Health monitoring method, range hood and health monitoring system

Abstract

The invention relates to a health monitoring method, a range hood and a health monitoring system.The health monitoring method comprises the steps that under the condition that the range hood is in a working state, kitchen environment oil smoke data are obtained, and the kitchen environment oil smoke data comprise suspended particulate matter concentration; acquiring portrait data of the target object under the condition that the kitchen environment lampblack data meets a first preset condition; based on the kitchen environment lampblack data, the camera shooting data and the thermal imaging data, health data of the target object are determined, and the health data comprise blood oxygen saturation and heart rate variability. The health monitoring function of the range hood can be automatically started after the kitchen environment oil smoke reaches a certain concentration, and the health data of the target object is determined by using the kitchen environment oil smoke data and the portrait data acquired by the range hood, so that the influence of the kitchen environment oil smoke on the accuracy of the health monitoring result can be improved; and it is ensured that the health of the target object can be accurately monitored in real time in the kitchen environment.

Description

Technical Field

[0001] This disclosure relates to the field of range hood technology, and in particular to a health monitoring method, a range hood, and a health monitoring system. Background Technology

[0002] A range hood is an appliance used in the kitchen to remove cooking fumes. Nowadays, range hoods are no longer limited to simple tools for removing kitchen fumes; they have incorporated more entertainment and functional features, such as range hoods with added television displays, range hoods with integrated smart home security systems, and network-controlled range hoods.

[0003] However, existing range hoods lack sufficient depth in intelligent health monitoring applications, offering only fixed functions such as remote power-off, which are inadequate to support users' health monitoring needs. In the kitchen setting, traditional wearable health monitoring devices are easily affected by the kitchen's fumes, leading to inaccurate monitoring results and poor applicability. Therefore, it is necessary to configure health monitoring functions on range hoods to meet users' needs for real-time health monitoring in the kitchen environment. Summary of the Invention

[0004] To address at least one of the aforementioned technical problems, this disclosure provides a health monitoring method, a range hood, and a health monitoring system.

[0005] According to some embodiments of this disclosure, a health monitoring method is provided, implemented based on a range hood with health monitoring function. The range hood includes a controller, an environmental sensing module, a vision module, and a cloud collaboration module. The cloud collaboration module is used to connect to an external health monitoring device. The method is applied to the controller. The method includes: when the range hood is in operation, acquiring kitchen environmental fume data based on the environmental sensing module; when the kitchen environmental fume data meets the first preset condition, acquiring facial image data of a target object based on the vision module, wherein the target object is the current user of the range hood; determining the health data of the target object based on the kitchen environmental fume data and the facial image data, the health data including blood index information and heart rate index information; and sending the blood index information and the heart rate index information to the external health monitoring device based on the cloud collaboration module.

[0006] Based on the above solution, when the concentration of cooking fumes in the kitchen reaches a certain level, the health monitoring function of the range hood is automatically activated. The health data of the target individual is determined by using the kitchen environment cooking fume data and human image data obtained by the range hood, and the health data is fed back to the external health monitoring equipment. This can improve the impact of kitchen environment cooking fumes on the accuracy of health monitoring results and ensure that the target individual can also be monitored for health in real time and accurately in the kitchen environment.

[0007] In some possible implementations, the environmental sensing module includes a sensor for acquiring the concentration of suspended particles; the kitchen environment oil fume data includes the concentration of suspended particles, and the first preset condition includes: the concentration of suspended particles is greater than or equal to a preset concentration.

[0008] Based on the above scheme, determining the activation conditions of the health monitoring function based on the concentration of suspended particulate matter helps to promptly identify the impact of suspended particulate matter on users and protect their health.

[0009] In some possible implementations, the vision module includes a camera and an infrared sensor for acquiring facial image data, which includes camera video data and thermal imaging data. The step of determining the health data of the target object based on the kitchen environment oil fume data and the facial image data includes: determining facial imaging data of the target object based on the camera video data; determining chest thermal imaging data of the target object based on the thermal imaging data; correcting the facial imaging data and chest thermal imaging data based on the kitchen environment oil fume data to obtain corrected facial imaging data and corrected chest thermal imaging data; extracting first respiratory signal features and heart rate features based on the corrected facial imaging data and corrected chest thermal imaging data; and determining the blood index information obtained based on the first respiratory signal features and the heart rate index information obtained based on the heart rate features as the health data.

[0010] Based on the above scheme, facial imaging data and chest thermal imaging data are further separated from human image data. The two types of feature data are then corrected using kitchen environmental oil fume data. Feature extraction and feature fusion are then performed on the corrected feature data to obtain respiratory features and heart rate features, thereby accurately obtaining the health data of the target object.

[0011] In some possible implementations, the range hood further includes a voiceprint module, which includes a microphone array for acquiring ambient sound data; the health data also includes cough sound data and respiratory frequency; the method further includes: acquiring kitchen sound data when the kitchen ambient smoke data meets the first preset condition; separating and processing the kitchen sound data to obtain the target object's voice data and kitchen noise data; determining cough sound data and a second respiratory signal feature based on the voice data; obtaining the respiratory frequency based on the first respiratory signal feature and the second respiratory signal feature, and merging the cough sound data and the respiratory frequency into the health data.

[0012] Based on the above scheme, voiceprint recognition is further added on the basis of visual recognition. By using sound data separation processing, human voice data is obtained, and cough sound features and breathing features are extracted from the human voice data. Cough sound features can be directly added to health data as cough sound data, while breathing features are verified and processed with breathing features obtained from visual recognition to obtain breathing frequency. By combining visual recognition and voiceprint recognition, the accuracy of health data can be further improved, ensuring accurate and effective health monitoring.

[0013] In some possible implementations, the method further includes: extracting facial features based on the facial imaging data of the target object; matching the facial features with pre-stored user data to determine the identity information of the target object; determining the basic health data of the target object based on the identity information; and generating a second preset condition based on the basic health data, wherein the second preset condition indicates a user health monitoring and early warning condition.

[0014] Based on the above scheme, when the range hood is conducting health monitoring, it also identifies the current user and sets corresponding health monitoring and early warning conditions according to the user's identity, so as to achieve the purpose of intelligent matching monitoring and early warning.

[0015] In some possible implementations, the method further includes: acquiring external health data stored in an external health monitoring device; determining an oil fume interference coefficient based on the difference between the external health data and the health data; and sending the oil fume interference coefficient to the external health monitoring device.

[0016] Based on the above scheme, the range hood determines the interference coefficient according to its health monitoring results and the health detection results of external health monitoring equipment, and feeds it back to the external health monitoring equipment. This can improve the synchronization and coordination of health monitoring and ensure the accuracy of health monitoring results.

[0017] In some possible implementations, the range hood also includes a control panel and a speaker for interaction; the method further includes generating a health monitoring report based on the health data if the health data meets a second preset condition.

[0018] Based on the above solution, the range hood displays the health monitoring report through the control panel and speaker, thereby promptly reminding the current user of the range hood and achieving the effect of real-time alarm.

[0019] In some possible implementations, the cloud collaboration module is also used to connect to external kitchen appliances. After generating a health monitoring report based on the health data when the health data meets a second preset condition, the method further includes: acquiring the status data of the external kitchen appliance, the status data including appliance type and operating parameters; matching corresponding recommended parameters from a pre-stored kitchen appliance parameter recommendation table based on the health monitoring report and the appliance type; and sending a control command corresponding to the recommended parameters to the external kitchen appliance when the operating parameters are inconsistent with the recommended parameters.

[0020] Based on the above solution, after the range hood detects that the current user's health data meets the warning conditions, it will also control other kitchen appliances in conjunction to realize the function of multiple kitchen appliances working together, thereby improving the comprehensiveness and intelligence of health monitoring and improving the user experience.

[0021] According to some other embodiments of this disclosure, a range hood with health monitoring function is provided, including: An environmental sensing module is used to acquire kitchen environmental oil fume data, and the environmental sensing module includes a suspended particulate matter sensor. A vision module for acquiring human image data, the vision module including a camera and an infrared sensor; The cloud-based collaboration module is used to connect to external health monitoring devices; A controller for performing a health monitoring method as described in some of the above embodiments.

[0022] According to some other embodiments of this disclosure, a health monitoring system is provided, including a wearable monitoring device, a kitchen appliance, a cloud server, and a range hood with health monitoring function as described in the above embodiments.

[0023] According to other embodiments of this disclosure, a computer-readable storage medium is provided that stores at least one instruction or at least one program, which is loaded and executed by a processor to implement a health monitoring method described in the above embodiments.

[0024] According to other embodiments of this disclosure, an electronic device is provided, including at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the at least one processor implements a health monitoring method as described in the above embodiments by executing the instructions stored in the memory.

[0025] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure.

[0026] Other features and aspects of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0027] To more clearly illustrate the technical solutions and advantages in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This diagram illustrates a flowchart of the steps of a health monitoring method according to an embodiment of the present disclosure; Figure 2 A flowchart illustrating the steps of a sound data processing method according to an embodiment of the present disclosure is shown. Figure 3 This diagram illustrates the steps of an identity recognition method according to an embodiment of the present disclosure. Figure 4 A flowchart illustrating the steps of an external health monitoring device feedback method according to an embodiment of the present disclosure is shown. Figure 5 A flowchart illustrating the steps of an external kitchen appliance feedback method according to an embodiment of the present disclosure is shown. Figure 6 A flowchart illustrating the steps of a portrait data processing method according to an embodiment of the present disclosure is shown. Figure 7 A system block diagram of a range hood with health monitoring function according to an embodiment of the present disclosure is shown. Detailed Implementation

[0029] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0031] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0032] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0033] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0034] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0035] It is worth noting that all data obtained in this embodiment of the disclosure has been obtained after being fully authorized by the relevant users or entities.

[0036] A range hood is an appliance used in the kitchen to remove cooking fumes. Nowadays, range hoods are no longer limited to simple tools for removing kitchen fumes; they have incorporated more entertainment and functional features, such as range hoods with added television displays, range hoods with integrated smart home security systems, and network-controlled range hoods.

[0037] Currently, existing range hoods fall short in their performance within the smart home ecosystem. Specifically, their integration with other smart home appliances is limited, hindering deeper smart home integration. Furthermore, existing range hoods are particularly lacking in their application of smart health monitoring, failing to adequately support users' health monitoring needs.

[0038] To address the aforementioned technical problems, this invention provides a health monitoring method based on a range hood with health monitoring capabilities. Please refer to... Figure 7 The range hood includes a controller, an environmental sensing module, and a vision module. The environmental sensing module is used to acquire kitchen environment oil fume data, the vision module is used to acquire the facial image data of the range hood user, and the controller is used to execute health detection methods.

[0039] The kitchen environment fume data includes at least the concentration of suspended particulate matter. Therefore, the environmental sensing module should include at least a suspended particulate matter sensor. This sensor detects the concentration of suspended particulate matter of a specified diameter in the kitchen environment, such as PM2.5 (2.5-micrometer Particulate Matter) concentration, which is the concentration of particles with a diameter of 2.5 micrometers or less. Additionally, the kitchen environment fume data may also include VOC (volatile organic compounds) concentration; therefore, the environmental sensing module also includes a VOC sensor / volatile organic compound sensor. Integrating multiple sensors into the environmental sensing module is for accurate detection of kitchen environment fume data, enabling the automatic activation of the range hood's health monitoring function when the fume concentration exceeds the standard. It should be understood that, to improve the accuracy of fume detection, sensors other than the two types mentioned above can be integrated into the environmental sensing module according to actual needs; this embodiment of the invention does not impose any limitations on this.

[0040] The facial data acquired by the vision module includes ordinary optical imaging data and special optical imaging data. Ordinary optical imaging data refers to imaging data acquired by normal optical imaging equipment such as cameras or camcorders, while special optical imaging data refers to imaging data acquired by special imaging equipment such as infrared, lidar, or acoustic waves. In some embodiments, the vision module includes a camera and an infrared sensor. The image data captured by the camera is the camera video data, and the image data captured by the infrared sensor is the thermal imaging data. Therefore, thermal imaging data includes both camera video data and thermal imaging data. The infrared sensor is used to simultaneously acquire the user's facial thermal imaging data to compensate for the visible light image blurring caused by cooking fumes. To improve imaging accuracy, an infrared sensor with a temperature resolution of less than or equal to 0.1°C can be selected. It should be understood that this embodiment does not limit the specific selection of the camera and infrared sensor in the vision module, nor does it limit the specific parameters.

[0041] In some embodiments, the camera can be configured as a 3D ToF camera (Time of Flight camera), with a resolution of at least 640×480 pixels and a frame rate of at least 30fps. A 3D ToF camera is a depth-sensing device that calculates distance by measuring the time of flight of light. It features high accuracy, fast response speed, strong resistance to ambient light interference, and low power consumption, making it suitable for facial recognition technology. Configuring a 3D ToF camera helps obtain clear facial data for subsequent analysis of the user's health status. The 3D ToF camera is mounted on the outer casing of the range hood, and multiple 3D ToF cameras can be installed on the casing. These multiple 3D ToF cameras can shoot at different angles. For example, at least one 3D ToF camera can be positioned directly above the stove and shooting at a 45° downward angle; or at least one 3D ToF camera can be positioned directly above the stove and shooting from a horizontal, direct view; or multiple 3D ToF cameras can be arranged circumferentially around the range hood casing. By setting multiple different shooting angles, it can be ensured that users can be captured when they are near the range hood, and the imaging data obtained from different shooting angles can be cross-validated, thereby improving the accuracy of subsequent facial feature extraction.

[0042] In some embodiments, the range hood is further equipped with a voiceprint module, which is used to acquire ambient sound data, including human voice data and kitchen noise data. After acquiring the ambient sound data, the controller separates the human voice data and kitchen noise data, and extracts health data features based on the separated human voice data. In some specific embodiments, the voiceprint module includes a microphone array, which is disposed on the outer casing of the range hood. The microphone array can be a linear array or a planar array (such as a rectangular array). Based on the linear array or planar array, the voiceprint module can accurately and comprehensively acquire sound data in the kitchen environment, improving the accuracy of subsequent human voice data extraction.

[0043] In some embodiments, the range hood further includes an interaction module, which includes a control panel and a speaker. The control panel displays an interactive interface and receives user operation commands, while the speaker emits audio signals. In this embodiment, the control panel can be a touchscreen or a control panel with buttons and a screen. The control panel can display the range hood's operating parameters, kitchen environment fume data, acquired current user health data, and a health monitoring report generated by the range hood based on the health data. In a further embodiment, the interaction module and / or the controller have a built-in intelligent voice program that can respond to user button or voice commands and execute corresponding operation steps.

[0044] In some embodiments, the range hood further includes a cloud collaboration module for connecting external health monitoring devices and external kitchen appliances. The external health monitoring devices include wearable health monitoring devices (smartwatches, smart bracelets, smart belts, etc.) or mobile health monitoring terminal devices (portable blood pressure monitors, scales, etc.). The external kitchen appliances include kitchen appliances other than the range hood, such as ovens, refrigerators, rice cookers, water purifiers, kitchen air conditioners, etc.

[0045] The reason for setting up a cloud-based collaborative module to connect to external health monitoring devices in this embodiment is that, in actual kitchen scenarios, traditional wearable health monitoring devices are easily affected by kitchen fumes. For example, fumes and fine particulate matter can easily cause the circuits or electrical components of wearable devices to malfunction, leading to inaccurate monitoring results. In other words, wearable health monitoring devices have poor applicability in kitchen fume environments. Therefore, after completing the health monitoring of the user, the range hood will feed back the health monitoring report to the external health monitoring device, ensuring the synchronization and consistency of health data.

[0046] The purpose of setting up a cloud-based collaborative module to connect external kitchen appliances in this embodiment is to enable the range hood to send health data or health monitoring reports back to various external kitchen appliances when it determines that the user's health status is abnormal based on the monitored user health data. For kitchen appliances with built-in health monitoring functions, they can make intelligent adjustments based on health data or health monitoring reports. For example, the range hood can send health data to the kitchen air conditioner, which will automatically adjust the air outlet temperature; or, the range hood can send health monitoring reports to a smart refrigerator, which will generate dietary suggestions when the user opens the refrigerator to take out food if it detects that the user's health status is abnormal. For kitchen appliances without health monitoring functions, the range hood can send control commands to external kitchen appliances based on health data or health monitoring reports. For example, when it detects that the user's health status is abnormal, it can lock certain functions of the oven.

[0047] The foregoing embodiments have described in detail a range hood with health monitoring function according to the present invention. Based on this range hood, a health monitoring method of the present invention can be implemented. This method is applied in the controller of the range hood. Figure 1 A flowchart illustrating the steps of a health monitoring method according to the present invention is shown, as follows: Figure 1 As shown, the method includes: Step S101: When the range hood is in operation, acquire kitchen environmental oil fume data based on the environmental sensing module.

[0048] In this embodiment, the purpose of acquiring kitchen fume data is twofold: firstly, to determine the fume concentration for subsequent health monitoring corrections to mitigate fume interference; and secondly, to detect changes in the kitchen fume environment to determine whether the user is cooking, thus preventing the range hood from being mistakenly activated for health monitoring and resulting in wasted energy. The kitchen fume data includes the concentration of suspended particulate matter, which includes at least PM2.5 concentration (particulate matter with a diameter of 2.5 micrometers or less). In a further embodiment, the kitchen fume data may also include VOC concentration. Additionally, the kitchen fume data may include the concentration of other gases, such as CO (carbon monoxide) and CO2 (carbon dioxide).

[0049] Step S102: If the kitchen environment oil fume data meets the first preset condition, obtain the facial image data of the target object, wherein the target object is the current user of the range hood.

[0050] In this embodiment, the first preset condition is used to indicate a situation where the concentration of cooking fumes is too high. Based on the above, when the concentration of cooking fumes is too high, the components of the fumes can cause the electronic components or circuits of the wearable health monitoring device to malfunction, resulting in inaccurate monitoring. Therefore, the purpose of setting the first preset condition is to ensure that the range hood automatically activates the health monitoring function when it detects that the concentration of cooking fumes in the kitchen environment is too high, so as to ensure that the health data of the target object can be accurately obtained even in a kitchen scenario with a high concentration of cooking fumes, and to ensure that the health monitoring is uninterrupted. Another purpose of setting the first preset condition in this embodiment is that the range hood automatically activates the health monitoring function after the kitchen environment deteriorates, which helps to reduce the power consumption of the range hood. It is worth noting that in some cases, users can also manually activate the health monitoring function according to the control panel on the range hood, or customize the activation conditions of the health monitoring function. For example, the activation condition can be set to activate the health monitoring function as soon as the range hood is turned on. In a specific implementation, the first preset condition includes: the concentration of suspended particulate matter is greater than or equal to a preset concentration, such as PM2.5 concentration greater than or equal to 150 μg / m³.

[0051] In some embodiments, the portrait data may include camera image data and thermal imaging data. The camera image data can be obtained using 3D ToF cameras distributed on the range hood casing, capable of acquiring portrait images of the target object from multiple angles. The camera image data should include image data of the target object's chest and above to facilitate subsequent extraction of health features. Since in practical applications, images captured by multiple 3D ToF cameras may contain image data that does not meet the above requirements, the images captured by multiple 3D ToF cameras can be pre-processed and filtered to ensure that the retained camera image data includes image data of the target object's chest and above. In a specific embodiment, face localization can use a Haar cascade classifier or a deep learning model (such as SSD) to locate the face, perform denoising (median filtering) and threshold segmentation on the depth image, and delineate regions such as the forehead / cheeks as ROIs, i.e., extract the facial contour region (ROI). Chest localization is completed based on face localization. The chest cavity detection area can be set as a rectangular area 1.5-2 times the length of the face downwards from the lower boundary of the face to achieve chest localization.

[0052] In this embodiment, the thermal imaging data can be obtained based on an infrared sensor with a temperature resolution of less than or equal to 0.1°C. Corresponding to the camera-captured data, the thermal imaging data should also include image data of the target object's chest and above. In some cases, the thermal imaging data may only include image data of the target object's chest.

[0053] Step S103: Based on kitchen environment oil fume data and human image data, determine the health data of the target object. The health data includes blood index information and heart rate index information.

[0054] In this embodiment, the visual module on the range hood acquires facial image data of the target object, and health data features are extracted based on the facial image data to determine the target object's health data. Compared to solutions using electrodes or other sensors for monitoring external health devices, the solution using facial image data to determine health data is less affected by oil fume interference. In particular, the range hood uses multiple 3D ToF cameras to acquire camera image data, which has high accuracy and strong anti-interference capabilities, enabling the acquisition of clear imaging data even in oil fume environments. Furthermore, during the process of extracting health data features and determining health data, the acquired kitchen environment oil fume data is also combined to obtain comprehensive health data, thereby ensuring the accuracy of the health data.

[0055] In a further embodiment, please refer to Figure 6 The above step S103 specifically includes: Step S1031: Determine the facial imaging data of the target object based on the camera image data.

[0056] Step S1032: Based on the thermal imaging data, determine the chest thermal imaging data of the target object.

[0057] Step S1033: Based on kitchen environment oil fume data, correct the facial imaging data and chest thermal imaging data to obtain corrected facial imaging data and corrected chest thermal imaging data.

[0058] In this embodiment, the correction of facial imaging data and chest thermal imaging data is based on image restoration algorithms. Specifically, a mapping model between oil fume concentration and image blurriness is pre-established. After determining the PM2.5 concentration based on kitchen environment oil fume data, the parameters in the image restoration algorithm, such as the noise power spectrum of Wiener filtering, are dynamically adjusted according to the PM2.5 concentration to achieve the purpose of oil fume interference compensation. It should be understood that the kitchen environment oil fume data in this embodiment may contain concentration data of more than one different substance. Correspondingly, the oil fume concentration-image blurriness mapping model and the image restoration algorithm should be flexibly adjusted according to the number and types of data contained in the kitchen environment oil fume data.

[0059] In a further embodiment, a multi-frame image super-resolution reconstruction algorithm is applied to correct facial imaging data. Specifically, when a PM2.5 concentration of 200 μg / m³ or higher is detected, the multi-frame image super-resolution reconstruction algorithm is activated, fusing five consecutive frames of images to improve the clarity of facial features. Based on the multi-frame image super-resolution reconstruction algorithm, the original resolution of 640×480 pixels can be improved to 1280×960 pixels, so as to accurately extract facial features.

[0060] Step S1034: Based on the corrected facial imaging data and the corrected chest thermal imaging data, extract the first respiratory signal features and heart rate features.

[0061] In this embodiment, the principle for extracting heart rate features is based on blood flow effects and micro-motion. Specifically, since heartbeats cause periodic congestion of facial microvessels, resulting in skin color changes (enhanced red light reflection), and the heartbeat is transmitted to the head, generating an inertial displacement of approximately 0.2-0.4 seconds, the green channel is extracted using corrected facial imaging data, and the pixel values ​​within the ROI are spatially averaged to generate the original photoplethysmography (IPPG) signal for spatial noise reduction. Then, the Lucas-Kanade optical flow method is used to correct head motion interference. Finally, bandpass filtering is used to preserve the physiological frequency band, and the time-domain signal is converted to the frequency domain using FFT (Fast Fourier Transform). The obtained spectral peak value is the heart rate value.

[0062] In this embodiment, the principle for extracting the first respiratory signal feature is based on chest cavity movement and head micro-movement. Specifically, during respiration, the chest cavity expands / contracts, causing periodic displacement of the trunk region, and respiration may be accompanied by slight forward / backward tilting of the head. Before extracting the first respiratory signal feature, facial respiratory features and chest respiratory features are extracted by correcting facial imaging data and chest thermal imaging data, respectively. The process of extracting facial respiratory features includes calculating the change in ROI area in consecutive frames (maximum area at the end of inspiration, minimum at the end of expiration), then using the displacement of tracking feature points (such as Harris corners) to generate a motion vector diagram, and finally retaining the respiratory signal in the physiological frequency band, determining the respiratory frequency by counting the number of peaks per unit time. The process of extracting chest respiratory features includes performing time-series analysis on the corrected chest thermal imaging data, segmenting the chest cavity region using a region growing algorithm, extracting the temperature gradient change curve of chest undulations during respiration, converting the time-domain signal to the frequency domain using FFT (Fast Fourier Transform), and locating the obtained spectral peak as the respiratory frequency. After obtaining the facial and chest respiratory features, they are averaged to determine the first respiratory feature.

[0063] In this embodiment, pupil changes can also be determined based on corrected facial imaging data. Specifically, an Active Shape Model (ASM) is set up, and multiple key points such as the corners of the eyes, nose, and mouth are located using the ASM. The displacement vectors of the key points are calculated (accuracy ≤ 0.1 mm), and micro-expressions such as frowning and blinking frequency are analyzed. Then, an image pyramid algorithm based on Gaussian pyramids is used to track the pupil edge at different scales, and the pupil diameter change is calculated through ellipse fitting (error ≤ 0.2 mm).

[0064] Step S1035: Determine the blood index information obtained based on the first respiratory signal characteristics and the heart rate index information obtained based on the heart rate characteristics as health data.

[0065] In this embodiment, heart rate information includes heart rate variability, which can be directly obtained based on heart rate features. Blood indicator information includes blood oxygen saturation, which is indirectly determined based on the features of the first respiratory signal. Specifically, by pre-establishing an association prediction model, which is trained based on the association data between respiratory patterns and blood oxygen saturation, the blood oxygen saturation can be obtained by inputting the features of the first respiratory signal into the trained association prediction model. The association prediction model can be an LSTM network or a random forest classifier.

[0066] Step S104: Based on the cloud collaboration module, send blood index information and heart rate index information to external health monitoring equipment.

[0067] Because external health monitoring devices detect a user's heart rate and blood parameters based on electrodes or detection circuits, the fumes in a kitchen can cause these electrodes or circuits to malfunction, leading to inaccurate heart rate and blood parameter data from the external health monitoring device. In contrast, the health data determined by a range hood using visual data is unaffected by fumes. To ensure the data from the external health monitoring device remains consistently valid, the range hood sends its blood parameter and heart rate data to the external health monitoring device. In a further embodiment, the range hood sends all health data in the time domain during the range hood's operation to the external health monitoring device.

[0068] Based on the above steps S101~S104, after the kitchen environment oil fumes reach a certain concentration, the health monitoring function of the range hood is automatically activated. The health data of the target object is determined by using the kitchen environment oil fume data and human image data obtained by the range hood, and the health data is fed back to the external health monitoring equipment. This can improve the impact of kitchen environment oil fumes on the accuracy of health monitoring results and ensure that the target object can also be monitored for health in real time and accurately in the kitchen environment.

[0069] In some embodiments, the range hood further includes a voiceprint module, which includes a microphone array for acquiring ambient sound data. Correspondingly, the health data also includes cough sound data and respiratory rate. Please refer to [reference needed]. Figure 2 Health monitoring methods also include: Step S201: If the kitchen environment oil fume data meets the first preset condition, acquire kitchen sound data.

[0070] Step S202: Separate and process the kitchen sound data to obtain the target object's human voice data and kitchen noise data.

[0071] In this embodiment, independent component analysis (ICA) is used to separate kitchen sound data into target human voice data and kitchen noise data. Specifically, a kitchen noise database (including noise from different settings of the range hood, water flow sounds, and pot collision sounds) is first constructed, and then an ICA model is trained to separate environmental noise from user voice signals. The separated user voice signals are further suppressed by bandpass filtering to suppress low-frequency mechanical noise and high-frequency oil fume turbulence sounds, thus obtaining human voice data. The bandpass filtering frequency band can be 300-3000Hz, which is the main frequency range of cough sounds.

[0072] Step S203: Based on human voice data, determine cough sound data and second respiratory signal characteristics.

[0073] In this embodiment, the method for identifying cough / wheezing sounds includes extracting Mel-frequency cepstral coefficients (MFCC, 13th order) and zero-crossing rate variation coefficients as feature vectors, employing a Hidden Markov Model (HMM) classifier, and matching cough sound templates (the template library can contain 10 typical patterns such as dry / wet cough and wheezing) using the Viterbi algorithm, achieving an accuracy of ≥95%. The method for extracting the second respiratory signal feature includes obtaining respiratory sound data (or respiratory sound signals) from human voice data, performing Hilbert-Huang transform (HHT) on the denoised respiratory sound signal, extracting the respiratory cycle component from the intrinsic mode function (IMF), aligning the continuous respiratory waveform using the Dynamic Time Warping (DTW) algorithm, calculating the average respiratory interval, and obtaining the respiratory frequency, achieving an error of ≤±0.5 breaths / minute.

[0074] Step S204: Based on the first respiratory signal features and the second respiratory signal features, obtain the respiratory frequency, and merge the cough sound data and respiratory frequency into the health data.

[0075] In this embodiment, the first respiratory signal feature extracted based on human face data is combined with the second respiratory signal feature extracted based on human voice data, and the respiratory frequency is determined after feature fusion processing. This can avoid the inaccurate monitoring results caused by the limitations of a single monitoring method and help improve the accuracy of health data.

[0076] In some embodiments, the health monitoring method of the present invention further includes identity recognition and intelligent early warning; specifically, please refer to... Figure 3 The methods also include: Step S301: Extract facial features based on the facial imaging data of the target object.

[0077] Step S302: Match facial features with pre-stored user data to determine the identity information of the target object.

[0078] Step S303: Based on the identity recognition information, determine the basic health data of the target object.

[0079] Step S304: Generate a second preset condition based on the basic health data. The second preset condition indicates the user's health monitoring and early warning conditions.

[0080] Based on steps S301-S304 above, when the range hood performs health monitoring, it also identifies the current user, thereby setting corresponding health monitoring and warning conditions based on the user's identity to achieve intelligent matching of monitoring and warnings. The basic health data includes the user's age, gender, height, weight, etc., which determines the user's health standard. The health standard includes a range of multiple vital signs, and the second preset condition also includes a range of multiple vital signs, with the second preset condition partially overlapping or not overlapping with the health standard. This embodiment, by setting an identity recognition step, can provide personalized monitoring and health reminder solutions when different users use the range hood, helping to improve the user experience.

[0081] In a further embodiment, the range hood also includes an interactive control panel and a speaker. The health monitoring method further includes generating a health monitoring report based on the health data when the health data meets a second preset condition. In this embodiment, the second preset condition indicates a health monitoring warning condition for the user. When the health data meets the second preset condition, it indicates that the user's health status is not normal. Therefore, the health monitoring report is visually notified to the user through the control panel and speaker to remind the user to check in time. In some specific embodiments, the range hood can also adjust its own parameters according to the health monitoring report. For example, when the monitoring report includes abnormal cough frequency, the range hood actively adjusts the fan speed.

[0082] In a further embodiment, the range hood also includes a cloud-based collaborative module for connecting external health monitoring devices and external kitchen appliances; please refer to [reference needed]. Figure 4 Based on cloud-based collaborative modules, health monitoring methods also include: Step S401: Obtain external health data stored in the external health monitoring device.

[0083] Step S402: Determine the oil fume interference coefficient based on the difference between external health data and health data.

[0084] Step S403: Send the oil fume interference coefficient to the external health monitoring device.

[0085] In this embodiment, the external health data refers to the health data of the target object acquired by the external health monitoring device after the range hood's health monitoring function is activated. The external health data and the actual health data should correspond to each other in the time domain. By comparing the health data monitored by the range hood with the external data, it is determined whether the external health monitoring device is functioning properly in the kitchen fume environment. The fume interference coefficient is then fed back to the external health monitoring device, allowing it to adjust accordingly. In some preferred embodiments, the aforementioned fume interference coefficient can also be directly obtained based on the fume concentration-image blurring mapping model.

[0086] In a further embodiment, please refer to Figure 5 Based on cloud-based collaborative modules, health monitoring methods also include: Step S501: Obtain the status data of external kitchen appliances, including appliance type and operating parameters.

[0087] Step S502: Based on the health test report and appliance type, match the corresponding recommended parameters from the pre-stored kitchen appliance parameter recommendation table.

[0088] Step S503: If the operating parameters are inconsistent with the recommended parameters, send control commands corresponding to the recommended parameters to the external kitchen appliances.

[0089] In this embodiment, external kitchen appliances include all appliances except the range hood. Kitchen types include ovens, refrigerators, rice cookers, water purifiers, and kitchen air conditioners. Operating parameters include speed settings and modes. Recommended parameters represent the recommended operating parameters for kitchen appliances under different user health conditions. Taking a kitchen air conditioner as an example, if the user is in a normal health condition, the recommended parameters are full speed and full temperature settings; if the user is in an abnormal health condition, the recommended parameters are low to medium speed and medium to high temperature settings. This embodiment determines whether the operating parameters of the external kitchen appliances match the health monitoring report by looking up a table, and if they do not match, it feeds back control commands to achieve coordinated control between kitchen appliances.

[0090] The above embodiments have described in detail a health monitoring method of the present invention. This health monitoring method is implemented based on a range hood with health monitoring function as described in the above embodiments. It should be understood that the method of determining health data based on human facial data in the health monitoring method of the present invention can also be applied to other kitchen appliances. That is, health monitoring functions can be configured on different kitchen appliances to achieve further collaborative health monitoring functions of kitchen appliances.

[0091] In addition, some embodiments of the present invention also provide a health monitoring system, which includes a wearable monitoring device, a kitchen appliance, a cloud server, and a range hood with health monitoring function as described in some of the above embodiments.

[0092] In addition, some embodiments of the present invention also provide a computer-readable storage medium storing at least one instruction or at least one program, wherein the at least one instruction or at least one program is loaded and executed by a processor to implement a health monitoring method as described in the above embodiments.

[0093] In addition, some embodiments of the present invention also provide an electronic device, including at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the at least one processor implements a health monitoring method described in the above embodiments by executing the instructions stored in the memory.

[0094] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A health monitoring method, characterized in that, This is based on a range hood with health monitoring function, the range hood including a controller, an environmental sensing module, a vision module, and a cloud collaboration module, the cloud collaboration module being used to connect to external health monitoring devices, and the method being applied to the controller; the method includes: When the range hood is in operation, kitchen environmental oil fume data is acquired based on the environmental sensing module; When the kitchen environment oil fume data meets the first preset condition, the visual module acquires the portrait data of the target object, wherein the target object is the current user of the range hood; Based on the kitchen environment oil fume data and the human image data, the health data of the target object is determined, including blood index information and heart rate index information; The cloud-based collaborative module sends the blood index information and the heart rate index information to the external health monitoring device.

2. The method according to claim 1, characterized in that, The environmental sensing module includes a sensor for acquiring the concentration of suspended particles; the kitchen environment oil fume data includes the concentration of suspended particles, and the first preset condition includes: the concentration of suspended particles is greater than or equal to a preset concentration.

3. The method according to claim 2, characterized in that, The vision module includes a camera and an infrared sensor for acquiring facial data, the facial data including camera video data and thermal imaging data. The step of determining the health data of the target object based on the kitchen environment oil fume data and the facial data includes: Based on the camera capture data, determine the facial imaging data of the target object; Based on the thermal imaging data, determine the chest thermal image data of the target object; Based on the kitchen environment oil fume data, the facial imaging data and the chest thermal image data are corrected to obtain corrected facial imaging data and corrected chest thermal image data. Based on the corrected facial imaging data and the corrected chest thermogram data, first respiratory signal features and heart rate features are extracted; The blood index information obtained based on the first respiratory signal feature and the heart rate index information obtained based on the heart rate feature are determined as the health data.

4. The method according to claim 3, characterized in that, The range hood further includes a voiceprint module, which includes a microphone array for acquiring ambient sound data; the health data also includes cough sound data and respiratory rate; the method further includes: If the kitchen environment oil fume data meets the first preset condition, acquire kitchen sound data; The kitchen sound data is separated and processed to obtain the human voice data and kitchen noise data of the target object; Based on the human voice data, determine the cough sound data and the characteristics of the second respiratory signal; Based on the first respiratory signal features and the second respiratory signal features, the respiratory frequency is obtained, and the cough sound data and the respiratory frequency are merged into the health data.

5. The method according to claim 4, characterized in that, The method further includes: Based on the facial imaging data of the target object, facial features are extracted; The facial features are matched with pre-stored user data to determine the identity information of the target object; Based on the identity information, the basic health data of the target object is determined; A second preset condition is generated based on the basic health data, and the second preset condition indicates the user's health monitoring and early warning conditions.

6. The method according to claim 5, characterized in that, The method further includes: Acquire external health data stored by external health monitoring devices; The oil fume interference coefficient is determined based on the difference between the external health data and the health data. The oil fume interference coefficient is sent to the external health monitoring device.

7. The method according to claim 6, characterized in that, The range hood also includes a control panel and speakers for interaction; the method further includes: If the health data meets the second preset condition, a health monitoring report is generated based on the health data.

8. The method according to claim 7, characterized in that, The cloud-based collaboration module is also used to connect to external kitchen appliances. After generating a health monitoring report based on the health data when the health data meets the second preset condition, the method further includes: Acquire the status data of the external kitchen appliance, the status data including appliance type and operating parameters; Based on the health test report and the type of appliance, match the corresponding recommended parameters from the pre-stored kitchen appliance parameter recommendation table; If the operating parameters are inconsistent with the recommended parameters, a control command corresponding to the recommended parameters is sent to the external kitchen appliance.

9. A range hood with health monitoring function, characterized in that, include: An environmental sensing module is used to acquire kitchen environmental oil fume data, and the environmental sensing module includes a suspended particulate matter sensor. A vision module for acquiring human image data, the vision module including a camera and an infrared sensor; The cloud-based collaboration module is used to connect to external health monitoring devices; A controller for performing a health monitoring method as described in any one of claims 1-8.

10. A health monitoring system, characterized in that, This includes wearable monitoring devices, kitchen appliances, cloud servers, and a range hood with health monitoring function as described in claim 9.

Images