Method and system for recognizing sleeping posture of user by intelligent pillow

Abstract

The invention discloses a method and system for recognizing the sleeping posture of a user by an intelligent pillow, and relates to the technical field of sleeping posture recognition methods, and the method comprises the steps: determining an image of the head of the user according to the division of a current sleeping image of the user; the head sleeping posture coefficient of the head of the user to the intelligent pillow is determined according to the image of the head of the user and the spatial positions and the regional forms of the multiple sub-regions, and the accuracy of the head sleeping posture coefficient is improved. Therefore, the image of the body is determined according to the division of the current sleep image of the user, and the sleeping posture coefficient of the upper half part of the body and the sleeping posture coefficient of the lower half part of the body are determined based on the recognition of the image of the body; in the intelligent pillow, the current sleeping posture of the user is determined based on the sleeping posture coefficient of the head, the sleeping posture coefficient of the upper half part of the body and the sleeping posture coefficient of the lower half part of the body, the accuracy of the current sleeping posture of the user is guaranteed, the intelligent pillow and cameras on the peripheral sides are fully utilized, and cooperative control over the intelligent pillow and the cameras on the peripheral sides is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of sleeping posture recognition methods, and in particular to a method and system for recognizing a user's sleeping posture using a smart pillow. Background Art

[0002] With the development of science and technology, pillows are gradually used in people's lives and support the user's head. When the user's head contacts the pillow, it exerts pressure on the pillow, so that the pillow has a corresponding pressure area. In the existing technology, the user's head exerts pressure on the pillow, and the pillow determines the sleeping position coefficient of the user's head based on the analysis of the pressure area. A single-dimensional analysis is performed along the pressure area to determine the user's current sleeping position. The influence of the sleeping position coefficient of the upper and lower parts of the body is not considered, resulting in low accuracy of the user's current sleeping position. Summary of the Invention

[0003] The purpose of the present invention is to overcome the deficiencies of the prior art. The present invention provides a method and system for a smart pillow to recognize a user's sleeping posture.

[0004] An embodiment of the present invention provides a method for recognizing a user's sleeping posture using a smart pillow, comprising:

[0005] When the smart pillow is pressed against the user's head, the pressed area of ​​the smart pillow is collected, and the spatial positions and regional shapes of multiple sub-areas are determined based on the detection of the pressed area;

[0006] Triggering a response from a surrounding camera according to the position of the smart pillow, and collecting a current sleep image of the user based on the camera, and determining an image of the user's head according to the division of the current sleep image of the user;

[0007] determining a head sleeping posture coefficient of the user's head relative to the smart pillow based on an image of the user's head, spatial positions of the multiple sub-regions, and regional morphologies;

[0008] determining a body image according to the division of the user's current sleep image, and determining a sleeping posture coefficient of the upper half of the body and a sleeping posture coefficient of the lower half of the body based on recognition of the body image;

[0009] In the smart pillow, the user's current sleeping posture is determined based on the sleeping posture coefficient of the head, the sleeping posture coefficient of the upper body, and the sleeping posture coefficient of the lower body.

[0010] An embodiment of the present invention provides a system for recognizing a user's sleeping posture using a smart pillow. The system is applied to the above-mentioned method for recognizing a user's sleeping posture using a smart pillow. The system comprises:

[0011] A sub-region module is used to detect the pressure area of ​​the smart pillow when the smart pillow is pressed against the user's head, and determine the spatial position and regional morphology of multiple sub-regions based on the detection of the pressure area;

[0012] a first imaging module, configured to trigger a response from a surrounding camera according to the position of the smart pillow, collect a current sleep image of the user based on the camera, and determine an image of the user's head according to the division of the current sleep image of the user;

[0013] A head sleeping posture coefficient module, used to determine the head sleeping posture coefficient of the user's head relative to the smart pillow based on the image of the user's head, the spatial positions of multiple sub-regions, and the regional morphology;

[0014] a body sleeping posture coefficient module, configured to determine a body image according to the division of the user's current sleeping image, and determine a sleeping posture coefficient of the upper body and a sleeping posture coefficient of the lower body based on recognition of the body image;

[0015] The sleeping posture module is used in the smart pillow to determine the user's current sleeping posture based on the sleeping posture coefficient of the head, the sleeping posture coefficient of the upper body, and the sleeping posture coefficient of the lower body.

[0016] Compared with the prior art, the present invention has the following beneficial effects:

[0017] In an embodiment of the present invention, through the method in the embodiment of the present invention, when the smart pillow is pressed against the user's head, the pressed area of ​​the smart pillow is collected, and the spatial positions and regional shapes of multiple sub-areas are determined based on the detection of the pressed area; the response of the surrounding cameras is triggered according to the position of the smart pillow, and the user's current sleep image is collected based on the camera, and the image of the user's head is determined according to the division of the user's current sleep image; the head sleeping posture coefficient of the user's head relative to the smart pillow is determined based on the image of the user's head, the spatial positions and regional shapes of multiple sub-areas, which introduces the image of the user's head and multiple sub-areas, and is compatible with the overall consideration of the image of the user's head, the spatial positions and regional shapes of multiple sub-areas, thereby improving the accuracy of the head sleeping posture coefficient.

[0018] Therefore, the image of the body is determined according to the division of the user's current sleep image, and the sleeping posture coefficient of the upper body and the sleeping posture coefficient of the lower body are determined based on the recognition of the body image; in the smart pillow, the user's current sleeping posture is determined based on the sleeping posture coefficient of the head, the sleeping posture coefficient of the upper body and the sleeping posture coefficient of the lower body, and the sleeping posture coefficient of the head, the sleeping posture coefficient of the upper body and the sleeping posture coefficient of the lower body are introduced, which realizes the overall consideration of the sleeping posture coefficient of the head, the sleeping posture coefficient of the upper body and the sleeping posture coefficient of the lower body, ensures the accuracy of the user's current sleeping posture, makes full use of the smart pillow and the cameras on the surrounding sides, and realizes the coordinated control of the smart pillow and the cameras on the surrounding sides. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 1 is a flow chart of a method for recognizing a user's sleeping posture using a smart pillow according to an embodiment of the present invention;

[0020] Figure 2 1 is a flow chart of step S11 in the method for recognizing a user's sleeping posture using a smart pillow in an embodiment of the present invention;

[0021] Figure 3 1 is a flow chart of step S12 in the method for recognizing a user's sleeping posture using a smart pillow in an embodiment of the present invention;

[0022] Figure 4 1 is a flow chart of step S13 in the method for recognizing a user's sleeping posture using a smart pillow in an embodiment of the present invention;

[0023] Figure 5 1 is a flow chart of step S14 in the method for recognizing a user's sleeping posture using a smart pillow in an embodiment of the present invention;

[0024] Figure 6 1 is a flow chart of step S15 in the method for recognizing a user's sleeping posture using a smart pillow in an embodiment of the present invention;

[0025] Figure 7 This is a schematic diagram of the structure of the system for recognizing a user's sleeping posture using a smart pillow in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present invention.

[0027] See also Figures 1 to 7 A method for recognizing a user's sleeping posture using a smart pillow is provided, and is applied to a scenario where a smart pillow recognizes a user's sleeping posture. The method comprises:

[0028] Step S11: When the smart pillow is pressed against the user's head, the pressed area of ​​the smart pillow is detected, and the spatial positions and regional shapes of multiple sub-areas are determined based on the detection of the pressed area;

[0029] Step S12: triggering a response from a surrounding camera according to the position of the smart pillow, collecting a current sleep image of the user based on the camera, and determining an image of the user's head according to the division of the current sleep image of the user;

[0030] Step S13: determining a sleeping posture coefficient of the user's head relative to the smart pillow based on the image of the user's head, the spatial positions of the multiple sub-regions, and the regional morphology;

[0031] Step S14: determining a body image according to the division of the user's current sleep image, and determining a sleeping posture coefficient of the upper half of the body and a sleeping posture coefficient of the lower half of the body based on the recognition of the body image;

[0032] Step S15: In the smart pillow, the user's current sleeping posture is determined based on the sleeping posture coefficient of the head, the sleeping posture coefficient of the upper body, and the sleeping posture coefficient of the lower body;

[0033] refer to Figure 2 In step S11, when the smart pillow is pressed against the user's head, the pressed area of ​​the smart pillow is detected, and the spatial positions and regional shapes of multiple sub-areas are determined based on the detection of the pressed area;

[0034] In the specific implementation process of the present invention, the specific steps are:

[0035] S111: responding to the working state of the smart pillow based on contact of the user's head with the smart pillow, the user's head continuously applies pressure to the smart pillow, and determining a pressure state diagram of the smart pillow based on pressure parameters detected by the smart pillow;

[0036] S112: Determining a detection node for detecting the user's sleeping posture based on the recognition of the pressure state diagram of the smart pillow, collecting multiple pressure locations of the smart pillow at the detection node for detecting the user's sleeping posture, and determining a pressure area of ​​the smart pillow based on the multiple pressure locations and the shape of the smart pillow;

[0037] S113: Detect the compressed area of ​​the smart pillow, determine multiple sub-areas based on the detection of the compressed area of ​​the smart pillow, and mark the spatial positions and regional shapes of the multiple sub-areas. At this time, the multiple sub-areas serve as the positions of the compressed areas and are arranged adjacent to each other in sequence.

[0038] In an embodiment of the present application, a plurality of pressure sensors are embedded in the smart pillow. These sensors are usually in a low-power standby state. When the user's head contacts the smart pillow, one or more sensors are triggered to respond, thereby activating the entire smart pillow's operating system. This triggering mechanism is based on a pressure threshold design. That is, when the pressure applied by the head reaches or exceeds a certain preset value, the sensor sends a signal to activate the system.

[0039] Once the smart pillow is activated, it will continuously monitor the pressure exerted by the user's head. This continuous pressure is the key to identifying the user's sleeping position, because different sleeping positions will result in different distribution and pressure of the head on the pillow. At this time, when the user lies on their side, one side of their head will exert greater pressure on the pillow, while the other side will have less pressure. The smart pillow will continuously record the changes in this pressure distribution and provide data for subsequent analysis.

[0040] The smart pillow collects pressure data through its internal sensor network and processes it to generate a pressure map. This map, typically displayed in two or three dimensions, visually illustrates the pressure applied to various areas of the pillow. The map typically includes information such as pressure magnitude, distribution, and shape. Specifically, assuming a user lies supine, the smart pillow detects that the pressure is greatest in the center of the head, forming a distinct pressure peak. Simultaneously, the pressure on both sides of the pillow gradually decreases. By processing this data through an algorithm, the smart pillow generates a pressure map showing a highlighted area in the center of the head, indicating the highest pressure. This pressure map serves as an important basis for subsequent sleeping position recognition. The smart pillow's pressure sensor network monitors the contact between the user's head and the pillow in real time and generates a pressure map reflecting the pressure applied, providing critical data support for subsequent sleeping position recognition. In practical applications, the smart pillow will incorporate other sensors (such as accelerometers and gyroscopes) to improve the accuracy and reliability of sleeping position recognition.

[0041] Furthermore, in step S111, a pressure state map of the smart pillow has been obtained, which shows the pressure conditions of various areas of the pillow; in this step, it is necessary to identify key areas or nodes closely related to the user's sleeping posture based on this pressure state map. These nodes are usually the positions where the pressure is most obvious and can reflect the posture of the user's head and neck; to achieve this, image processing or machine learning algorithms are used to analyze the pressure state map; the algorithm will identify the peaks and troughs in the pressure distribution, as well as the relative position relationship between them, to determine the detection nodes; at this time, assuming that the user's pressure state map shows that there is an obvious pressure peak in the center of the head, and a relatively small pressure peak in the neck area; the algorithm will identify these two areas as detection nodes because they represent the positions of the user's head and neck, respectively.

[0042] After the detection nodes are determined, more pressure position data need to be collected in these nodes. These data will be used to more accurately describe the shape and size of the pressure area, as well as the specific position of the user's head and neck on the pillow. To achieve this, a higher resolution sensor array is used, or additional sensors are added to the identified detection nodes. These sensors will record more detailed pressure distribution data for subsequent analysis. At this point, more sensors are added to the identified head and neck detection nodes to collect pressure position data. For example, in the head node, 5 sensors are set to capture the pressure distribution in different areas of the head; in the neck node, 3 sensors are set to capture the pressure distribution of the neck.

[0043] After collecting data on multiple pressure positions, it is necessary to combine the morphology of the smart pillow (such as shape, size, material, etc.) to determine the overall shape and size of the pressure area. This step usually involves further processing and analysis of the data to extract key features that can describe the pressure area. To achieve this, geometric modeling or machine learning algorithms are used to fit the pressure area. The algorithm will generate a model that can accurately describe the pressure area based on the collected pressure position data and the morphological parameters of the smart pillow. At the same time, combined with the collected pressure position data and the morphological parameters of the smart pillow (such as length, width, height, etc.), a machine learning algorithm is used to generate a three-dimensional model to fit the pressure area. This model shows a slightly concave elliptical area, representing the position of the user's head and neck on the pillow. By identifying key nodes in the pressure state diagram, collecting multiple pressure position data, and combining the morphological parameters of the smart pillow, the pressure area is accurately determined, which provides important data support for subsequent sleeping posture recognition.

[0044] Therefore, the pressure area of ​​the smart pillow is detected, and multiple sub-areas are determined based on the detection of the pressure area of ​​the smart pillow, and the spatial positions and regional shapes of the multiple sub-areas are marked. At this time, the multiple sub-areas are used as the positions of the pressure areas and are arranged adjacent to each other in sequence, which is compatible with the overall consideration of the detection of the pressure area of ​​the smart pillow and ensures the accuracy of multiple sub-areas.

[0045] At this point, in step S112, the pressure area of ​​the smart pillow has been determined; further, this pressure area is subjected to more detailed detection to identify its internal detailed features, which usually involves accurately measuring the pressure values ​​of each point in the pressure area and recording these measurements; to achieve this step, a higher-precision sensor array is used, or the sensor is moved within the pressure area to obtain denser data points, which will be used for subsequent sub-area division and morphological analysis. At this point, it is assumed that there is a smart pillow whose pressure area has been determined through step S112; now, a high-precision pressure sensor array is used to scan at certain intervals within the pressure area; each sensor will record the pressure value at its location, thereby generating a dense pressure data set.

[0046] After obtaining detailed pressure data within the compressed area, these data need to be divided into multiple sub-areas, which are determined based on the distribution of pressure values, morphological changes or algorithmic segmentation; each sub-area represents a specific part within the compressed area and has a unique spatial position and morphology; to achieve this step, image processing technology or machine learning algorithms are used to segment the pressure data, which can identify natural boundaries or patterns in the data to divide sub-areas; at the same time, an image processing algorithm is used to segment the pressure data set; the algorithm identifies several obvious pressure peaks and troughs, as well as the transition areas between them; based on these features, the algorithm divides the compressed area into five sub-areas: the central area of ​​the head, the areas on both sides of the head, the front area of ​​the neck, and the back area of ​​the neck.

[0047] After the sub-regions are determined, each sub-region needs to be marked to record its spatial position and morphology. This usually involves assigning a unique identifier to each sub-region and recording its boundaries, shape, size and other characteristics. This information will be used for subsequent sleeping posture recognition and analysis. Geometric modeling techniques or data visualization tools are used to generate a labeled map of the sub-regions. These tools can intuitively display the spatial position and morphology of the sub-regions, facilitating subsequent analysis and interpretation. At this time, a data visualization tool is used to generate a labeled map of the sub-regions. Each sub-region is assigned a unique color or pattern to distinguish the boundaries between them. At the same time, the tool also records the shape, size and position information of each sub-region. This information is saved in a data file for subsequent analysis.

[0048] By conducting more detailed detection of the pressure area of ​​the smart pillow, it is divided into multiple sub-areas, and the spatial positions and shapes of these sub-areas are marked; in this example, the pressure area is divided into five sub-areas: the central area of ​​the head, the areas on both sides of the head, the front area of ​​the neck, and the back area of ​​the neck. These sub-areas, as the specific locations of the pressure areas, are arranged adjacent to each other in sequence, providing accurate data support for subsequent sleeping posture recognition.

[0049] In some optional embodiments of the present application, a sub-region matching table is collected, and the sub-region matching table is shown in Table 1:

[0050] Table 1 Sub-region matching table

[0051] Sub-area Spatial location description Regional morphology 1 Center of the head, near the top of the pillow Round shape, uniform pressure distribution 2 Left side of the head, near the edge of the pillow Oval shape, pressure distribution slightly above average 3 Right side of the head, near the edge of the pillow Oval shape, pressure distribution slightly above average 4 Below the neck, near the center of the pillow Long strip shape, low pressure distribution 5 The shoulder area, near the edges of the pillow Irregular shape, uneven pressure distribution

[0052] This sub-region matching table records the spatial location and morphological description of each sub-region, providing basic data for subsequent analysis.

[0053] refer to Figure 3 In step S12, the position of the smart pillow triggers the response of the surrounding cameras, and the current sleeping image of the user is collected based on the cameras, and the image of the user's head is determined according to the division of the current sleeping image of the user;

[0054] In the specific implementation process of the present invention, the specific steps are:

[0055] S121: The location of the smart pillow is collected. The smart pillow detects surrounding devices at the location and triggers responses from surrounding cameras. At this time, the smart pillow is in online communication with surrounding cameras.

[0056] S122: Determine, among the surrounding cameras, a shooting mode of the surrounding cameras for the smart pillow according to the position of the smart pillow, the corresponding surrounding environment type, and the current orientation of the surrounding cameras;

[0057] S123: The surrounding cameras only take pictures in this shooting mode and collect the user's current sleeping image; determine the user's head features based on the recognition of the user's current sleeping image, and determine the image of the user's head based on the position and shape of the user's head features and the matching of the user's current sleeping image.

[0058] In an embodiment of the present application, the smart pillow has a built-in position sensor (such as an accelerometer, a gyroscope or a GPS module, although GPS is not the best choice in an indoor environment, other sensors are sufficient), which can collect the position information of the pillow in real time; the position information includes the relative position of the pillow in the room, or more advanced, the position of the pillow relative to the user's body (for example, whether the pillow is correctly placed under the user's head).

[0059] Once the smart pillow collects its own location information, it will begin to detect whether there are other smart devices in the surrounding environment, especially cameras. This is usually achieved through wireless communication protocols (such as Wi-Fi Direct, Bluetooth Low Energy, etc.). The smart pillow will send a broadcast signal or query request to find nearby smart devices; at this time, the smart pillow will use the built-in wireless communication module to send signals, which will be received and responded to by nearby smart devices; if the camera is within the reception range and has been configured to be compatible with the smart pillow, it will respond to the query request.

[0060] When the smart pillow detects nearby cameras, it sends instructions to the cameras via wireless communication, triggering them to enter working mode. This usually involves sending a data packet containing specific commands, telling the camera to start recording video, adjust the focus, or make other necessary settings. At the same time, a secure wireless communication channel (such as through an encrypted Wi-Fi connection) will be established between the smart pillow and the camera. The smart pillow will send a data packet containing instructions to the camera. After receiving the instructions, the camera will parse and perform the corresponding operations. For example, the camera will start recording video, or adjust its viewing angle to ensure that it can capture the area where the smart pillow is located.

[0061] Specifically, the smart pillow is placed on the bed in the bedroom, and the camera is installed on the ceiling of the bedroom; when the user lies down and puts his head on the smart pillow, the position sensor in the pillow will collect the position information of the pillow; the sensor detects that the pillow is placed in the center of the bed and is in close contact with the user's head; the smart pillow then sends a broadcast signal through the Wi-Fi Direct protocol to find nearby smart devices; after receiving this signal, the camera will respond and confirm its existence; once the smart pillow confirms the existence of the camera, it will send a command data packet to the camera through an encrypted Wi-Fi connection. This data packet contains a command to start recording video, as well as specific information about the location of the smart pillow (such as the distance and angle relative to the camera); after receiving this command, the camera will immediately start recording video and ensure that it can clearly capture the image of the area where the smart pillow is located. Through this example, we can see how the smart pillow interacts with surrounding cameras to realize intelligent sleep monitoring functions.

[0062] Furthermore, the camera needs to obtain accurate location information from the smart pillow, which is usually achieved through wireless communication (such as Wi-Fi, Bluetooth, etc.). The smart pillow will send its location data to the camera or central control system; the location information includes the relative coordinates of the smart pillow in the room, its relative position to the user's body, etc.

[0063] The camera needs to understand the type of surrounding environment where the smart pillow is located, which helps determine the optimal shooting parameters; the surrounding environment types include lighting conditions (bright, dim, direct light, etc.), obstacles (such as furniture, curtains, etc.), and whether there are other factors that affect the shooting quality. This information is obtained through the camera's own sensors (such as light sensors, infrared sensors, etc.) or provided by other devices in the smart home system (such as smart lighting systems, curtain control systems, etc.).

[0064] The camera needs to know its current orientation and position so that it can accurately adjust its viewing angle to capture the area where the smart pillow is located. This is usually achieved through the camera's built-in sensors (such as gyroscopes, accelerometers, etc.), which can provide real-time attitude and position information of the camera. In addition, if the camera is movable (such as a gimbal camera), its control system also needs to know the camera's current mechanical position (such as pitch angle, yaw angle, etc.). After obtaining the location information of the smart pillow, analyzing the type of surrounding environment, and determining the current orientation and position of the camera, the camera needs to integrate this information to determine the best shooting mode. The shooting mode includes focus adjustment, exposure setting, white balance adjustment, frame rate selection, etc. These settings are designed to ensure that the camera can capture clear, accurate, and user-friendly images.

[0065] Specifically, the smart pillow is placed on the bed in the bedroom, and the camera is installed in a corner of the bedroom and can be rotated horizontally and vertically through the pan-tilt head; when the user lies down and puts his head on the smart pillow, the position sensor inside the pillow will collect the pillow's position information and send it to the central control system via Wi-Fi; at this time, the system knows that the smart pillow is placed in the center of the bed and is in close contact with the user's head.

[0066] The camera detects, through its built-in light sensor, that the lighting conditions in the bedroom are moderate—neither too bright nor too dim. It also learns from other devices in the smart home system that there are no large obstacles blocking its view and that the curtains are open, allowing natural light in. The camera uses its built-in gyroscope and accelerometer to determine its current orientation and position. In this example, the camera is initially pointed toward the bedroom door, but needs to be rotated using the gimbal to capture the area where the smart pillow is located to ensure the camera has determined the optimal shooting mode. Because the lighting conditions are moderate and there are no obstacles blocking the view, the camera selects standard exposure settings and white balance adjustments. Furthermore, because the smart pillow is placed in the center of the bed, the camera uses the gimbal to rotate horizontally and vertically to adjust the viewing angle to the optimal position. Finally, the camera begins recording video and transmits it in real time to the central control system for storage and analysis. This example shows how the camera determines the optimal shooting mode based on the location of the smart pillow, the type of surrounding environment, and its own orientation and position.

[0067] Therefore, the surrounding cameras only shoot in this shooting mode and collect the user's current sleep image; the user's head features are determined based on the recognition of the user's current sleep image, and the image of the user's head is determined based on the position and shape of the user's head features and the matching of the user's current sleep image, which is compatible with the overall consideration of the position and shape of the user's head features and the matching of the user's current sleep image, ensuring the accuracy of the image of the user's head.

[0068] At this point, the camera starts capturing the user's current sleep image according to the previously determined shooting mode (such as focus, exposure, white balance and other settings). This usually involves starting the camera's image sensor and capturing a series of frames to form a continuous video stream or static image sequence. The camera will ensure that shooting starts at the right time (such as a period of time after the user lies down) and continuously records the user's sleep status. The images captured by the camera will be collected and stored in real time, which involves transmitting the image data from the camera's image sensor to its internal processor or storage device, or transmitting it to the central control system via the network for further processing. The collected image data should be of high definition to facilitate subsequent accurate image recognition and analysis.

[0069] The system uses image recognition algorithms to process the collected sleep images to identify the user's head features, including the outlines and positions of the face, eyes, nose, mouth and other parts; image recognition algorithms are usually based on machine learning or deep learning technology, and can automatically extract useful information from images; at the same time, once the user's head features are identified, the system will determine the user's head image based on the position, shape and degree of match with the current sleep image of these features. This usually involves comparing the identified features with a pre-stored user facial database to confirm the user's identity and extract the most matching head image; if the system does not have the user's facial data before, it will require the user to register for facial recognition or manually enter relevant information.

[0070] Specifically, the smart pillow can monitor the user's sleeping state and work with the camera to capture the user's sleeping images; when the user lies down and starts to sleep, the camera starts shooting according to the previously determined shooting mode (such as adjusting the focal length to clearly capture the bed surface, and setting moderate exposure to ensure appropriate image brightness); the camera continuously records the user's sleeping state and captures a series of frames to form a video stream; the images taken by the camera are collected in real time and stored in its internal memory. These images are of high definition and can clearly show the user's head features.

[0071] The system uses an image recognition algorithm to process the collected sleep images, identify the outlines and positions of the user's face, eyes, nose, mouth and other parts. These features are extracted and used for subsequent identity confirmation and head image determination; the system compares the identified head features with the pre-stored user facial database; in this example, it is assumed that the system has previously obtained the user's facial data through facial recognition registration; through comparison, the system finds the head image that best matches the user's current sleep image and confirms the user's identity; at the same time, the system also provides users with personalized sleep analysis and suggestions based on the user's head features and sleeping posture; the camera captures the user's sleep image according to the shooting mode, and identifies the user's head features through the image recognition algorithm, and finally determines the user's head image.

[0072] In some optional embodiments of the present application, to determine the user's head image, the system uses a pre-built image matching table. This image matching table contains multiple known user head features and their corresponding head images. The image matching table is shown in Table 2:

[0073] Table 2 Image matching table

[0074]

[0075]

[0076] The system will compare the recognized user head features with the features in the image matching table to find the most matching user ID and corresponding head image.

[0077] refer to Figure 4 , in step S13, determining the head sleeping posture coefficient of the user's head relative to the smart pillow according to the image of the user's head, the spatial positions of the multiple sub-regions, and the regional morphology;

[0078] In the specific implementation process of the present invention, the specific steps are:

[0079] S131: Capturing an image of the user's head, determining multiple contact nodes of the user's head on the smart pillow based on recognition of the image of the user's head, and determining multiple head pressure characteristics based on positions of the multiple contact nodes and the shape of the user's head;

[0080] S132: Determining a first matching coefficient based on a comparison between the multiple head pressure features and the spatial positions of the multiple sub-regions, and determining a second matching coefficient based on a comparison between the multiple head pressure features and the regional morphologies of the multiple sub-regions;

[0081] S133: Determine the head sleeping posture coefficient of the user's head relative to the smart pillow based on the first matching coefficient, the second matching coefficient, and the head sleeping posture matching table.

[0082] In an embodiment of the present application, an image of the user's head is collected, and multiple contact nodes of the user's head on the smart pillow are determined based on the recognition of the image of the user's head. Multiple head pressure features are determined based on the positions of the multiple contact nodes and the shape of the user's head. This takes into account the overall consideration of the positions of the multiple contact nodes and the shape of the user's head, thereby ensuring the accuracy of the multiple head pressure features.

[0083] At this time, the system uses the camera to capture the user's head image while sleeping; to ensure the clarity and accuracy of the image, the camera is usually placed directly above or to the side of the user's head, and shoots at an appropriate angle and focal length; the captured image will be transmitted to the image processing module for further processing; after the image processing module receives the captured head image, it uses image recognition algorithms to process the image. These algorithms are usually based on machine learning or deep learning technology, and can automatically identify and extract key features in the image, such as head contour, facial features position, etc.; by identifying these features, the system can construct a three-dimensional model or two-dimensional contour map of the user's head, providing basic data for subsequent steps.

[0084] After identifying the image of the user's head, the system needs to combine the internal sensor data of the smart pillow to determine the contact node between the head and the pillow; smart pillows usually have built-in pressure sensors, temperature sensors, etc., which can monitor the contact status and pressure distribution between the head and the pillow in real time; the system matches these sensor data with the head image to find the actual contact point between the head and the pillow, that is, the contact node.

[0085] Once the contact nodes are determined, the system calculates the head pressure characteristics based on the positions of these nodes and the user's head shape. These characteristics include the pressure value, pressure distribution, contact area, etc. of each contact point; by comprehensively analyzing these characteristics, the system can evaluate the pressure distribution and morphological adaptability of the user's head to the smart pillow, thereby providing key data for subsequent steps.

[0086] Specifically, the smart pillow has multiple built-in pressure sensors that can monitor the contact and pressure distribution between the head and the pillow in real time; when the user lies down and starts to sleep, the camera captures the user's head image; the camera is placed directly above the user's head and shoots at an appropriate angle and focal length to ensure the clarity and accuracy of the image; after the image processing module receives the collected head image, it uses an image recognition algorithm to process the image; the algorithm automatically identifies key features such as the user's head outline and facial features, and constructs a two-dimensional outline of the user's head. The system combines the internal sensor data of the smart pillow and matches the identified head outline with the sensor data; through matching, the system finds the actual contact position between the head and the pillow, that is, the contact node; in this example, it is assumed that the system identifies three contact nodes, which are located at the back, left and right sides of the user's head.

[0087] Based on the identified contact node positions and the user's head shape, the system calculates the pressure characteristics of each contact point, including pressure value, pressure distribution, and contact area. For example, the system finds that the contact point pressure value at the back of the head is higher, while the contact point pressure values ​​on the left and right sides are relatively low. By comprehensively analyzing these characteristics, the system can evaluate the pressure distribution and morphological adaptability of the user's head to the smart pillow, providing key data for subsequent steps. Through this example, we can see how the system collects the user's head image, identifies key features in the image, determines the contact nodes between the head and the pillow, and calculates the head pressure characteristics based on these node positions and head shape. These characteristics provide an important basis for automatic pillow adjustment and sleep health analysis in subsequent steps.

[0088] Furthermore, the first matching coefficient is determined based on the comparison between multiple head pressure features and the spatial positions of multiple sub-regions, and the second matching coefficient is determined based on the comparison between multiple head pressure features and the regional morphology of multiple sub-regions. This takes into account the overall comparison between multiple head pressure features and the regional morphology of multiple sub-regions, thereby ensuring the accuracy of the second matching coefficient.

[0089] At this time, the system first obtains the spatial position information of multiple sub-areas of the smart pillow. These sub-areas are usually pre-defined according to the structural design of the pillow, and each sub-area has specific support and comfort characteristics; next, the system compares the multiple pressure characteristics of the user's head (such as pressure value, pressure distribution, etc.) with the spatial position of the sub-area; the purpose of the comparison is to evaluate the degree of match between the head pressure position and the pillow sub-area design; in order to quantify this degree of match, the system calculates a first matching coefficient; specifically, the system calculates the distance between the head pressure point and the center of each sub-area, or evaluates the degree of fit between the pressure distribution and the sub-area shape, thereby obtaining a numerical value reflecting the degree of spatial position matching.

[0090] After determining the first matching coefficient, the system next focuses on the match between the head pressure characteristics and the pillow sub-area morphology. The morphology here not only refers to the geometric shape of the sub-area, but also includes factors affecting comfort such as its surface curvature and material; the system evaluates the adaptability between them by comparing the morphology of the head pressure characteristics (such as contact area, pressure gradient, etc.) with the morphological characteristics of the sub-area; in order to quantify this adaptability, the system calculates a second matching coefficient; for example, the system calculates the similarity between the shape of the head pressure area and the shape of the sub-area, or evaluates the degree of fit between the pressure gradient and the support force distribution of the sub-area; through these calculations, the system obtains a numerical value reflecting the degree of morphological matching.

[0091] Specifically, assume that the smart pillow is designed to have three sub-areas: area A (back of the head support area), area B (side lying support area) and area C (neck support area); each sub-area has specific shape, support and comfort characteristics.

[0092] Regarding the first matching coefficient, when the user lies down, the system captures the pressure characteristics of the user's head through internal sensors. Suppose the system identifies a large pressure point in the back of the head, two smaller pressure points in the side lying area, and almost no pressure in the neck area. The system compares these pressure characteristics with the spatial positions of the three sub-areas A, B, and C. The comparison results show that the pressure point at the back of the head is very close to the center of area A, the pressure point when lying on the side partially overlaps with area B, and the lack of pressure on the neck is inconsistent with the design of area C. Based on these comparison results, the system calculates a first matching coefficient, which reflects the overall degree of match between the head pressure position and the pillow sub-area design. In this example, assume the first matching coefficient is 0.8, indicating that the head pressure position has a high degree of match with the pillow design.

[0093] For the second matching coefficient, the system compares the shape of the head pressure feature with the morphological characteristics of the sub-region; assuming that the shape of the pressure area at the back of the head is similar to that of area A, and the pressure is evenly distributed; although the pressure point when lying on the side is small, the pressure is higher, which is consistent with the support force distribution of area B; and the lack of pressure on the neck is inconsistent with the soft material and design of area C; based on these morphological comparison results, the system calculates a second matching coefficient, which reflects the adaptability between the head pressure feature and the sub-region morphology; in this example, assuming that the second matching coefficient is 0.75, it means that the head pressure feature has a certain adaptability to the sub-region morphology, but there is still room for improvement; through this example, we can see how the system determines the first and second matching coefficients by comparing the head pressure feature with the spatial position and morphological characteristics of the pillow sub-region.

[0094] Therefore, the head sleeping position coefficient of the user's head to the smart pillow is determined based on the first matching coefficient, the second matching coefficient and the head sleeping position matching table, which is compatible with the overall consideration of the first matching coefficient, the second matching coefficient and the head sleeping position matching table, ensuring the accuracy of the head sleeping position coefficient of the user's head to the smart pillow. At the same time, the image of the user's head and multiple sub-regions are introduced, which is compatible with the overall consideration of the image of the user's head, the spatial position of multiple sub-regions and the regional morphology, thereby improving the accuracy of the head sleeping position coefficient.

[0095] At this time, the system first integrates the first matching coefficient and the second matching coefficient calculated previously. These two coefficients respectively reflect the degree of matching between the user's head pressure position and the spatial position of the smart pillow sub-area, as well as the adaptability of the head pressure characteristics to the sub-area morphology; when integrating these two coefficients, the system uses weighted average, multiplication or other mathematical operations to comprehensively consider the matching of both spatial position and morphology; next, the system refers to a pre-established head sleeping position matching table, which is a database that contains the relationship between different head pressure characteristics, matching coefficients and corresponding sleeping position coefficients; the matching table is constructed based on a large amount of previous user data and evaluation results, and aims to provide users with personalized pillow matching recommendations.

[0096] Specifically, assume that the smart pillow company has a detailed head-sleeping position matching table, which is built based on the sleep data of thousands of users and expert evaluations; the matching table contains multiple entries, each entry corresponds to a specific set of head pressure characteristics, a matching coefficient range and a corresponding sleeping position coefficient; assume that the first matching coefficient calculated previously is 0.8 (reflecting the degree of spatial position matching) and the second matching coefficient is 0.75 (reflecting morphological adaptability); the system uses a weighted average method to integrate these two coefficients, with weights of 0.6 and 0.4 respectively (these weights are determined based on user preferences); therefore, the integrated matching coefficient is 0.80.6+0.750.4=0.78.

[0097] The system determines the head sleeping position coefficient of the user's head for the smart pillow based on the integrated matching coefficient and the head sleeping position matching table. This coefficient is a comprehensive indicator that reflects the degree of matching and comfort between the user's current sleeping position and the design of the smart pillow. The system obtains this coefficient by looking up the matching table, interpolation calculation or other algorithms. Specifically, the system now refers to the head sleeping position matching table to find the sleeping position coefficient corresponding to the integrated matching coefficient. Suppose there is an entry in the matching table indicating that when the matching coefficient is between 0.75 and 0.80, the corresponding sleeping position coefficient is 0.85 (indicating a higher degree of matching and comfort). Based on the matching table and the integrated matching coefficient, the system determines that the user's head sleeping position coefficient is 0.85. This coefficient indicates that the user's current sleeping position is very matched with the design of the smart pillow and is expected to provide a higher degree of comfort.

[0098] In some optional embodiments of the present application, the system combines the first matching coefficient, the second matching coefficient, and a predefined head sleeping position matching table to determine the user's head sleeping position coefficient. The system uses a pre-built head sleeping position matching table, which is shown in Table 3:

[0099] Table 3 Head sleeping position matching table

[0100] The first matching coefficient range Second matching coefficient range Head sleeping position 0.8-1.0 0.8-1.0 0.95 0.6-0.79 0.8-1.0 0.85 0.8-1.0 0.6-0.79 0.80 0.6-0.79 0.6-0.79 0.70

[0101] This head sleeping posture matching table reflects the correspondence between the first matching coefficient and the second matching coefficient in different ranges and the sleeping posture coefficient; the sleeping posture coefficient is a value between 0 and 1, and the higher the value, the higher the matching degree and comfort of the user's head and the smart pillow.

[0102] refer to Figure 5 In step S14, a body image is determined according to the division of the user's current sleep image, and a sleeping posture coefficient of the upper half of the body and a sleeping posture coefficient of the lower half of the body are determined based on the recognition of the body image;

[0103] In the specific implementation process of the present invention, the specific steps are:

[0104] S141: collecting a current sleep image of the user, determining multiple body features based on recognition of the current sleep image of the user, and determining a corresponding body image based on the positions and shapes of the multiple body features; marking the multiple body features in the body image, and determining a feature combination of the upper half of the body and a feature combination of the lower half of the body based on the screening of the multiple body features;

[0105] S142: Determine the sleeping posture type of the upper body part based on the positions and shapes of the corresponding multiple body features and the connection areas between the multiple body features in the feature combination of the upper body part, and determine the sleeping posture coefficient of the upper body part based on the identification of the sleeping posture type of the upper body part;

[0106] S143: In the feature combination of the lower half of the body, the sleeping posture type of the lower half of the body is determined based on the positions, shapes and connection areas between the corresponding multiple body features, and the sleeping posture coefficient of the lower half of the body is determined based on the identification of the sleeping posture type of the lower half of the body.

[0107] In an embodiment of the present application, a user's current sleep image is collected, multiple body features are determined based on the recognition of the user's current sleep image, and an image of the corresponding body is determined based on the positions and shapes of the multiple body features; multiple body features are marked in the body image, and a feature combination of the upper half of the body and a feature combination of the lower half of the body are determined based on the screening of the multiple body features, which is compatible with the overall consideration of the positions and shapes of the multiple body features, thereby ensuring the accuracy of the corresponding body image.

[0108] At this time, the system uses a camera or other image acquisition device to capture the user's current sleep state. This is usually done automatically at preset time intervals after the user falls asleep, or according to the user's instructions; the captured image should be clear, accurate and able to fully display the user's sleeping posture; the system uses image recognition technology, such as shape matching, to identify multiple body features of the user from the captured sleep images. These features include the head, shoulders, arms, torso, buttocks, thighs and calves; the system needs to be able to accurately distinguish these features and determine their position and shape in the image.

[0109] After determining multiple body features, the system will construct or reconstruct a complete body image based on the position and shape of these features. This image is two-dimensional or three-dimensional, depending on the system's capabilities and needs. In two-dimensional images, the system will use lines, outlines or filled areas to represent body features. In three-dimensional images, the system will use point clouds, meshes or solid models to represent them. After constructing or reconstructing the body image, the system will mark all previously identified body features in the image, which will help the system to further analyze and process the body features. The marking is done in the form of highlights, borders, labels or other forms, depending on the system's interface design and user preferences.

[0110] Finally, the system will classify body features into upper body feature combinations and lower body feature combinations based on certain screening criteria or rules. These criteria include the feature's importance, its impact on sleeping posture judgment, and its correlation with other features. For example, the head, shoulders, and arms are considered upper body features, while the hips, thighs, and calves are considered lower body features.

[0111] Specifically, assume that the system is monitoring a user's sleep and has collected the user's current sleep image; in the image, the system identifies the shoulders (located below the head, in the form of two connected ovals), arms (located on both sides of the shoulders, in the form of long strips), torso (connecting the head and hips, in the form of a rectangle or oval), hips (located below the torso, in the form of a circle or oval), thighs (connecting the hips and knees, in the form of a long strip) and calves (connecting the knees and feet, in the form of a long strip); the system constructs a two-dimensional body contour map based on the position and shape of these features; in the map, the system marks each body feature with lines or filled areas of different colors; then, based on the screening criteria, the system classifies the shoulders and arms as a feature combination of the upper part of the body, and classifies the hips, thighs and calves as a feature combination of the lower part of the body. In this way, the system completes the recognition and processing of the user's current sleep image, providing a basis for sleeping posture analysis and suggestions in subsequent steps.

[0112] Furthermore, in the feature combination of the upper half of the body, the sleeping position type of the upper half of the body is determined based on the positions, shapes and connection areas between the corresponding multiple body features, and the sleeping position coefficient of the upper half of the body is determined based on the identification of the sleeping position type of the upper half of the body, which is compatible with the overall consideration of the identification of the sleeping position type of the upper half of the body and ensures the accuracy of the sleeping position coefficient of the upper half of the body.

[0113] At this time, the system first focuses on the feature combination of the upper part of the body, which usually includes the shoulders, arms and the connecting areas between them (such as the neck, shoulder blades, etc.); the system needs to carefully analyze the position, shape and relative relationship of these features; based on the analysis of the feature combination of the upper part of the body, the system will next determine the type of sleeping position of the user's upper body; sleeping positions include supine, prone, side (left or right), etc.; the system will judge based on the specific performance of the features, for example: if the shoulders and arms are flat on the bed, it is a supine position; if the shoulders and arms are in a bent or folded state, it is a prone position; if the shoulders are tilted, one arm is under the body, and the other arm is stretched out or placed on the pillow, this is a side position.

[0114] After determining the type of sleeping position for the upper body, the system will determine the corresponding sleeping position coefficient based on the preset sleeping position coefficient table; the sleeping position coefficient is a quantitative indicator used to evaluate the comfort and health of the sleeping position; the coefficient value is between 0 and 1, where 1 represents the most ideal and comfortable sleeping position, and 0 represents the most uncomfortable or unhealthy sleeping position; the determination of the sleeping position coefficient takes into account multiple factors, such as the impact of the sleeping position on health (such as sleeping on the side helps reduce snoring, but also causes discomfort in the shoulders or arms), the user's personal sleep preferences and habits, and existing health problems.

[0115] Specifically, assume that the system is analyzing a user's upper body sleeping position; in the collected image, the system recognizes that the user's shoulders are slightly tilted, one arm (assuming it is the right arm) is flat on the bed, and the other arm (left arm) is bent and placed next to the pillow; based on this information, the system determines that the user's upper body sleeping position is right side sleeping; then, the system assigns a coefficient value to the sleeping position according to a preset sleeping position coefficient table or algorithm; assuming that in the table, right side sleeping is a more comfortable sleeping position for most users, especially for reducing snoring and acid reflux, so the system assigns a higher coefficient value to right side sleeping, such as 0.85 (out of 1 point), in this way, the system completes the determination of the sleeping position type and sleeping position coefficient of the upper part of the body, providing a basis for health analysis and recommendations in subsequent steps; at the same time, this information is also used for automatic adjustment of smart pillows to better adapt to the user's sleeping position and needs.

[0116] Therefore, in the feature combination of the lower half of the body, the sleeping position type of the lower half of the body is determined according to the positions, shapes and connection areas of the corresponding multiple body features, and the sleeping position coefficient of the lower half of the body is determined based on the identification of the sleeping position type of the lower half of the body, which is compatible with the overall consideration of the positions, shapes and connection areas of the corresponding multiple body features, thereby ensuring the accuracy of the sleeping position type of the lower half of the body.

[0117] At this time, the system turns its attention to the feature combination of the lower part of the body, which usually includes the buttocks, thighs, calves and the connecting areas between them (such as knees, hips, etc.); the system needs to carefully analyze the position, shape and relative relationship of these features in order to accurately determine the type of sleeping position of the lower body; based on the analysis of the feature combination of the lower part of the body, the system next determines the type of sleeping position of the user's lower body; the types of sleeping positions of the lower body include straight, bent, crossed, etc.; the system will judge according to the specific manifestations of the features, for example: if the buttocks, thighs and calves are arranged in a straight line, without obvious bending or crossing, it is a straight posture; if the thigh is bent at a certain angle relative to the buttocks, and the calf is further bent or straightened, this is a bent posture; if the thigh and calf of one leg are crossed above or below the other leg, this is a crossed posture.

[0118] After determining the type of sleeping position for the lower body, the system will determine the corresponding sleeping position coefficient based on the preset sleeping position coefficient table or algorithm; similar to the upper body sleeping position coefficient, the lower body sleeping position coefficient is also a quantitative indicator used to evaluate the comfort and health of the sleeping position; the coefficient value is between 0 and 1, where 1 represents the most ideal and comfortable sleeping position, and 0 represents the most uncomfortable or unhealthy sleeping position; the determination of the sleeping position coefficient takes into account multiple factors, such as the impact of the lower body sleeping position on the spine, joints and muscles, and the user's personal sleep preferences and habits. These factors will jointly affect the system's judgment of the lower body sleeping position coefficient.

[0119] Specifically, suppose the system is analyzing the sleeping posture of a user's lower body; in the collected image, the system recognizes that the user's buttocks are located in the middle and lower part of the bed, the thighs are bent at a certain angle relative to the buttocks, the calves are further bent, and the knees are facing the ceiling; at the same time, the user's two legs are not crossed and each remains independent; based on this information, the system determines that the user's lower body sleeping posture is a bent posture (assuming a slight knee bend); then, the system assigns a coefficient value to the sleeping posture according to a preset sleeping posture coefficient table or algorithm; assuming that in the table, a slight knee bend is relatively comfortable for most users A comfortable sleeping posture, especially for relieving waist pressure and promoting blood circulation, has a positive effect. Therefore, the system assigns a higher coefficient value to this bending posture, such as 0.8 (out of 1 point). In this way, the system completes the determination of the sleeping posture type and sleeping posture coefficient of the lower half of the body. This information will be combined with the upper body sleeping posture data to provide comprehensive support for subsequent sleep health analysis, automatic adjustment of smart pillows and user suggestions; for example, the system will recommend that users maintain the current sleeping posture combination (upper body lying on the right side + lower body slightly bent), or make adjustment suggestions based on the user's health status and preferences.

[0120] In an optional embodiment of the present application, it is assumed that there is a preset sleeping posture coefficient matching table for the lower half of the body, which is used to determine the sleeping posture type and sleeping posture coefficient of the lower half of the body based on the feature combination of the lower half of the body; the sleeping posture coefficient matching table for the lower half of the body is shown in Table 4:

[0121] Table 4. Sleeping posture coefficient matching table for the lower half of the body

[0122]

[0123]

[0124] Suppose that when the system analyzes the user's lower body sleeping position, it identifies the following features: the buttocks are located in the center of the bed, the thighs are slightly bent relative to the buttocks, the calves are further bent, the knees do not touch the bed, and the two legs are not crossed; according to the sleeping posture coefficient matching table for the lower half of the body, these features best fit the description of "mild bending"; therefore, the system determines that the user's lower body sleeping posture type is "mild bending" and assigns a sleeping posture coefficient of 0.85 to the lower half of the body.

[0125] refer to Figure 6 , in step S15, in the smart pillow, the user's current sleeping posture is determined based on the sleeping posture coefficient of the head, the sleeping posture coefficient of the upper body, and the sleeping posture coefficient of the lower body;

[0126] In the specific implementation process of the present invention, the specific steps are:

[0127] S151: The smart pillow has a built-in sleeping posture database, and determines the user's head sleeping posture based on the sleeping posture database, the head sleeping posture coefficient, and the image of the user's head;

[0128] S152: Determining a corresponding body matching coefficient based on the sleeping posture coefficient of the upper body and the sleeping posture coefficient of the lower body. If the body matching coefficient is less than a preset matching coefficient threshold, triggering autonomous adjustment of the sleeping posture coefficient of the upper body and the sleeping posture coefficient of the lower body to determine optimized sleeping posture coefficients of the upper body and the lower body;

[0129] S153: If the body matching coefficient is greater than the preset matching coefficient threshold, a first body posture coefficient is determined based on the user's head sleeping posture and the sleeping posture coefficient of the upper body, a second body posture coefficient is determined based on the user's head sleeping posture and the sleeping posture coefficient of the lower body, and the user's current sleeping posture is determined based on the mapping relationship between the first body posture coefficient, the second body posture coefficient and the user's sleeping posture.

[0130] In an embodiment of the present application, the smart pillow has a built-in sleeping position database, and determines the user's head sleeping position based on the sleeping position database, the head sleeping position coefficient and the image of the user's head. It is compatible with the overall consideration of the sleeping position database, the head sleeping position coefficient and the image of the user's head, ensuring the accuracy of the user's head sleeping position.

[0131] At this time, the smart pillow has a sleeping position database integrated inside. This database stores image data of various head sleeping positions and their corresponding sleeping position coefficients. These image data cover various sleeping positions such as front-facing, side-facing (left or right), and prone. The sleeping position coefficient is obtained through a comprehensive evaluation based on factors such as user feedback, and is used to quantify the comfort and health impact of each sleeping position.

[0132] Smart pillows are typically equipped with cameras or sensors that automatically capture images of the user's head after they lie down. These images can be two-dimensional or three-dimensional, depending on the pillow's hardware configuration and technical level. The captured images are then compared with samples in a sleeping position database. After capturing the user's head image, the system compares it with multiple samples in the sleeping position database. The system aims to find the database sample that best matches the user's head image. Once the best-matching database sample is found, the system determines the user's head sleeping position and obtains the corresponding sleeping position coefficient, which reflects the comfort level and health impact of the current sleeping position.

[0133] Specifically, assume that the smart pillow captures the following image features of the user's head: the head is facing up, slightly tilted to the right, the eyes are closed, and the face is relaxed; the database contains image data of various sleeping positions such as front-facing, side-facing (left / right), and prone, and their corresponding sleeping position coefficients; for example, the front-facing sleeping position has a higher coefficient (such as 0.85), indicating that this sleeping position is relatively comfortable and healthy for most people; while the prone sleeping position has a lower coefficient (such as 0.60) because long-term prone sleeping puts pressure on the cervical spine and respiratory system.

[0134] The built-in camera of the smart pillow captures a real-time image of the user's head, showing that the head is facing up and slightly tilted to the right; the system compares the captured image with multiple front-facing sleeping posture samples in the database and finds that one of the samples is highly matched with the user's image; based on the comparison results, the system determines that the user's head sleeping posture is front-facing, and obtains the corresponding sleeping posture coefficient (such as 0.85) from the database, which means that the current sleeping posture is relatively comfortable and healthy for the user. This example shows how the smart pillow uses its built-in sleeping posture database to determine the user's head sleeping posture and its corresponding sleeping posture coefficient. This information is crucial for subsequently providing personalized sleep advice and improving the user's sleep quality.

[0135] Furthermore, a corresponding body matching coefficient is determined based on the sleeping posture coefficient of the upper body and the sleeping posture coefficient of the lower body. If the body matching coefficient is less than a preset matching coefficient threshold, the sleeping posture coefficient of the upper body and the sleeping posture coefficient of the lower body are triggered to be autonomously adjusted to determine the optimized sleeping posture coefficient of the upper body and the sleeping posture coefficient of the lower body, which is compatible with the overall consideration of the sleeping posture coefficient of the upper body and the sleeping posture coefficient of the lower body, and ensures the accuracy of the corresponding body matching coefficient.

[0136] At this point, the system has determined the sleeping posture coefficients of the upper part of the user's body (such as shoulders, chest and back) and the lower part (such as buttocks, thighs and calves) based on previous analysis. These coefficients are based on the analysis of the position, shape and interconnected areas of various parts of the user's body, and are used to quantitatively evaluate the comfort and health impact of the sleeping posture; the body matching coefficient is a comprehensive indicator used to evaluate the coordination and matching degree between the sleeping postures of the upper and lower parts of the user's body. This coefficient is calculated by an algorithm that takes into account the differences, similarities or other relevant factors between the sleeping posture coefficients of the upper and lower body; the value of the body matching coefficient is usually between 0 and 1, where 1 means that the sleeping postures of the upper and lower body are completely matched and the most ideal, and 0 means completely mismatched and the least ideal.

[0137] The system compares the calculated body matching coefficient with the preset matching coefficient threshold, which is used to determine whether the current sleeping position needs to be adjusted; if the body matching coefficient is less than the preset threshold, the system considers that the current sleeping position is not ideal and needs to trigger the autonomous adjustment mechanism.

[0138] If the body matching coefficient is less than the preset threshold, the system will trigger the autonomous adjustment mechanism, which includes adjusting the hardness and inclination of the mattress, changing the shape, height or material of the pillow, or guiding the user to adjust the sleeping position through other means (such as sound prompts, vibration feedback, etc.); the purpose of the adjustment is to optimize the sleeping coefficients of the upper and lower body to make them more matched, thereby improving the overall sleeping comfort and health impact; after adjustment, the system will recalculate the sleeping coefficients of the upper and lower body until the body matching coefficient reaches or exceeds the preset threshold.

[0139] Specifically, assume that the system has determined that the sleeping posture coefficient of the upper part of the user's body is 0.75 (indicating that it is relatively comfortable but still has room for improvement), and the sleeping posture coefficient of the lower part is 0.60 (indicating that it is not comfortable enough); the preset matching coefficient threshold is 0.80; the system has calculated that the sleeping posture coefficient of the upper body is 0.75, and the sleeping posture coefficient of the lower body is 0.60; the system uses a certain algorithm to calculate the body matching coefficient, assuming that the algorithm takes into account factors such as the average value and difference of the sleeping posture coefficients of the upper and lower body; in this example, the body matching coefficient is calculated as (0.75+0.60) / 2-|0.75-0.60| / 2=0.675 (this formula is only an example, the actual algorithm is more complicated);.

[0140] The system compares the calculated body matching coefficient of 0.675 with the preset threshold of 0.80 and finds that it is less than the threshold; the system triggers the autonomous adjustment mechanism to improve the sleeping position of the lower body by adjusting the hardness or inclination of the mattress; after the adjustment, the system recalculates the sleeping position coefficients of the upper and lower body, assuming that the optimized sleeping position coefficient of the upper body is 0.80, and the sleeping position coefficient of the lower body is 0.75; at this time, the body matching coefficient is increased to (0.80+0.75) / 2-|0.80-0.75| / 2=0.875; this demonstrates how the system determines the body matching coefficient based on the sleeping position coefficients of the upper and lower parts of the body, and triggers the autonomous adjustment mechanism to optimize the sleeping position coefficient when necessary. This mechanism helps to improve the user's overall sleeping comfort.

[0141] Therefore, if the body matching coefficient is greater than the preset matching coefficient threshold, the first body posture coefficient is determined according to the user's head sleeping posture and the sleeping posture coefficient of the upper body, the second body posture coefficient is determined based on the user's head sleeping posture and the sleeping posture coefficient of the lower body, and the user's current sleeping posture is determined based on the first body posture coefficient, the second body posture coefficient and the user's sleeping posture mapping relationship, which is compatible with the overall consideration of the first body posture coefficient, the second body posture coefficient and the user's sleeping posture mapping relationship, and ensures the accuracy of the user's current sleeping posture. At the same time, the sleeping posture coefficient of the head, the sleeping posture coefficient of the upper body and the sleeping posture coefficient of the lower body are introduced, and the overall consideration of the sleeping posture coefficient of the head, the sleeping posture coefficient of the upper body and the sleeping posture coefficient of the lower body is realized, which ensures the accuracy of the user's current sleeping posture, makes full use of the smart pillow and the cameras on the surrounding sides, and realizes the coordinated control of the smart pillow and the cameras on the surrounding sides.

[0142] At this time, the system first checks whether the previously calculated body matching coefficient is greater than the preset matching coefficient threshold. This threshold is used to determine whether the user's overall sleeping posture has reached or exceeded the ideal matching standard without further analysis and adjustment, or is used to identify excellent sleeping posture cases that require special attention; if the body matching coefficient is greater than the preset threshold, the system will further analyze the user's head sleeping posture and the sleeping posture coefficient of the upper part of the body to determine the first body posture coefficient to quantitatively evaluate the coordination and comfort between the head and upper body in this excellent sleeping posture. The calculation method of this coefficient involves a comprehensive consideration of the head sleeping posture characteristics (such as front facing up, side facing up, prone, etc.) and the upper body sleeping posture coefficient.

[0143] The system will also determine a second body posture coefficient based on the user's head sleeping posture and the sleeping posture coefficient of the lower body to quantitatively evaluate the coordination and comfort of the head and lower body in this excellent sleeping posture. The calculation method of this coefficient is similar to that of the first body posture coefficient, but it focuses more on the analysis of the lower body sleeping posture coefficient; at the same time, the system will use the first body posture coefficient and the second body posture coefficient, combined with a preset user sleeping posture mapping relationship to determine the user's current sleeping posture. This mapping relationship is a complex algorithm or lookup table that maps different body posture coefficient combinations to specific categories representing excellent or ideal sleeping postures. These sleeping posture categories are also defined based on medical research or user preferences, and aim to describe whether the user's overall sleeping posture characteristics have reached an ideal state.

[0144] Specifically, assuming that the user's head sleeping posture is facing up, the sleeping posture coefficient of the upper body is 0.90, the sleeping posture coefficient of the lower body is 0.85, and the preset matching coefficient threshold is 0.85; the system first calculates the body matching coefficient (assuming it is the average of the sleeping posture coefficients of the upper and lower body) and finds that it is greater than the preset threshold 0.85.

[0145] Based on the head facing up and the upper body sleeping position coefficient of 0.90, the system uses an algorithm to calculate the first body posture coefficient of 0.92 (this value is only an example; the actual algorithm is more complex). This coefficient reflects the excellent coordination and comfort between the head and upper body sleeping positions;

[0146] Based on the head facing up posture and the lower body sleeping posture coefficient of 0.85, the system uses the same or similar algorithm to calculate the second body posture coefficient of 0.88, which indicates that the coordination between the head and lower body sleeping postures is also good;

[0147] The system uses the first body posture coefficient of 0.92 and the second body posture coefficient of 0.88, combined with a preset user sleeping posture mapping relationship to determine the user's current sleeping position; assuming that the mapping relationship maps the combination of a first body posture coefficient between 0.90 and 1.00 and a second body posture coefficient between 0.85 and 0.95 to "a very comfortable front-facing sleeping position with excellent whole-body coordination"; therefore, in this example, the system ultimately determines that the user's current sleeping position is "a very comfortable front-facing sleeping position with excellent whole-body coordination". This conclusion is used to show the user as a positive case or as a reference for further optimizing the sleeping environment.

[0148] In an optional embodiment of the present application, a current sleeping posture matching table is collected, and the current sleeping posture matching table is shown in Table 5:

[0149] Table 5 Current sleeping posture matching table

[0150]

[0151] According to the previously determined first body posture coefficient 0.85 and second body posture coefficient 0.72, the corresponding current sleeping posture description is found in the current sleeping posture matching table as "relatively comfortable face-up sleeping posture, with slightly uncomfortable lower body."

[0152] See also Figure 7 , Figure 7 Schematic diagram of the structure of a smart pillow system for recognizing a user's sleeping posture in an embodiment of the present invention; the smart pillow system for recognizing a user's sleeping posture includes:

[0153] The sub-region module 21 is used to detect the pressure area of ​​the smart pillow when the smart pillow is pressed against the user's head, and determine the spatial position and regional shape of multiple sub-regions based on the detection of the pressure area;

[0154] The first imaging module 22 is configured to trigger a response from a surrounding camera according to the position of the smart pillow, collect a current sleep image of the user based on the camera, and determine an image of the user's head according to the division of the current sleep image of the user;

[0155] A head sleeping posture coefficient module 23 is used to determine the head sleeping posture coefficient of the user's head relative to the smart pillow based on the image of the user's head, the spatial positions of the multiple sub-regions, and the regional morphology;

[0156] a body sleeping posture coefficient module 24 for determining a body image according to the division of the user's current sleeping image, and determining a sleeping posture coefficient of the upper body and a sleeping posture coefficient of the lower body based on recognition of the body image;

[0157] The sleeping posture module 25 is used to determine the user's current sleeping posture based on the sleeping posture coefficient of the head, the sleeping posture coefficient of the upper body, and the sleeping posture coefficient of the lower body in the smart pillow.

[0158] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A method for recognizing a user's sleeping posture using a smart pillow, characterized in that: include: When the smart pillow is pressed against the user's head, the pressed area of ​​the smart pillow is collected, and the spatial positions and regional shapes of multiple sub-areas are determined based on the detection of the pressed area; Triggering a response from a surrounding camera according to the position of the smart pillow, and collecting a current sleep image of the user based on the camera, and determining an image of the user's head according to the division of the current sleep image of the user; determining a head sleeping posture coefficient of the user's head relative to the smart pillow based on an image of the user's head, spatial positions of the multiple sub-regions, and regional morphologies; determining a body image according to the division of the user's current sleep image, and determining a sleeping posture coefficient of the upper half of the body and a sleeping posture coefficient of the lower half of the body based on recognition of the body image; In the smart pillow, the user's current sleeping posture is determined based on the sleeping posture coefficient of the head, the sleeping posture coefficient of the upper body, and the sleeping posture coefficient of the lower body.

2. The method for recognizing a user's sleeping posture using a smart pillow according to claim 1, wherein: When the smart pillow is pressed against the user's head, the pressed area of ​​the smart pillow is collected, and the spatial positions and regional shapes of multiple sub-areas are determined based on the detection of the pressed area, including: The smart pillow responds to the working state of the smart pillow based on the contact of the user's head with the smart pillow, the user's head continuously applies pressure to the smart pillow, and a pressure state diagram of the smart pillow is determined based on the pressure parameters detected by the smart pillow; Determining a detection node for detecting the user's sleeping posture based on recognition of the pressure state diagram of the smart pillow, collecting multiple pressure locations of the smart pillow at the detection node for detecting the user's sleeping posture, and determining a pressure area of ​​the smart pillow based on the multiple pressure locations and the shape of the smart pillow; The pressure area of ​​the smart pillow is detected, and multiple sub-areas are determined based on the detection of the pressure area of ​​the smart pillow, and the spatial positions and regional shapes of the multiple sub-areas are marked. At this time, the multiple sub-areas serve as the positions of the pressure areas and are arranged adjacent to each other in sequence.

3. The method for recognizing a user's sleeping posture using a smart pillow according to claim 1, wherein: The method triggers a response of a surrounding camera according to the position of the smart pillow, collects a current sleep image of the user based on the camera, and determines an image of the user's head according to the division of the current sleep image of the user, including: The location of the smart pillow is collected. The smart pillow detects surrounding devices at that location and triggers responses from surrounding cameras. At this time, the smart pillow is in online communication with surrounding cameras. Among the surrounding cameras, determining a shooting mode of the surrounding cameras for the smart pillow according to the position of the smart pillow, the corresponding surrounding environment type, and the current orientation of the surrounding cameras; The surrounding cameras only shoot in this shooting mode and collect the user's current sleep image; determine the user's head features based on the recognition of the user's current sleep image, and determine the image of the user's head based on the position and shape of the user's head features and the matching of the user's current sleep image.

4. The method for recognizing a user's sleeping posture using a smart pillow according to claim 1, wherein: The method of determining the sleeping posture coefficient of the user's head relative to the smart pillow based on the image of the user's head, the spatial positions of the multiple sub-regions, and the regional shapes includes: An image of the user's head is collected, and multiple contact nodes of the user's head on the smart pillow are determined based on recognition of the image of the user's head. Multiple head pressure features are determined based on the positions of the multiple contact nodes and the shape of the user's head.

5. The method for recognizing a user's sleeping posture using a smart pillow according to claim 4, wherein: The method of determining the sleeping posture coefficient of the user's head relative to the smart pillow based on the image of the user's head, the spatial positions of the multiple sub-regions, and the regional shapes also includes: Determining a first matching coefficient based on a comparison between the plurality of head pressure features and the spatial positions of the plurality of sub-regions, and determining a second matching coefficient based on a comparison between the plurality of head pressure features and the regional morphologies of the plurality of sub-regions; The head sleeping posture coefficient of the user's head relative to the smart pillow is determined based on the first matching coefficient, the second matching coefficient, and the head sleeping posture matching table.

6. The method for recognizing a user's sleeping posture using a smart pillow according to claim 1, wherein: The determining of the body image according to the division of the current sleep image of the user, and determining the sleeping posture coefficient of the upper half of the body and the sleeping posture coefficient of the lower half of the body based on the recognition of the body image, includes: The user's current sleep image is collected, multiple body features are determined based on the recognition of the user's current sleep image, and a corresponding body image is determined based on the positions and shapes of the multiple body features; multiple body features are marked in the body image, and a feature combination of the upper half of the body and a feature combination of the lower half of the body are determined based on the screening of the multiple body features.

7. The method for recognizing a user's sleeping posture using a smart pillow according to claim 6, characterized in that: The method of determining a body image according to the division of the user's current sleep image, and determining a sleeping posture coefficient of the upper half of the body and a sleeping posture coefficient of the lower half of the body based on the recognition of the body image, further includes: In the feature combination of the upper half of the body, determining the sleeping posture type of the upper half of the body according to the positions, shapes and connection areas between the corresponding multiple body features, and determining the sleeping posture coefficient of the upper half of the body according to the identification of the sleeping posture type of the upper half of the body; In the feature combination of the lower half of the body, the sleeping posture type of the lower half of the body is determined based on the positions, shapes and connection areas between the corresponding multiple body features, and the sleeping posture coefficient of the lower half of the body is determined based on the identification of the sleeping posture type of the lower half of the body.

8. The method for recognizing a user's sleeping posture using a smart pillow according to claim 1, wherein: In the smart pillow, determining the user's current sleeping posture based on the sleeping posture coefficient of the head, the sleeping posture coefficient of the upper body, and the sleeping posture coefficient of the lower body includes: The smart pillow has a built-in sleeping posture database, and determines the user's head sleeping posture based on the sleeping posture database, the head sleeping posture coefficient and the user's head image; The corresponding body matching coefficient is determined based on the sleeping posture coefficient of the upper body and the sleeping posture coefficient of the lower body. If the body matching coefficient is less than the preset matching coefficient threshold, the sleeping posture coefficient of the upper body and the sleeping posture coefficient of the lower body are triggered to autonomously adjust to determine the optimized sleeping posture coefficient of the upper body and the sleeping posture coefficient of the lower body.

9. The method for recognizing a user's sleeping posture using a smart pillow according to claim 8, wherein: The smart pillow determines the user's current sleeping position based on the sleeping position coefficient of the head, the sleeping position coefficient of the upper body, and the sleeping position coefficient of the lower body, and further includes: If the body matching coefficient is greater than the preset matching coefficient threshold, the first body posture coefficient is determined based on the user's head sleeping posture and the sleeping posture coefficient of the upper body, the second body posture coefficient is determined based on the user's head sleeping posture and the sleeping posture coefficient of the lower body, and the user's current sleeping posture is determined based on the mapping relationship between the first body posture coefficient, the second body posture coefficient and the user's sleeping posture.

10. A smart pillow system for recognizing a user's sleeping posture, characterized in that: The smart pillow's sleeping posture recognition system for a user is applied to the smart pillow's sleeping posture recognition method for a user as claimed in any one of claims 1 to 9, and the smart pillow's sleeping posture recognition system for a user includes: A sub-region module is used to detect the pressure area of ​​the smart pillow when the smart pillow is pressed against the user's head, and determine the spatial position and regional morphology of multiple sub-regions based on the detection of the pressure area; a first imaging module, configured to trigger a response from a surrounding camera according to the position of the smart pillow, collect a current sleep image of the user based on the camera, and determine an image of the user's head according to the division of the current sleep image of the user; A head sleeping posture coefficient module, used to determine the head sleeping posture coefficient of the user's head relative to the smart pillow based on the image of the user's head, the spatial positions of multiple sub-regions, and the regional morphology; a body sleeping posture coefficient module, configured to determine a body image according to the division of the user's current sleeping image, and determine a sleeping posture coefficient of the upper body and a sleeping posture coefficient of the lower body based on recognition of the body image; The sleeping posture module is used in the smart pillow to determine the user's current sleeping posture based on the sleeping posture coefficient of the head, the sleeping posture coefficient of the upper body, and the sleeping posture coefficient of the lower body.

Images