children; obtaining the correction suggestions for the reading posture of adolescents and children based on the current reading posture data and a preset posture-sitting correction module of a preset reading posture correction model, wherein the preset reading posture correction model is a model obtained after training with reading sample data and learning of a standard reading sitting posture. The use of the method of the present invention improves the efficiency of monitoring the reading posture of adolescents and children, achieves the purpose of timely and accurately correcting the bad reading posture of adolescents and children, and enhances the ability to prevent myopia or spinal diseases in adolescents and children.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, device and electronic equipment for correcting the reading posture of adolescents and children. Background Art

[0002] With the continuous development and progress of science and technology, people are spending more and more time using mobile phones, computers and other electronic products for learning and entertainment, resulting in an increase in the incidence of myopia and spinal diseases. This is especially true for adolescents and children whose academic burdens are gradually increasing. As they are students and in the growth and development period, their myopia and spinal health problems are becoming more and more serious due to their improper posture when reading and studying for a long time.

[0003] In the related art, the reading correction device of the reader includes a controller and a camera facing the reader. The camera is used to take a photo of the reader's sitting posture and send the sitting posture photo to the controller. When the controller determines that the reader's current sitting posture is incorrect based on the reader's sitting posture photo, it reminds the reader to correct the sitting posture.

[0004] However, since the controller only uses the sitting posture photo to determine whether the reader's current sitting posture is correct, it does not take the reader's body shape and posture into consideration. Furthermore, since the body shape and posture of adolescents and children are quite different from those of adults, the accuracy of correcting the reader's sitting posture is not high. Summary of the invention

[0005] The present invention provides a method, device and electronic device for correcting the reading posture of adolescents and children, so as to solve the defect of low accuracy of correcting the reader's sitting posture caused by only using a reader's sitting posture photo to judge whether the reader's sitting posture is correct in the prior art, and achieve the purpose of timely and accurately correcting the bad reading posture of adolescents and children.

[0006] The present invention provides a method for correcting the reading posture of young children, comprising:

[0007] Inputting the to-be-tested reading data of the adolescent child into a preset body shape prediction module of a preset reading posture correction model to obtain the current body shape data of the adolescent child;

[0008] Inputting the current body shape data and the reading data to be tested into the preset body shape-posture recognition module of the preset reading posture correction model to obtain the current reading posture data of the adolescent child;

[0009] Based on the current reading posture data and the preset posture-sitting posture correction module of the preset reading posture correction model, obtaining reading posture correction suggestions for the adolescent child;

[0010] The preset reading posture correction model is a model obtained after training based on reading sample data and learning the standard reading sitting posture.

[0011] According to a method for correcting the reading posture of adolescents and children provided by the present invention, the preset posture-sitting posture correction module based on the current reading posture data and the preset reading posture correction model obtains the reading posture correction suggestion of the adolescents and children, including:

[0012] Inputting the current reading posture data into the preset posture-sitting posture correction module of the preset reading posture correction model to obtain the current reading sitting posture score of the adolescent child;

[0013] Based on the preset posture-sitting posture correction module, obtaining the deviation between the current reading sitting posture score and the standard reading sitting posture;

[0014] Based on the deviation, correction suggestions for the reading posture of the adolescent child are obtained.

[0015] According to a method for correcting the reading posture of adolescents and children provided by the present invention, the training process of the preset reading posture correction model includes:

[0016] When determining that the reading posture data of the sample adolescents and children is represented based on nodes and degrees of freedom, obtaining the reading sample data of the sample adolescents and children and model constraints, wherein the model constraints are used to limit the rotation angle of the node to not exceed the limit of the human body;

[0017] Based on the preset conditions of the model, the reading sample data is used to perform statistical learning on the body shapes of adolescents and children to obtain a preset body shape prediction module;

[0018] Based on the preset body shape prediction module and the reading sample data, a body shape-posture recognition training for adolescents and children is performed to obtain a preset body shape-posture recognition module;

[0019] Performing posture-sitting posture prediction training based on the preset body shape-posture recognition module and the reading sample data and comparing the deviation with the standard reading sitting posture to obtain a preset posture-sitting posture correction module;

[0020] The preset reading posture correction model is determined to be a model including the preset body shape prediction module, the preset body shape-posture recognition module and the preset posture-sitting posture correction module.

[0021] According to a method for correcting the reading posture of adolescents and children provided by the present invention, the learning process of the standard reading sitting posture includes:

[0022] Acquire reading sample label data carrying a sitting posture identifier, wherein the sitting posture identifier is used to indicate that the reading sitting posture of the corresponding sample adolescent child is normal;

[0023] The reading sample label data is learned to obtain the standard reading sitting posture.

[0024] According to a method for correcting the reading posture of adolescents and children provided by the present invention, the standard reading sitting posture includes standard reading posture data, and the learning process of the standard reading posture data includes:

[0025] When the reading posture data of the sample adolescents and children are initially represented by d different nodes, it is determined whether the expression effects of the d nodes for the standard reading sitting posture meet the preset requirements;

[0026] If the expression effect does not meet the preset requirement, d is adjusted to t;

[0027] If the expression effects of t different nodes for the standard reading sitting posture meet the preset requirements, it is determined that the standard reading posture data of the sample adolescent children is represented by t different nodes, and the t different nodes are determined as standard reading posture data; wherein each of the nodes is represented by a posture with a preset number of degrees of freedom, and d and t are positive integers respectively.

[0028] According to a method for correcting the reading posture of adolescents and children provided by the present invention, the step of obtaining reading sample data of sample adolescents and children comprises:

[0029] When the reading posture data of the sample adolescents and children include t different nodes and each of the nodes is represented by a posture with m different degrees of freedom, obtain t1 of the nodes with a focus on the head of the sample adolescents and children, obtain t2 of the nodes with a focus on the neck of the sample adolescents and children, and obtain t3 of the nodes with a focus on the spine of the sample adolescents and children; wherein t=t1+t2+t3, t1, t2, t3 and m are positive integers respectively.

[0030] The present invention also provides a device for correcting the reading posture of young children, comprising:

[0031] A body shape prediction unit, used for inputting the to-be-tested reading data of the adolescent child into a preset body shape prediction module of a preset reading posture correction model to obtain the current body shape data of the adolescent child;

[0032] A posture recognition unit, used for inputting the current body shape data and the reading data to be tested into a preset body shape-posture recognition module of the preset reading posture correction model to obtain the current reading posture data of the adolescent child;

[0033] A posture correction unit, configured to obtain a reading posture correction suggestion for the adolescent child based on the current reading posture data and a preset posture-sitting posture correction module of the preset reading posture correction model;

[0034] The preset reading posture correction model is a model obtained after training based on reading sample data and learning the standard reading sitting posture.

[0035] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the above-mentioned methods for correcting the reading posture of adolescents and children is implemented.

[0036] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements any of the above-mentioned methods for correcting the reading posture of adolescents and children.

[0037] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for correcting the reading posture of adolescents and children.

[0038] The present invention provides a method, device and electronic device for correcting the reading posture of adolescents and children. The method for correcting the reading posture of adolescents and children inputs the reading data to be tested of adolescents and children into a preset reading posture correction model to first predict the body shape, then perform posture recognition, and finally perform reading posture mapping, so as to accurately and quickly obtain correction suggestions for the reading posture of adolescents and children, which not only improves the monitoring efficiency of the reading posture of adolescents and children, but also achieves the purpose of timely and accurate correction of the bad reading posture of adolescents and children; further, since the preset reading posture correction model is a model obtained after training based on reading sample data and learning the standard reading sitting posture, the combination of model training and model learning technology can ensure the accuracy and reliability of the preset reading posture correction model, thereby further improving the ability to prevent myopia or spinal diseases in adolescents and children. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 It is a schematic diagram of the flow of the method for correcting the reading posture of adolescents and children provided by the present invention;

[0041] Figure 2 It is a structural schematic diagram of the device for correcting the reading posture of teenagers and children provided by the present invention;

[0042] Figure 3It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Combine the following Figure 1-Figure 3 The present invention describes a method, device and electronic device for correcting the reading posture of young people and children, wherein the executor of the method for correcting the reading posture of young people and children can be a device for correcting the reading posture of young people and children, and the device for correcting the reading posture of young people and children can be implemented as part or all of a terminal device through software, hardware or a combination of software and hardware. Optionally, the terminal device can be a personal computer (PC), a portable device, a laptop computer, a smart phone, a tablet computer, a portable wearable device and other electronic devices. The present invention does not limit the specific form of the terminal device.

[0045] It should be noted that the execution subject of the following method embodiment may be part or all of the above terminal device. The following method embodiment is described by taking the execution subject as the terminal device as an example.

[0046] Figure 1 The flowchart of the method for correcting the reading posture of adolescents and children provided by the present invention is as follows: Figure 1 As shown, the method for correcting the reading posture of adolescents and children comprises the following steps:

[0047] Step 110: input the to-be-tested reading data of the adolescent or child into a preset body shape prediction module of a preset reading posture correction model to obtain the current body shape data of the adolescent or child.

[0048] Among them, the teenagers and children can be boys or girls aged over six years old and under eighteen years old; the preset reading posture correction model is a model obtained after training with reading sample data and learning the standard reading sitting posture, that is, a model obtained after using reading sample data for body shape training, body shape-posture recognition training, and posture-reading sitting posture recommendation training; the preset body shape prediction module is used to predict the current body shape data of teenagers and children from their reading data to be tested.

[0049] Specifically, when it is determined that the teenagers and children are sitting at a desk or table to read, the reading data to be tested of the teenagers and children can be obtained through a camera, a lidar, an RGBD camera or other sensors. The reading data to be tested can represent the three-dimensional data of the teenagers and children's current reading posture, and the reading data to be tested is input into a preset body shape prediction module of a preset reading posture correction model to predict the current body shape of the teenagers and children. For example, a parameterized three-dimensional teenager and child human body model is obtained through three-dimensional reconstruction technology, and further based on the parameterized three-dimensional teenager and child human body model, the current body shape data including at least the current height and appearance of the teenager and children can be obtained.

[0050] Step 120: input the current body shape data of the adolescent and the reading data to be tested into a preset body shape-posture recognition module of a preset reading posture correction model to obtain the current reading posture data of the adolescent and the child.

[0051] Among them, the preset body shape-posture recognition module is used to output the number of matching nodes and the specific position of each node based on the current body shape data of the adolescent child and the reading data to be tested.

[0052] Specifically, considering that different teenagers and children have different body shapes, different teenagers and children may have the same reading posture, and the reading posture of the same teenager and child may also be different. Therefore, for the current body shape data of the teenager and child, it is necessary to first obtain the number of nodes that can express the current reading posture and the specific position of each node, so as to accurately identify the current reading posture of the teenager and child. That is, the current body shape data of the teenager and the reading data to be tested are input into the preset body shape-posture recognition module of the preset reading posture correction model to identify the current reading posture data that matches the current body shape data, that is, identify the number of nodes that can accurately express the current reading posture and the specific position of each node, so as to obtain the current reading posture data of the teenager and child.

[0053] It should be noted that the current reading posture data of adolescents and children can be represented based on nodes and degrees of freedom, that is, it includes t different nodes and each node is represented by m different degrees of freedom. T and m are positive integers. The definition of nodes is conducive to extracting features that can distinguish between correct and incorrect reading postures of adolescents and children. The more nodes there are, the more accurate the defined reading posture is. For example, nodes can be located on the head, neck and spine. In addition, each node can be represented as a quaternion in addition to being represented by degrees of freedom. No specific limitation is made here.

[0054] Step 130: Based on the current reading posture data of the adolescent and child and the preset posture-sitting posture correction module of the preset reading posture correction model, obtain reading posture correction suggestions for the adolescent and child.

[0055] Specifically, the current reading posture data of the teenagers and children is input into the preset posture-sitting posture correction model of the preset reading posture correction model to identify the current sitting posture of the teenagers and children. When it is determined that the current sitting posture of the teenagers and children does not meet the standards, the corresponding reading posture correction suggestions are output. For example, the reading posture correction suggestions may be to raise the head, straighten the chest, and keep one fist away from the table.

[0056] The method for correcting the reading posture of adolescents and children provided by the present invention inputs the reading data to be tested of adolescents and children into a preset reading posture correction model to first perform body shape prediction, then perform posture recognition, and finally perform reading posture mapping, so as to accurately and quickly obtain correction suggestions for the reading posture of adolescents and children, which not only improves the monitoring efficiency of the reading posture of adolescents and children, but also achieves the purpose of timely and accurate correction of the bad reading posture of adolescents and children; further, since the preset reading posture correction model is a model obtained after training based on reading sample data and learning the standard reading sitting posture, the combination of model training and model learning technology can ensure the accuracy and reliability of the preset reading posture correction model, thereby further improving the ability to prevent myopia or spinal diseases in adolescents and children.

[0057] Optionally, the implementation process of step 130 may include:

[0058] First, the current reading posture data of adolescents and children are input into the preset posture-sitting posture correction module of the preset reading posture correction model to obtain the current reading sitting posture score of the adolescents and children; then, based on the preset posture-sitting posture correction module, the deviation between the current reading sitting posture score and the standard reading sitting posture is obtained; further, based on the deviation between the current reading sitting posture score and the standard reading sitting posture, the reading posture correction suggestions for adolescents and children are obtained.

[0059] Among them, the preset posture-sitting posture correction module is used to identify the current reading posture corresponding to the current reading posture data, and to score and provide sitting posture correction suggestions based on the current reading posture.

[0060] Specifically, since the current reading posture data of adolescents and children can accurately express the number of nodes of the current body shape data and the specific position of each node, the current reading posture of adolescents and children can also be accurately identified based on the current reading posture data. Based on this, the current reading posture data of adolescents and children are input into the preset posture-sitting correction module of the preset reading posture correction model to first identify the current reading sitting posture, and then score the identified current reading sitting posture, so as to obtain the current reading sitting posture score of adolescents and children, and further determine whether the current reading sitting posture score meets the standard, that is, compare the current reading sitting posture with the standard reading sitting posture. If there is a deviation in the comparison result standard, the current distance between the adolescents and children and the book and the current line of sight of the adolescents and children reading the book are determined based on the deviation between the current reading sitting posture and the standard reading sitting posture, and then the reading posture correction suggestion for the current reading sitting posture is output based on the current distance and the current line of sight, so that the corrected reading sitting posture is the same as the standard reading sitting posture. For example, if the current reading sitting posture is one fist one foot one inch, uneven shoulders, scoliosis, tilted head, lowered head, etc., and it deviates from the standard reading sitting posture, it can output reading posture correction suggestions such as raising the head, straightening the chest, and one fist away from the table; among them, one fist one foot one inch means that the upper body is kept upright and slightly leaning forward, the chest is one fist away from the table, the hands are held one inch away from the tip of the pen, the head is upright and naturally leaning forward, and the eyes are about one foot away from the table.

[0061] The method for correcting the reading posture of adolescents and children provided by the present invention can achieve the purpose of accurately correcting the bad reading sitting posture of adolescents and children by means of posture recognition, posture scoring and posture correction suggestions in a preset posture-sitting posture correction module, and can also improve the possibility and reliability of early prevention, early detection and early treatment of myopia and spinal diseases among adolescents and children.

[0062] Optionally, the training process of the preset reading posture correction model includes:

[0063] Firstly, when determining the reading posture data of sample adolescents and children based on the representation of nodes and degrees of freedom, the reading sample data of sample adolescents and children and model constraints are obtained, and the model constraints are used to limit the rotation angle of each node to not exceed the limit of the human body; then, based on the preset conditions of the model, the reading sample data are used to perform statistical learning of the body shape of adolescents and children, and a preset body shape prediction module is obtained; then, based on the preset body shape prediction module and the reading sample data, the body shape-posture recognition training of adolescents and children is performed to obtain a preset body shape-posture recognition module; further, based on the preset body shape-posture recognition module and the reading sample data, posture-sitting posture prediction training is performed and the deviation comparison with the standard reading sitting posture is performed to obtain a preset posture-sitting posture correction module; finally, the preset reading posture correction model is determined to be a model containing a preset body shape prediction module, a preset body shape-posture recognition module and a preset posture-sitting posture correction module.

[0064] Among them, the sample teenagers and children are also boys or girls under the age of 18. The number of sample teenagers and children can be one or more. When the number of sample teenagers and children is one, it can be the same as the teenagers and children corresponding to the current reading data to be tested.

[0065] Specifically, when it is determined that the reading posture data of the sample adolescents and children is represented by t different nodes and each node is represented by m postures with different degrees of freedom, the reading sample data of the sample adolescents and children is further obtained. The number of reading sample data is multiple and can be obtained for the same sample adolescent and child, or for different sample adolescents and children. In addition, the reading sample data of the sample adolescent and children can be obtained based on the sample adolescent and children who are actually in the reading scene, or the reading sample data of the sample adolescent and children who meet the training conditions can be obtained from the cloud big data. No specific limitation is made here.

[0066] Further obtain the model constraints, which not only help to express the current reading posture of adolescents and children, but also make the body shape, reading posture data and reading posture correction suggestions have certain constraints, that is, the model constraints are for body shape training, posture recognition and sitting posture correction suggestions, so that the body shape data obtained by training, the reading posture data obtained by recognition and the reading posture correction suggestions given are all within a reasonable range. For example, the model constraints may include that the rotation of each node cannot exceed the limit of the human body, the head cannot rotate 180° when the neck, head and body rotate relative to each other; for the relative position of the n degrees of freedom obtained by the rotation, the relative angle of the two nodes of the head and body cannot exceed 180°; and the height range of the sample adolescents is less than 1.7m, and the relationship between the height of the sample adolescents and children and their fatness is within a reasonable range, etc.

[0067] Then, under the constraints of the model, the reading sample data is used to conduct statistical learning of the body shape of adolescents and children, until the corresponding preset body shape prediction module is obtained at the end of the statistical learning; the preset body shape prediction module and the reading sample data are then combined to conduct recognition training of the body shape-posture of adolescents and children, until the corresponding preset body shape-posture recognition module is obtained at the end of the recognition training; finally, based on the preset body shape-posture recognition module and the reading sample data, posture-sitting posture prediction training and deviation comparison with the standard reading sitting posture are conducted, until the corresponding preset posture-sitting posture correction module is obtained at the end of the prediction training and deviation comparison, and finally the preset reading posture correction model is determined to be a model containing a preset body shape prediction module, a preset body shape-posture recognition module and a preset posture-sitting posture correction module.

[0068] It should be noted that the present invention can also pre-set an initial reading posture correction model and the initial reading posture correction model has a body shape training function, a body shape-posture recognition training function and a posture-reading sitting posture suggestion training function, and the posture-reading sitting posture suggestion training function includes a posture-sitting posture prediction training function and a deviation comparison function with a standard reading sitting posture. Based on this, the initial reading posture correction model can be trained using reading sample data until the training is completed, and then the posture correction model corresponding to the end of the training is determined as a preset reading posture correction model, wherein the part with the body shape training function becomes a preset body shape prediction module after training, the part with the body shape-posture recognition training function becomes a preset body shape-posture recognition module after training, and the part with the posture-reading sitting posture suggestion training function becomes a preset posture-sitting posture correction module after training.

[0069] The method for correcting the reading posture of adolescents and children provided by the present invention obtains a preset reading posture correction model for correcting the reading posture of adolescents and children by using reading sample data of adolescents and children to perform body shape statistical learning, body shape-posture recognition training, posture-sitting posture prediction training and deviation comparison with the standard reading sitting posture. The combination of statistical learning and model training principles can improve the accuracy of reading posture correction, thereby effectively preventing myopia and spinal diseases.

[0070] Optionally, for the training of the preset reading posture correction model, during the process of the adolescent and child body shape-posture recognition training, the standard reading sitting posture can also be learned, and the learned standard reading sitting posture can be stored for subsequent deviation comparison. Based on this, during the adolescent and child body shape-posture recognition training, the learning process of the standard reading sitting posture includes:

[0071] First, reading sample label data with sitting posture identification is obtained, and the sitting posture identification is used to indicate that the reading sitting posture of the corresponding sample adolescent children is normal; then, the reading sample label data is learned to obtain the standard reading sitting posture.

[0072] Specifically, the standard reading sitting posture in the embodiment of the present invention can be obtained in advance from the cloud big data and then stored, or it can be learned. When the standard reading sitting posture is obtained based on learning, the reading sample label data carrying the sitting posture identification can be obtained first. The reading sample label data can also be obtained based on sample teenagers and children in the reading scene and their reading sitting posture is manually marked as normal. Then the reading sample label data is learned until the learning is completed, and the corresponding standard reading sitting posture at the end of the learning is obtained. The standard reading sitting posture carries the standard distance between teenagers and children and books and the standard line of sight for teenagers and children to read books.

[0073] The method for correcting the reading posture of adolescents and children provided in the embodiment of the present invention obtains a standard reading posture for subsequent judgment on whether the current reading posture of adolescents and children is normal by learning reading sample label data that represents the normal reading posture of adolescents and children, thereby improving the judgment accuracy and reliability of the reading posture of adolescents and children.

[0074] Optionally, for the learned or acquired standard reading sitting posture, the standard reading sitting posture also includes standard reading posture data. The learning of the standard reading posture data is specifically the learning of standard nodes that can accurately express the standard reading posture. The standard nodes include the number of standard nodes, the specific position of each standard node and the representation form of each standard node. The process includes:

[0075] When the reading posture data of the sample adolescent children are initially represented by d different nodes, it is determined whether the expression effects of the d nodes for the standard reading sitting posture meet the preset requirements; if the expression effects do not meet the preset requirements, d is adjusted to t; if the expression effects of t different nodes for the standard reading sitting posture meet the preset requirements, it is determined that the standard reading posture data of the sample adolescent children are represented by t different nodes, and the t different nodes are determined as the standard reading posture data; wherein each node is represented by a posture with a preset number of degrees of freedom, and d and t are positive integers respectively.

[0076] Among them, the reading posture data can characterize the posture of sample adolescents and children in the reading scene. The preset requirement is that the expression level of the standard reading sitting posture is optimal and meets the needs of sitting posture recognition.

[0077] Specifically, when the reading posture data is initially represented by d different nodes, it is determined whether the expression effects of the d different nodes for the standard reading sitting posture meet the preset requirements. When it is determined that the d different nodes can reasonably express the standard reading sitting posture, that is, their expression effect reaches the optimal, the d different nodes are directly determined as the standard reading posture data; on the contrary, when it is determined that the precision of the d different nodes in expressing the standard reading sitting posture is too high or too low, that is, d is too large or too small, then d can be increased or decreased, for example, d is adjusted to t, and then it is further determined whether the expression effects of the t different nodes for the standard reading sitting posture meet the preset requirements. When the expression effects of the t different nodes for the standard reading sitting posture meet the preset requirements, it is determined that the standard reading posture data of the sample adolescent children are represented by t different nodes, each node is represented by a posture with a preset number of degrees of freedom. When the preset number is 6, each node can include the three-dimensional coordinates of the standard reading sitting posture in the three-dimensional space and three angles relative to the three-dimensional coordinates, that is, each coordinate in the three-dimensional coordinates has an angle component, so that the three angles are related to the three-dimensional coordinates, thereby determining the angle of the reading posture of the sample adolescent children in the three-dimensional space. If the precision of t different nodes in expressing the standard reading posture is too high or too low, the size of t is adjusted again until the expression effect of the adjusted nodes for the standard reading posture meets the preset requirements.

[0078] The method for correcting the reading posture of adolescents and children provided by the present invention determines the standard reading posture data by adjusting the number of nodes expressing the standard reading sitting posture, thereby improving the content richness of the standard reading sitting posture, thereby also providing a strong basis for the subsequent clear and accurate expression of the reading sitting posture of adolescents and children and the precision of identifying the reading posture.

[0079] Optionally, the process of obtaining reading sample data for sample adolescent children may include:

[0080] When the reading posture data of the sample adolescents and children include t different nodes and each node is represented by m postures with different degrees of freedom, t1 nodes are obtained to focus on the reading sample data of the head of the sample adolescents and children, t2 nodes are obtained to focus on the reading sample data of the neck of the sample adolescents and children, and t3 nodes are obtained to focus on the reading sample data of the spine of the sample adolescents and children; wherein t=t1+t2+t3, t1, t2, t3 and m are positive integers respectively.

[0081] Specifically, in a reading scenario, a large amount of reading sample data is obtained for the same sample adolescent children or different sample adolescent children, and when obtaining the reading sample data, they can be obtained with different focuses, that is, a first reading sample data, b second reading sample data and c third reading sample data are obtained, t1 nodes in each first reading sample data focus on the head of the sample adolescent children, t2 nodes in each second reading sample data focus on the neck of the sample adolescent children, and t3 nodes in each third reading sample data focus on the spine of the sample adolescent children, so that the reading sample data of the sample adolescent children include a first reading sample data, b second reading sample data and c third reading sample data, a, b, c, t1, t2, t3 are positive integers greater than 0, respectively, and t=t1+t2+t3.

[0082] The method for correcting the reading posture of adolescents and children provided by the present invention obtains reading sample data of sample adolescents and children by focusing on the head, neck and spine respectively, so as to improve the reliability and accuracy of subsequent model training and sitting posture learning, thereby further improving the pertinence and flexibility of subsequent correction of bad reading posture of adolescents and children.

[0083] The following is a description of the apparatus for correcting the reading posture of teenagers and children provided by the present invention. The apparatus for correcting the reading posture of teenagers and children described below and the method for correcting the reading posture of teenagers and children described above can be referenced to each other.

[0084] Reference Figure 2 , which is a schematic diagram of the structure of a device for correcting the reading posture of young people and children provided by an embodiment of the present invention, Figure 2 In the present invention, the device 200 for correcting the reading posture of young people and children comprises:

[0085] The body shape prediction unit 210 is used to input the reading data to be tested of the adolescent and child into the preset body shape prediction module of the preset reading posture correction model to obtain the current body shape data of the adolescent and child; the posture recognition unit 220 is used to input the current body shape data and the reading data to be tested into the preset body shape-posture recognition module of the preset reading posture correction model to obtain the current reading posture data of the adolescent and child; the posture correction unit 230 is used to obtain the reading posture correction suggestion of the adolescent and child based on the current reading posture data and the preset posture-sitting posture correction module of the preset reading posture correction model; wherein the preset reading posture correction model is a model obtained after training with reading sample data and learning the standard reading sitting posture.

[0086] Optionally, the posture correction unit 230 can be specifically used to input the current reading posture data into the preset posture-sitting posture correction module of the preset reading posture correction model to obtain the current reading sitting posture score of the adolescent child; based on the preset posture-sitting posture correction module, obtain the deviation between the current reading sitting posture score and the standard reading sitting posture; based on the deviation, obtain the reading posture correction suggestion for the adolescent child.

[0087] Optionally, the device also includes a training unit, which can be specifically used to determine the reading posture data of sample adolescents and children based on nodes and degrees of freedom, obtain the reading sample data of the sample adolescents and children and model constraints, and the model constraints are used to limit the rotation angle of the node to not exceed the limit of the human body; based on the model preset conditions, use the reading sample data to perform adolescent and child body shape statistical learning to obtain a preset body shape prediction module; based on the preset body shape prediction module and the reading sample data, perform adolescent and child body shape-posture recognition training to obtain a preset body shape-posture recognition module; based on the preset body shape-posture recognition module and the reading sample data, perform posture-sitting posture prediction training and compare the deviation with the standard reading sitting posture to obtain a preset posture-sitting posture correction module; determine that the preset reading posture correction model is a model containing the preset body shape prediction module, the preset body shape-posture recognition module and the preset posture-sitting posture correction module.

[0088] Optionally, the training unit can also be used to obtain t1 reading sample data of the sample adolescent and child's head, obtain t2 reading sample data of the sample adolescent and child's neck, and obtain t3 reading sample data of the sample adolescent and child's spine when the reading posture data of the sample adolescent and child includes t different nodes and each node is represented by m postures with different degrees of freedom; wherein t=t1+t2+t3, t1, t2, t3 and m are positive integers respectively.

[0089] Optionally, the device also includes a learning unit, which can be specifically used to obtain reading sample label data carrying a sitting posture mark, wherein the sitting posture mark is used to indicate that the reading sitting posture of the corresponding sample adolescent child is normal; the reading sample label data is learned to obtain the standard reading sitting posture.

[0090] Optionally, the learning unit can also be used to set the reading posture data of the sample adolescent children to be initially represented by d different nodes, and determine whether the expression effects of the d nodes for the standard reading sitting posture meet the preset requirements; if the expression effects do not meet the preset requirements, d is adjusted to t; if the expression effects of t different nodes for the standard reading sitting posture meet the preset requirements, it is determined that the standard reading posture data of the sample adolescent children is represented by t different nodes, and the t different nodes are determined to be standard reading posture data; wherein each of the nodes is represented by a posture with a preset number of degrees of freedom, and d and t are positive integers respectively.

[0091] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3 As shown, the electronic device 300 may include: a processor 310, a communications interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communications interface 320 and the memory 330 communicate with each other via the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the method for correcting the reading posture of young children, which includes:

[0092] Inputting the to-be-tested reading data of the adolescent child into a preset body shape prediction module of a preset reading posture correction model to obtain the current body shape data of the adolescent child;

[0093] Inputting the current body shape data and the reading data to be tested into the preset body shape-posture recognition module of the preset reading posture correction model to obtain the current reading posture data of the adolescent child;

[0094] Based on the current reading posture data and the preset posture-sitting posture correction module of the preset reading posture correction model, obtaining reading posture correction suggestions for the adolescent child;

[0095] The preset reading posture correction model is a model obtained after training based on reading sample data and learning the standard reading sitting posture.

[0096] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0097] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the method for correcting the reading posture of adolescents and children provided by the above methods, the method comprising:

[0098] Inputting the to-be-tested reading data of the adolescent child into a preset body shape prediction module of a preset reading posture correction model to obtain the current body shape data of the adolescent child;

[0099] Inputting the current body shape data and the reading data to be tested into the preset body shape-posture recognition module of the preset reading posture correction model to obtain the current reading posture data of the adolescent child;

[0100] Based on the current reading posture data and the preset posture-sitting posture correction module of the preset reading posture correction model, obtaining reading posture correction suggestions for the adolescent child;

[0101] The preset reading posture correction model is a model obtained after training based on reading sample data and learning the standard reading sitting posture.

[0102] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform the method for correcting the reading posture of adolescents and children provided by the above methods, the method comprising:

[0103] Inputting the to-be-tested reading data of the adolescent child into a preset body shape prediction module of a preset reading posture correction model to obtain the current body shape data of the adolescent child;

[0104] Inputting the current body shape data and the reading data to be tested into the preset body shape-posture recognition module of the preset reading posture correction model to obtain the current reading posture data of the adolescent child;

[0105] Based on the current reading posture data and the preset posture-sitting posture correction module of the preset reading posture correction model, obtaining reading posture correction suggestions for the adolescent child;

[0106] The preset reading posture correction model is a model obtained after training based on reading sample data and learning the standard reading sitting posture.

[0107] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0108] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0109] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for correcting the reading posture of adolescents and children, characterized in that: include: Inputting the to-be-tested reading data of the adolescent child into a preset body shape prediction module of a preset reading posture correction model, obtaining a parameterized three-dimensional adolescent child human body model through a three-dimensional reconstruction technology, and obtaining the current body shape data of the adolescent child based on the parameterized three-dimensional adolescent child human body model; The reading data to be tested represents three-dimensional data of the current reading posture of the young child; Inputting the current body shape data and the reading data to be tested into the preset body shape-posture recognition module of the preset reading posture correction model to obtain the current reading posture data of the adolescent child; the current reading posture data includes a plurality of different nodes and each of the nodes is represented by a plurality of postures with different degrees of freedom; Based on the current reading posture data and the preset posture-sitting posture correction module of the preset reading posture correction model, a reading posture correction suggestion for the teenager or child is obtained; the reading posture correction suggestion includes raising the head, straightening the chest, and standing one fist away from the table; The preset reading posture correction model is a model obtained after training with reading sample data and learning standard reading sitting posture, including: a model obtained after body shape training, body shape-posture recognition training, and posture-reading sitting posture suggestion training using the reading sample data; The preset posture-sitting posture correction module based on the current reading posture data and the preset reading posture correction model obtains the reading posture correction suggestions for the teenagers and children, including: inputting the current reading posture data into the preset posture-sitting posture correction module of the preset reading posture correction model to obtain the current reading sitting posture score of the teenagers and children; based on the preset posture-sitting posture correction module, obtaining the deviation between the current reading sitting posture score and the standard reading sitting posture; based on the deviation, determining the current distance between the teenagers and children and the book and the current line of sight of the teenagers and children when reading the book, and obtaining the reading posture correction suggestions for the teenagers and children based on the current distance and the current line of sight.

2. The method for correcting the reading posture of adolescents and children according to claim 1, characterized in that: The training process of the preset reading posture correction model includes: When determining that the reading posture data of the sample adolescents and children is represented based on nodes and degrees of freedom, obtaining the reading sample data of the sample adolescents and children and model constraints, wherein the model constraints are used to limit the rotation angle of the node to not exceed the limit of the human body; Based on the preset conditions of the model, the reading sample data is used to perform statistical learning on the body shapes of adolescents and children to obtain a preset body shape prediction module; Based on the preset body shape prediction module and the reading sample data, a body shape-posture recognition training for adolescents and children is performed to obtain a preset body shape-posture recognition module; Performing posture-sitting posture prediction training based on the preset body shape-posture recognition module and the reading sample data and comparing the deviation with the standard reading sitting posture to obtain a preset posture-sitting posture correction module; The preset reading posture correction model is determined to be a model including the preset body shape prediction module, the preset body shape-posture recognition module and the preset posture-sitting posture correction module.

3. The method for correcting the reading posture of adolescents and children according to claim 2, characterized in that: The learning process of the standard reading posture includes: Acquire reading sample label data carrying a sitting posture identifier, wherein the sitting posture identifier is used to indicate that the reading sitting posture of the corresponding sample adolescent child is normal; The reading sample label data is learned to obtain the standard reading sitting posture.

4. The method for correcting the reading posture of adolescents and children according to claim 2, characterized in that: The standard reading sitting posture includes standard reading posture data, and the learning process of the standard reading posture data includes: When the reading posture data of the sample adolescents and children are initially represented by d different nodes, it is determined whether the expression effects of the d nodes for the standard reading sitting posture meet the preset requirements; If the expression effect does not meet the preset requirement, d is adjusted to t; If the expression effects of t different nodes for the standard reading sitting posture meet the preset requirements, it is determined that the standard reading posture data of the sample adolescent children is represented by t different nodes, and the t different nodes are determined as standard reading posture data; wherein each of the nodes is represented by a posture with a preset number of degrees of freedom, and d and t are positive integers respectively.

5. The method for correcting the reading posture of adolescents and children according to claim 2, characterized in that: The obtaining of reading sample data of sample adolescent children includes: When the reading posture data of the sample adolescents and children include t different nodes and each of the nodes is represented by a posture with m different degrees of freedom, obtain t1 of the nodes with a focus on the head of the sample adolescents and children, obtain t2 of the nodes with a focus on the neck of the sample adolescents and children, and obtain t3 of the nodes with a focus on the spine of the sample adolescents and children; wherein t=t1+t2+t3, t1, t2, t3 and m are positive integers respectively.

6. A device for correcting the reading posture of young children, characterized in that: include: A body shape prediction unit, used for inputting the to-be-tested reading data of the adolescent child into a preset body shape prediction module of a preset reading posture correction model, obtaining a parameterized three-dimensional adolescent child human body model through a three-dimensional reconstruction technology, and obtaining the current body shape data of the adolescent child based on the parameterized three-dimensional adolescent child human body model; The reading data to be tested represents three-dimensional data of the current reading posture of the young child; A posture recognition unit, used for inputting the current body shape data and the reading data to be tested into a preset body shape-posture recognition module of the preset reading posture correction model to obtain the current reading posture data of the adolescent child; the current reading posture data includes a plurality of different nodes and each of the nodes is represented by a plurality of postures with different degrees of freedom; A posture correction unit, for obtaining reading posture correction suggestions for the adolescent child based on the current reading posture data and the preset posture-sitting posture correction module of the preset reading posture correction model; the reading posture correction suggestions include raising the head, straightening the chest, and leaving the table by one fist; The preset reading posture correction model is a model obtained after training with reading sample data and learning standard reading sitting posture, including: a model obtained after body shape training, body shape-posture recognition training, and posture-reading sitting posture suggestion training using the reading sample data; The preset posture-sitting posture correction module based on the current reading posture data and the preset reading posture correction model obtains the reading posture correction suggestions for the teenagers and children, including: inputting the current reading posture data into the preset posture-sitting posture correction module of the preset reading posture correction model to obtain the current reading sitting posture score of the teenagers and children; based on the preset posture-sitting posture correction module, obtaining the deviation between the current reading sitting posture score and the standard reading sitting posture; based on the deviation, determining the current distance between the teenagers and children and the book and the current line of sight of the teenagers and children when reading the book, and obtaining the reading posture correction suggestions for the teenagers and children based on the current distance and the current line of sight.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for correcting the reading posture of adolescents and children as described in any one of claims 1 to 5 is implemented.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for correcting the reading posture of adolescents and children as described in any one of claims 1 to 5 is implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for correcting the reading posture of adolescents and children as described in any one of claims 1 to 5 is implemented.

Images