Personal health steady state monitoring and calibration method and system, equipment and storage medium

Abstract

The invention provides a personal health steady state monitoring and calibration method and system, equipment and a storage medium. The method comprises the following steps: acquiring a current measurement result of a user physiological index, multi-camera data recorded during measurement and corresponding measurement time; calculating a face temperature field and breath / pulse data when the physiological indexes of the user are measured through the multi-camera data; adjusting the current measurement result of the physiological indexes of the user by referring to the steady-state data of the same time node according to the respiratory frequency and the face temperature field of the user; and judging whether the user index is abnormal or not based on the adjustment result and the normal range standard of each physiological index. According to the invention, when health monitoring is carried out on residents in the field of health management, physiological index fluctuation caused by physical activity states or external environments can be compensated intelligently and automatically, stable health state boundaries of the residents can be calculated more accurately, and real abnormal fluctuation conditions of the residents can be better monitored.

Description

Technical Field

[0001] The present invention relates to the fields of health monitoring and artificial intelligence technology, and in particular to a personal health steady-state monitoring and calibration method and system, equipment, and storage medium. Background Art

[0002] The health all-in-one machine is a device that integrates multiple health monitoring functions and can comprehensively detect multiple physiological indicators of the human body, such as heart rate, blood pressure, blood sugar, blood oxygen, body temperature, etc. It has the characteristics of comprehensiveness, convenience, intelligence and interactivity.

[0003] The all-in-one health machine uses various physical, chemical and biological sensors to continuously monitor human physiological status information, including electrocardiogram, electroencephalogram, respiration, blood oxygen, blood pressure, blood sugar, activity, etc. in a non-invasive or minimally invasive manner.

[0004] The health all-in-one machine has intelligent data analysis and early warning capabilities, which can automatically save each measurement result of the user and generate a detailed health report. Through big data analysis and artificial intelligence algorithms, it can assess the user's health risks and issue early warnings in a timely manner when abnormalities are found.

[0005] Provide personalized health advice based on the user's measurement results and lifestyle habits. Use big data and artificial intelligence technology to analyze the user's health status and needs and tailor diet, exercise and other advice for the user.

[0006] All-in-one health machines are widely used in many fields such as families, communities, and medical institutions, providing strong support for people's health monitoring and management.

[0007] At present, the challenges and development trends facing health all-in-one machine technology include:

[0008] Portability: Under the premise of ensuring the function and measurement accuracy of the equipment, reduce the size and weight of the equipment to make it easier for users to use and carry.

[0009] Intelligence: Equipment functions are becoming more and more complete, with more and more measurable parameters and becoming more and more intelligent. Artificial intelligence and big data technologies are used to make human-computer interaction more humane.

[0010] Precision: The usage scenarios of all-in-one health machines are much richer than those of traditional hospital physical examination centers. The diverse scenarios and corresponding user status lead to poor consistency in the collected physiological indicators, making it difficult to ensure the accuracy of the user's health status assessment. Summary of the invention

[0011] In order to achieve the above-mentioned purpose and other advantages of the present invention, the first object of the present invention is to provide a personal health steady-state monitoring and calibration method, comprising the following steps:

[0012] Obtain the current measurement results of the user's physiological indicators and the multi-camera data recorded during the measurement and the corresponding measurement time;

[0013] Calculate the facial temperature field and respiration / pulse data of the user during physiological index measurement through the multi-camera data;

[0014] According to the user's breathing frequency and facial temperature field, the current measurement results of the user's physiological indicators are adjusted with reference to the steady-state data at the same time node;

[0015] Based on the adjustment results and the normal range standards of various physiological indicators, it is judged whether the user indicators are abnormal.

[0016] Furthermore, before the step of obtaining the current measurement results of the user's physiological indicators and the multi-camera data recorded during the measurement and the corresponding measurement time step, the step of establishing a personal steady-state model is also included:

[0017] In response to the user registering personal information, facial recognition is performed by using a multi-camera registration method;

[0018] Obtain the user's physiological index data measured multiple times within a preset time, as well as the multi-camera data recorded during each measurement and the corresponding measurement time and room temperature;

[0019] The measured physiological index data are grouped by time;

[0020] The facial temperature field and respiration / pulse data when measuring physiological index data are calculated through the multi-camera data recorded during each measurement;

[0021] The grouped physiological index data are secondary classified based on the respiration / pulse data and the room temperature to obtain steady-state data.

[0022] Furthermore, the step of performing facial recognition by multi-camera registration includes:

[0023] Obtain a face image captured by a visible light camera and use it as a login credential;

[0024] Acquire a three-dimensional point cloud of a face acquired by a depth camera, and match the three-dimensional point cloud of the face with the face image;

[0025] A temperature distribution map of a human face at room temperature captured by an infrared camera is obtained, and the temperature distribution map of the human face at room temperature is matched with the face image.

[0026] Furthermore, the step of matching the three-dimensional face point cloud with the face image includes:

[0027] According to the average normal of the reconstructed patch of the 3D point cloud and the center of the angle between the eyes and the camera in the point cloud space, the positive direction of the 3D face is determined, and the 3D point cloud of the face is projected along this direction to a 2D plane orthogonal to the direction;

[0028] For the two-dimensional plane of the depth camera and the image of the visible light camera, based on the relationship between the internal parameters of the camera, the two-dimensional plane of the depth camera is converted into the visible light image space;

[0029] The contour convex hulls of the depth two-dimensional plane and the visible light image are calculated to obtain the point sets on the two sets of convex hulls. The ICP rigid registration algorithm is used to align the depth two-dimensional plane to the visible light image to complete the matching of the three-dimensional point cloud data and the visible light image.

[0030] Furthermore, the step of matching the temperature distribution map of the human face at room temperature with the human face image comprises:

[0031] According to the internal parameters of the visible light camera and the infrared camera, the infrared camera image is transformed into the visible light camera image space;

[0032] Based on the Haar wavelet filter, the eye area is identified, and the contour convex hull is used to identify the outer contour of the face;

[0033] Based on the identified feature points, ICP rigid registration is performed to register the infrared temperature measurement image to the visible light image.

[0034] Furthermore, the step of obtaining the physiological data of the user measured multiple times within a preset time, as well as the multi-camera data recorded during each measurement and the corresponding measurement time and room temperature includes:

[0035] Obtain the user's body temperature, blood pressure, and blood sugar data measured multiple times within a month, as well as the facial visible light, infrared temperature measurement, and three-dimensional point cloud data recorded during each measurement, as well as the recorded measurement time and room temperature. The blood pressure data includes pulse data.

[0036] Furthermore, the step of grouping the measured physiological data by time includes:

[0037] According to the 24-hour system, the measurement data are distributed with time tags, a time node is set every 2 hours starting from 0 o'clock, and the data are grouped according to the shortest distance between the measurement time and the node.

[0038] Furthermore, the method further comprises the steps of:

[0039] When measuring various physiological indicators, the visible light camera image determines whether the user is facing the camera. If the user is facing the camera, the infrared camera and depth camera are controlled to continuously record to collect data.

[0040] Furthermore, the calculation of the facial temperature field and respiration / pulse data includes the following steps:

[0041] Using the 3D point cloud data collected by the depth camera, the real-time distance between each point on the face and the camera is calculated to form a distance field.

[0042] The distance field is used to correct the face temperature distribution map of the infrared camera to obtain a temperature field;

[0043] The respiration / pulse is calculated according to the brightness change of the face pixels using the corrected temperature distribution map video to obtain the respiration / pulse data at the time of measurement.

[0044] Furthermore, the step of correcting the face temperature distribution map of the infrared camera using the distance field includes:

[0045] Based on distance normalization, all pixels in the temperature distribution map are unified to the same distance, and the temperature is weightedly corrected according to the deviation of each point from the distance.

[0046] Furthermore, the step of performing secondary classification on the grouped physiological indicator data based on the respiration / pulse data and the room temperature to obtain steady-state data includes:

[0047] For the data at each time node, according to the principle of uniform room temperature, select the data classification at the specified room temperature, sort the respiratory rate and pulse of the data involved, and after removing the items with the highest and lowest frequencies, calculate the mean of the remaining data as the steady-state value at the time node and the uniform room temperature;

[0048] The steady-state values ​​at a uniform room temperature were calculated for all time nodes to obtain a 24-hour steady-state curve.

[0049] Furthermore, the step of adjusting the current measurement result of the user's physiological index according to the user's breathing frequency and facial temperature field and referring to the steady-state data at the same time node includes:

[0050] For the blood pressure measurement value and the body temperature measurement value, the ratio of the respiratory frequency to the respiratory frequency of the steady-state data at the time node is taken. When the ratio is higher than a first preset value, the measurement value is lowered; when the ratio is lower than the first preset value, the measurement value is increased;

[0051] For blood pressure measurement values, body temperature measurement values, and blood sugar measurement values, based on the similarity between the temperature field and the steady-state temperature field, a temperature difference map is calculated after the two temperature sensors are aligned, and a weighted temperature difference is calculated according to the preset weights of each area. The corresponding blood pressure measurement value adjustment strategy, body temperature measurement value adjustment strategy, and blood sugar measurement value adjustment strategy are executed based on the weighted temperature difference.

[0052] Furthermore, the step of calculating the weighted temperature difference according to the preset weights of each area includes:

[0053] The weighted temperature difference is calculated according to the respective preset weights of the forehead area, eye area, face area, and mouth area.

[0054] Furthermore, the steps of executing the corresponding blood pressure measurement value adjustment strategy, body temperature measurement value adjustment strategy, and blood sugar measurement value adjustment strategy according to the weighted temperature difference include:

[0055] When the weighted temperature difference is within the range formed by the first temperature threshold and the second temperature threshold, the blood pressure measurement value, the body temperature measurement value, and the blood sugar measurement value are not adjusted;

[0056] When the weighted temperature difference is above the second temperature threshold, lowering the body temperature measurement value;

[0057] When the weighted temperature difference is within the range formed by the second temperature threshold and the third temperature threshold, lowering the blood pressure measurement value and the blood sugar measurement value;

[0058] When the weighted temperature difference is above the third temperature threshold, the difference between the body temperature and the steady-state body temperature is calculated; when the body temperature is higher than the steady-state body temperature and reaches above the preset temperature threshold, the blood pressure measurement value and the blood sugar measurement value are not adjusted; when the body temperature is within the range formed by the preset temperature threshold of the steady-state body temperature, the blood pressure measurement value and the blood sugar measurement value are further lowered;

[0059] When the weighted temperature difference is within the range formed by the fourth temperature threshold and the first temperature threshold, the blood pressure measurement value and the blood sugar measurement value are increased; wherein the fourth temperature threshold, the first temperature threshold, the second temperature threshold, and the third temperature threshold are increased in sequence;

[0060] When the weighted temperature difference is above the fourth temperature threshold, increasing the body temperature measurement value;

[0061] When the weighted temperature difference is above the fourth temperature threshold, the difference between the body temperature and the steady-state body temperature is calculated; when the body temperature is lower than the steady-state body temperature and reaches above the preset temperature threshold, the blood pressure measurement value and the blood sugar measurement value are not adjusted; when the body temperature is within the range formed by the preset temperature threshold of the steady-state body temperature, the blood pressure measurement value and the blood sugar measurement value are further adjusted.

[0062] Furthermore, the method further comprises the steps of:

[0063] When the user's age exceeds a first age threshold, and the time since the last steady-state establishment exceeds a first preset time, the personal steady-state model is reestablished and updated;

[0064] When the user's age exceeds a second age threshold and the time since the last steady-state was established exceeds a second preset time, the personal steady-state model is re-established and updated; wherein the second age threshold is greater than the first age threshold, and the second preset time is less than the first preset time.

[0065] Furthermore, the method further comprises the steps of:

[0066] When a user registers personal information, the personal health record data filled in by the user is obtained.

[0067] The second object of the present invention is to provide a personal health steady-state monitoring and calibration system, including a visible light camera, an infrared camera, a depth camera, a measurement module, and a calculation module; wherein:

[0068] The visible light camera is used to capture facial images;

[0069] The infrared camera is used to capture infrared images of human faces and measure temperature distribution maps of human faces;

[0070] The depth camera is used to realize three-dimensional point cloud reconstruction of the face surface;

[0071] The measuring module is used to measure human physiological index data;

[0072] The calculation module applies the above method to realize personal health steady-state monitoring and calibration.

[0073] A third object of the present invention is to provide 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 steps of the above method when executing the computer program.

[0074] A fourth object of the present invention is to provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0075] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0076] The present invention provides a personal health steady-state monitoring and calibration method and system, equipment, and storage medium, which can realize intelligent and automatic compensation for fluctuations in physiological indicators caused by physical activity or external environment when monitoring residents in the field of health management, and can more accurately calculate the boundary of the stable health state of residents to better monitor their true abnormal fluctuations. The present invention can reduce the size and weight of the equipment while ensuring the function and measurement accuracy of the equipment, so as to facilitate user use and carrying; the equipment functions are becoming more and more perfect, the measurable parameters are increasing, and it is becoming more and more intelligent, using artificial intelligence and big data technology to make human-computer interaction more humane.

[0077] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and implement it according to the contents of the specification, the following is a detailed description of the preferred embodiments of the present invention in conjunction with the accompanying drawings. The specific implementation of the present invention is given in detail by the following embodiments and their accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0079] Figure 1 Schematic diagram of the personal health homeostasis monitoring and calibration system;

[0080] Figure 2 is a schematic diagram of the optical system;

[0081] Figure 3 A flow chart of the personal health homeostasis monitoring and calibration method;

[0082] Figure 4 To establish a personal steady-state model flow chart;

[0083] Figure 5 It is a facial recognition flow chart;

[0084] Figure 6 Calculate the flow chart for facial temperature field and respiration / pulse data;

[0085] Figure 7 It is a schematic diagram of computer equipment;

[0086] Figure 8 A schematic diagram of a computer-readable storage medium. DETAILED DESCRIPTION

[0087] The present invention is further described below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. It should be noted that, under the premise of no conflict, the embodiments or technical features described below can be arbitrarily combined to form a new embodiment.

[0088] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0089] The figure numbers in this application are only used to distinguish the various steps in the scheme, and are not used to limit the execution order of the various steps. The specific execution order is subject to the description in the specification.

[0090] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0091] Example 1

[0092] A personal health homeostasis monitoring and calibration method, such as Figure 3 As shown, the following steps are included:

[0093] S1. Obtain the current measurement results of the user's physiological indicators and the multi-camera data recorded during the measurement and the corresponding measurement time;

[0094] The health all-in-one machine provided in this embodiment is as follows: Figure 1 , Figure 2 As shown, it is equipped with visible light, infrared, and depth cameras, measurement modules such as thermometer, blood pressure meter, and blood glucose meter, and a host computing module. There is data communication between all measurement modules and computing modules.

[0095] Among them, the visible light camera can capture facial images, the infrared camera can capture facial infrared images, and can measure the temperature distribution map of the face, that is, pixel-by-pixel temperature measurement, and the depth camera can realize the three-dimensional point cloud reconstruction of the face surface; Figure 2 As shown, the axial distance between the infrared camera and the visible light camera is the same as the axial distance between the depth camera and the visible light camera. Figure 2 The arrow next to the mid-depth camera indicates the direction of the lens, which is toward the user.

[0096] The data communication between the measuring modules such as thermometer, blood pressure meter, blood glucose meter and the host can be wired communication (such as serial port), Bluetooth communication or Wi-Fi communication.

[0097] In some optional embodiments, the steps are further included:

[0098] When measuring various physiological indicators, the visible light camera image determines whether the user is facing the camera. If the user is facing the camera, the infrared camera and depth camera are controlled to continuously record to collect data.

[0099] When the user actually uses the health all-in-one machine for measurement, the data is collected through the three cameras mentioned above, and the measurement results are corrected using the collected data, and then compared with the steady-state data. At the same time, the normal range standards of various indicators are referred to to determine whether the user's indicators are abnormal. The specific steps are as follows:

[0100] S2. Calculating the facial temperature field and respiration / pulse data of the user during physiological index measurement using the multi-camera data;

[0101] In some optional embodiments, such as Figure 6 As shown, the calculation of the facial temperature field and respiration / pulse data includes the following steps:

[0102] S231, using the three-dimensional point cloud data collected by the depth camera, calculating the real-time distance between each point on the face and the camera to form a distance field;

[0103] S232, using the distance field to correct the face temperature distribution map of the infrared camera to obtain a temperature field;

[0104] Optionally, the step of correcting the face temperature distribution map of the infrared camera using the distance field includes:

[0105] Based on distance normalization, all pixels in the temperature distribution map are unified to the same distance, and the temperature is weightedly corrected according to the deviation of each point from the distance.

[0106] Specifically, firstly, the corresponding maximum depth distances of all pixels are counted, then the temperature value of each pixel is multiplied by its corresponding distance, and then divided by the maximum distance to obtain the pixel temperature value after weighted correction.

[0107] S233. Using the corrected temperature distribution video, calculate the respiration / pulse according to the brightness change of the face pixels to obtain the respiration / pulse data when the measurement data is obtained.

[0108] S3, adjusting the current measurement results of the user's physiological indicators according to the user's breathing frequency and facial temperature field and referring to the steady-state data at the same time node;

[0109] In some embodiments, the step of adjusting the current measurement result of the user's physiological index according to the user's breathing frequency and facial temperature field and referring to the steady-state data at the same time node includes:

[0110] For the blood pressure measurement value and the body temperature measurement value, the ratio of the respiratory frequency to the respiratory frequency of the steady-state data at the time node is taken. When the ratio is higher than a first preset value, the measurement value is lowered; when the ratio is lower than the first preset value, the measurement value is increased;

[0111] For example, for blood pressure measurement values, the current measurement result is adjusted according to the user's breathing frequency, facial temperature field, and reference to the steady-state data at the same time node. The ratio of the breathing frequency to the breathing frequency of the steady-state data at that time point is taken. When the ratio is higher than 1, the measurement value is appropriately lowered (*0.9); when the ratio is lower than 1, the measurement value is appropriately increased (*1.1).

[0112] For body temperature measurement values, according to the user's breathing rate, facial temperature field, and reference to the steady-state data at the same time node, the current measurement result is adjusted, and the ratio of the breathing rate to the breathing rate of the steady-state data at that time point is taken. When the ratio is higher than 1, the measurement value is appropriately lowered (*0.9); when the ratio is lower than 1, the measurement value is appropriately increased (*1.1).

[0113] For blood pressure measurement values, body temperature measurement values, and blood sugar measurement values, based on the similarity between the temperature field and the steady-state temperature field, a temperature difference map is calculated after the two temperature sensors are aligned, and a weighted temperature difference is calculated according to the preset weights of each area. The corresponding blood pressure measurement value adjustment strategy, body temperature measurement value adjustment strategy, and blood sugar measurement value adjustment strategy are executed based on the weighted temperature difference.

[0114] The step of calculating the weighted temperature difference according to the preset weights of each area includes:

[0115] The weighted temperature difference is calculated according to the respective preset weights of the forehead area, eye area, face area, and mouth area.

[0116] Specifically, the steps of executing the corresponding blood pressure measurement value adjustment strategy, body temperature measurement value adjustment strategy, and blood sugar measurement value adjustment strategy according to the weighted temperature difference include:

[0117] When the weighted temperature difference is within the range formed by the first temperature threshold and the second temperature threshold, the blood pressure measurement value, the body temperature measurement value, and the blood sugar measurement value are not adjusted;

[0118] When the weighted temperature difference is above the second temperature threshold, lowering the body temperature measurement value;

[0119] When the weighted temperature difference is within the range formed by the second temperature threshold and the third temperature threshold, lowering the blood pressure measurement value and the blood sugar measurement value;

[0120] When the weighted temperature difference is above the third temperature threshold, the difference between the body temperature and the steady-state body temperature is calculated; when the body temperature is higher than the steady-state body temperature and reaches above the preset temperature threshold, the blood pressure measurement value and the blood sugar measurement value are not adjusted; when the body temperature is within the range formed by the preset temperature threshold of the steady-state body temperature, the blood pressure measurement value and the blood sugar measurement value are further lowered;

[0121] When the weighted temperature difference is within the range formed by the fourth temperature threshold and the first temperature threshold, the blood pressure measurement value and the blood sugar measurement value are increased; wherein the fourth temperature threshold, the first temperature threshold, the second temperature threshold, and the third temperature threshold are increased in sequence;

[0122] When the weighted temperature difference is above the fourth temperature threshold, increasing the body temperature measurement value;

[0123] When the weighted temperature difference is above the fourth temperature threshold, the difference between the body temperature and the steady-state body temperature is calculated; when the body temperature is lower than the steady-state body temperature and reaches above the preset temperature threshold, the blood pressure measurement value and the blood sugar measurement value are not adjusted; when the body temperature is within the range formed by the preset temperature threshold of the steady-state body temperature, the blood pressure measurement value and the blood sugar measurement value are further adjusted.

[0124] For example, for blood pressure measurement values, based on the similarity between the temperature field and the steady-state temperature field, after the two temperature fields are aligned, the filter-based average difference calculation is used to obtain a temperature difference map. The weighted temperature difference is calculated in the form of 60% weight for the forehead area, 10% weight for the eye area, 10% weight for the face area, and 20% weight for the mouth area. When the difference is within -1 to +1°C, no correction is made. When the difference is between +1 and +3°C, the blood pressure measurement value is appropriately lowered (*0.9). When the difference is above +3°C, the difference between the body temperature and the steady-state body temperature is calculated. When the body temperature is higher than the steady-state body temperature by more than 1.5°C, the blood pressure measurement value is not adjusted. When the body temperature is within ±1.5°C of the steady-state body temperature, the blood pressure measurement value is further lowered (*0.8). When the weighted temperature difference is between -1 and -3℃, adjust the blood pressure measurement value appropriately. When the difference is above -3℃, calculate the difference between body temperature and steady-state body temperature. When the body temperature is more than 1.5℃ lower than the steady-state body temperature, do not adjust the blood pressure measurement value. When the body temperature is within ±1.5℃ of the steady-state body temperature, further adjust the blood pressure measurement value (*1.2).

[0125] For blood glucose measurement values, according to the similarity between the temperature field and the steady-state temperature field, after the two temperature fields are aligned, the filter-based average difference calculation is used to obtain the temperature difference map. The weighted temperature difference is calculated in the form of 60% weight for the forehead area, 10% weight for the eye area, 10% weight for the face area, and 20% weight for the mouth area. When the difference is within -1 to +1°C, no correction is made. When the difference is between +1 and +3°C, the blood glucose measurement value is appropriately lowered (*0.95). When the difference is above +3°C, the difference between body temperature and steady-state body temperature is calculated. When the body temperature is higher than the steady-state body temperature by more than 1.5°C, the blood glucose measurement value is not adjusted. When the body temperature is within ±1.5°C of the steady-state body temperature, the blood pressure measurement value is further lowered (*0.9). When the weighted temperature difference is between -1 and -3°C, the blood glucose measurement value is appropriately increased (*1.05). When the difference is above -3°C, the difference between body temperature and steady-state body temperature is calculated. When the body temperature is lower than the steady-state body temperature by more than 1.5°C, the blood glucose measurement value is not adjusted. When the body temperature is within ±1.5°C of the steady-state body temperature, the blood glucose measurement value is further increased (*1.1).

[0126] For body temperature measurement values, according to the similarity between the temperature field and the steady-state temperature field, after the two temperature fields are aligned, the filter-based average difference calculation is used to obtain the temperature difference map. The weighted temperature difference is calculated in the form of 60% weight for the forehead area, 10% weight for the eye area, 10% weight for the face area, and 20% weight for the mouth area. When the difference is within -1 to +1°C, no correction is made. When the difference is above +1, the body temperature measurement value is appropriately lowered (*0.9). When the weighted temperature difference is -1 and below, the body temperature measurement value is appropriately increased (*1.1).

[0127] S4. Determine whether the user's indicators are abnormal based on the adjustment results and the normal range standards of various physiological indicators.

[0128] In some optional embodiments, such as Figure 4 As shown, before the step of obtaining the current measurement results of the user's physiological indicators and the multi-camera data recorded during the measurement and the corresponding measurement time step, it also includes the step of establishing a personal steady-state model:

[0129] S200, in response to the user registering personal information, performing facial recognition by using a multi-camera registration method;

[0130] First, the user registers personal information and enters facial recognition. Among them, facial recognition adopts the above-mentioned three-camera phase registration method, that is, visible light collects facial images as login credentials, the depth camera collects the three-dimensional point cloud of the face, and the infrared camera collects the temperature distribution map of the face at room temperature. The three-dimensional point cloud is matched with the visible light face image based on the two-dimensional projection algorithm and the rigid registration algorithm based on the convex hull. The matching process also includes spatial transformation based on the internal parameters of the camera. The infrared camera uses feature points and convex hull as the basis to match the visible light face image, and also includes spatial transformation based on the internal parameters of the camera. Finally, the three-dimensional point cloud and infrared temperature measurement image are converted to the visible light space and registered.

[0131] Specifically, Figure 5 As shown, the steps of performing facial recognition by using multi-camera registration include:

[0132] S201, obtaining a face image captured by a visible light camera and using it as a login credential;

[0133] S202, obtaining a three-dimensional point cloud of a face acquired by a depth camera, and matching the three-dimensional point cloud of the face with the face image;

[0134] In some optional embodiments, the step of matching the three-dimensional face point cloud with the face image includes:

[0135] According to the average normal of the reconstructed patch of the 3D point cloud and the center of the angle between the eyes and the camera in the point cloud space, the positive direction of the 3D face is determined, and the 3D point cloud of the face is projected along this direction to a 2D plane orthogonal to the direction;

[0136] For the two-dimensional plane of the depth camera and the image of the visible light camera, based on the relationship between the internal parameters of the camera, the two-dimensional plane of the depth camera is converted into the visible light image space;

[0137] The contour convex hulls of the depth two-dimensional plane and the visible light image are calculated to obtain the point sets on the two sets of convex hulls. The ICP rigid registration algorithm is used to align the depth two-dimensional plane to the visible light image to complete the matching of the three-dimensional point cloud data and the visible light image.

[0138] S203: Obtain a temperature distribution map of the human face at room temperature collected by an infrared camera, and match the temperature distribution map of the human face at room temperature with the face image.

[0139] In some optional embodiments, the step of matching the temperature distribution map of the human face at room temperature with the human face image comprises:

[0140] According to the internal parameters of the visible light camera and the infrared camera, the infrared camera image is transformed into the visible light camera image space;

[0141] Based on the Haar wavelet filter, the eye area is identified, and the contour convex hull is used to identify the outer contour of the face;

[0142] Based on the identified feature points, ICP rigid registration is performed to register the infrared temperature measurement image to the visible light image.

[0143] In some optional embodiments, the steps are further included:

[0144] When a user registers personal information, the personal health record data filled in by the user is obtained. That is, when a user registers personal information, he or she also fills in the personal health record, including height, weight, age, medical history, allergy history and other information.

[0145] S210, obtaining physiological index data of the user measured multiple times within a preset time, as well as multi-camera data recorded during each measurement and the corresponding measurement time and room temperature;

[0146] In some optional embodiments, the step of obtaining the physiological data of the user measured multiple times within a preset time, as well as the multi-camera data recorded during each measurement and the corresponding measurement time and room temperature includes:

[0147] Obtain the user's body temperature, blood pressure, blood sugar and other data measured multiple times within a month, as well as facial visible light, infrared temperature measurement, 3D point cloud data recorded during each measurement, as well as the recorded measurement time and room temperature. The blood pressure data includes pulse data.

[0148] In some optional embodiments, the steps are further included:

[0149] When measuring various physiological indicators, the visible light camera image determines whether the user is facing the camera. If the user is facing the camera, the infrared camera and depth camera are controlled to continuously record to collect data.

[0150] S220, grouping the measured physiological index data by time;

[0151] In some optional embodiments, the step of grouping the measured physiological data by time includes:

[0152] According to the 24-hour system, the measurement data are distributed with time tags, a time node is set every 2 hours starting from 0 o'clock, and the data are grouped according to the shortest distance between the measurement time and the node.

[0153] S230, calculating the facial temperature field and respiration / pulse data when measuring physiological index data through the multi-camera data recorded during each measurement;

[0154] In some optional embodiments, such as Figure 6 As shown, the calculation of the facial temperature field and respiration / pulse data includes the following steps:

[0155] S231, using the three-dimensional point cloud data collected by the depth camera, calculating the real-time distance between each point on the face and the camera to form a distance field;

[0156] S232, using the distance field to correct the face temperature distribution map of the infrared camera to obtain a temperature field;

[0157] Optionally, the step of correcting the face temperature distribution map of the infrared camera using the distance field includes:

[0158] Based on distance normalization, all pixels in the temperature distribution map are unified to the same distance, and the temperature is weightedly corrected according to the deviation of each point from the distance.

[0159] Specifically, firstly, the corresponding maximum depth distances of all pixels are counted, then the temperature value of each pixel is multiplied by its corresponding distance, and then divided by the maximum distance to obtain the pixel temperature value after weighted correction.

[0160] S233. Using the corrected temperature distribution video, calculate the respiration / pulse according to the brightness change of the face pixels to obtain the respiration / pulse data when the measurement data is obtained.

[0161] S240, performing secondary classification on the grouped physiological indicator data based on the respiration / pulse data and the room temperature to obtain steady-state data. Specifically, the measurement data belonging to each time node classification is secondary classified based on respiration, pulse (if there is a pulse for blood pressure measurement, blood pressure pulse is used), and room temperature. The classification method can adopt low-dimensional data classification methods such as logistic regression, hierarchical clustering or random forest.

[0162] In some optional embodiments, the step of performing secondary classification on the grouped physiological indicator data based on the respiration / pulse data and the room temperature to obtain steady-state data includes:

[0163] For the data at each time node, according to the principle of uniform room temperature, select the data classification at the specified room temperature, sort the respiratory rate and pulse for the data involved, and after removing the items with the highest and lowest frequencies, for example, remove the items with the highest and lowest frequencies according to a certain ratio or directly count the category with the largest amount of data in the classification, calculate the mean of the remaining data as the steady-state value at the time node and the uniform room temperature;

[0164] The steady-state values ​​at a uniform room temperature were calculated for all time nodes to obtain a 24-hour steady-state curve.

[0165] After the steady-state curve is established, when the user takes measurements again, data is still collected through the three cameras mentioned above. The collection method is the same as the above process. The measurement results are corrected using the collected data and compared with the steady-state data. At the same time, the normal range standards of various indicators of the country are referred to to determine whether the user indicators are abnormal. That is, the above steps S1 to S4 are executed to achieve personal health steady-state monitoring and calibration.

[0166] In some embodiments, the steps include:

[0167] When the user's age exceeds a first age threshold, and the time since the last steady-state establishment exceeds a first preset time, the personal steady-state model is reestablished and updated;

[0168] For example, when the user is over 40 years old and the time since the last steady state was established is more than 3 years, the steady state will be re-established. The judgment during the establishment process uses the previous steady state model, and it will be automatically replaced by the new model when the new model is completed.

[0169] When the user's age exceeds a second age threshold and the time since the last steady-state was established exceeds a second preset time, the personal steady-state model is re-established and updated; wherein the second age threshold is greater than the first age threshold, and the second preset time is less than the first preset time.

[0170] For example, when the age is over 55 years old and the time since the last steady state was established is more than 1.5 years, the steady state will be re-established. The judgment during the establishment process uses the previous steady state model, and it will be automatically replaced by the new model when the new model is completed.

[0171] This embodiment provides a personal health steady-state monitoring and calibration method, which can realize intelligent and automatic compensation for fluctuations in physiological indicators caused by physical activity status or external environment when conducting health monitoring of residents in the field of health management, and can more accurately calculate the boundaries of the residents' stable health state to better monitor their actual abnormal fluctuations.

[0172] Example 2

[0173] A personal health steady-state monitoring and calibration system is based on the above method. For a detailed description of the method, please refer to the corresponding description in the above method embodiment, which will not be repeated here. Figure 1 , Figure 2 As shown, the system 100 includes a visible light camera 110, an infrared camera 120, a depth camera 130, a measurement module 140, and a calculation module 150; wherein,

[0174] The visible light camera is used to capture facial images;

[0175] The infrared camera is used to capture infrared images of human faces and measure the temperature distribution map of the human face, that is, pixel-by-pixel temperature measurement;

[0176] The depth camera is used to realize three-dimensional point cloud reconstruction of the face surface;

[0177] like Figure 2 As shown, the axial distance between the infrared camera and the visible light camera is the same as the axial distance between the depth camera and the visible light camera. Figure 2 The arrow next to the mid-depth camera indicates the direction of the lens, which is toward the user.

[0178] The measuring module is used to measure human physiological index data; for example, thermometers, sphygmomanometers, blood glucose meters and other measuring modules are used to measure body temperature, blood pressure, blood sugar and other data. There is data communication between all measuring modules and the calculation module, and the data communication between the measuring module and the host can be wired communication (such as serial port), or Bluetooth communication or WiFi communication, etc.

[0179] The calculation module applies the above method to realize personal health steady-state monitoring and calibration.

[0180] This embodiment provides a personal health steady-state monitoring and calibration system, which can realize intelligent and automatic compensation for fluctuations in physiological indicators caused by physical activity or external environment when monitoring residents in the field of health management, and can more accurately calculate the boundary of the stable health state of residents to better monitor their true abnormal fluctuations. This embodiment can reduce the size and weight of the device while ensuring the function and measurement accuracy of the device, so as to facilitate user use and carrying; the device functions are becoming more and more complete, the measurable parameters are increasing, and it is becoming more and more intelligent, using artificial intelligence and big data technology to make human-computer interaction more humane.

[0181] Example 3

[0182] A computer device 500, such as Figure 7 As shown, it includes a memory 510, a processor 520, and a computer program 530 stored in the memory and executable on the processor. When the processor executes the computer program, the steps of a method for monitoring and calibrating a personal health steady state are implemented. For a detailed description of the method, reference may be made to the corresponding description in the above method embodiment, which will not be repeated here.

[0183] Example 4

[0184] A computer readable storage medium such as Figure 8 As shown, a computer program is stored thereon, and when the computer program is executed by the processor, the steps of a method for monitoring and calibrating a personal health steady state are implemented. For a detailed description of the method, reference may be made to the corresponding description in the above method embodiment, and no further description is given here.

[0185] Example 5

[0186] A computer program product, the computer program product comprising a computer program, the computer program when executed by a processor implements the steps of a personal health steady-state monitoring and calibration method. For a detailed description of the method, reference may be made to the corresponding description in the above method embodiment, which will not be repeated here.

[0187] The number of devices and processing scales described here are used to simplify the description of the present invention. Applications, modifications and variations of the present invention will be obvious to those skilled in the art.

[0188] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and implementation modes. They can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the illustrations shown and described herein.

[0189] The apparatus, computer device, non-volatile computer storage medium and method provided in the embodiments of this specification correspond to each other, and therefore, the apparatus, computer device and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, computer device and non-volatile computer storage medium will not be repeated here.

[0190] Those skilled in the art also know that, in addition to implementing the controller in a purely computer-readable program code, the controller can be made to implement the same function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered as a hardware component, and the devices for implementing various functions included therein can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software units for implementing the method and structures within the hardware component.

[0191] The systems, devices or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. For the convenience of description, the above devices are described separately by functions in various units. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in the same or more software and / or hardware.

[0192] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0193] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0194] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0195] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0196] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0197] The specification may be described in the general context of computer-executable instructions executed by a computer, such as program units. Generally, program units include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communications network. In a distributed computing environment, program units may be located in local and remote computer storage media, including storage devices.

[0198] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0199] The above description is only an embodiment of this specification and is not intended to limit one or more embodiments of this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of one or more embodiments of this specification.

Claims

1. A method for monitoring and calibrating a personal health steady state, characterized in that: The following steps are involved: Obtain the current measurement results of the user's physiological indicators and the multi-camera data recorded during the measurement and the corresponding measurement time; Calculate the facial temperature field and respiration / pulse data of the user during physiological index measurement through the multi-camera data; According to the user's breathing frequency and facial temperature field, the current measurement results of the user's physiological indicators are adjusted with reference to the steady-state data at the same time node; Based on the adjustment results and the normal range standards of various physiological indicators, it is judged whether the user indicators are abnormal.

2. A personal health steady-state monitoring and calibration method as claimed in claim 1, characterized in that: Before the step of obtaining the current measurement results of the user's physiological indicators and the multi-camera data recorded during the measurement and the corresponding measurement time step, the step of establishing a personal steady-state model is also included: In response to the user registering personal information, facial recognition is performed by using a multi-camera registration method; Obtain the user's physiological index data measured multiple times within a preset time, as well as the multi-camera data recorded during each measurement and the corresponding measurement time and room temperature; The measured physiological index data are grouped by time; The facial temperature field and respiration / pulse data when measuring physiological index data are calculated through the multi-camera data recorded during each measurement; The grouped physiological index data are secondary classified based on the respiration / pulse data and the room temperature to obtain steady-state data.

3. A personal health steady-state monitoring and calibration method as claimed in claim 2, characterized in that: The step of performing facial recognition by multi-camera registration includes: Obtain a face image captured by a visible light camera and use it as a login credential; Acquire a three-dimensional point cloud of a face acquired by a depth camera, and match the three-dimensional point cloud of the face with the face image; A temperature distribution map of a human face at room temperature captured by an infrared camera is obtained, and the temperature distribution map of the human face at room temperature is matched with the face image.

4. A personal health steady-state monitoring and calibration method as claimed in claim 3, characterized in that: The step of matching the three-dimensional face point cloud with the face image comprises: According to the average normal of the reconstructed patch of the 3D point cloud and the center of the angle between the eyes and the camera in the point cloud space, the positive direction of the 3D face is determined, and the 3D point cloud of the face is projected along this direction to a 2D plane orthogonal to the direction; For the two-dimensional plane of the depth camera and the image of the visible light camera, based on the relationship between the internal parameters of the camera, the two-dimensional plane of the depth camera is converted into the visible light image space; The contour convex hulls of the depth two-dimensional plane and the visible light image are calculated to obtain the point sets on the two sets of convex hulls. The ICP rigid registration algorithm is used to align the depth two-dimensional plane to the visible light image to complete the matching of the three-dimensional point cloud data and the visible light image.

5. A personal health steady-state monitoring and calibration method as claimed in claim 3, characterized in that: The step of matching the temperature distribution map of the human face at room temperature with the human face image comprises: According to the internal parameters of the visible light camera and the infrared camera, the infrared camera image is transformed into the visible light camera image space; Based on the Haar wavelet filter, the eye area is identified, and the contour convex hull is used to identify the outer contour of the face; Based on the identified feature points, ICP rigid registration is performed to register the infrared temperature measurement image to the visible light image.

6. A personal health steady-state monitoring and calibration method as claimed in claim 3, characterized in that: The step of obtaining the physiological data of the user measured multiple times within a preset time, as well as the multi-camera data recorded during each measurement and the corresponding measurement time and room temperature includes: Obtain the user's body temperature, blood pressure, and blood sugar data measured multiple times within a month, as well as the facial visible light, infrared temperature measurement, and three-dimensional point cloud data recorded during each measurement, as well as the recorded measurement time and room temperature. The blood pressure data includes pulse data.

7. A personal health steady-state monitoring and calibration method as claimed in claim 6, characterized in that: The step of grouping the measured physiological data by time includes: According to the 24-hour system, the measurement data are distributed with time tags, a time node is set every 2 hours starting from 0 o'clock, and the data are grouped according to the shortest distance between the measurement time and the node.

8. A personal health steady-state monitoring and calibration method as claimed in claim 1 or 6, characterized in that: Also includes the steps: When measuring various physiological indicators, the visible light camera image determines whether the user is facing the camera. If the user is facing the camera, the infrared camera and depth camera are controlled to continuously record to collect data.

9. A personal health steady-state monitoring and calibration method as claimed in claim 1 or 6, characterized in that: The calculation of the facial temperature field and respiration / pulse data includes the following steps: Using the 3D point cloud data collected by the depth camera, the real-time distance between each point on the face and the camera is calculated to form a distance field. The distance field is used to correct the face temperature distribution map of the infrared camera to obtain a temperature field; The respiration / pulse is calculated according to the brightness change of the face pixels using the corrected temperature distribution map video to obtain the respiration / pulse data at the time of measurement.

10. A personal health steady-state monitoring and calibration method as claimed in claim 9, characterized in that: The step of correcting the face temperature distribution map of the infrared camera using the distance field comprises: Based on distance normalization, all pixels in the temperature distribution map are unified to the same distance, and the temperature is weightedly corrected according to the deviation of each point from the distance.

11. A personal health steady-state monitoring and calibration method as claimed in claim 7, characterized in that: The step of performing secondary classification on the grouped physiological index data based on the respiration / pulse data and the room temperature to obtain steady-state data comprises: For the data at each time node, according to the principle of uniform room temperature, select the data classification at the specified room temperature, sort the respiratory rate and pulse of the data involved, and after removing the items with the highest and lowest frequencies, calculate the mean of the remaining data as the steady-state value at the time node and the uniform room temperature; The steady-state values ​​at a uniform room temperature were calculated for all time nodes to obtain a 24-hour steady-state curve.

12. A personal health steady-state monitoring and calibration method as claimed in claim 6, characterized in that: The step of adjusting the current measurement result of the user's physiological index according to the user's breathing frequency and facial temperature field and referring to the steady-state data at the same time node includes: For the blood pressure measurement value and the body temperature measurement value, the ratio of the respiratory frequency to the respiratory frequency of the steady-state data at the time node is taken. When the ratio is higher than a first preset value, the measurement value is lowered; when the ratio is lower than the first preset value, the measurement value is increased; For blood pressure measurement values, body temperature measurement values, and blood sugar measurement values, based on the similarity between the temperature field and the steady-state temperature field, a temperature difference map is calculated after the two temperature sensors are aligned, and a weighted temperature difference is calculated according to the preset weights of each area. The corresponding blood pressure measurement value adjustment strategy, body temperature measurement value adjustment strategy, and blood sugar measurement value adjustment strategy are executed based on the weighted temperature difference.

13. A personal health steady-state monitoring and calibration method as claimed in claim 12, characterized in that: The step of calculating the weighted temperature difference according to the preset weights of each area includes: The weighted temperature difference is calculated according to the respective preset weights of the forehead area, eye area, face area, and mouth area.

14. A personal health steady-state monitoring and calibration method as claimed in claim 12, characterized in that: The steps of executing the corresponding blood pressure measurement value adjustment strategy, body temperature measurement value adjustment strategy, and blood sugar measurement value adjustment strategy according to the weighted temperature difference include: When the weighted temperature difference is within the range formed by the first temperature threshold and the second temperature threshold, the blood pressure measurement value, the body temperature measurement value, and the blood sugar measurement value are not adjusted; When the weighted temperature difference is above the second temperature threshold, lowering the body temperature measurement value; When the weighted temperature difference is within the range formed by the second temperature threshold and the third temperature threshold, lowering the blood pressure measurement value and the blood sugar measurement value; When the weighted temperature difference is above the third temperature threshold, the difference between the body temperature and the steady-state body temperature is calculated; when the body temperature is higher than the steady-state body temperature and reaches above the preset temperature threshold, the blood pressure measurement value and the blood sugar measurement value are not adjusted; when the body temperature is within the range formed by the preset temperature threshold of the steady-state body temperature, the blood pressure measurement value and the blood sugar measurement value are further lowered; When the weighted temperature difference is within the range formed by the fourth temperature threshold and the first temperature threshold, the blood pressure measurement value and the blood sugar measurement value are increased; wherein the fourth temperature threshold, the first temperature threshold, the second temperature threshold, and the third temperature threshold are increased in sequence; When the weighted temperature difference is above the fourth temperature threshold, increasing the body temperature measurement value; When the weighted temperature difference is above the fourth temperature threshold, the difference between the body temperature and the steady-state body temperature is calculated; when the body temperature is lower than the steady-state body temperature and reaches above the preset temperature threshold, the blood pressure measurement value and the blood sugar measurement value are not adjusted; when the body temperature is within the range formed by the preset temperature threshold of the steady-state body temperature, the blood pressure measurement value and the blood sugar measurement value are further adjusted.

15. A personal health steady-state monitoring and calibration method as claimed in claim 2, characterized in that: Also includes the steps: When the user's age exceeds a first age threshold, and the time since the last steady-state establishment exceeds a first preset time, the personal steady-state model is reestablished and updated; When the user's age exceeds a second age threshold and the time since the last steady-state was established exceeds a second preset time, the personal steady-state model is re-established and updated; wherein the second age threshold is greater than the first age threshold, and the second preset time is less than the first preset time.

16. A personal health steady-state monitoring and calibration method as claimed in claim 2, characterized in that: Also includes the steps: When a user registers personal information, the personal health record data filled in by the user is obtained.

17. A personal health steady-state monitoring and calibration system, characterized in that: It includes a visible light camera, an infrared camera, a depth camera, a measurement module, and a calculation module; among them, The visible light camera is used to capture facial images; The infrared camera is used to capture infrared images of human faces and measure temperature distribution maps of human faces; The depth camera is used to realize three-dimensional point cloud reconstruction of the face surface; The measuring module is used to measure human physiological index data; The computing module implements personal health steady-state monitoring and calibration using the method described in any one of claims 1 to 16.

18. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 16 are implemented.

19. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 16 are implemented.

Images