Health monitoring method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of smart televisions, in particular to a health monitoring method and device, computer equipment and a storage medium, and the method comprises the steps: collecting a human body image of a user based on image collection equipment connected with a television terminal, collecting first body data of the user based on sensing equipment connected with the television terminal, decomposing the human body image, and analyzing the first body data; determining second body data and emotion data of the user, determining posture data of the user, obtaining body function data, and generating a user health report according to the body function data, the emotion data and the posture data. A face image and a limb image are obtained by collecting a human body image and first body data of a user, and second body data, emotion data and posture data are determined, so that a user health report is generated and displayed on a television terminal. Therefore, the television terminal is used for carrying out data analysis on the human body behaviors of the user, health monitoring based on the television equipment is realized, and the intelligent degree of health monitoring of the television equipment is improved.

Description

Technical Field

[0001] The present invention relates to the field of smart televisions, and in particular to a health monitoring method, device, computer equipment and storage medium. Background Art

[0002] With the rapid development of smart home technology, smart TVs have become an important tool for obtaining information. At the same time, with the increasing prevalence of health issues, people's demand for health monitoring and management is also increasing. Traditional health monitoring devices, such as smart bracelets and smart watches, can provide certain health data, but due to the inconvenience of wearing and the limitations of the data, they cannot fully meet user needs.

[0003] At present, most health monitoring methods through smart TVs are based on simple single data monitoring, such as detecting human body temperature through infrared devices to determine whether there are physical abnormalities. This method has large errors and is difficult to provide users with more comprehensive health data, resulting in users' health problems not being taken seriously.

[0004] Therefore, how to use TV terminals to perform data analysis on users' human behaviors and thus realize health monitoring based on TV devices has become an urgent problem to be solved. Summary of the Invention

[0005] Embodiments of the present invention provide a health monitoring method, apparatus, computer device, and storage medium to solve the problem of how to use a television terminal to perform data analysis on a user's human behavior, thereby realizing health monitoring based on a television device.

[0006] In a first aspect, an embodiment of the present invention provides a health monitoring method, which is applied to a television terminal and includes: Based on the image acquisition device connected to the television terminal, the user's body image is collected; based on the sensor device connected to the television terminal, the user's first body data is collected; Decomposing the human body image to obtain a facial image and a limb image, determining second body data and emotion data of the user based on the facial image, and determining posture data of the user based on the limb image; The first body data and the second body data are integrated to obtain human body function data, a user health report is generated based on the human body function data, the emotion data and the posture data, and the user health report is displayed on the television terminal.

[0007] In a second aspect, an embodiment of the present invention provides a health monitoring device, which is applied to a television terminal and includes: a data acquisition module, configured to acquire a human body image of a user based on an image acquisition device connected to the television terminal, and to acquire first body data of the user based on a sensor device connected to the television terminal; a facial image decomposition module, configured to decompose the human body image to obtain a facial image and a limb image, determine the second body data and emotion data of the user based on the facial image, and determine the posture data of the user based on the limb image; A health report generation module is used to fuse the first body data with the second body data to obtain human body function data, generate a user health report based on the human body function data, the emotion data and the posture data, and display the user health report on the TV terminal.

[0008] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned health monitoring method when executing the computer program.

[0009] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above-mentioned health monitoring method when executed by a processor.

[0010] Compared with the prior art, the present invention has the following beneficial effects: by collecting a user's body image based on an image acquisition device connected to a television terminal, collecting the user's first body data based on a sensing device connected to the television terminal, decomposing the body image to obtain a facial image and a limb image, determining the user's second body data and emotional data based on the facial image, determining the user's posture data based on the limb image, fusing the first body data with the second body data to obtain human body function data, generating a user health report based on the human body function data, emotional data, and posture data, and displaying the user health report on the television terminal. By collecting the user's body image and first body data, obtaining facial images and limb images, and determining the second body data, emotional data, and posture data, a user health report is generated and displayed on the television terminal. Thus, the television terminal is used to perform data analysis on the user's human behavior to achieve health monitoring based on the television device, thereby improving the intelligence level of health monitoring performed by the television device. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0012] Figure 1 This is a schematic diagram of an application environment of a health monitoring method provided in Example 1 of the present invention; Figure 2 This is a flow chart of a health monitoring method provided in the second embodiment of the present invention; Figure 3 This is a flow chart of a health monitoring method provided in Example 3 of the present invention; Figure 4 This is a flow chart of a health monitoring method provided in the fourth embodiment of the present invention; Figure 5 This is a flowchart of a health monitoring method provided in Example 5 of the present invention; Figure 6 This is a flowchart of a health monitoring method provided by Example 6 of the present invention; Figure 7 This is a flow chart of a health monitoring device provided by Embodiment 7 of the present invention; Figure 8 This is a structural diagram of a computer device provided in Example 8 of the present invention. DETAILED DESCRIPTION

[0013] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0014] like Figure 1As shown, it is a schematic diagram of the application environment of a health monitoring method provided in Example 1 of the present invention, wherein the health monitoring method is applied to a television terminal, wherein the client and the server are connected for communication, the server is connected for communication with the television terminal, and the user can provide conditions, requirements and operation instructions for health monitoring by operating the client, and the server is used to generate control instructions for the television terminal according to the relevant content sent by the client, so that the user can remotely control the television terminal. The client includes but is not limited to various computer devices such as personal computers, laptops, smart phones, tablet computers and portable wearable devices. The computer device corresponding to the server can be implemented with an independent server or a server cluster composed of multiple servers.

[0015] like Figure 2 FIG. 1 is a flow chart of a health monitoring method provided in Embodiment 2 of the present invention. The health monitoring method is applied to a television terminal and may include the following steps: Step S201: Based on the image acquisition device connected to the TV terminal, a user's body image is acquired; based on the sensor device connected to the TV terminal, first body data of the user is acquired.

[0016] The image acquisition device needs to be connected to the TV terminal. A common image acquisition device is a camera. In practical scenarios, this can be a built-in camera on a smart TV or an external camera connected via a USB port. This connection method ensures that the captured image data can be smoothly transmitted to the TV terminal for subsequent processing.

[0017] Image acquisition devices capture users at a regular interval, capturing images containing comprehensive body information. These images include rich content, such as facial features, body movements, and body contours. It's like taking a photo of a user, except that the images are captured for a specific purpose, allowing for subsequent health analysis.

[0018] Sensor devices also need to be connected to the TV terminal. Different types of sensor devices may connect to the TV in different ways, such as wireless connections such as Bluetooth and Wi-Fi, or through wired interfaces. This ensures that the data collected by the sensor devices can be transmitted to the TV terminal in a timely and accurate manner.

[0019] The first body data includes a variety of information related to the user's health, such as body temperature data, heart rate data, and environmental data.

[0020] Step S202 , decomposing the human body image to obtain a facial image and a limb image, determining the second body data and emotion data of the user based on the facial image, and determining the posture data of the user based on the limb image.

[0021] The captured human body image, which contains the user's overall body information, is separated into facial and limb images through image processing technology. Image recognition and segmentation algorithms are typically used to decompose the image based on information such as the body's physiological characteristics and the distribution of pixels in the image. For example, the facial area is segmented from the overall image by identifying facial contours and facial features. The limbs are then determined and segmented based on information such as limb joints and body contours.

[0022] Secondary body data includes information related to human physiological functions, such as heart rate, extracted from facial images. Advanced image processing and analysis techniques extract specific features and patterns of change from facial images to infer relevant physiological indicators. For example, to determine heart rate, blood circulation in the human body causes subtle periodic changes in facial skin color. Using high-frame-rate image acquisition equipment and specialized algorithms, continuous facial images are analyzed to capture the frequency of these color changes, thereby calculating heart rate. This non-contact heart rate measurement method provides a more convenient way to monitor health.

[0023] Facial expressions are used to determine the user's current emotional state. Human emotions are often intuitively expressed through facial expressions, such as a smile when happy and a frown when sad. Expression recognition algorithms identify and analyze features such as facial muscle movements, the shape and position of facial features, and other changes. These algorithms are typically trained on large amounts of facial expression data and can learn facial feature patterns corresponding to different emotions. For example, detecting a combination of features such as a raised mouth corner and narrowed eyes can indicate that the user is in a happy state.

[0024] Limb images are used to determine the user's body posture, including standing, sitting, and lying down, as well as whether the posture is correct, such as hunching over or sitting crookedly. Using a skeletal keypoint detection algorithm, the system identifies the various joints of the human body, such as the shoulders, elbows, wrists, hips, knees, and ankles, in limb images. The system analyzes the position, angle, and relationship between these joints to determine the user's posture. For example, if the line connecting the shoulder and back joints deviates from the normal vertical position, it can be determined that the user is hunched over.

[0025] Step S203: Fusing the first body data with the second body data to obtain human body function data, generating a user health report based on the human body function data, the emotion data and the posture data, and displaying the user health report on the TV terminal.

[0026] Among them, the first body data is directly collected by sensing equipment, such as body temperature, heart rate and environmental data measured by sensors, and the second body data is obtained by analyzing facial images, such as the heart rate value determined by facial images.

[0027] Because the two data sources are different but both are related to human physiological functions, the fusion process requires comprehensive consideration of their characteristics and reliability. A common fusion method is weighted averaging, which assigns different weights to the two data types based on their accuracy and stability, then calculates the weighted average. For example, if heart rate data directly measured by a sensor is relatively stable and accurate over a long period of time, it can be given a higher weight. On the other hand, heart rate data obtained through facial image analysis may be affected by factors such as lighting and facial expression, so it can be given a relatively lower weight. This approach allows for the generation of comprehensive data that more comprehensively and accurately reflects the functional state of the human body—in other words, human function data.

[0028] Based on human function data, emotional data, and posture data, a comprehensive analysis is performed using pre-set algorithms and models. Human function data reflects the body's physiological state, emotional data reflects the psychological state, and posture data is related to the body's daily posture habits. For example, combining heart rate and body temperature in human function data can determine whether the body is in a healthy physiological state; emotional data can be analyzed to understand the user's recent psychological stress and mood swings; and posture data can be reviewed to assess whether the user's daily posture is correct and whether there are any potential health risks.

[0029] Health reports can include detailed information on multiple aspects. In terms of physical health, there will be a judgment on the normality of indicators such as heart rate and body temperature, as well as trend analysis. On the psychological level, emotional states will be described and suggestions will be given, such as prompting users to take appropriate relaxation measures when under great emotional stress. In terms of posture, poor posture problems will be pointed out and improvement suggestions will be given, such as reminding users to maintain correct sitting and standing postures. The generated health report is displayed on the TV terminal with an intuitive and easy-to-understand interface. Interface design usually combines multiple forms such as charts and text descriptions. For example, a line chart can be used to display the changing trends of heart rate and body temperature, allowing users to clearly see the dynamic changes in their physical indicators. The meaning of each data and health suggestions are described in detail in text to facilitate user understanding and operation.

[0030] Displaying health reports on TV terminals fully leverages the popularity and large-screen display advantages of smart TVs in the home. Users can conveniently view their health reports at home without using additional devices, keeping abreast of their health status and adapting their lifestyles and health management based on the recommendations in the reports.

[0031] Optionally, after the user health report is displayed on the television terminal, the following steps may be further included: Performing an abnormality analysis on the health report according to a preset health standard to obtain an abnormality analysis result; Determine an early warning strategy based on the abnormality analysis results.

[0032] Different warning levels are determined based on factors such as the severity and urgency of the abnormality analysis results. For example, a minor abnormality, such as a slightly elevated heart rate, might be assigned a low-level warning, while a severe abnormality, such as a sharp rise in blood pressure exceeding the dangerous range, might be assigned a high-level warning.

[0033] Choose the appropriate warning method for different warning levels. Low-level warnings may use gentle reminders, such as a pop-up prompt box on the TV screen, informing the user in text form that there is a slight abnormality in a certain data and suggesting that the user pay appropriate attention. Medium-level warnings may add sound reminders, emitting specific prompt sounds through the TV, and displaying more detailed abnormality information and suggestions, such as reminding the user to conduct further inspections. High-level warnings will adopt more urgent and intense warning methods, such as frequent sound and light alarms, and automatically contact the user's emergency contacts or medical service agencies to ensure that the user can get professional help in a timely manner.

[0034] The warning content is customized based on the abnormality analysis results. In addition to informing users of the specific abnormal data and warning level, relevant health advice and countermeasures are also provided. For example, if blood sugar is abnormal, the user will be advised to control diet, increase exercise, and be reminded to measure blood sugar regularly; if posture is abnormal, corrective posture adjustment suggestions will be given.

[0035] In an embodiment of the present application, a human body image of a user is collected based on an image acquisition device connected to a television terminal, and first body data of the user is collected based on a sensing device connected to the television terminal. The human body image is decomposed to obtain a facial image and a limb image, and the second body data and emotional data of the user are determined based on the facial image. The posture data of the user is determined based on the limb image. The first body data and the second body data are fused to obtain human body function data. Based on the human body function data, emotional data and posture data, a user health report is generated, and the user health report is displayed on the television terminal. By collecting the human body image and the first body data of the user, a facial image and a limb image are obtained, and the second body data, emotional data and posture data are determined, a user health report is generated and displayed on the television terminal. Thus, the television terminal is used to perform data analysis on the user's human behavior to realize health monitoring based on the television device and improve the intelligence level of health monitoring performed by the television device.

[0036] like Figure 3FIG. 2 is a flow chart of a health monitoring method according to a third embodiment of the present invention. In step S202, determining the second body data and emotion data of the user based on the facial image may include the following steps: Step S301 , extracting the primary target color and the secondary target color in the facial image, analyzing image changes of the primary target color and the secondary target color, determining the user's heart rate signal, and calculating the heart rate value based on the heart rate signal.

[0037] Optionally, according to a preset facial area to be analyzed, the main target light intensity of the main target color and the secondary target light intensity of the secondary target color in the area to be analyzed in the facial image are analyzed to obtain a main signal corresponding to the main target light intensity and a motion artifact signal corresponding to the secondary target color.

[0038] The main signal is corrected using the motion artifact signal to obtain a heart rate signal, and the heart rate signal is calculated to obtain a heart rate value.

[0039] Step S302: determining the second body data of the user according to the heart rate value.

[0040] The primary and secondary target colors are colors with specific characteristics in facial images. Generally speaking, the primary target color may be related to the color of the blood beneath the facial skin, as blood flow causes subtle changes in skin color. The secondary target color may serve as a reference color to assist in analysis. For example, the primary target color may be a hue close to red, as blood is rich in hemoglobin and thus appears red. The secondary target color may be the color of the facial surroundings or a relatively stable color in other parts of the skin.

[0041] Blood circulation in the human body causes subtle, periodic changes in facial skin color. Using high-frame-rate image acquisition equipment, facial images are continuously captured. The changes in primary and secondary target colors within these consecutive images are then analyzed. A specialized algorithm captures the frequency of these color changes, which corresponds to the heart rate signal. This is because each heartbeat causes a corresponding change in skin color due to blood circulation. By detecting the periodicity of these color changes, the heart rate rhythm can be determined.

[0042] The purpose of pre-selecting facial regions for analysis is to more accurately obtain color information related to heart rate. Typically, we select areas with even skin and a relatively concentrated distribution of blood vessels, such as the cheeks.

[0043] The primary target light intensity of the primary target color and the secondary target light intensity of the secondary target color in the analyzed area are analyzed. Changes in the primary target light intensity are related to color changes caused by blood flow, while the secondary target light intensity can serve as a reference for environmental interference factors. Through this analysis, a primary signal corresponding to the primary target light intensity and a motion artifact signal corresponding to the secondary target color are obtained. Motion artifact signals are mainly caused by color changes due to factors such as slight facial movements and changes in expression. These changes are not caused by heart rate but are interference signals.

[0044] The motion artifact signal corrects the primary signal, removing interference and producing a more accurate heart rate signal. This is like filtering out noise in a noisy environment to retain only the useful sound signal. This corrected heart rate signal more accurately reflects the user's heart rate. Further computational processing is performed on this corrected heart rate signal, using an algorithm to convert the signal's frequency into a specific heart rate value, or beats per minute.

[0045] Secondary body data is data related to human physiological functions obtained from facial image analysis, with heart rate being a key component. In health monitoring, heart rate is a key indicator of heart function and overall health. Normal heart rate ranges vary by age, gender, and physical condition. By determining the heart rate, we can initially determine whether the user's heart function is normal and whether there are any potential health issues. For example, a fast heart rate may indicate stress, certain medical conditions, or excessive exercise; a slow heart rate may be associated with heart disease or prolonged rest. Therefore, incorporating heart rate into secondary body data provides important physiological information for subsequent health assessments.

[0046] In this embodiment, heart rate information is obtained by analyzing facial images, greatly facilitating health monitoring. This method requires no additional equipment from the user; heart rate monitoring can be achieved using only an image acquisition device, making it particularly suitable for home health monitoring scenarios. Furthermore, combining heart rate values ​​as part of the secondary body data with other health data allows for a more comprehensive and accurate assessment of the user's health status, laying the foundation for generating personalized health reports and providing targeted health recommendations.

[0047] like Figure 4 FIG. 1 is a flow chart of a health monitoring method provided in a fourth embodiment of the present invention. Step S301 of extracting the primary target color and the secondary target color from the facial image, analyzing image changes of the primary target color and the secondary target color, determining the user's heart rate signal, and calculating the heart rate value based on the heart rate signal may include the following steps: Step S401 , obtaining a preset action unit library corresponding to facial expressions, extracting facial feature points of the facial image, and analyzing position changes of the facial feature points.

[0048] Step S402 : Calculate the position change to obtain the relative position distance between each of the facial feature points, and determine the facial action based on the position change of the feature points and the action unit library.

[0049] Step S403: obtaining emotion data according to the facial action and the relative position distance.

[0050] The preset action unit library for facial expressions is a pre-established knowledge base containing basic action units corresponding to various facial expressions. These action units are the fundamental elements that make up different facial expressions, such as raising an eyebrow or lowering the corners of the mouth. This action unit library is based on extensive facial expression research and statistical data, providing a reference standard for subsequent facial expression analysis.

[0051] In facial images, a specific algorithm extracts representative facial feature points. These feature points are typically located in key areas such as the eyes, eyebrows, nose, and mouth. Changes in their position and shape can reflect changes in facial expression. The positions of these feature points at different times are analyzed to observe their movement and changes. For example, when a person smiles, the feature points at the corners of the mouth move upward, and the feature points around the eyes also change accordingly.

[0052] The positional changes of the feature points are calculated to obtain the relative distances between each facial feature point. These changes in relative distances can more accurately describe the degree of change in facial expression. For example, when calculating the distance between the corner of the mouth feature point and the cheek feature point, if this distance increases, it may indicate that the user is smiling or laughing.

[0053] Facial movements are determined based on changes in feature point positions and the action unit library. The actual changes in feature points are compared with the standard actions in the action unit library to determine which basic action unit or combination of action units the facial movement belongs to. For example, if feature point changes such as a raised eyebrow and widened eyes are detected, the combination with the action unit library can determine that this is part of a surprised expression.

[0054] Facial movements and relative distances are crucial for determining emotions. Different emotions correspond to distinct combinations of facial movements and changes in the relative distances between key points. For example, happiness is often accompanied by movements like an upturned mouth corner and narrowed eyes, and the relative distances between these key points exhibit specific patterns of change. Sadness, on the other hand, can be manifested by drooping eyebrows and a drooping mouth corner. By comprehensively analyzing these facial movements and relative distances, and utilizing pre-set algorithms and models, the user's current emotional state, such as happiness, sadness, anger, or surprise, can be determined.

[0055] Emotional data goes beyond simple emotion types and can also quantify the intensity of emotions. For example, based on the degree of change in relative distance, it can be used to determine whether happiness is mild joy or intense excitement. This type of emotional data can more accurately reflect the user's true emotional state, providing more detailed information for subsequent health assessments and interventions.

[0056] In this embodiment, by accurately capturing the user's emotional data, emotional issues can be promptly identified and appropriate intervention measures can be taken, such as providing psychological counseling and recommending relaxation activities. This helps promote the user's physical and mental health and improve their quality of life. Furthermore, combining emotional data with other health data (such as physiological function data and posture data) enables a more comprehensive assessment of the user's health status, providing stronger support for personalized health management.

[0057] like Figure 5 FIG. 2 is a flow chart of a health monitoring method according to a fifth embodiment of the present invention. Step S202 of determining the user's posture data based on the limb image may further include the following steps: Step S501 : extracting the key point position coordinates corresponding to the body key points in the limb image according to preset body key points.

[0058] Step S502: determining the real-time relative position relationship according to the key point position coordinates.

[0059] Step S503: determining the user's posture data according to the real-time relative position relationship.

[0060] The preset body key points are pre-defined representative points on the human body, typically including the head, shoulders, elbows, wrists, hips, knees, ankles, etc. These key points form the basic framework of the human skeleton, and their position and movement can reflect the overall posture and movement of the human body.

[0061] Computer vision techniques, such as deep learning-based human pose estimation algorithms, are used to identify and extract the coordinates of these pre-defined key points in limb images. These coordinates are typically expressed in two dimensions, such as (x, y) coordinates in pixels. For example, the algorithm can accurately locate the pixel locations of key points on the shoulder by analyzing features such as the body's contour and texture in the image.

[0062] Based on the extracted keypoint coordinates, the real-time relative positional relationships between keypoints are calculated. This may include information such as the distance and angle between the two points. For example, calculating the distance between two keypoints on the shoulder can reveal the width of the shoulder; calculating the angle between the line connecting the elbow and shoulder keypoints and the vertical direction can determine the arm's lift angle.

[0063] Real-time relative position relationships reflect the posture structure of the human body at the current moment. Different postures can cause significant changes in the relative positions of key points. For example, when a person is standing, the relative position relationships between key points on the legs are different from when they are bending over. By analyzing these changes in relative position relationships, dynamic changes in human posture can be captured.

[0064] Based on the calculated real-time relative position relationship, combined with preset posture judgment rules or models, the user's posture data is determined. Posture data can include posture types, such as standing, sitting, stooping, and lying down. The specific posture state can be further refined, such as correct sitting posture or hunched sitting posture. For example, if the distance and angle between the key points of the legs are detected to conform to the typical characteristics of standing, and the relative positions of the key points of the upper body remain upright, the user can be judged to be in a standing posture.

[0065] Posture data is valuable for health monitoring. Long-term poor posture can lead to health problems such as muscle fatigue and spinal deformity. By continuously monitoring posture data, we can promptly identify users' poor posture habits and provide corresponding reminders and suggestions to help them improve their posture and maintain their health.

[0066] In this embodiment, by accurately capturing user posture data from limb images, the health monitoring system is provided with detailed information about the user's body posture. This posture data can be combined with other health data (such as physiological function data and emotional data) to provide a more comprehensive assessment of the user's health status. Furthermore, in scenarios requiring careful attention to posture, such as rehabilitation training and physical exercise, posture data can serve as an important reference, guiding users in performing appropriate activities and training.

[0067] like Figure 6FIG. 2 is a flow chart of a health monitoring method provided by Embodiment 6 of the present invention. In step S201, the first body data of the user is collected based on a sensor device connected to the television terminal. The method may further include the following steps: Step S601: Acquire body temperature data, heart rate data, and environmental data collected by the sensor device.

[0068] Step S602: determining the first body data of the user according to the body temperature data, the heart rate data and the environmental data.

[0069] After acquiring body temperature, heart rate, and environmental data, a comprehensive analysis is required. Normal body temperature and heart rate ranges may vary under different environmental conditions. For example, in a hot environment, a person's body temperature may rise slightly, and their heart rate may also increase accordingly to adapt to the changing environment. Therefore, body temperature and heart rate data cannot be viewed in isolation; they must be combined with environmental data for a comprehensive assessment.

[0070] The user's primary body data is determined based on comprehensive analysis using pre-set algorithms and models. This primary body data isn't just simple body temperature and heart rate values; it may also include corrected and evaluated physiological status information. For example, if the ambient temperature is high, but the user's body temperature and heart rate are within a reasonable range, this indicates that the user's body is adapting well to the environment. However, if the body temperature and heart rate exceed the normal adaptation range, this may indicate an abnormality in the user's body. This determined primary body data more accurately reflects the user's basic physical condition in the current environment.

[0071] In this embodiment, sensor devices are used to collect multiple data points and conduct comprehensive analysis to determine the first body data, providing more comprehensive and accurate information for health monitoring. This method of collecting and analyzing health data that comprehensively considers environmental factors helps to detect abnormal changes in the user's body more promptly, providing early warning of potential health problems, and also provides strong support for the subsequent development of personalized health recommendations and intervention measures. For example, based on the first body data, users can be reminded to pay attention to heatstroke prevention and cooling in high-temperature environments, and to reasonably adjust the intensity of activities, thereby better maintaining the user's physical health.

[0072] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0073] like Figure 7FIG. 7 is a schematic diagram of a health monitoring device according to a seventh embodiment of the present invention. The health monitoring device corresponds to the health monitoring method according to the above embodiment. The health monitoring device includes a data acquisition module 71, a facial image decomposition module 72, and a health report generation module 73. The functional modules are described in detail as follows: A data acquisition module 71 is configured to acquire a user's body image based on an image acquisition device connected to the television terminal, and to acquire first body data of the user based on a sensor device connected to the television terminal; a facial image decomposition module 72 for decomposing the human body image to obtain a facial image and a limb image, determining the second body data and emotion data of the user based on the facial image, and determining the posture data of the user based on the limb image; The health report generation module 73 is used to fuse the first body data with the second body data to obtain human body function data, generate a user health report based on the human body function data, the emotion data and the posture data, and display the user health report on the TV terminal.

[0074] Optionally, the facial image decomposition module 72 includes: a heart rate signal determination unit, configured to extract a primary target color and a secondary target color from the facial image, analyze image changes of the primary target color and the secondary target color, determine a heart rate signal of the user, and calculate a heart rate value based on the heart rate signal; The second body data determining unit is configured to determine the second body data of the user according to the heart rate value.

[0075] Optionally, the heart rate signal determining unit includes: a facial image analysis subunit, configured to analyze, based on a preset facial area to be analyzed, a primary target light intensity of a primary target color and a secondary target light intensity of a secondary target color in the area to be analyzed in the facial image, to obtain a primary signal corresponding to the primary target light intensity and a motion artifact signal corresponding to the secondary target color; The heart rate value calculation subunit is configured to use the motion artifact signal to correct the main signal to obtain a heart rate signal, and calculate the heart rate signal to obtain a heart rate value.

[0076] Optionally, the facial image decomposition module 72 includes: a position change analysis unit, configured to obtain a preset action unit library corresponding to facial expressions, extract facial feature points of the facial image, and analyze position changes of the facial feature points; A facial action determination unit is configured to calculate the position change to obtain relative position distances between the facial feature points, and determine the facial action based on the position change of the feature points and the action unit library; The emotion data obtaining unit is configured to obtain emotion data according to the facial action and the relative position distance.

[0077] Optionally, the facial image decomposition module 72 includes: A key position coordinate extraction unit, configured to extract key point position coordinates corresponding to the body key points in the limb image based on preset body key points; A real-time relative position relationship determining unit, configured to determine the real-time relative position relationship based on the position coordinates of the key points; A posture data determining unit is used to determine the posture data of the user according to the real-time relative position relationship.

[0078] Optionally, the data acquisition module 71 includes: A data acquisition unit, configured to acquire body temperature data, heart rate data, and environmental data collected by the sensing device; The first body data confirmation unit is used to determine the first body data of the user according to the body temperature data, the heart rate data and the environmental data.

[0079] Optionally, the health monitoring device further includes: an abnormality analysis module, configured to, after displaying the user health report on the television terminal, perform abnormality analysis on the health report according to preset health standards to obtain abnormality analysis results; The early warning strategy determination module is used to determine the early warning strategy based on the abnormality analysis results.

[0080] For the specific definition of the health monitoring device, please refer to the definition of the health monitoring method above and will not be repeated here. The above-mentioned health monitoring device and each module in the health monitoring device can be implemented in whole or in part by software, hardware, or a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0081] like Figure 8The figure shows a schematic diagram of the structure of a computer device provided in Example 8 of the present invention. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a health monitoring method is implemented.

[0082] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the health monitoring method in the above embodiment is implemented, for example Figures 2 to 6 Alternatively, when the processor executes the computer program, the functions of the health monitoring device or each module / unit in the embodiment of the health monitoring device are realized, for example Figure 7 The functions of the data acquisition module 71, facial image decomposition module 72, and health report generation module 73 are not described here in detail to avoid repetition.

[0083] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the health monitoring method in the above embodiment is implemented, such as Figures 2 to 6 Alternatively, when the computer program is executed by the processor, the functions of each module / unit in the embodiment of the health monitoring device are realized, for example Figure 7 The data acquisition module 71, the facial image decomposition module 72, and the health report generation module 73 are not described here in detail to avoid repetition. The computer-readable storage medium may be non-volatile or volatile.

[0084] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0085] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0086] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A health monitoring method, characterized in that: The health monitoring method is applied to a television terminal, and the health monitoring method includes: Based on the image acquisition device connected to the television terminal, the user's body image is collected; based on the sensor device connected to the television terminal, the user's first body data is collected; Decomposing the human body image to obtain a facial image and a limb image, determining second body data and emotion data of the user based on the facial image, and determining posture data of the user based on the limb image; The first body data and the second body data are integrated to obtain human body function data, a user health report is generated based on the human body function data, the emotion data and the posture data, and the user health report is displayed on the television terminal.

2. The health monitoring method according to claim 1, characterized in that: Determining the second body data and emotion data of the user based on the facial image includes: extracting a primary target color and a secondary target color from the facial image, analyzing image changes of the primary target color and the secondary target color, determining a heart rate signal of the user, and calculating a heart rate value based on the heart rate signal; Determine second body data of the user according to the heart rate value.

3. The health monitoring method according to claim 2, characterized in that: The extracting the primary target color and the secondary target color from the facial image, analyzing image changes of the primary target color and the secondary target color, determining a heart rate signal of the user, and calculating a heart rate value according to the heart rate signal includes: According to a preset facial area to be analyzed, analyzing the primary target brightness intensity of the primary target color and the secondary target brightness intensity of the secondary target color in the area to be analyzed in the facial image, to obtain a primary signal corresponding to the primary target brightness intensity and a motion artifact signal corresponding to the secondary target color; The main signal is corrected using the motion artifact signal to obtain a heart rate signal, and the heart rate signal is calculated to obtain a heart rate value.

4. The health monitoring method according to claim 1, wherein: Determining the second body data and emotion data of the user based on the facial image includes: Obtaining a preset action unit library corresponding to facial expressions, extracting facial feature points of the facial image, and analyzing position changes of the facial feature points; Calculating the position changes to obtain relative position distances between the facial feature points, and determining facial actions based on the position changes of the feature points and the action unit library; Emotion data is obtained according to the facial action and the relative position distance.

5. The health monitoring method according to claim 1, characterized in that: Determining the posture data of the user based on the limb image includes: Extracting the key point position coordinates corresponding to the body key point in the limb image according to the preset body key points; Determining the real-time relative position relationship according to the position coordinates of the key points; The user's posture data is determined based on the real-time relative position relationship.

6. The health monitoring method according to claim 1, characterized in that: The collecting the first body data of the user based on the sensor device connected to the television terminal includes: Acquiring body temperature data, heart rate data, and environmental data collected by the sensing device; The first body data of the user is determined according to the body temperature data, the heart rate data, and the environmental data.

7. The health monitoring method according to any one of claims 1 to 6, characterized in that: After the user health report is displayed on the television terminal, the method further includes: Performing an abnormality analysis on the health report according to a preset health standard to obtain an abnormality analysis result; Determine an early warning strategy based on the abnormality analysis results.

8. A health monitoring device, characterized in that: The health monitoring device is applied to a television terminal, and the health monitoring device includes: a data acquisition module, configured to acquire a human body image of a user based on an image acquisition device connected to the television terminal, and to acquire first body data of the user based on a sensor device connected to the television terminal; a facial image decomposition module, configured to decompose the human body image to obtain a facial image and a limb image, determine the second body data and emotion data of the user based on the facial image, and determine the posture data of the user based on the limb image; A health report generation module is used to fuse the first body data with the second body data to obtain human body function data, generate a user health report based on the human body function data, the emotion data and the posture data, and display the user health report on the TV terminal.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the health monitoring method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the health monitoring method according to any one of claims 1 to 7 is implemented.

Images