Sitting posture detection method and system, and electronic device

Abstract

A sitting posture detection method and system, and an electronic device, which are used for constructing a three-dimensional sitting posture model of a user and comparing the three-dimensional sitting posture model with a standard sitting posture model, thereby improving the precision of detecting sitting postures. The method comprises: collecting a sitting posture image of a user, and constructing a three-dimensional sitting posture model of the user on the basis of the collected sitting posture image (100); and comparing the three-dimensional sitting posture model of the user with a preset standard sitting posture model, and detecting whether the sitting posture of the user is abnormal on the basis of a comparison result (101).

Description

Sitting posture detection method, system and electronic equipment

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of the People's Republic of China on January 2, 2024, with application number 202410004073.1 and invention name "A sitting posture detection method, system and electronic device", the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present disclosure relates to the field of image processing technology, and in particular to a sitting posture detection method, system and electronic equipment. Background Art

[0004] Electronic devices play a vital role in our daily lives and are indispensable companions. In modern society, we often spend extended periods of time using electronic devices such as computers, mobile phones, and tablets. However, improper posture and prolonged periods of inactivity can negatively impact our eyes. Improper sitting posture and close viewing distance can lead to eye strain. Staring at a screen for extended periods of time requires constant adjustment of focus, which can lead to eye muscle fatigue, resulting in soreness, blurry vision, and blurred vision.

[0005] Therefore, how to accurately detect sitting posture and thus improve users' bad sitting habits has become a technical problem that needs to be solved urgently. Summary of the Invention

[0006] The present disclosure provides a sitting posture detection method, system and electronic device for improving the accuracy of sitting posture detection by constructing a three-dimensional sitting posture model of the user and comparing the three-dimensional sitting posture model with a standard sitting posture model.

[0007] In a first aspect, an embodiment of the present disclosure provides a sitting posture detection method, the method comprising:

[0008] Collecting a user's sitting posture image, and constructing a three-dimensional sitting posture model of the user based on the collected sitting posture image;

[0009] The user's three-dimensional sitting posture model is compared with a pre-set standard sitting posture model, and whether the user's sitting posture is abnormal is detected based on the comparison result.

[0010] As an optional implementation manner, collecting the user's sitting posture image includes:

[0011] Capturing the user's sitting posture image by using a capture device placed directly opposite the user; or

[0012] The user's sitting posture image is collected by collecting devices arranged in different directions; wherein, the collecting devices in different directions include the collecting devices directly opposite the user, and the field of view of the collecting devices in different directions can cover the user's sitting posture from any angle.

[0013] As an optional implementation, comparing the three-dimensional sitting posture model of the user with a preset standard sitting posture model, and detecting whether the user's sitting posture is abnormal based on the comparison result, includes:

[0014] determining key parts in the user's three-dimensional sitting posture model and the standard sitting posture model, wherein the key parts include human body parts related to the sitting posture;

[0015] Compare the positions and angles of key parts in the three-dimensional sitting posture model and the standard sitting posture model, and detect whether the user's sitting posture is abnormal based on the comparison results.

[0016] As an optional implementation, the method further includes:

[0017] Determining the distance between the user and the display device, wherein the distance is used to determine the tilt state of the user's sitting posture;

[0018] Based on the comparison result and the distance, it is detected whether the user's sitting posture is abnormal.

[0019] As an optional implementation, the method further includes:

[0020] Determine the user's facial posture based on the user's three-dimensional sitting posture model and obtain the user's eye usage time;

[0021] Determine whether the user is overusing their eyes based on facial posture and eye usage duration.

[0022] As an optional implementation, the method further includes:

[0023] When it is determined that the user is in a state of excessive eye use, the display device is controlled to enter a rest mode or shut down, wherein the rest mode is used to prompt the user to perform at least one of eye exercises, eye rest, and sitting posture correction.

[0024] As an optional implementation, the method further includes:

[0025] When the user's sitting posture is detected to be abnormal according to the comparison result, abnormal sitting posture data is determined;

[0026] The user is guided to correct the sitting posture according to the abnormal sitting posture data.

[0027] As an optional implementation, when the user's sitting posture is detected to be abnormal according to the comparison result, after determining the abnormal sitting posture data, the method further includes:

[0028] The abnormal sitting posture data is stored, and according to the type of the abnormal sitting posture data, different types of abnormal sitting posture data within a preset period are counted.

[0029] As an optional implementation, the method further includes:

[0030] In response to the user's abnormal display instruction, the total number of different types of abnormal sitting postures and / or the total number of abnormal sitting postures corresponding to a unit time length in the preset period are displayed based on the statistical data of different types of abnormal sitting postures within the preset period.

[0031] As an optional implementation, the method further includes:

[0032] At least one of the user's three-dimensional sitting posture model, the standard sitting posture model, and the comparison result is displayed.

[0033] As an optional implementation, after displaying the three-dimensional sitting posture model and the standard sitting posture model of the user, the method further includes:

[0034] In response to a user's touch and slide operation on the standard sitting posture model, controlling the standard sitting posture model to rotate;

[0035] Compare the standard sitting posture model and the three-dimensional sitting posture model, and display the comparison results.

[0036] As an optional implementation, the method further includes:

[0037] In response to a single sitting posture adjustment instruction of the user, when it is detected that the user's sitting posture is abnormal, the user is guided to correct the sitting posture; when it is detected that the adjusted sitting posture is normal, the sitting posture correction for the user is terminated; or,

[0038] In response to the user's real-time sitting posture adjustment instruction, when it is detected that the user's sitting posture is abnormal, the user is guided to correct the sitting posture; when it is detected that the adjusted sitting posture is normal, the user's next sitting posture is continued to be detected.

[0039] As an optional implementation, the method further includes:

[0040] When it is detected that the user's sitting posture is abnormal and the duration of the abnormal sitting posture exceeds a threshold, the display device is controlled to enter at least one of the sitting posture correction mode, rest mode, and off mode, wherein the sitting posture correction mode is used to guide the user to correct the sitting posture.

[0041] In a second aspect, an embodiment of the present disclosure provides a sitting posture detection system, comprising at least one first device; the first device is configured to:

[0042] Collecting a user's sitting posture image and constructing a three-dimensional sitting posture model of the user based on the sitting posture image;

[0043] The user's three-dimensional sitting posture model is compared with a pre-set standard sitting posture model, and whether the user's sitting posture is abnormal is detected based on the comparison result.

[0044] As an optional embodiment, the system further includes at least one second device, and the first device and the second device are arranged in different positions;

[0045] The second device is used to collect a sitting posture image of the user and send the collected sitting posture image of the user to the first device, so as to instruct the first device to construct a three-dimensional sitting posture model of the user according to the sitting posture image.

[0046] As an optional implementation, the first device is arranged directly opposite the user.

[0047] As an optional implementation, the field of view of the first device and the second device can cover the user's sitting posture from any angle.

[0048] As an optional implementation manner, the first device is specifically configured to:

[0049] determining key parts in the user's three-dimensional sitting posture model and the standard sitting posture model, wherein the key parts include human body parts related to the sitting posture;

[0050] Compare the positions and angles of key parts in the three-dimensional sitting posture model and the standard sitting posture model, and detect whether the user's sitting posture is abnormal based on the comparison results.

[0051] As an optional implementation manner, the first device is further configured to:

[0052] Determining the distance between the user and the display device, wherein the distance is used to determine the tilt state of the user's sitting posture;

[0053] Based on the comparison result and the distance, it is detected whether the user's sitting posture is abnormal.

[0054] As an optional implementation manner, the first device is further configured to:

[0055] Determine the user's facial posture based on the user's three-dimensional sitting posture model and obtain the user's eye usage time;

[0056] Determine whether the user is overusing their eyes based on facial posture and eye usage duration.

[0057] As an optional implementation manner, the first device is further configured to:

[0058] When it is determined that the user is in a state of excessive eye use, the display device is controlled to enter a rest mode or shut down, wherein the rest mode is used to prompt the user to perform at least one of eye exercises, eye rest, and sitting posture correction.

[0059] As an optional implementation manner, the first device is further configured to:

[0060] When the user's sitting posture is detected to be abnormal according to the comparison result, abnormal sitting posture data is determined;

[0061] The user is guided to correct the sitting posture according to the abnormal sitting posture data.

[0062] As an optional implementation manner, when the user's sitting posture is detected to be abnormal according to the comparison result, after determining the abnormal sitting posture data, the first device is further configured to:

[0063] The abnormal sitting posture data is stored, and according to the type of the abnormal sitting posture data, different types of abnormal sitting posture data within a preset period are counted.

[0064] As an optional implementation manner, the first device is further configured to:

[0065] In response to the user's abnormal display instruction, the total number of different types of abnormal sitting postures and / or the total number of abnormal sitting postures corresponding to a unit time length in the preset period are displayed based on the statistical data of different types of abnormal sitting postures within the preset period.

[0066] As an optional implementation manner, the first device is further configured to:

[0067] At least one of the user's three-dimensional sitting posture model, the standard sitting posture model, and the comparison result is displayed.

[0068] As an optional implementation manner, after displaying the three-dimensional sitting posture model and the standard sitting posture model of the user, the first device is further configured to:

[0069] In response to a user's touch and slide operation on the standard sitting posture model, controlling the standard sitting posture model to rotate;

[0070] Compare the standard sitting posture model and the three-dimensional sitting posture model, and display the comparison results.

[0071] As an optional implementation manner, the first device is further configured to:

[0072] In response to a single sitting posture adjustment instruction of the user, when it is detected that the user's sitting posture is abnormal, the user is guided to correct the sitting posture; when it is detected that the adjusted sitting posture is normal, the sitting posture correction for the user is terminated; or,

[0073] In response to the user's real-time sitting posture adjustment instruction, when it is detected that the user's sitting posture is abnormal, the user is guided to correct the sitting posture; when it is detected that the adjusted sitting posture is normal, the user's next sitting posture is continued to be detected.

[0074] As an optional implementation manner, the first device is further configured to:

[0075] When it is detected that the user's sitting posture is abnormal and the duration of the abnormal sitting posture exceeds a threshold, the display device is controlled to enter at least one of the sitting posture correction mode, rest mode, and off mode, wherein the sitting posture correction mode is used to guide the user to correct the sitting posture.

[0076] In a third aspect, an embodiment of the present disclosure further provides an electronic device, including a processor and a memory, wherein the memory is configured to store a program executable by the processor, and the processor is configured to read the program in the memory and perform the following steps:

[0077] Collecting a user's sitting posture image, and constructing a three-dimensional sitting posture model of the user based on the collected sitting posture image;

[0078] The user's three-dimensional sitting posture model is compared with a pre-set standard sitting posture model, and whether the user's sitting posture is abnormal is detected based on the comparison result.

[0079] As an optional implementation, the processor is specifically configured to execute:

[0080] Capturing the user's sitting posture image by using a capture device placed directly opposite the user; or

[0081] The user's sitting posture image is collected by collecting devices arranged in different directions; wherein, the collecting devices in different directions include the collecting devices directly opposite the user, and the field of view of the collecting devices in different directions can cover the user's sitting posture from any angle.

[0082] As an optional implementation, the processor is specifically configured to execute:

[0083] determining key parts in the user's three-dimensional sitting posture model and the standard sitting posture model, wherein the key parts include human body parts related to the sitting posture;

[0084] Compare the positions and angles of key parts in the three-dimensional sitting posture model and the standard sitting posture model, and detect whether the user's sitting posture is abnormal based on the comparison results.

[0085] As an optional implementation manner, the processor is further configured to execute:

[0086] Determining the distance between the user and the display device, wherein the distance is used to determine the tilt state of the user's sitting posture;

[0087] Based on the comparison result and the distance, it is detected whether the user's sitting posture is abnormal.

[0088] As an optional implementation manner, the processor is further configured to execute:

[0089] Determine the user's facial posture based on the user's three-dimensional sitting posture model and obtain the user's eye usage time;

[0090] Determine whether the user is overusing their eyes based on facial posture and eye usage duration.

[0091] As an optional implementation manner, the processor is further configured to execute:

[0092] When it is determined that the user is in a state of excessive eye use, the display device is controlled to enter a rest mode or shut down, wherein the rest mode is used to prompt the user to perform at least one of eye exercises, eye rest, and sitting posture correction.

[0093] As an optional implementation manner, the processor is further configured to execute:

[0094] When the user's sitting posture is detected to be abnormal according to the comparison result, abnormal sitting posture data is determined;

[0095] The user is guided to correct the sitting posture according to the abnormal sitting posture data.

[0096] As an optional implementation, when the user's sitting posture is detected to be abnormal according to the comparison result, after determining the abnormal sitting posture data, the processor is further configured to execute:

[0097] The abnormal sitting posture data is stored, and according to the type of the abnormal sitting posture data, different types of abnormal sitting posture data within a preset period are counted.

[0098] As an optional implementation manner, the processor is further configured to execute:

[0099] In response to the user's abnormal display instruction, the total number of different types of abnormal sitting postures and / or the total number of abnormal sitting postures corresponding to a unit time length in the preset period are displayed based on the statistical data of different types of abnormal sitting postures within the preset period.

[0100] As an optional implementation manner, the processor is further configured to execute:

[0101] At least one of the user's three-dimensional sitting posture model, the standard sitting posture model, and the comparison result is displayed.

[0102] As an optional implementation, after displaying the three-dimensional sitting posture model and the standard sitting posture model of the user, the processor is further configured to execute:

[0103] In response to a user's touch and slide operation on the standard sitting posture model, controlling the standard sitting posture model to rotate;

[0104] Compare the standard sitting posture model and the three-dimensional sitting posture model, and display the comparison results.

[0105] As an optional implementation manner, the processor is further configured to execute:

[0106] In response to a single sitting posture adjustment instruction of the user, when it is detected that the user's sitting posture is abnormal, the user is guided to correct the sitting posture; when it is detected that the adjusted sitting posture is normal, the sitting posture correction for the user is terminated; or,

[0107] In response to the user's real-time sitting posture adjustment instruction, when it is detected that the user's sitting posture is abnormal, the user is guided to correct the sitting posture; when it is detected that the adjusted sitting posture is normal, the user's next sitting posture is continued to be detected.

[0108] As an optional implementation manner, the processor is further configured to execute:

[0109] When it is detected that the user's sitting posture is abnormal and the duration of the abnormal sitting posture exceeds a threshold, the display device is controlled to enter at least one of the sitting posture correction mode, rest mode, and off mode, wherein the sitting posture correction mode is used to guide the user to correct the sitting posture.

[0110] In a fourth aspect, an embodiment of the present disclosure further provides a sitting posture detection device, comprising:

[0111] A model building unit is used to collect a user's sitting posture image and build a three-dimensional sitting posture model of the user based on the collected sitting posture image;

[0112] The sitting posture detection unit is used to compare the user's three-dimensional sitting posture model with a pre-set standard sitting posture model, and detect whether the user's sitting posture is abnormal based on the comparison result.

[0113] As an optional implementation manner, the model building unit is specifically used to:

[0114] Capturing the user's sitting posture image by using a capture device placed directly opposite the user; or

[0115] The user's sitting posture image is collected by collecting devices arranged in different directions; wherein, the collecting devices in different directions include the collecting devices directly opposite the user, and the field of view of the collecting devices in different directions can cover the user's sitting posture from any angle.

[0116] As an optional implementation manner, the sitting posture detection unit is specifically used to:

[0117] determining key parts in the user's three-dimensional sitting posture model and the standard sitting posture model, wherein the key parts include human body parts related to the sitting posture;

[0118] Compare the positions and angles of key parts in the three-dimensional sitting posture model and the standard sitting posture model, and detect whether the user's sitting posture is abnormal based on the comparison results.

[0119] As an optional implementation manner, the sitting posture detection unit is further configured to:

[0120] Determining the distance between the user and the display device, wherein the distance is used to determine the tilt state of the user's sitting posture;

[0121] Based on the comparison result and the distance, it is detected whether the user's sitting posture is abnormal.

[0122] As an optional implementation manner, the sitting posture detection unit is further configured to:

[0123] Determine the user's facial posture based on the user's three-dimensional sitting posture model and obtain the user's eye usage time;

[0124] Determine whether the user is overusing their eyes based on facial posture and eye usage duration.

[0125] As an optional implementation manner, the sitting posture detection unit is further configured to:

[0126] When it is determined that the user is in a state of excessive eye use, the display device is controlled to enter a rest mode or shut down, wherein the rest mode is used to prompt the user to perform at least one of eye exercises, eye rest, and sitting posture correction.

[0127] As an optional implementation manner, the sitting posture detection unit is further configured to:

[0128] When the user's sitting posture is detected to be abnormal according to the comparison result, abnormal sitting posture data is determined;

[0129] The user is guided to correct the sitting posture according to the abnormal sitting posture data.

[0130] As an optional embodiment, when the user's sitting posture is detected to be abnormal according to the comparison result, after determining the abnormal sitting posture data, the sitting posture detection unit is further configured to:

[0131] The abnormal sitting posture data is stored, and according to the type of the abnormal sitting posture data, different types of abnormal sitting posture data within a preset period are counted.

[0132] As an optional implementation manner, the sitting posture detection unit is further configured to:

[0133] In response to the user's abnormal display instruction, the total number of different types of abnormal sitting postures and / or the total number of abnormal sitting postures corresponding to a unit time length in the preset period are displayed based on the statistical data of different types of abnormal sitting postures within the preset period.

[0134] As an optional implementation manner, the sitting posture detection unit is further configured to:

[0135] At least one of the user's three-dimensional sitting posture model, the standard sitting posture model, and the comparison result is displayed.

[0136] As an optional implementation, after displaying the user's three-dimensional sitting posture model and the standard sitting posture model, the sitting posture detection unit is further configured to:

[0137] In response to a user's touch and slide operation on the standard sitting posture model, controlling the standard sitting posture model to rotate;

[0138] Compare the standard sitting posture model and the three-dimensional sitting posture model, and display the comparison results.

[0139] As an optional implementation manner, the sitting posture detection unit is further configured to:

[0140] In response to a single sitting posture adjustment instruction of the user, when it is detected that the user's sitting posture is abnormal, the user is guided to correct the sitting posture; when it is detected that the adjusted sitting posture is normal, the sitting posture correction for the user is terminated; or,

[0141] In response to the user's real-time sitting posture adjustment instruction, when it is detected that the user's sitting posture is abnormal, the user is guided to correct the sitting posture; when it is detected that the adjusted sitting posture is normal, the user's next sitting posture is continued to be detected.

[0142] As an optional implementation manner, the sitting posture detection unit is further configured to:

[0143] When it is detected that the user's sitting posture is abnormal and the duration of the abnormal sitting posture exceeds a threshold, the display device is controlled to enter at least one of the sitting posture correction mode, rest mode, and off mode, wherein the sitting posture correction mode is used to guide the user to correct the sitting posture.

[0144] In a fifth aspect, an embodiment of the present disclosure further provides a computer storage medium on which a computer program is stored, which, when executed by a processor, is used to implement the steps of the method described in any one of the above-mentioned first aspects.

[0145] In a sixth aspect, the present disclosure provides a computer program product, comprising: a computer program code, which, when executed on a computer, enables the computer to execute any one of the methods described in the first aspect.

[0146] These and other aspects of the present disclosure will become more readily apparent from the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0147] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0148] FIG1 is a flowchart of an implementation method of a sitting posture detection method provided by an embodiment of the present disclosure;

[0149] FIG2 is a schematic diagram of an auxiliary device provided by an embodiment of the present disclosure;

[0150] 3A-3B are diagrams of a sitting posture correction reminder interface provided by an embodiment of the present disclosure;

[0151] FIG4 is a diagram of a sitting posture comparison interface provided by an embodiment of the present disclosure;

[0152] FIG5 is a diagram showing a sliding operation display interface of a standard sitting posture model provided by an embodiment of the present disclosure;

[0153] FIG6 is a diagram of a real-time sitting posture detection interface provided by an embodiment of the present disclosure;

[0154] FIG7 is a schematic diagram of the architecture of a sitting posture detection application system provided by an embodiment of the present disclosure;

[0155] FIG8 is a schematic diagram of a sitting posture detection system provided by an embodiment of the present disclosure;

[0156] FIG9 is a schematic diagram of another sitting posture detection system provided by an embodiment of the present disclosure;

[0157] FIG10 is a schematic diagram of an electronic device provided by an embodiment of the present disclosure;

[0158] FIG11 is a schematic diagram of a sitting posture detection device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0159] To make the objectives, technical solutions, and advantages of the present disclosure more clear, the present disclosure will be further described in detail below with reference to the accompanying drawings. It is apparent that the embodiments described are only a portion of the embodiments of the present disclosure, rather than all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present disclosure without creative effort are intended to fall within the scope of protection of the present disclosure.

[0160] In the embodiments of the present disclosure, the term "and / or" describes the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0161] The application scenarios described in the embodiments of the present disclosure are intended to more clearly illustrate the technical solutions of the embodiments of the present disclosure and do not constitute a limitation on the technical solutions provided by the embodiments of the present disclosure. Persons skilled in the art will appreciate that, as new application scenarios emerge, the technical solutions provided by the embodiments of the present disclosure will also be applicable to similar technical problems. In the description of the present disclosure, unless otherwise specified, "multiple" means two or more.

[0162] Before introducing the sitting posture detection method provided by the embodiment of the present disclosure, for ease of understanding, the technical background of the embodiment of the present disclosure is first introduced in detail below.

[0163] Electronic products occupy a very important position in our daily lives and are indispensable companions in life. In modern society, we often need to use electronic devices such as computers, mobile phones and tablets for long periods of time. However, incorrect sitting posture and sedentary behavior can have a negative impact on our eyes. Incorrect sitting posture and too close a viewing distance can lead to visual fatigue. Staring at the screen for a long time requires the eyes to constantly adjust their focus, which can easily lead to eye muscle fatigue, sore eyes, blurred vision and other problems. Nowadays, electronic products have entered all aspects of children's and young people's learning and life, especially with the increasing popularity of online learning. Whether children and young people will become nearsighted or hunchbacked when learning online has also become a concern for parents. Therefore, how to accurately detect sitting posture and improve users' bad sitting habits has become a technical problem that needs to be solved urgently.

[0164] Currently, the sitting posture detection solutions on the market are generally divided into the following two methods:

[0165] The first method uses a camera + sensor method to calculate the distance between the user, the table, and the device, and detect the sitting posture based on the distance.

[0166] The second method is to collect facial portraits and use image information models to detect and analyze sitting posture, or synchronize with the cloud to improve accuracy.

[0167] However, the accuracy of sitting posture detection performed in the above-mentioned method is not high.

[0168] Based on this, the present disclosure provides a sitting posture detection method, which improves the accuracy of abnormal sitting posture detection by constructing a three-dimensional sitting posture model of the user and comparing the three-dimensional sitting posture model of the user with a pre-set standard sitting posture model.

[0169] As shown in FIG1 , the implementation process of a sitting posture detection method provided in this embodiment is as follows:

[0170] Step 100: Collect a user's sitting posture image, and construct a three-dimensional sitting posture model of the user based on the collected sitting posture image;

[0171] In some embodiments, the user's sitting posture image is collected by any of the following methods:

[0172] Method 1a: Capture the user's sitting posture image through a capture device placed directly opposite the user;

[0173] During implementation, the acquisition device is integrated into the display device directly opposite the user, so that when the user watches the content displayed on the display device, the user's front image can be acquired through the acquisition device integrated on the display device, such as a camera, etc., wherein the front image of the user acquired by the acquisition device includes the front image of the user's upper body.

[0174] Optionally, the user's sitting posture image captured in this manner is a frontal image of the user. The captured frontal image is used to construct a three-dimensional sitting posture model of the user, wherein in the process of constructing the three-dimensional sitting posture model based on the frontal image, the user's side and back data can be filled in through an algorithm.

[0175] Method 1b: Capture the user's sitting posture image by means of acquisition devices arranged at different positions; wherein, the acquisition devices at different positions include the acquisition devices directly opposite the user, and the field of view of the acquisition devices at different positions can cover the user's sitting posture from any angle.

[0176] During implementation, multiple acquisition devices may be set up in different locations, for example, one acquisition device directly opposite the user and one acquisition device on each side of the user's seat. Optionally, the angle between the acquisition devices on both sides and the acquisition device directly opposite may be approximately 120 degrees. The acquisition device directly opposite the user may be integrated into a display device that faces the user. This allows the user to use the acquisition device on the display device, such as a camera, to capture a frontal image of the user while viewing the display device. The acquisition devices on both sides capture side images of the user's sitting posture, such as a left-side sitting posture image and a right-side sitting posture image. It should be noted that the sitting posture image in this embodiment includes the user's entire sitting posture.

[0177] Optionally, the user's sitting posture image collected in this manner includes a frontal image and a side full-body sitting posture image of the user. The collected frontal image and side full-body sitting posture image are used to construct a three-dimensional sitting posture model of the user.

[0178] Step 101: Compare the user's three-dimensional sitting posture model with a preset standard sitting posture model, and detect whether the user's sitting posture is abnormal based on the comparison result.

[0179] Optionally, the standard sitting posture model in this embodiment can be a pre-set fixed sitting posture model, or can be constructed based on body data input by the user. The body data includes but is not limited to information such as height, weight, and shoulder width. The standard sitting posture model constructed using body data can more closely match the user's actual sitting posture, and when comparing the three-dimensional sitting posture model with the standard sitting posture model, the accuracy of sitting posture detection can be improved.

[0180] During implementation, when the standard sitting posture model for setting is not detected, a default standard sitting posture model (i.e., a pre-set fixed sitting posture model) is provided. Users can also set the standard sitting posture model by themselves. After the setting is successful, the display interface will give priority to displaying the standard sitting posture model set by the user, and when performing sitting posture comparison, the self-set standard sitting posture model will be used for sitting posture comparison and adjustment.

[0181] In some embodiments, the user's three-dimensional sitting posture model is compared with a pre-set standard sitting posture model in the following manner:

[0182] determining key parts in the user's three-dimensional sitting posture model and the standard sitting posture model, wherein the key parts include human body parts related to the sitting posture;

[0183] Compare the positions and angles of key parts in the 3D sitting model with those in the standard sitting model, and detect whether the user's sitting posture is abnormal based on the comparison results. The angles include rotation angle and tilt angle.

[0184] Optionally, key parts include but are not limited to the head, shoulders, upper body, legs, waist, etc.

[0185] During implementation, when the positions and angles of key parts in the 3D sitting model and the standard sitting model are identical, the user's sitting posture is determined to be normal. Alternatively, when the positions of key parts in the 3D sitting model fall within the preset position range corresponding to the key parts in the standard sitting model, and the angles fall within the preset angle range corresponding to the key parts in the standard sitting model, the user's sitting posture is determined to be normal. When the positions of key parts in the 3D sitting model exceed the preset position range, or the angles exceed the preset angle range, the user's sitting posture is determined to be abnormal.

[0186] In some embodiments, the present embodiment may further detect the distance between the user and the display device, and determine whether the user's sitting posture is abnormal by:

[0187] Determine the distance between the user and the display device, the distance being used to determine the tilt state of the user's sitting posture; and detect whether the user's sitting posture is abnormal based on the comparison result and the distance.

[0188] During implementation, the distance can be used to determine whether the user is too close to the display screen, and then determine whether the user's sitting posture is abnormal. For example, whether the distance exceeds the set distance range and the comparison results can be combined to determine whether the user's sitting posture is tilted.

[0189] Optionally, the distance from the user to the display device can be determined by a distance acquisition device, wherein the distance acquisition device includes but is not limited to distance measuring devices such as TOF (Time-of-Flight, laser pulse), so as to obtain the distance from the user to the display device. Optionally, the acquisition device includes but is not limited to a camera, a camera, etc. In implementation, the TOF and the front camera can be integrated on the display device, so that when the user watches the content displayed on the display device, the front camera can be used to capture the user's sitting image, and the TOF can be used to capture the distance from the user to the display device. Among them, TOF is an imaging technology used to form a set of distance depth data through laser pulses, thereby obtaining a three-dimensional 3D model. The front camera is an ordinary color camera, such as an RGB camera. Optionally, the display device in this embodiment can allow the acquisition device and TOF to collect data in the application background.

[0190] During implementation, the main device in this disclosure is equipped with a customized front-facing dual camera, a time-of-flight (TOF), and auxiliary devices to generate a 3D sitting posture data model of a person. The current user's sitting posture status is determined by comparing the current user's 3D sitting posture model with a standard sitting posture model. The main device refers to a capture device facing the user, which can be a display device with an integrated camera. The auxiliary device is located to the side of the user's seat and can be a capture device such as a camera. As shown in Figure 2, this embodiment provides a schematic diagram of an auxiliary device. Optionally, the main device in this disclosure is equipped with a customized front-facing dual camera, and auxiliary devices to generate a 3D sitting posture model of a person. The current user's sitting posture status is determined by comparing the current user's 3D sitting posture model with a standard sitting posture model. Compared to sensor ranging, the present disclosure is more intelligent through front-facing dual camera ranging and person recognition. Compared to facial image recognition, the present disclosure uses a 3D sitting posture model of a person to simultaneously detect sitting posture information such as the head and body, providing richer and more vivid information. By simultaneously detecting the body, head, table, and chair, distance calculation and sitting posture detection have higher accuracy.

[0191] In some embodiments, this embodiment can also determine the user's eye status. The specific steps are as follows:

[0192] Determine the user's facial posture based on the user's three-dimensional sitting posture model and obtain the user's eye usage time; based on the facial posture and eye usage time, determine whether the user is in a state of excessive eye use.

[0193] In practice, facial posture can be derived from the eye position and angle information in the 3D sitting posture model to determine whether the user is experiencing eye fatigue. Furthermore, the duration of eye use can be combined to determine whether the user is experiencing eye overuse. The duration of eye use can be determined based on the length of time the user has been sitting.

[0194] In some embodiments, when it is determined that the user is overusing their eyes, the display device is controlled to enter a rest mode or shut down. The rest mode prompts the user to perform at least one of eye exercises, eye rest, or posture correction. When the user determines to perform posture correction, the display device is controlled to enter a sitting correction mode to begin posture correction.

[0195] In practice, the user's eye usage time can be controlled through methods such as function locks and setting specific modes. Users can also be prompted to perform eye exercises or rest their eyes through voice, images, and videos. For example, a video could prompt the user to perform eye exercises. If the user is detected to be experiencing eye fatigue or continuous eye use exceeding a threshold, the system can force the user to enter rest mode to correct their sitting posture.

[0196] In some embodiments, this embodiment further provides a method for correcting sitting posture, and the specific implementation steps are as follows:

[0197] When it is detected that the user's sitting posture is abnormal according to the comparison result, abnormal sitting posture data is determined; and the user is guided to correct the sitting posture according to the abnormal sitting posture data.

[0198] Optionally, this embodiment can guide the user to correct their sitting posture through at least one of video, image, and voice.

[0199] In some embodiments, when the user's sitting posture is detected to be abnormal according to the comparison results, after determining the abnormal sitting posture data, the abnormal sitting posture data can be stored, and according to the type of the abnormal sitting posture data, different types of abnormal sitting posture data within a preset period can be counted.

[0200] During implementation, abnormal sitting posture data during the sitting posture correction process is not counted into the data storage system, that is, it is not stored and statistics of abnormal sitting posture are not performed.

[0201] Optionally, in response to the user's abnormal display instruction, the total number of different types of abnormal sitting postures and / or the total number of abnormal sitting postures corresponding to a unit time length within the preset period are displayed based on the statistical data of different types of abnormal sitting postures within the preset period.

[0202] As shown in Figures 3A-3B, this embodiment provides a sitting posture correction reminder interface. This interface displays the total number of abnormal sitting postures per unit time within a preset period in the form of charts, text, etc. When a user clicks on the sitting posture types with the highest total number of abnormal sitting postures in this reminder interface, they will enter the sitting posture correction interface to compare their posture corrections and improve their sitting posture.

[0203] In practice, the preset period may be one day, one week, one month, etc., and the unit time length in the preset period includes every day in a week, every hour in a day, every week in a month, etc. This embodiment does not impose too many limitations on this.

[0204] In some embodiments, this embodiment may further display at least one of the user's three-dimensional sitting posture model, the standard sitting posture model, and the comparison result.

[0205] Optionally, this embodiment provides multiple sitting posture interface diagrams for posture comparison, with both pictures and text to assist in understanding the correct sitting posture. The correction reminder interface is used to let users understand the type of abnormal sitting posture, so that they can pay targeted attention and make adjustments. It can also be used to understand whether the sitting posture habit has improved or deteriorated based on the trend. Reminders and suggestions will be given in a timely manner for the type of abnormal sitting posture that has been corrected. In practice, as shown in Figure 4, this embodiment provides a sitting posture comparison interface diagram. By displaying a three-dimensional sitting posture model, a standard sitting posture model, and the comparison results, the user can more clearly understand whether the current sitting posture is abnormal and how to adjust the current abnormal sitting posture.

[0206] Optionally, the comparison results may be displayed or played in the form of text, images, videos, voice, etc., which is not limited in this embodiment.

[0207] In some embodiments, after displaying the user's three-dimensional sitting posture model and the standard sitting posture model, in response to the user's touch and slide operation on the standard sitting posture model, the standard sitting posture model is controlled to rotate; the standard sitting posture model and the three-dimensional sitting posture model are compared, and the comparison result is displayed.

[0208] During implementation, when adjusting the sitting posture, the user can manually rotate the standard sitting posture model to view the comparison results of the standard sitting posture model and the three-dimensional sitting posture model in 360 degrees. As shown in Figure 5, a sliding operation display interface diagram of a standard sitting posture model is provided, and the sliding trajectory from the starting point to the end point is defined as a rotation cycle. The standard sitting posture model can rotate 360 ​​degrees in each rotation cycle. The angle of the standard sitting posture model within a rotation cycle is calculated according to the user's sliding distance, and the sitting posture comparison results of the standard sitting posture model and the three-dimensional sitting posture model at this angle are obtained in real time, wherein the comparison results include the three-dimensional images corresponding to the two models at this angle, abnormal sitting posture data, etc. The content of the display interface is updated by the three-dimensional images and abnormal sitting posture data of the rotated standard sitting posture model and the three-dimensional sitting posture model. Abnormal sitting posture data and correction suggestions can also be synchronously broadcast through the voice system. The present disclosure improves novelty and fun through the 360-degree rotation correction interactive design.

[0209] Optionally, when the user manually rotates the standard sitting posture model, the three-dimensional sitting posture model can be rotated synchronously according to the angle, so that the comparison result can be displayed in the form of an image, which is more three-dimensional and provides a better experience.

[0210] In some embodiments, when a user is rotating, the user's angle is calculated, and the corresponding 3D sitting posture model is compared with a standard sitting posture model to obtain a comparison result. Based on the comparison result, whether the user's sitting posture is abnormal can be detected. In implementation, during the user's rotation, the standard sitting posture model displayed on the display device can also be rotated to the corresponding angle, making the comparison of the two models more intuitive.

[0211] During implementation, when a user rotates in a swivel chair, a 3D sitting posture model is generated by capturing the user's sitting posture image in real time. The angle of the 3D sitting posture model is calculated, for example, by taking the front of the 3D sitting posture model as the starting point for model rotation. The 3D sitting posture model and the standard comparison model at that angle are then compared in real time. The comparison results include the corresponding 3D images of the two models at that angle, as well as data on abnormal sitting postures. The displayed interface content is updated based on the comparison results. Abnormal sitting posture information and correction suggestions can also be simultaneously broadcast.

[0212] In some embodiments, when an abnormal sitting posture is detected and the duration of the abnormal sitting posture exceeds a threshold, the display device is controlled to enter at least one of a sitting posture correction mode, a rest mode, or a shutdown mode. The sitting posture correction mode is used to guide the user to correct their sitting posture. Optionally, in the sitting posture correction mode, the user can only perform sitting posture correction.

[0213] During implementation, the judgment can also be made in combination with the eye usage status. For example, when the user has been in an incorrect sitting posture, has eye fatigue, or has been using the eyes for more than 60 minutes continuously, the user will be forced to correct the sitting posture or turn off the device to achieve the effect of sitting posture correction and protecting eyesight.

[0214] It should be noted that the sitting posture detection method provided in this embodiment can be implemented in the form of an application (APP) and installed in a display device. When a user uses the display device, the sitting posture detection application on the display device is activated to capture a sitting posture image of the user. Based on the captured sitting posture image, a three-dimensional sitting posture model of the user is constructed. The three-dimensional sitting posture model of the user is compared with a pre-set standard sitting posture model, and the comparison result is used to detect whether the user's sitting posture is abnormal. Further, when an abnormal sitting posture is detected, the user is assisted in correcting the sitting posture.

[0215] In some embodiments, this embodiment further provides any one or more of the following sitting posture correction modes:

[0216] Mode 1: Single sitting posture correction.

[0217] In response to the user's single sitting posture adjustment instruction, when it is detected that the user's sitting posture is abnormal, the user is guided to correct the sitting posture; when it is detected that the adjusted sitting posture is normal, the sitting posture correction for the user is ended.

[0218] During implementation, when a user first starts the display device and enters the main interface, an image of the user's sitting posture is captured. Based on the captured image, a 3D sitting posture model of the user is constructed. The 3D sitting posture model of the user is compared with a pre-set standard sitting posture model, and the comparison result is used to detect whether the user's sitting posture is abnormal. If an abnormal sitting posture is detected, the user is guided to correct the sitting posture. The 3D sitting posture model of the user's sitting posture during the posture correction process is continuously constructed and compared with the standard sitting posture model. When the adjusted sitting posture is detected to be normal, the posture correction process for the user is terminated. At this point, the user can automatically exit the posture correction application interface when entering the next application interface, and can then use the display device normally.

[0219] Mode 2: Real-time sitting posture correction.

[0220] In response to the user's real-time sitting posture adjustment instruction, when it is detected that the user's sitting posture is abnormal, the user is guided to correct the sitting posture; when it is detected that the adjusted sitting posture is normal, the user's next sitting posture is continued to be detected.

[0221] During implementation, users can activate the sitting posture correction function. This function, regardless of the user's current application interface, can capture the user's sitting posture image in real time in the background. Based on the captured sitting posture image, a 3D sitting posture model of the user is constructed. The 3D sitting posture model of the user is compared with a pre-set standard sitting posture model. Based on the comparison results, the user's sitting posture is detected to be abnormal. If an abnormal sitting posture is detected, the user is guided to correct the sitting posture. This disclosure can detect sitting posture in real time and provide sitting posture correction training, continuously improving the user's sitting habits.

[0222] As shown in FIG6 , a real-time sitting posture detection interface diagram is provided. At this time, a floating window (sitting posture detection application) is displayed at the top of the display interface, so that the user can feel that the sitting posture detection function can be used normally, and a prompt message of abnormal sitting posture is displayed. Optionally, Android smart devices can add a floating window through WindowManager. During implementation, in the correction mode, the user's sitting posture image is collected in real time, and a three-dimensional sitting posture model of the user is constructed based on the collected sitting posture image. The three-dimensional sitting posture model of the user is compared with the pre-set standard sitting posture model. According to the comparison result, it is detected whether the user's sitting posture is abnormal, and the abnormal sitting posture data and the length of time of eye use are recorded. The user's expression is analyzed to determine whether there is eye fatigue; the abnormal sitting posture data and eye use data are saved; the display interface is updated according to the abnormal sitting posture data, and the wrong sitting posture information and prompt suggestions are broadcast. For example, prompts can be given by applying pop-up windows. Application pop-up windows include but are not limited to: Toast prompt box, Dialog dialog box, Actionbar function box, Snackbar prompt dialog box or one or more. For example, a Toast prompt box is used for prompting. The Toast prompt box is a non-modal pop-up window that pops up a small message as a reminder or message feedback. It is generally used to display operation results or changes in application status.

[0223] This disclosure uses an artificial intelligence algorithm to create a three-dimensional sitting model of the user and a standard sitting model. By comparing the two models, it detects eye use and sitting posture, identifies unhealthy eye use and sitting habits, and corrects them through scientific interface reminders and auxiliary design, helping users to use their eyes healthily and develop good sitting habits. When the device detects unhealthy eye use or sitting posture, the display interface will give a real-time reminder. If the reminder exceeds the set rules, the interface will be restored to normal use after the user makes the correct adjustments.

[0224] As shown in FIG7 , the present disclosure provides a schematic diagram of the architecture of a sitting posture detection application system, which includes an image acquisition system, a timer system, a data analysis system, a data storage system, a display system, a voice system, and a correction training system.

[0225] The image acquisition system captures image information using an acquisition device, such as a device camera. The image acquisition system includes a primary device camera and other auxiliary device cameras. The timer system records usage time and other information. The timer system is primarily implemented through Android scheduled tasks, such as Handler (a thread-to-thread communication mechanism). The data analysis system analyzes images captured by the image acquisition system and records whether sitting posture or eye use is correct. The data analysis system primarily utilizes AI facial recognition, image and video data modeling, such as model synthesis using FFmpeg (an open-source computer program that can record, convert, and stream digital audio and video), and 3D model recognition. The data storage system records data on incorrect sitting posture or eye use, such as location, frequency, cause, time, and correction suggestions. The display system is responsible for the device interface display. The voice system is used to announce reminders or the correction process and receive user voice commands. The voice system uses a player such as MediaPlayer for broadcasting. The correction training system is used for self-developed activity designs, such as providing correction training for various abnormal sitting postures that have been observed frequently recently. This system analyzes the user's sitting posture and eye use in three dimensions, records incorrect posture and eye use data, and then prompts the user to correct their sitting posture and use their eyes correctly, thereby correcting their sitting posture and protecting their eyesight. The data storage system primarily uses the ROOM open source framework for database operations, and stores data including abnormal sitting posture type, date, number of times, total number, duration of eye use, and type of eye fatigue.

[0226] This application system consists of a master device and 0 to N auxiliary devices. The master device is a common intelligent display device with a camera, including smartphones, tablets, and computers. The auxiliary devices are data acquisition devices equipped with cameras, optionally with audio capabilities. The image acquisition system includes the master device camera and the auxiliary device camera functions. The master device is used to capture a frontal image of the user, including the upper half. The auxiliary devices are used to capture a side view of the user in a sitting position, including the entire sitting position and images of the chair, table, and other scenes.

[0227] The application system can display a three-dimensional sitting posture comparison display interface on the main device, provide 360-degree rotation interaction for sitting posture comparison, and use pictures and texts to assist in understanding the correct sitting posture; provide voice broadcasts to remind users how to adjust their sitting posture at any time; provide fatigue detection to remind users to take proper rest to protect their eyesight. Eye protection activities, eye protection reminders and eye protection mode interaction designs can also be provided. Eye protection activities include: eye exercises, screen saver function (entering the screen saver function), eye protection rewards and other activities. Eye protection reminders include daily sitting posture correction prompts and weekly sitting posture correction prompts, eye reminders and suggestions, etc. Eye protection modes include dark mode, paper-like mode, etc. In addition, the front camera equipped with the main device of the present disclosure can also be used to capture images and the distance between the user and the display device, and the display device allows the application background to collect sitting images, such as TOF+RGB front dual cameras.

[0228] The application uses a default fixed standard sitting posture model as the standard comparison model by default, and also supports the creation of user-defined standard comparison models. The standard sitting posture model is packaged with several image resources for a 360-degree display of sitting posture. When correcting sitting posture, users can rotate the standard sitting posture model in place by touching and sliding the display device screen to view and correct their posture 360 ​​degrees. Users can also use auxiliary devices to display their sitting posture in real time in 360 degrees.

[0229] The application system can display a standard sitting posture model, a three-dimensional sitting posture model of the user, and abnormal sitting posture data reminders, such as the number of daily and weekly sitting posture correction reminders. When the user enters the sitting posture correction interface to adjust their sitting posture, the application system activates the main device camera, and the image acquisition system begins to collect the user's sitting posture images and transmits the sitting posture images to the data analysis system. The data analysis system uses the received sitting posture images to create a three-dimensional sitting posture model of the user. By comparing the three-dimensional sitting posture model with the standard sitting posture model, the system obtains the user's abnormal sitting posture data and prompts, such as: head straight, shoulders straight, body straight, distance, etc., and transmits the three-dimensional sitting posture model, abnormal sitting posture data, and prompts and suggestions to the downstream in real time. The system records the duration of abnormal sitting posture and the duration of abnormal eye use. After receiving the abnormal sitting posture data and prompts, the data storage system promptly updates the database information. After receiving the abnormal sitting posture data and prompts, the display system synchronously refreshes the three-dimensional posture model and abnormal sitting posture prompts on the display interface. The voice system synchronously broadcasts the abnormal sitting posture data and correction suggestions.

[0230] Compared to ordinary cameras, TOF cameras can collect data on the distance between the user and the device. The image acquisition system sends the distance and sitting posture image to the data analysis system. The data analysis system creates a real-time three-dimensional sitting posture model of the user based on the distance and sitting posture image, and then compares it with the standard sitting posture model. The user's abnormal sitting posture type and improvement suggestions are obtained in real time. Then they are transmitted to the data storage system and display system. The data analysis system performs comparative analysis based on the three-dimensional recognition algorithm of deep learning. Auxiliary devices synchronously collect the user's sitting posture image and transmit it to the data analysis system. Among them, 1 to 2 auxiliary devices are optimal, which can not only ensure 360-degree image information without blind spots but also save costs. When in use, users can place the auxiliary devices as needed. It is recommended to place them at 120 degrees with the main device.

[0231] This embodiment uses a main device and auxiliary device to jointly collect, analyze, and process image data. By creating a 3D sitting posture model of the user, the current 3D sitting posture model is compared with a standard sitting posture model in real time, thereby achieving the effect of correcting sitting posture and protecting eyesight. The standard sitting posture model can also be rotated 360 degrees for a comprehensive sitting posture comparison. Daily and weekly correction reminders are provided to indicate the three most common abnormal sitting posture types recently, and corrective training is provided for each abnormal sitting posture type, thereby achieving the effect of correcting sitting posture and protecting eyesight.

[0232] Based on the same inventive concept, the embodiment of the present disclosure also provides a sitting posture detection system, and the principle of solving the problem by the system is similar to that of the method, so the implementation of the system can refer to the implementation of the method, and the repeated parts will not be repeated.

[0233] As shown in FIG8 , the system includes at least one first device 800 , wherein the first device 800 is configured to:

[0234] Collecting a user's sitting posture image and constructing a three-dimensional sitting posture model of the user based on the sitting posture image;

[0235] The user's three-dimensional sitting posture model is compared with a pre-set standard sitting posture model, and whether the user's sitting posture is abnormal is detected based on the comparison result.

[0236] Optionally, the first device includes a display screen, including but not limited to mobile phones, tablets and other terminal devices.

[0237] In some embodiments, as shown in FIG9 , the system further includes at least one second device 801 , wherein the first device and the second device are disposed in different positions;

[0238] The second device is used to collect a sitting posture image of the user and send the collected sitting posture image of the user to the first device, so as to instruct the first device to construct a three-dimensional sitting posture model of the user according to the sitting posture image.

[0239] Optionally, the second device sends the collected sitting posture image of the user directly to the first device, or forwards it to the first device through a network server.

[0240] During implementation, the second device sends the collected sitting posture image of the user to the data analysis system, wherein the data analysis system can be implemented by the first device or by a (network) server.

[0241] Optionally, when there is only one first device, the first device is a display device, which can be understood as a primary device and can capture images of sitting postures and display content. When there are multiple first devices, one first device is a display device, and the remaining first devices are image capture devices such as cameras, which can capture faces from different angles. The second device is an image capture device, which can be understood as an auxiliary device. The first device and / or the second device can also be equipped with audio functions.

[0242] Optionally, the positions of the first device and each second device are different, and the first device and each second device are set in different directions, and the field of view of the first device and the second device in different directions can cover the user's sitting posture from any angle.

[0243] As an optional implementation, the first device 800 is arranged directly opposite the user.

[0244] As an optional implementation, the field of view of the first device 800 and the second device 801 can cover the user's sitting posture from any angle.

[0245] As an optional implementation manner, the first device 800 is specifically configured to:

[0246] determining key parts in the user's three-dimensional sitting posture model and the standard sitting posture model, wherein the key parts include human body parts related to the sitting posture;

[0247] Compare the positions and angles of key parts in the three-dimensional sitting posture model and the standard sitting posture model, and detect whether the user's sitting posture is abnormal based on the comparison results.

[0248] As an optional implementation manner, the first device 800 is further configured to:

[0249] Determining the distance between the user and the display device, wherein the distance is used to determine the tilt state of the user's sitting posture;

[0250] Based on the comparison result and the distance, it is detected whether the user's sitting posture is abnormal.

[0251] As an optional implementation manner, the first device 800 is further configured to:

[0252] Determine the user's facial posture based on the user's three-dimensional sitting posture model and obtain the user's eye usage time;

[0253] Determine whether the user is overusing their eyes based on facial posture and eye usage duration.

[0254] As an optional implementation manner, the first device 800 is further configured to:

[0255] When it is determined that the user is in a state of excessive eye use, the display device is controlled to enter a rest mode or shut down, wherein the rest mode is used to prompt the user to perform at least one of eye exercises, eye rest, and sitting posture correction.

[0256] As an optional implementation manner, the first device 800 is further configured to:

[0257] When the user's sitting posture is detected to be abnormal according to the comparison result, abnormal sitting posture data is determined;

[0258] The user is guided to correct the sitting posture according to the abnormal sitting posture data.

[0259] As an optional implementation, when the user's sitting posture is detected to be abnormal according to the comparison result, after determining the abnormal sitting posture data, the first device 800 is further configured to:

[0260] The abnormal sitting posture data is stored, and according to the type of the abnormal sitting posture data, different types of abnormal sitting posture data within a preset period are counted.

[0261] As an optional implementation manner, the first device 800 is further configured to:

[0262] In response to the user's abnormal display instruction, the total number of different types of abnormal sitting postures and / or the total number of abnormal sitting postures corresponding to a unit time length in the preset period are displayed based on the statistical data of different types of abnormal sitting postures within the preset period.

[0263] As an optional implementation manner, the first device 800 is further configured to:

[0264] At least one of the user's three-dimensional sitting posture model, the standard sitting posture model, and the comparison result is displayed.

[0265] As an optional implementation, after displaying the three-dimensional sitting posture model and the standard sitting posture model of the user, the first device 800 is further configured to:

[0266] In response to a user's touch and slide operation on the standard sitting posture model, controlling the standard sitting posture model to rotate;

[0267] Compare the standard sitting posture model and the three-dimensional sitting posture model, and display the comparison results.

[0268] As an optional implementation manner, the first device 800 is further configured to:

[0269] In response to a single sitting posture adjustment instruction of the user, when it is detected that the user's sitting posture is abnormal, the user is guided to correct the sitting posture; when it is detected that the adjusted sitting posture is normal, the sitting posture correction for the user is terminated; or,

[0270] In response to the user's real-time sitting posture adjustment instruction, when it is detected that the user's sitting posture is abnormal, the user is guided to correct the sitting posture; when it is detected that the adjusted sitting posture is normal, the user's next sitting posture is continued to be detected.

[0271] As an optional implementation manner, the first device 800 is further configured to:

[0272] When it is detected that the user's sitting posture is abnormal and the duration of the abnormal sitting posture exceeds a threshold, the display device is controlled to enter at least one of the sitting posture correction mode, rest mode, and off mode, wherein the sitting posture correction mode is used to guide the user to correct the sitting posture.

[0273] Based on the same inventive concept, the embodiment of the present disclosure also provides an electronic device. Since the electronic device is the electronic device in the method in the embodiment of the present disclosure, and the principle of solving the problem by the electronic device is similar to that of the method, the implementation of the electronic device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0274] As shown in FIG10 , the electronic device includes a processor 1000 and a memory 1001. The memory 1001 is used to store programs executable by the processor 1000. The processor 1000 is used to read the programs in the memory 1001 and perform the following steps:

[0275] Collecting a user's sitting posture image, and constructing a three-dimensional sitting posture model of the user based on the collected sitting posture image;

[0276] The user's three-dimensional sitting posture model is compared with a pre-set standard sitting posture model, and whether the user's sitting posture is abnormal is detected based on the comparison result.

[0277] As an optional implementation manner, the processor 1000 is specifically configured to execute:

[0278] Capturing the user's sitting posture image by using a capture device placed directly opposite the user; or

[0279] The user's sitting posture image is collected by collecting devices arranged in different directions; wherein, the collecting devices in different directions include the collecting devices directly opposite the user, and the field of view of the collecting devices in different directions can cover the user's sitting posture from any angle.

[0280] As an optional implementation manner, the processor 1000 is specifically configured to execute:

[0281] determining key parts in the user's three-dimensional sitting posture model and the standard sitting posture model, wherein the key parts include human body parts related to the sitting posture;

[0282] Compare the positions and angles of key parts in the three-dimensional sitting posture model and the standard sitting posture model, and detect whether the user's sitting posture is abnormal based on the comparison results.

[0283] As an optional implementation manner, the processor 1000 is further configured to execute:

[0284] Determining the distance between the user and the display device, wherein the distance is used to determine the tilt state of the user's sitting posture;

[0285] Based on the comparison result and the distance, it is detected whether the user's sitting posture is abnormal.

[0286] As an optional implementation manner, the processor 1000 is further configured to execute:

[0287] Determine the user's facial posture based on the user's three-dimensional sitting posture model and obtain the user's eye usage time;

[0288] Determine whether the user is overusing their eyes based on facial posture and eye usage duration.

[0289] As an optional implementation manner, the processor 1000 is further configured to execute:

[0290] When it is determined that the user is in a state of excessive eye use, the display device is controlled to enter a rest mode or shut down, wherein the rest mode is used to prompt the user to perform at least one of eye exercises, eye rest, and sitting posture correction.

[0291] As an optional implementation manner, the processor 1000 is further configured to execute:

[0292] When the user's sitting posture is detected to be abnormal according to the comparison result, abnormal sitting posture data is determined;

[0293] The user is guided to correct the sitting posture according to the abnormal sitting posture data.

[0294] As an optional implementation, when the user's sitting posture is detected to be abnormal according to the comparison result, after determining the abnormal sitting posture data, the processor 1000 is further configured to execute:

[0295] The abnormal sitting posture data is stored, and according to the type of the abnormal sitting posture data, different types of abnormal sitting posture data within a preset period are counted.

[0296] As an optional implementation manner, the processor 1000 is further configured to execute:

[0297] In response to the user's abnormal display instruction, the total number of different types of abnormal sitting postures and / or the total number of abnormal sitting postures corresponding to a unit time length in the preset period are displayed based on the statistical data of different types of abnormal sitting postures within the preset period.

[0298] As an optional implementation manner, the processor 1000 is further configured to execute:

[0299] At least one of the user's three-dimensional sitting posture model, the standard sitting posture model, and the comparison result is displayed.

[0300] As an optional implementation, after displaying the three-dimensional sitting posture model and the standard sitting posture model of the user, the processor 1000 is further configured to execute:

[0301] In response to a user's touch and slide operation on the standard sitting posture model, controlling the standard sitting posture model to rotate;

[0302] Compare the standard sitting posture model and the three-dimensional sitting posture model, and display the comparison results.

[0303] As an optional implementation manner, the processor 1000 is further configured to execute:

[0304] In response to a single sitting posture adjustment instruction of the user, when it is detected that the user's sitting posture is abnormal, the user is guided to correct the sitting posture; when it is detected that the adjusted sitting posture is normal, the sitting posture correction for the user is terminated; or,

[0305] In response to the user's real-time sitting posture adjustment instruction, when it is detected that the user's sitting posture is abnormal, the user is guided to correct the sitting posture; when it is detected that the adjusted sitting posture is normal, the user's next sitting posture is continued to be detected.

[0306] As an optional implementation manner, the processor 1000 is further configured to execute:

[0307] When it is detected that the user's sitting posture is abnormal and the duration of the abnormal sitting posture exceeds a threshold, the display device is controlled to enter at least one of the sitting posture correction mode, rest mode, and off mode, wherein the sitting posture correction mode is used to guide the user to correct the sitting posture.

[0308] Based on the same inventive concept, the embodiment of the present disclosure also provides a sitting posture detection device. Since the device is the device in the method in the embodiment of the present disclosure, and the principle of solving the problem by the device is similar to that of the method, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0309] As shown in FIG11 , the device includes:

[0310] The model building unit 1100 is used to collect a user's sitting posture image and build a three-dimensional sitting posture model of the user based on the collected sitting posture image;

[0311] The sitting posture detection unit 1101 is used to compare the user's three-dimensional sitting posture model with a preset standard sitting posture model, and detect whether the user's sitting posture is abnormal based on the comparison result.

[0312] As an optional implementation manner, the model building unit 1100 is specifically configured to:

[0313] Capturing the user's sitting posture image by using a capture device placed directly opposite the user; or

[0314] The user's sitting posture image is collected by collecting devices arranged in different directions; wherein, the collecting devices in different directions include the collecting devices directly opposite the user, and the field of view of the collecting devices in different directions can cover the user's sitting posture from any angle.

[0315] As an optional implementation manner, the sitting posture detection unit 1101 is specifically configured to:

[0316] determining key parts in the user's three-dimensional sitting posture model and the standard sitting posture model, wherein the key parts include human body parts related to the sitting posture;

[0317] Compare the positions and angles of key parts in the three-dimensional sitting posture model and the standard sitting posture model, and detect whether the user's sitting posture is abnormal based on the comparison results.

[0318] As an optional implementation manner, the sitting posture detection unit 1101 is further configured to:

[0319] Determining the distance between the user and the display device, wherein the distance is used to determine the tilt state of the user's sitting posture;

[0320] Based on the comparison result and the distance, it is detected whether the user's sitting posture is abnormal.

[0321] As an optional implementation manner, the sitting posture detection unit 1101 is further configured to:

[0322] Determine the user's facial posture based on the user's three-dimensional sitting posture model and obtain the user's eye usage time;

[0323] Determine whether the user is overusing their eyes based on facial posture and eye usage duration.

[0324] As an optional implementation manner, the sitting posture detection unit 1101 is further configured to:

[0325] When it is determined that the user is in a state of excessive eye use, the display device is controlled to enter a rest mode or shut down, wherein the rest mode is used to prompt the user to perform at least one of eye exercises, eye rest, and sitting posture correction.

[0326] As an optional implementation manner, the sitting posture detection unit 1101 is further configured to:

[0327] When the user's sitting posture is detected to be abnormal according to the comparison result, abnormal sitting posture data is determined;

[0328] The user is guided to correct the sitting posture according to the abnormal sitting posture data.

[0329] As an optional implementation manner, when the user's sitting posture is detected to be abnormal according to the comparison result, after determining the abnormal sitting posture data, the sitting posture detection unit 1101 is further configured to:

[0330] The abnormal sitting posture data is stored, and according to the type of the abnormal sitting posture data, different types of abnormal sitting posture data within a preset period are counted.

[0331] As an optional implementation manner, the sitting posture detection unit 1101 is further configured to:

[0332] In response to the user's abnormal display instruction, the total number of different types of abnormal sitting postures and / or the total number of abnormal sitting postures corresponding to a unit time length in the preset period are displayed based on the statistical data of different types of abnormal sitting postures within the preset period.

[0333] As an optional implementation manner, the sitting posture detection unit 1101 is further configured to:

[0334] At least one of the user's three-dimensional sitting posture model, the standard sitting posture model, and the comparison result is displayed.

[0335] As an optional implementation, after displaying the user's three-dimensional sitting posture model and the standard sitting posture model, the sitting posture detection unit is further configured to:

[0336] In response to a user's touch and slide operation on the standard sitting posture model, controlling the standard sitting posture model to rotate;

[0337] Compare the standard sitting posture model and the three-dimensional sitting posture model, and display the comparison results.

[0338] As an optional implementation manner, the sitting posture detection unit 1101 is further configured to:

[0339] In response to a single sitting posture adjustment instruction of the user, when it is detected that the user's sitting posture is abnormal, the user is guided to correct the sitting posture; when it is detected that the adjusted sitting posture is normal, the sitting posture correction for the user is terminated; or,

[0340] In response to the user's real-time sitting posture adjustment instruction, when it is detected that the user's sitting posture is abnormal, the user is guided to correct the sitting posture; when it is detected that the adjusted sitting posture is normal, the user's next sitting posture is continued to be detected.

[0341] As an optional implementation manner, the sitting posture detection unit 1101 is further configured to:

[0342] When it is detected that the user's sitting posture is abnormal and the duration of the abnormal sitting posture exceeds a threshold, the display device is controlled to enter at least one of the sitting posture correction mode, rest mode, and off mode, wherein the sitting posture correction mode is used to guide the user to correct the sitting posture.

[0343] Based on the same inventive concept, embodiments of the present disclosure provide a computer storage medium comprising computer program code. When executed on a computer, the computer program code causes the computer to execute any of the sitting posture detection methods discussed above. Because the principles underlying the problems solved by the computer storage medium are similar to those of the sitting posture detection method, the implementation of the computer storage medium can be referenced to the implementation of the method, and any repetitions will be omitted.

[0344] In a specific implementation process, computer storage media may include: Universal Serial Bus Flash Drive (USB), mobile hard disk, Read-Only Memory (ROM), Random Access Memory (RAM), magnetic disk or optical disk, and other storage media that can store program code.

[0345] Based on the same inventive concept, embodiments of the present disclosure further provide a computer program product comprising computer program code that, when executed on a computer, causes the computer to perform any of the sitting posture detection methods discussed above. Because the principles underlying the problems solved by the aforementioned computer program products are similar to those of the sitting posture detection methods, the implementation of the aforementioned computer program products can be referenced to the implementation of the methods, and any repetitive details will not be repeated.

[0346] The computer program product can employ any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0347] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0348] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0349] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0350] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0351] Obviously, those skilled in the art may make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is intended to include these modifications and variations.

Claims

1. A sitting posture detection method, wherein, The method includes: Collecting a sitting posture image of a user, and constructing a three-dimensional sitting posture model of the user according to the collected sitting posture image; Comparing the three-dimensional sitting posture model of the user with a preset standard sitting posture model, and detecting whether the sitting posture of the user is abnormal according to the comparison result.

2. The method according to claim 1, wherein The collecting the sitting posture image of the user includes: Collecting the sitting posture image of the user through a collecting device arranged directly opposite the user; or, Collecting the sitting posture image of the user through collecting devices arranged in different orientations; wherein, the collecting devices in different orientations include the collecting device directly opposite the user, and the visual field ranges of the collecting devices in different orientations can cover the sitting posture of the user from any angle.

3. The method according to claim 1, wherein, The comparing the three-dimensional sitting posture model of the user with a preset standard sitting posture model, and detecting whether the sitting posture of the user is abnormal according to the comparison result includes: Determining key parts in the three-dimensional sitting posture model and the standard sitting posture model of the user, wherein the key parts include human body parts related to the sitting posture; Comparing the positions and angles of the key parts in the three-dimensional sitting posture model and the standard sitting posture model, and detecting whether the sitting posture of the user is abnormal according to the comparison result.

4. The method according to claim 1, wherein The method further includes: Determining the distance from the user to the display device, and the distance is used to judge the inclination state of the user's sitting posture; Detecting whether the sitting posture of the user is abnormal according to the comparison result and the distance.

5. The method according to claim 1, wherein The method further includes: Determining the face posture according to the three-dimensional sitting posture model of the user, and obtaining the user's eye usage duration; Judging whether the user is in a state of excessive eye use according to the face posture and the eye usage duration.

6. The method according to claim 5, wherein, The method further includes: When it is determined that the user is in a state of excessive eye use, controlling the display device to enter a rest mode or turn off, wherein the rest mode is used to prompt the user to perform at least one of eye exercises, eye rest, and sitting posture correction.

7. The method according to claim 1, wherein, The method further includes: When it is detected that the sitting posture of the user is abnormal according to the comparison result, determining abnormal sitting posture data; Guiding the user to correct the sitting posture according to the abnormal sitting posture data.

8. The method according to claim 7, wherein, After determining the abnormal sitting posture data when it is detected that the sitting posture of the user is abnormal according to the comparison result, the method further includes: Storing the abnormal sitting posture data, and counting the abnormal sitting posture data of different types within a preset period according to the type of the abnormal sitting posture data.

9. The method according to claim 8, wherein The method further includes: In response to the abnormal display instruction of the user, displaying the total number of abnormal sitting postures of different types, and / or, the total number of abnormal sitting postures corresponding to the unit time within a preset period according to the counted abnormal sitting posture data of different types within a preset period.

10. The method according to claim 1, wherein, The method further includes: Displaying at least one of the three-dimensional sitting posture model of the user, the standard sitting posture model, and the comparison result.

11. The method according to claim 10, wherein, After displaying the three-dimensional sitting posture model and the standard sitting posture model of the user, the method further includes: In response to the touch and slide operation of the user on the standard sitting posture model, controlling the standard sitting posture model to rotate; Comparing the standard sitting posture model and the three-dimensional sitting posture model, and displaying the comparison result.

12. The method according to claim 1, wherein, The method further includes: In response to the single sitting posture adjustment instruction of the user, when it is detected that the sitting posture of the user is abnormal, guiding the user to correct the sitting posture; when it is detected that the adjusted sitting posture is normal, ending the correction of the user's sitting posture; or, In response to a real-time adjustment instruction of the user's sitting posture, when it is detected that the user's current sitting posture is abnormal, guide the user to correct the sitting posture; when it is detected that the adjusted sitting posture is normal, continue to detect the user's next sitting posture.

13. The method according to claim 1, wherein, The method further includes: When it is detected that the user's sitting posture is abnormal and the duration of the abnormal sitting posture exceeds a threshold, control the display device to enter at least one of a sitting posture correction mode, a rest mode, and a shutdown mode, where the sitting posture correction mode is used to guide the user to correct the sitting posture.

14. A sitting posture detection system, wherein, It includes at least one first device; the first device is used for: Collect the user's sitting posture image and construct a three-dimensional sitting posture model of the user based on the sitting posture image; Compare the three-dimensional sitting posture model of the user with a preset standard sitting posture model, and detect whether the user's sitting posture is abnormal according to the comparison result.

15. The system according to claim 14, wherein The system further includes at least one second device, and the first device and the second device are arranged in different orientations; The second device is used to collect the user's sitting posture image and send the collected user's sitting posture image to the first device, for instructing the first device to construct a three-dimensional sitting posture model of the user based on the sitting posture image.

16. An electronic device, wherein, The electronic device includes a processor and a memory, the memory is used to store a program executable by the processor, and the processor is used to read the program in the memory and execute the steps of the method according to any one of claims 1 to 13.

17. A computer storage medium, on which a computer program is stored, wherein, When the program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 13.

Images