Health detection method and device, wearable equipment, earphone and storage medium

Abstract

The invention discloses a health detection method and device, wearable equipment, an earphone and a storage medium, and relates to the technical field of wearable equipment, the method is applied to the wearable equipment, and the wearable equipment comprises a microphone, a temperature detection module and a heart rate detection module; the method comprises the following steps: acquiring a target sound signal and a target heart rate signal of a wearer through a microphone; acquiring target body temperature data of a wearer through a temperature detection module; preprocessing the target sound signal, the target heart rate signal and the target body temperature data to obtain a target sound feature, a target heart rate feature and a target body temperature feature; and obtaining a health detection result of the wearer based on the target sound feature, the target heart rate feature and the target body temperature feature. According to the method, the health state of the wearer is comprehensively analyzed by adopting the three parameters of the sound, the heart rate and the body temperature, and the health state of the wearer can be accurately and comprehensively reflected.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wearable devices, in particular to a health detection method and device, a wearable device, an earphone and a storage medium. BACKGROUND

[0002] With the increasing demand for health and the continuous progress of technology, personal health management is becoming increasingly important. In order to better monitor and maintain personal health, various health detection devices and technologies have appeared on the market.

[0003] Traditional health detection methods mainly rely on a single physiological parameter to evaluate the health status of an individual, such as a sphygmomanometer that only measures blood pressure, a blood glucose meter that only detects blood glucose levels, etc. These methods can provide information on specific physiological indicators, but are not sufficient for a comprehensive assessment of an individual's overall health status.

[0004] Therefore, how to accurately and comprehensively detect the health status of a user has become a technical problem to be solved.

[0005] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0006] The main purpose of the present application is to provide a health detection method, device, wearable device, earphone and storage medium, which aims to solve the technical problem of accurately and comprehensively detecting the health status of a user.

[0007] To achieve the above purpose, the present application provides a health detection method, which is applied to a wearable device, the wearable device comprising a microphone, a temperature detection module and a heart rate detection module; the method comprising:

[0008] acquiring a target sound signal of a wearer through the microphone;

[0009] acquiring target temperature data of the wearer through the temperature detection module;

[0010] acquiring a target heart rate signal of the wearer through the heart rate detection module;

[0011] preprocessing the target sound signal, the target heart rate signal and the target temperature data to obtain target sound features, target heart rate features and target temperature features;

[0012] obtaining a health detection result of the wearer based on the target sound features, the target heart rate features and the target temperature features.

[0013] In one embodiment, the step of preprocessing the target sound signal, the target heart rate signal, and the target body temperature data to obtain target sound features, target heart rate features, and target body temperature features includes:

[0014] The target sound signal and the target heart rate signal are preprocessed to obtain intermediate sound signal and intermediate heart rate signal;

[0015] The target sound features and the target heart rate features are obtained by extracting the features of the intermediate sound signal and the intermediate heart rate signal in the time domain and frequency domain, respectively.

[0016] The target body temperature data is smoothed to obtain the target body temperature characteristics.

[0017] In one embodiment, the step of obtaining the wearer's health detection result based on the target sound features, the target heart rate features, and the target body temperature features includes:

[0018] The target voice features are input into a preset age prediction model to obtain the wearer's predicted age, wherein the age prediction model is trained using voice features as input and age as a label.

[0019] The wearer's health detection results are obtained based on the predicted age, the target voice characteristics, the target heart rate characteristics, and the target body temperature characteristics.

[0020] In one embodiment, the step of obtaining the wearer's health test result based on the predicted age, the target voice feature, the target heart rate feature, and the target body temperature feature includes:

[0021] The target health detection model corresponding to the predicted age is determined from a set of multiple preset health detection models. The health detection model is trained using voice features, heart rate and body temperature features as inputs and health status as a label.

[0022] The target sound features, target heart rate features, and target body temperature features are input into the target health detection model to obtain the wearer's health detection results.

[0023] In one embodiment, before the step of determining the target health detection model corresponding to the predicted age from a plurality of preset health detection models, the method further includes:

[0024] Obtain sample datasets for different age groups, wherein the sample datasets include the voice features, heart rate features, and body temperature features of multiple samples;

[0025] The preset prediction model is trained using each of the aforementioned sample datasets to obtain the health detection model corresponding to each of the aforementioned age groups after training.

[0026] In one embodiment, the step of obtaining the wearer's health test result based on the predicted age, the target voice feature, the target heart rate feature, and the target body temperature feature includes:

[0027] The set of health detection features corresponding to the predicted age is determined from a preset storage space. The set of health detection features includes: multiple reference voice features, multiple reference heart rate features, and body temperature range.

[0028] Calculate the first similarity between the target sound feature and each of the reference sound features, and determine the target reference sound feature with the highest first similarity among the reference sound features;

[0029] The sound label of the target reference sound feature is used as the sound detection result of the wearer;

[0030] Calculate the second similarity between the target heart rate feature and each of the reference heart rate features, and determine the target reference heart rate feature with the highest second similarity among the reference heart rate features;

[0031] The heart rate label of the target reference heart rate feature is used as the heart rate detection result of the wearer;

[0032] The target body temperature feature is compared with the body temperature range to obtain a body temperature comparison result, and the body temperature comparison result is used as the body temperature detection result of the wearer.

[0033] The target health detection result corresponding to the sound detection result, the heart rate detection result, and the body temperature detection result in the preset health detection result set is used as the wearer's health detection result.

[0034] In one embodiment, after the step of obtaining the wearer's health detection result based on the target voice feature, the target heart rate feature, and the target body temperature feature, the method further includes:

[0035] The health test results are input into a preset health report template to generate a target test report for the wearer;

[0036] When a negative label exists among the result labels of the health test results, the test item corresponding to the negative label is marked in the target test report.

[0037] Furthermore, to achieve the above objectives, this application also proposes a health monitoring device, which is installed in a wearable device, the wearable device including: a microphone, a temperature detection module, and a heart rate detection module; the device includes:

[0038] A microphone detection module is used to acquire the wearer's target sound signal through the microphone;

[0039] A body temperature detection module is used to acquire the wearer's target body temperature data through the temperature detection module;

[0040] A heart rate detection module is used to acquire the wearer's target heart rate signal.

[0041] The feature extraction module is used to preprocess the target sound signal, the target heart rate signal, and the target body temperature data to obtain target sound features, target heart rate features, and target body temperature features.

[0042] The prediction module is used to obtain the wearer's health detection results based on the target sound features, the target heart rate features, and the target body temperature features.

[0043] In addition, to achieve the above objectives, this application also proposes a wearable device, the wearable device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the health detection method as described above.

[0044] In addition, to achieve the above objectives, this application also proposes an earphone, the earphone comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the health detection method as described above.

[0045] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and which, when executed by a processor, implements the steps of the health detection method described above.

[0046] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the health detection method described above.

[0047] This application provides a health detection method. The method involves setting up a microphone, a temperature detection module, and a heart rate detection module on a wearable device to detect the wearer's voice, heart rate, and body temperature. After processing the real-time collected target voice signal, target heart rate signal, and target body temperature data, the health status of the wearer is analyzed based on the processed target voice characteristics, target heart rate characteristics, and target body temperature characteristics to obtain the health detection result.

[0048] In summary, this application achieves the detection of the wearer's voice, heart rate, and body temperature by setting up a microphone, temperature detection module, and heart rate detection module on the wearable device. At the same time, it uses the three parameters of voice, heart rate, and body temperature to analyze the wearer's health status. Compared with the existing technology that uses a single parameter to detect the human body's health status, this method can more accurately and comprehensively reflect the wearer's health status. Attached Figure Description

[0049] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0050] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 This is a flowchart illustrating the health testing method of this application in Embodiment 1;

[0052] Figure 2 This is a flowchart illustrating Embodiment 2 of the health testing method of this application;

[0053] Figure 3 This is a flowchart illustrating Embodiment 2 of the health testing method of this application;

[0054] Figure 4 This is a schematic diagram of the module structure of the health detection device according to an embodiment of this application;

[0055] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the health detection method in the embodiments of this application.

[0056] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0057] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0058] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0059] The main solution of this application embodiment is as follows: acquiring the wearer's target sound signal through the microphone; acquiring the wearer's target body temperature data through the temperature detection module; acquiring the wearer's target heart rate signal through the heart rate detection module; preprocessing the target sound signal, the target heart rate signal, and the target body temperature data to obtain target sound features, target heart rate features, and target body temperature features; and obtaining the wearer's health detection result based on the target sound features, target heart rate features, and target body temperature features.

[0060] In this embodiment, for ease of description, the following description uses a wearable device as the execution subject.

[0061] With people's growing demand for health and the continuous advancement of technology, personal health management has become increasingly important. In order to better monitor and maintain personal health, a variety of health monitoring devices and technologies have emerged on the market.

[0062] Traditional health monitoring methods primarily rely on single physiological parameters to assess an individual's health status. For example, a blood pressure monitor only measures blood pressure, and a blood glucose meter only measures blood glucose levels. While these methods provide information on specific physiological indicators, they are insufficient for a comprehensive assessment of an individual's overall health. Furthermore, although wearable devices with multiple sensors exist, such as motion trackers and smartwatches, these devices typically detect only the relatively standard parameter of heart rate and rarely integrate multiple parameters for health status assessment. Therefore, the parameters used cannot accurately and comprehensively reflect the user's health condition.

[0063] Therefore, how to accurately and comprehensively detect users' health status has become a pressing technical problem that needs to be solved.

[0064] This application provides a health detection method. The method involves setting up a microphone, a temperature detection module, and a heart rate detection module on a wearable device to detect the wearer's voice, heart rate, and body temperature. After processing the real-time collected target voice signal, target heart rate signal, and target body temperature data, the health status of the wearer is analyzed based on the processed target voice characteristics, target heart rate characteristics, and target body temperature characteristics to obtain the health detection result.

[0065] In summary, this application achieves the detection of the wearer's voice, heart rate, and body temperature by setting up a microphone, temperature detection module, and heart rate detection module on the wearable device. At the same time, it uses the three parameters of voice, heart rate, and body temperature to analyze the wearer's health status. Compared with the existing technology that uses a single parameter to detect the human body's health status, this method can more accurately and comprehensively reflect the wearer's health status.

[0066] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, or an electronic device, wearable device, etc., capable of realizing the above functions. The following description uses a wearable device as an example to illustrate this embodiment and the subsequent embodiments.

[0067] Based on this, embodiments of this application provide a health detection method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the health detection method of this application.

[0068] In this embodiment, the health detection method is applied to a wearable device, which includes a microphone, a temperature detection module, and a heart rate detection module. The method includes steps S10 to S50:

[0069] Step S10: Acquire the wearer's target sound signal through the microphone;

[0070] In this embodiment, a microphone on the wearable device is used to capture the wearer's voice signal (e.g., speaking) and heart rate signal (i.e., heart rate sound). The captured voice signal can determine the user's voice state, thereby indirectly obtaining data on respiratory system health, which helps to detect respiratory diseases or other health problems early. The captured heart rate signal can directly obtain data on heart rate system health, which helps to detect heart rate diseases or other health problems early.

[0071] Step S20: Obtain the wearer's target body temperature data through the temperature detection module;

[0072] In this embodiment, the temperature detection module on the wearable device is used to measure the wearer's body temperature. Body temperature is an important indicator of human health. Abnormal changes in body temperature may be a precursor to diseases such as infection and fever. Timely detection of body temperature helps in the early diagnosis of diseases.

[0073] Step S30: Obtain the wearer's target heart rate signal through the heart rate detection module;

[0074] It should be noted that, in this embodiment, the heart rate detection module may include an optical heart rate sensor that emits light of a fixed wavelength onto the skin and then infers the heart rate by measuring the change in the intensity of the reflected light; or it may measure the electrical signal of the wearer's heart by setting electrodes, thereby measuring the heart rate. The structure of the heart rate detection module is not further limited here.

[0075] In this embodiment, the wearable device detects the wearer's heart rate through sensors in the heart rate monitoring module. The heart rate includes multiple pieces of information related to human health. For example, a high resting heart rate may indicate a risk of cardiovascular disease; an abnormal heart rhythm may indicate a disease requiring further medical evaluation; and high or low heart rate variability (HRV, which refers to the time variation of heartbeat intervals) is also related to human health. Real-time monitoring of the human heart rate helps in the early diagnosis of diseases.

[0076] Step S40: Preprocess the target sound signal, target heart rate signal, and target body temperature data to obtain target sound features, target heart rate features, and target body temperature features;

[0077] In this embodiment, the acquired sound signal, heart rate signal and body temperature data are preprocessed to extract useful information, such as sound features, heart rate features and body temperature features. The preprocessing process may include steps such as noise removal, signal enhancement and feature extraction.

[0078] Specifically, in one feasible implementation, step S40 above may include steps S41 to S43:

[0079] Step S41: Preprocess the target sound signal and the target heart rate signal to obtain intermediate sound signal and intermediate heart rate signal;

[0080] Step S42: Extract the features of the intermediate sound signal and the intermediate heart rate signal in the time domain and frequency domain respectively to obtain the target sound features and the target heart rate features;

[0081] Step S43: Smooth the target body temperature data to obtain the target body temperature characteristics.

[0082] In this embodiment, when processing the sound signal, it is necessary to first denoise the collected sound signal, then normalize the data, and then use common feature extraction methods to extract features from the preprocessed sound signal.

[0083] Similarly, when processing heart rate signals, it is also necessary to denoise the heart rate signals and then perform spectral analysis to separate each heart rate, so as to analyze the heart rate interval and extract the features of the heart rate in the time domain and frequency domain.

[0084] When processing body temperature signals, it is only necessary to smooth the collected body temperature data and remove outliers caused by various interferences.

[0085] Step S50: Obtain the wearer's health detection results based on the target voice features, target heart rate features, and target body temperature features.

[0086] In this embodiment, the wearer's health detection results can be obtained by analyzing the target sound features, target heart rate features, and target body temperature features. There are many ways to perform the analysis, and no further limitations are made here.

[0087] Specifically, as an example, when using headphones as the implementation subject, a temperature sensor and a heart rate detection module can be added to the headphones. After detecting that a user is wearing the headphones, the microphone of the headphones can collect the wearer's target sound signal in real time, the temperature sensor can collect the wearer's body temperature in real time, and the heart rate detection module can detect the wearer's heart rate in real time. The data is then transmitted to the control chip in the headphones. The control chip analyzes the collected data to obtain the wearer's health detection results. The health detection results are then transmitted to other devices (such as mobile phones, personal computers, etc.) through the communication connection between the headphones and other devices for the user to view. Alternatively, the collected data can be directly transmitted to other devices for data analysis to obtain the health detection results.

[0088] Furthermore, in one feasible implementation, after step S50 described above, the method may further include steps S60 to S70:

[0089] Step S60: Input the health test results into a preset health report template to generate the wearer's target test report;

[0090] It should be noted that, in this embodiment, the health report template can be pre-designed by a technician. The health report template may include parameters of various health indicators (such as characteristic values ​​of voice, respiratory rate, body temperature curve, etc.), predicted health status, label information of parameters related to health indicators (such as indicating that a certain parameter is too high or too low), and a report template of health recommendations.

[0091] In this embodiment, after obtaining the health test results, the system will input the health test results into a preset health report template and automatically generate a detailed health report.

[0092] Step S70: When there is a negative label among the result labels of the health test results, mark the test item corresponding to the negative label in the target test report.

[0093] It should be noted that in this embodiment, the health test results include multiple result labels. The result labels are used to characterize the comparison between the test results of various indicators of the user and the normal range. The result labels include positive labels and negative labels. When the test results are consistent with the normal range, the result label is a positive label, and when they are inconsistent, it is a negative label.

[0094] In this embodiment, all result labels are checked in the generated health report. If any negative labels indicating health problems or abnormalities are found, the corresponding test items are clearly marked in the report. Labeling can be done using graphics or different colors, as long as it is eye-catching.

[0095] This application detects the wearer's voice, heart rate, and body temperature by setting up a microphone, temperature detection module, and heart rate detection module on a wearable device. At the same time, it uses the three parameters of voice, heart rate, and body temperature to analyze the wearer's health status. Compared with the existing technology that uses a single parameter to detect the human body's health status, this method can more accurately and comprehensively reflect the wearer's health status.

[0096] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 , Figure 2 The flowchart of the second embodiment of the health detection method of this application is shown below. Figure 2 As shown, step S50 above may include steps S51 to S52:

[0097] Step S51: Input the target voice features into the preset age prediction model to obtain the wearer's predicted age. The age prediction model is trained using voice features as input and age as a label.

[0098] It should be noted that, in this embodiment, the age prediction model can use an existing neural network model, with sound features as input and age as a label for training, to obtain a model for predicting age based on sound.

[0099] In this embodiment, the system inputs the previously extracted target voice features into a pre-trained age prediction model to obtain the predicted age of the wearer.

[0100] The above method can identify the age of different wearers without restricting the identity of the wearer of the wearable device.

[0101] Alternatively, in another feasible implementation, user accounts can be stored in the wearable device. Each user account corresponds to the user's voiceprint features and a birthday including the year of birth. The voiceprint features and birthday can be pre-set and stored by the user. Then, the target voice features are matched with the voiceprint features. If a match is found, the age of the wearer is directly calculated using the birthday corresponding to the voiceprint features. This method can quickly identify the age of different wearers, but this implementation requires pre-setting by the user and cannot directly identify the age of new wearers.

[0102] Step S52: Obtain the wearer's health detection results based on predicted age, target voice characteristics, target heart rate characteristics, and target body temperature characteristics.

[0103] In this embodiment, the wearer's health test results can be obtained by analyzing the wearer's age, target voice characteristics, target heart rate characteristics, and target body temperature characteristics.

[0104] Specifically, in one feasible implementation, step S52 may include steps A10 to A20:

[0105] Step A10: Determine the target health detection model corresponding to the predicted age from a set of multiple preset health detection models, wherein the health detection model is trained using voice features, heart rate and body temperature features as input and health status as a label.

[0106] It should be noted that in this embodiment, the health detection model is trained using voice features, heart rate, and body temperature features as input and health status as a label. Furthermore, the sample data for the health detection model is subdivided by age; for example, 12 to 18 years old is one age group, and 19 to 25 years old is another. The age group division can be based on the similarity of physical functions and is not specifically limited. This specific division allows for optimization of the model for specific age groups; therefore, selecting a model that matches the predicted age is crucial.

[0107] In this embodiment, when using the trained health detection model for prediction, it is necessary to determine the most suitable health detection model. Therefore, it is necessary to determine the target detection model corresponding to the wearer's age. For example, if the predicted age of the wearer is 22, the health detection model for the 19 to 25 age group is selected as the target detection model.

[0108] Step A20: Input the target voice features, the target heart rate features, and the target body temperature features into the target health detection model to obtain the wearer's health detection results.

[0109] In this embodiment, the previously extracted target sound features, target heart rate features, and target body temperature features are input into the selected target health detection model, which will output the wearer's health detection results based on the input data.

[0110] Furthermore, prior to step A10 above, the method may also include steps B10 to B20:

[0111] Step B10: Obtain sample datasets for different age groups, wherein the sample datasets include the voice features, heart rate features, and body temperature features of multiple samples.

[0112] Step B20: Train the preset prediction model using each of the sample datasets to obtain the trained health detection model corresponding to each of the age groups.

[0113] It should be noted that, in this embodiment, the prediction model can be an existing neural network model, and no further limitations are imposed here.

[0114] In this embodiment, before training the prediction model, it is necessary to collect sample datasets of different age groups. These sample datasets contain data such as voice features, heart rate features, and body temperature features of multiple samples. Then, the sample datasets of different age groups are used to train the preset prediction model, thereby obtaining a health detection model for each age group.

[0115] Furthermore, prior to step B10 above, the method may also include:

[0116] The set time period is obtained through the controls of the wearable device;

[0117] Obtain historical sound characteristics, historical heart rate characteristics, and historical body temperature characteristics within the set time period from historical data;

[0118] The historical sound features, historical heart rate features, and historical body temperature features are added to the sample dataset corresponding to the predicted age.

[0119] It should be noted that, in this embodiment, the time period setting refers to a time period manually set by the user on the wearable device through physical or virtual controls. When the wearable device detects the user's voice, heart rate, and body temperature in real time, it simultaneously stores the detected parameters with timestamps in a preset storage space as historical data for later retrieval.

[0120] In this embodiment, the user-set time period is obtained through the control of the wearable device. The user is prompted that the various parameters detected during this period will be considered as parameters when the user is in good health. Then, the historical sound features, historical heart rate features, and historical body temperature features during this period are obtained. These parameters are used as samples corresponding to the user's age group to train the model, which can improve the model's adaptive learning ability and model prediction accuracy.

[0121] In this embodiment, by using a health prediction model trained for different age groups to predict the wearer's health status, the accuracy of health prediction can be improved based on the excellent generalization and robustness of neural networks.

[0122] Furthermore, in another feasible implementation, please refer to... Figure 3 Step S52 may also include steps C10 to C70:

[0123] Step C10: Determine the set of health detection features corresponding to the predicted age from the preset storage space. The set of health detection features includes: multiple reference voice features, multiple reference heart rate features, and body temperature range.

[0124] Step C20: Calculate the first similarity between the target sound feature and each reference sound feature, and determine the target reference sound feature with the highest first similarity among the reference sound features;

[0125] Step C30: Use the sound label of the target reference sound feature as the wearer's sound detection result;

[0126] It should be noted that, in this embodiment, the reference voice features can be the features of the voice when in various different physical conditions, such as the features of a hoarse voice, the features of a nasal voice, and the features of a normal voice. The voice has different features in different physical conditions, and the voice has the same pattern in the same physical condition. Therefore, the wearer's voice can be determined to be in which physical condition by comparing the similarity between the voice and multiple reference voice features.

[0127] In this embodiment, when analyzing the collected features, a set of health detection features matching the predicted age is first determined from a preset storage space. This feature set includes multiple reference voice features, multiple reference heart rate features, and a body temperature range. Then, for the wearer's target voice feature, the first similarity between the target voice feature and each reference voice feature in the health detection feature set is calculated. Next, the feature with the highest similarity to the target voice feature is found from these reference voice features. The first similarity helps identify which reference voice feature the wearer's voice feature is closest to, thereby judging the wearer's voice health status. Then, the voice tag corresponding to the reference voice feature with the highest first similarity is used as the wearer's voice detection result. The voice tag can provide specific information about the wearer's voice health, such as whether there are abnormal voice features.

[0128] Step C40: Calculate the second similarity between the target heart rate feature and each reference heart rate feature, and determine the target reference heart rate feature with the highest second similarity among the reference heart rate features;

[0129] Step C50: Use the heart rate label of the target reference heart rate feature as the wearer's heart rate detection result;

[0130] It should be noted that, similarly, in this embodiment, a person's heart rate characteristics differ depending on their physical state, and different physical states may cause changes in a person's heart rate. Therefore, the wearer's heart rate can be compared with the similarity between the target heart rate characteristics and multiple reference heart rate characteristics to determine which physical state the wearer's heart rate belongs to.

[0131] In this embodiment, a second similarity is calculated between the target heart rate feature and each reference heart rate feature in the health detection feature set. Then, the feature with the highest similarity to the target heart rate feature is found from these reference heart rate features. The second similarity helps to determine whether the wearer's heart rate feature is normal, thereby judging the health status of their cardiovascular system. Then, the heart rate label corresponding to the reference heart rate feature with the highest second similarity is used as the wearer's heart rate detection result. The heart rate label provides specific information about the wearer's heart rate, such as whether there are abnormal heart rate features.

[0132] Step C60: Compare the target body temperature characteristics with the body temperature range to obtain the body temperature comparison result, and use the body temperature comparison result as the wearer's body temperature detection result;

[0133] It should be noted that in this embodiment, under normal circumstances, a person's body temperature will be maintained within a certain range. A body temperature higher or lower than this range indicates that the person's body has become abnormal.

[0134] In this embodiment, the target body temperature feature is compared with the body temperature range in the health detection feature set to obtain the body temperature comparison result. By comparing, it can be determined whether the wearer's body temperature is within the normal range, thereby understanding their body temperature health status.

[0135] Step C70: The target health detection result corresponding to the sound detection result, heart rate detection result, and body temperature detection result in the preset health detection result set is taken as the wearer's health detection result.

[0136] In this embodiment, although sound, heart rate, and body temperature can all reflect a person's physical state to some extent, a single parameter cannot comprehensively and accurately predict the wearer's physical state. Therefore, combining the results of various tests to predict health status can improve the accuracy of the analysis. The preset health test results include the health status results corresponding to the three parameters of sound, heart rate, and body temperature in various states. By comprehensively comparing these results, the wearer's health status can be obtained more accurately and comprehensively.

[0137] For example, if the wearer is detected to have a hoarse voice, elevated body temperature, rapid heart rate, and cough, the wearer's health test result can be obtained by searching for the target health test result corresponding to each of the above test results in the health test result set.

[0138] In this embodiment, by judging each indicator separately and then comprehensively analyzing the health status, it is possible to detect the user's physical status by integrating multiple parameters without using model training methods, thus reducing the detection cost.

[0139] The above are only two feasible implementations of step S52 provided in this embodiment. This embodiment does not specifically limit the specific implementation of step S52.

[0140] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the health detection method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0141] This application also provides a health monitoring device, please refer to... Figure 4 The health detection device includes:

[0142] Microphone detection module 10 is used to acquire the wearer's target sound signal through the microphone;

[0143] Body temperature detection module 20 is used to acquire the wearer's target body temperature data through the temperature detection module;

[0144] Heart rate detection module 30, which acquires the wearer's target heart rate signal;

[0145] Feature extraction module 40 is used to preprocess the target sound signal, the target heart rate signal and the target body temperature data to obtain target sound features, target heart rate features and target body temperature features;

[0146] The prediction module 50 is used to obtain the wearer's health detection result based on the target sound features, the target heart rate features, and the target body temperature features.

[0147] Optionally, the feature extraction module is also used for:

[0148] The target sound signal and the target heart rate signal are preprocessed to obtain intermediate sound signal and intermediate heart rate signal;

[0149] The target sound features and the target heart rate features are obtained by extracting the features of the intermediate sound signal and the intermediate heart rate signal in the time domain and frequency domain, respectively.

[0150] The target body temperature data is smoothed to obtain the target body temperature characteristics.

[0151] Optionally, the prediction module is also used for:

[0152] The target health detection model corresponding to the predicted age is determined from a set of multiple preset health detection models. The health detection model is trained using voice features, heart rate and body temperature features as inputs and health status as a label.

[0153] The target sound features, target heart rate features, and target body temperature features are input into the target health detection model to obtain the wearer's health detection results.

[0154] Optionally, the prediction module is also used for:

[0155] Obtain sample datasets for different age groups, wherein the sample datasets include the voice features, heart rate features, and body temperature features of multiple samples;

[0156] The preset prediction model is trained using each of the aforementioned sample datasets to obtain the health detection model corresponding to each of the aforementioned age groups after training.

[0157] Optionally, the prediction module is also used for:

[0158] The set of health detection features corresponding to the predicted age is determined from a preset storage space. The set of health detection features includes: multiple reference voice features, multiple reference heart rate features, and body temperature range.

[0159] Calculate the first similarity between the target sound feature and each of the reference sound features, and determine the target reference sound feature with the highest first similarity among the reference sound features;

[0160] The sound label of the target reference sound feature is used as the sound detection result of the wearer;

[0161] Calculate the second similarity between the target heart rate feature and each of the reference heart rate features, and determine the target reference heart rate feature with the highest second similarity among the reference heart rate features;

[0162] The heart rate label of the target reference heart rate feature is used as the heart rate detection result of the wearer;

[0163] The target body temperature feature is compared with the body temperature range to obtain a body temperature comparison result, and the body temperature comparison result is used as the body temperature detection result of the wearer.

[0164] The target health detection result corresponding to the sound detection result, the heart rate detection result, and the body temperature detection result in the preset health detection result set is used as the wearer's health detection result.

[0165] Optionally, the health monitoring device is also used for:

[0166] The health test results are input into a preset health report template to generate a target test report for the wearer;

[0167] When a negative label exists among the result labels of the health test results, the test item corresponding to the negative label is marked in the target test report.

[0168] The health detection device provided in this application, employing the health detection method described in the above embodiments, can solve the technical problem of accurately and comprehensively detecting the user's health status. Compared with the prior art, the beneficial effects of the health detection device provided in this application are the same as those of the health detection method described in the above embodiments, and other technical features in the health detection device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0169] This application provides a wearable device, which includes: 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, which are executed by the at least one processor to enable the at least one processor to perform the health detection method in Embodiment 1 above.

[0170] The following is for reference. Figure 5This document illustrates a structural schematic diagram suitable for implementing wearable devices according to embodiments of this application. Wearable devices in embodiments of this application may include, but are not limited to, mobile terminals such as head-mounted displays, headphones, smartwatches, etc. Head-mounted displays may include, but are not limited to, Mixed Reality (MR) devices (e.g., MR glasses or MR helmets), Augmented Reality (AR) devices (e.g., AR glasses or AR helmets), Virtual Reality (VR) devices (e.g., VR glasses or VR helmets), Extended Reality (XR) devices, or some combination thereof, etc. Figure 5 The wearable device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of this application.

[0171] like Figure 5 As shown, the wearable device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the wearable device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the wearable device to communicate wirelessly or wiredly with other devices to exchange data. While wearable devices with various systems are shown in the figures, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0172] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0173] The wearable device provided in this application, employing the health detection method described in the above embodiments, can solve the technical problem of accurately and comprehensively detecting the user's health status. Compared with the prior art, the beneficial effects of the wearable device provided in this application are the same as those of the health detection method provided in the above embodiments, and other technical features of the wearable device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0174] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0175] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0176] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the health detection method described in the above embodiments.

[0177] In addition, this application also provides an earphone, the earphone 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, the instructions being executed by the at least one processor to enable the at least one processor to perform the health detection method in the first embodiment described above.

[0178] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0179] The aforementioned computer-readable storage medium may be included in the wearable device; or it may exist independently and not assembled into the wearable device.

[0180] The aforementioned computer-readable storage medium carries one or more programs that, when executed by a wearable device, cause the wearable device to: acquire a target sound signal of the wearer through the microphone; acquire a target body temperature data of the wearer through the temperature detection module; preprocess the target sound signal, the target heart rate signal, and the target body temperature data to obtain target sound features, target heart rate features, and target body temperature features; and obtain a health detection result of the wearer based on the target sound features, target heart rate features, and target body temperature features.

[0181] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0182] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0183] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0184] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described health detection method, thereby solving the technical problem of accurately and comprehensively detecting the user's health status. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the health detection method provided in the above embodiments, and will not be repeated here.

[0185] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the health detection method described above.

[0186] The computer program product provided in this application can solve the technical problem of accurately and comprehensively detecting a user's health status. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the health detection method provided in the above embodiments, and will not be repeated here.

[0187] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A health detection method, characterized by, The method is applied to a wearable device, and the wearable device comprises a microphone, a temperature detection module and a heart rate detection module; the method comprises: obtaining a target sound signal of a wearer through the microphone; obtaining target body temperature data of the wearer through the temperature detection module; obtaining a target heart rate signal of the wearer through the heart rate detection module; preprocessing the target sound signal, the target heart rate signal and the target body temperature data to obtain target sound features, target heart rate features and target body temperature features; obtaining a health detection result of the wearer based on the target sound features, the target heart rate features and the target body temperature features.

2. The health detection method of claim 1, wherein, The step of preprocessing the target sound signal, the target heart rate signal and the target body temperature data to obtain target sound features, target heart rate features and target body temperature features comprises: preprocessing the target sound signal and the target heart rate signal to obtain intermediate sound signals and intermediate heart rate signals; extracting features of the intermediate sound signals and the intermediate heart rate signals in time domain and frequency domain respectively to obtain the target sound features and the target heart rate features; smoothing the target body temperature data to obtain the target body temperature features.

3. The health detection method of claim 1, wherein, The step of obtaining a health detection result of the wearer based on the target sound features, the target heart rate features and the target body temperature features comprises: inputting the target sound features into a preset age prediction model to obtain a predicted age of the wearer, wherein the age prediction model is trained with sound features as input and age as label; obtaining a health detection result of the wearer based on the predicted age, the target sound features, the target heart rate features and the target body temperature features.

4. The health detection method according to claim 3, wherein The step of obtaining a health detection result of the wearer based on the predicted age, the target sound features, the target heart rate features and the target body temperature features comprises: determining a target health detection model corresponding to the predicted age from a plurality of preset health detection models, wherein the health detection model is trained with sound features, heart rate features and body temperature features as input and health status as label; inputting the target sound features, the target heart rate features and the target body temperature features into the target health detection model to obtain a health detection result of the wearer.

5. The health detection method according to claim 4, wherein Before the step of determining a target health detection model corresponding to the predicted age from a plurality of preset health detection models, the method further comprises: obtaining sample data sets of different age groups respectively, wherein each sample data set comprises sound features, heart rate features and body temperature features of a plurality of samples respectively; training a preset prediction model using each sample data set to obtain a health detection model corresponding to each age group after training.

6. The health detection method according to claim 3, wherein The step of obtaining a health detection result of the wearer based on the predicted age, the target sound features, the target heart rate features and the target body temperature features comprises: determining a health detection feature set corresponding to the predicted age from a preset storage space, the health detection feature set including a plurality of reference sound features, a plurality of reference heart rate features, and a body temperature range; calculating a first similarity between the target sound feature and each of the reference sound features, and determining a target reference sound feature with the highest first similarity among the reference sound features; taking a sound label of the target reference sound feature as a sound detection result of the wearer; calculating a second similarity between the target heart rate feature and each of the reference heart rate features, and determining a target reference heart rate feature with the highest second similarity among the reference heart rate features; taking a heart rate label of the target reference heart rate feature as a heart rate detection result of the wearer; comparing the target body temperature feature with the body temperature range to obtain a body temperature comparison result, and taking the body temperature comparison result as a body temperature detection result of the wearer; taking the sound detection result, the heart rate detection result, and the body temperature detection result as a target health detection result corresponding to the health detection result set in the preset health detection result set as a health detection result of the wearer.

7. The health detection method of claim 1, wherein, After the step of obtaining the health detection result of the wearer based on the target sound feature, the target heart rate feature, and the target body temperature feature, the method further includes: inputting the health detection result into a preset health report template to generate a target detection report of the wearer; when there is a negative label in each result label of the health detection result, marking a detection item corresponding to the negative label in the target detection report.

8. A health detection device, characterized by, The device is arranged in a wearable device, and the wearable device includes a microphone, a temperature detection module, and a heart rate detection module; the device includes: a microphone detection module configured to acquire a target sound signal of a wearer through the microphone; a temperature detection module configured to acquire target body temperature data of the wearer through the temperature detection module; a heart rate detection module configured to acquire a target heart rate signal of the wearer through the heart rate detection module; a feature extraction module configured to pre-process the target sound signal, the target heart rate signal, and the target body temperature data to obtain a target sound feature, a target heart rate feature, and a target body temperature feature; a prediction module configured to obtain a health detection result of the wearer based on the target sound feature, the target heart rate feature, and the target body temperature feature.

9. A wearable device, comprising: The wearable device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the health detection method according to any one of claims 1 to 7.

10. An earphone, characterized by The earphone includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the health detection method according to any one of claims 1 to 7.

11. A storage medium, characterized by The storage medium is a computer readable storage medium, and the storage medium stores a computer program. The computer program is executed by the processor to implement the steps of the health detection method in any one of claims 1 to 7.

Images