Data processing method, wearable device and electronic device

Abstract

The present application relates to the technical field of terminal equipment, and provides a data processing method, a wearable device, and an electronic device. The electronic device establishes a communication connection with the wearable device. The method includes: obtaining the measurement results of the user's preset physiological parameters collected by the wearable device using photoplethysmography based on the communication connection, the preset physiological parameters at least include pulse wave conduction velocity, and the measurement results include at least one sample feature, and the sample feature is the characteristic data corresponding to the preset physiological parameter; performing deviation analysis on each sample feature to obtain a first analysis result; based on the first analysis result, modifying the weight corresponding to each sample feature when generating the measurement result. In this way, the electronic device can analyze the deviation of each sample feature based on the deviation of the sample feature generated in the process of obtaining the measurement result, and modify the weight corresponding to the sample feature with a larger deviation, thereby improving the generation accuracy of subsequent measurement results and optimizing the user's measurement experience.

Description

Technical Field

[0001] The present application relates to the technical field of terminal devices, and in particular to a data processing method, a wearable device and an electronic device. Background Art

[0002] Photoplethysmography (PPG) is a method that uses photoelectric means to detect changes in blood volume in living tissues, and then infers physiological parameters such as pulse, blood oxygen and even blood pressure. Due to the simple acquisition of PPG signals and the easy-to-wear measurement device, it has gradually become the main method of health monitoring in non-hospital conditions.

[0003] When using PPG to detect and evaluate arteriosclerosis, a small amount of prediction errors may occur due to factors such as individual differences among users. Users can correct the data of prediction errors through hospital return visits, etc. However, due to the large number of links in the prediction process, it is difficult for the measurement device to locate and analyze the data of prediction errors, making it impossible for the measurement device to optimize the links that cause errors in a timely manner, reducing the user experience. Summary of the invention

[0004] The embodiments of the present application provide a data processing method, a wearable device, and an electronic device to solve the problem that error information is difficult to analyze and locate when performing artery detection using a portable measurement device.

[0005] In a first aspect, an embodiment of the present application provides a data processing method, which is applied to an electronic device, where the electronic device establishes a communication connection with a wearable device, and the method includes: obtaining, based on the communication connection, measurement results of user preset physiological parameters collected by the wearable device using photoplethysmography (PPG), where the preset physiological parameters at least include pulse wave velocity (PWV), and the measurement results include at least one sample feature, which is feature data corresponding to the preset physiological parameters; performing deviation analysis on each sample feature to obtain a first analysis result; and based on the first analysis result, modifying the weight corresponding to each sample feature when generating the measurement result.

[0006] In this way, the electronic device can analyze the deviation of each sample feature based on the deviation of the sample features generated in the process of obtaining the measurement results, locate the sample features with larger deviations according to the deviations, and modify the weights corresponding to the sample features with larger deviations, thereby reducing the impact of the sample features with larger deviations on the measurement results, improving the generation accuracy of subsequent measurement results, and optimizing the user's measurement experience.

[0007] In a feasible implementation, obtaining the measurement results of preset physiological parameters collected by the wearable device on the user based on the communication connection includes: obtaining the first waveform collected by the wearable device based on the communication connection, the first waveform at least includes the PPG waveform obtained by monitoring the user using PPG; intercepting at least one second waveform in the first waveform according to the basic state data corresponding to the user and the collection time of the first waveform, the second waveform is the waveform corresponding to any time period in the first waveform; generating at least one sample feature according to the at least one second waveform. In this way, the electronic device can obtain the waveform changes during the collection and transmission process of the wearable device to determine whether there is a deviation in the waveform during the collection and transmission process, and improve the positioning effect of the deviation.

[0008] In a feasible implementation, generating at least one sample feature includes: preprocessing each second waveform to obtain an AC component corresponding to each second waveform; determining the waveform feature of each second waveform according to the AC component; and performing feature extraction processing on the second waveform based on the waveform feature to obtain the sample feature. In this way, the electronic device can monitor the generation process of the sample feature, and thereby determine whether there is a deviation in the generation process of the sample feature, so as to locate the link where the deviation occurs.

[0009] In a feasible implementation, performing deviation analysis on each sample feature to obtain a first analysis result includes: determining a feature type corresponding to each sample feature, where the feature type includes at least one of a binary classification feature and a regression feature;

[0010] According to the feature type, each sample feature is analyzed to obtain the deviation level; according to the deviation level, the first analysis result corresponding to the sample feature is determined. In this way, the electronic device can perform targeted analysis according to the type of sample feature, improve the efficiency of the electronic device in analyzing the deviation of sample features, and reduce the probability of deviation in the analysis process.

[0011] In a feasible implementation, each sample feature is analyzed according to the feature type to obtain the deviation level, including: if the sample feature is a binary feature, the sample feature is analyzed according to the first analysis method to obtain the second analysis result; if the sample feature is a regression feature, the sample feature is analyzed according to the second analysis method to obtain the third analysis result, and the second analysis method includes the determination operation of the deviation correlation of the sample feature; based on the second analysis result or the third analysis result, the deviation level of the sample feature is determined. In this way, the electronic device can provide different analysis methods for different types of sample features, so as to complete the feature analysis process when the feature values ​​in the sample features are different, and reduce the probability of deviation in feature analysis.

[0012] In a feasible implementation, according to the first analysis method, the sample characteristics are analyzed to obtain the second analysis result, including: obtaining the standard characteristics and characteristic distribution data corresponding to the sample characteristics; determining the first parameter according to the difference coefficient between the standard characteristics and the sample characteristics, the first parameter is a parameter used to describe the difference between the standard characteristics and the sample characteristics; determining the second parameter according to the correlation between the sample characteristics and the abnormal state, the second parameter is a parameter used to describe the strength of the correlation between the sample characteristics and the abnormal state; determining the third parameter according to the conformity of the sample characteristics and the characteristic distribution data, the third parameter is a parameter used to describe the relationship between the sample characteristics and the characteristic distribution data; based on the first parameter, the second parameter and the third parameter, the second analysis result is obtained. In this way, the electronic device can analyze and obtain the various parameters corresponding to the binary classification characteristics, and thereby obtain the corresponding analysis results, so that the electronic device can obtain the deviation level in the subsequent process.

[0013] In a feasible implementation, the first parameter, the second parameter, and the third parameter all include the first feedback value or the second feedback value, and based on the second analysis result or the third analysis result, the deviation level of the sample feature is determined, including: if the third parameter includes the second feedback value, the deviation level is the first level; if at least two of the first parameter, the second parameter, and the third parameter include the first feedback value, and the difference coefficient is less than or equal to the first preset threshold, the deviation level is the second level; if the first parameter, the second parameter, and the third parameter all include the first feedback value, the deviation level is the third level, or, if the first parameter and the third parameter include the first feedback value, and the difference coefficient is greater than the first preset threshold, the deviation level is the third level. In this way, the electronic device can determine the deviation level corresponding to the binary feature and obtain the corresponding analysis result so as to adjust the weight corresponding to the sample feature in the subsequent process.

[0014] In a feasible implementation, according to the second analysis method, the sample features are analyzed to obtain a third analysis result, including: obtaining a feature density map corresponding to the sample features, the feature density map is used to display the distribution of numerical variables corresponding to the sample features, and the feature density map includes those corresponding to positive samples and negative samples; determining a fourth parameter based on the offset distance between the sample features and the peak point in the feature density map, the fourth parameter is a parameter used to describe the offset relationship between the sample features and the feature density map; determining a fifth parameter and a sixth parameter based on the density coefficient value of the sample features in the feature density map, the fifth parameter and the sixth parameter are both parameters used to describe the sample density around the sample features on the feature density map, the fifth parameter has a first density coefficient value, the sixth parameter has a second density coefficient value, and the first density coefficient value is greater than the second density coefficient value; determining a seventh parameter based on the distance between the sample features and the peak point in the feature density map, the seventh parameter is a parameter used to describe the relationship between the sample features and the peak point in the feature density map; obtaining the third analysis result based on the fourth parameter, the fifth parameter and the sixth parameter; or, obtaining the third analysis result based on the fourth parameter, the fifth parameter, the sixth parameter and the seventh parameter. In this way, the electronic device can analyze and obtain various parameters corresponding to the regression class features, and obtain corresponding analysis results, which is convenient for the electronic device to obtain the deviation level in the subsequent process.

[0015] In a feasible implementation, the fourth parameter, the fifth parameter, the sixth parameter and the seventh parameter all include the third feedback value or the fourth feedback value, and based on the second analysis result or the third analysis result, the deviation level of the sample feature is determined, including: if the fourth parameter, the fifth parameter, the sixth parameter and the seventh parameter all include the fourth feedback value, the deviation level is the first level; if the sixth parameter value or the seventh parameter includes the third feedback value, the deviation level is the second level; if the fourth parameter or the fifth parameter includes the third feedback value, the deviation level is the third level. In this way, the electronic device can determine the deviation level corresponding to the regression feature and obtain the corresponding analysis result so as to adjust the weight corresponding to the sample feature in the subsequent process.

[0016] In a feasible implementation, based on the first analysis result, the weight corresponding to each sample feature when generating the measurement result is modified, including: when generating the measurement result, intercepting the sample features whose deviation level is greater than or equal to the second preset threshold; or, when generating the measurement result, reducing the weight of the sample features whose deviation level is greater than or equal to the second preset threshold in the measurement result. In this way, the electronic device can adjust the weight of the sample features with higher deviation levels in the measurement result, reduce the influence of the sample features with larger deviations on the measurement result, and improve the accuracy of the measurement result obtained by the electronic device.

[0017] In a feasible implementation, after modifying the weight corresponding to each sample feature when generating the measurement result based on the first analysis result, the method further includes: obtaining and outputting the confidence level corresponding to the deviation level and the weight. In this way, the electronic device can determine the effect of the weight adjustment on the measurement result through the confidence level, avoiding negative optimization of the electronic device.

[0018] In a feasible implementation, the electronic device stores basic state data, the basic state data includes first state data corresponding to the preset physiological parameters of the user, and at least one second waveform is intercepted from the first waveform according to the basic state data corresponding to the user, including: if the measurement result does not match the first state data, then obtain the first time period, the first time period is any time period in which the measurement result is inconsistent with the first state data; intercept the waveform corresponding to the first time period in the first waveform to obtain at least one second waveform; pre-process each second waveform to obtain the AC component corresponding to the second waveform. In this way, the electronic device can intercept the part of the measurement result that deviates from the measured first waveform to reduce the amount of data that the electronic device needs to process and improve the efficiency of the electronic device in processing data.

[0019] In a feasible implementation, after obtaining the AC component corresponding to each second waveform, the method further includes: detecting the first waveform parameters corresponding to the second waveform and the AC component, the first waveform parameters including at least one of frequency, amplitude, waveform shape, and rate; if the first waveform parameter is outside the first preset range, a first alarm message is generated, and the first alarm message is used to indicate that the numerical acquisition error of the second waveform or the AC component. In this way, the electronic device can analyze the state of the waveform collected and transmitted by the wearable device to locate problems in the waveform acquisition process and / or transmission process, thereby improving the efficiency of the electronic device in locating problems.

[0020] In a feasible implementation, the waveform characteristics include the peaks, troughs and inflection points corresponding to the AC component. According to the AC component, the waveform characteristics of each second waveform are determined, including: determining the peaks and troughs in the AC component, and marking the second waveform corresponding to the AC component; obtaining the inflection point corresponding to the AC component based on the first-order derivative of the AC component; and performing feature extraction processing on the second waveform based on the waveform characteristics to obtain sample characteristics, including: processing the second waveform based on the peaks, troughs and inflection points to obtain sample characteristics. In this way, the electronic device can obtain sample characteristics based on the waveform obtained by measurement, and the electronic device can use the obtained sample characteristics to analyze the deviation of the sample characteristics in the subsequent process, so as to realize the problem detection and location of each link in the generation process of the measurement result.

[0021] In a feasible implementation, after determining the waveform characteristics of each second waveform according to the AC component, the method further includes: detecting the second waveform parameter corresponding to the waveform characteristic, the second waveform parameter including the peak, the trough and the inflection point; if the second waveform parameter is outside the second preset range, a second alarm message is generated, and the second alarm message is used to indicate that an error has occurred in the waveform feature extraction process. In this way, the electronic device can analyze the deviation of the sample feature after feature extraction to locate the problem in the waveform feature extraction process, thereby improving the efficiency of the electronic device in locating the problem link.

[0022] In a second aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory; the memory is coupled to the processor; computer program code is stored in the memory, and the computer program code includes computer instructions. When the computer instructions are executed by the processor, the electronic device executes the data processing method provided in the first aspect and any feasible implementation manner thereof.

[0023] In a third aspect, an embodiment of the present application provides a wearable device, comprising: a photoplethysmogram (PPG) sensor, a processor and a memory; the PPG sensor and the memory are respectively coupled to the processor; the PPG sensor is used to collect parameter values ​​corresponding to preset physiological parameters, and the preset physiological parameters at least include pulse wave velocity (PWV); computer program code is stored in the memory, and the computer program code includes computer instructions. When the computer instructions are executed by the processor, the wearable device controls the PPG sensor to collect the preset physiological parameters and send the measurement results to the electronic device.

[0024] It can be understood that the electronic devices and wearable devices provided in the second and third aspects participate in the data processing methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the data processing methods provided above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the embodiments are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0026] Figure 1 A schematic diagram of the structure of a communication system provided in an embodiment of the present application;

[0027] Figure 2 A schematic diagram of an interactive process for generating measurement results provided in an embodiment of the present application;

[0028] Figure 3 A display schematic diagram of an electronic device and a wearable device provided in an embodiment of the present application;

[0029] Figure 4 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application;

[0030] Figure 5 A schematic diagram of the hardware structure of a wearable device provided in an embodiment of the present application;

[0031] Figure 6 A software structure block diagram of an electronic device provided in an embodiment of the present application;

[0032] Figure 7 A flowchart of a data processing method provided in an embodiment of the present application;

[0033] Figure 8 A schematic diagram of a process for obtaining measurement results provided in an embodiment of the present application;

[0034] Fig. 9 A schematic diagram of a flow chart of deviation analysis of sample characteristics provided in an embodiment of the present application;

[0035] Fig.10 A schematic diagram of the process of the first analysis method provided in the embodiment of the present application;

[0036] Fig.11 A schematic diagram of a second analysis method provided in an embodiment of the present application;

[0037] Fig.12 A feature density map provided in an embodiment of the present application;

[0038] Fig.13 A schematic diagram of the structure of a chip system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] The technical solution of the embodiment of the present application will be clearly described below in conjunction with the drawings in the embodiment of the present application.

[0040] In the description of this application, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one" means one or more, and "plurality" means two or more. The words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not limit them to be different.

[0041] It should be noted that, in this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0042] First, the nouns involved in the embodiments of the present application are explained.

[0043] Photo plethysmo graphic (PPG) is a method based on photoelectric technology for non-invasive detection of human physiological parameters. This method records the pulsation state of blood vessels by emitting a light beam of a certain wavelength (usually green light) to the skin, and then measures the attenuated light after reflection and absorption by human blood vessels and tissues, and is used to monitor heart rate, respiratory rate, pulse wave velocity, blood pressure and other information based on the frequency, rhythm, waveform and the like of the pulsation. In the embodiment of the present application, a PPG sensor is used to monitor the human body, and the PPG sensor is composed of a light emitting diode (LED) light source and a light receiver.

[0044] Pulse wave velocity (PWV) reflects the elasticity of the human body's large arteries and is a test indicator for arteriosclerosis. PWV represents the speed at which blood pulses propagate in blood vessels, usually measured in meters per second. The speed of the conduction velocity can indirectly reflect the degree of arteriosclerosis. For example, when other indicators are the same, the pulse wave conduction velocity is slow when the artery elasticity is good, and the pulse wave conduction velocity is fast when the artery elasticity is poor.

[0045] The gold standard for diagnosing arteriosclerosis is arteriography. This method can clearly and intuitively observe the degree and location of arteriosclerosis, including intimal thickening, plaque formation, and stenosis and occlusion of arteries, by injecting contrast agents into the arteries and using X-ray development technology. However, arteriosclerosis is an invasive detection method and requires large medical equipment for diagnosis, which is relatively expensive. In practical applications, arteriosclerosis-related indicators are usually checked or ultrasound and nuclear magnetic resonance instruments are used for inspection. However, the above methods all require the use of large-scale inspection or analysis instruments, which need to be carried out in professional scenes such as hospitals, which is not conducive to daily physical condition detection. Arteriosclerosis is a degenerative and proliferative lesion. Usually, the disease progresses slowly, and the symptoms are relatively mild without complications. The driving force for detection using the above methods is insufficient. It should be understood that the gold standard is the gold standard, which refers to the currently generally recognized, best and most reliable inspection or diagnostic method for the diagnosis of a certain disease.

[0046] In related technical equipment, a PPG sensor is installed in an electronic device, such as a wearable device, so that the electronic device can illuminate the blood vessels of the wearer through the PPG sensor and receive the light transmitted or reflected by the blood vessels, and convert it into a corresponding electrical signal. The electrical signal includes change data such as light intensity and spectrum, so that the electronic device can calculate physiological parameters such as heart rate and PWV by analyzing the electrical signal. At the same time, due to the small size of the PPG sensor, the device equipped with the PPG sensor is usually easy to carry, and monitoring through PPG has become a common method for monitoring the health of users under non-hospital conditions.

[0047] In some embodiments, a corresponding computing module may be provided in the electronic device, and after receiving the optical signal using the PPG sensor and converting it into an electrical signal, the electrical signal is subjected to corresponding computing processing to obtain a measurement result. Exemplarily, a regression or classification model constructed by a machine learning method such as a random forest or a support vector machine (Support Vector Machine, SVM) may be provided in the computing module to analyze and process the electrical signal to obtain a corresponding measurement result.

[0048] However, in the process of using PPG sensors for user monitoring, there are many factors that can affect the parameters obtained by the PPG sensor, and due to individual differences between different users, there are some prediction errors in the measurement results. After the user obtains the gold standard results through hospital return visits, etc., it is necessary to correct the prediction results based on the gold standard results obtained by the user and provide the user with an explanation of the prediction results. However, at this time, due to the large number of influencing factors and the monitoring process involving multiple links, it is difficult to locate the location of the problem and it is impossible to deal with abnormal results in time, affecting the normal application of users.

[0049] In order to be able to handle errors in the results of PPG monitoring of physical status in a timely manner, the embodiments of the present application provide a data processing method, a wearable device, and an electronic device. The method obtains the measurement results of the user's preset physiological parameters collected by the wearable device using PPG through the electronic device based on the communication connection, and performs deviation analysis on each sample feature in the measurement result, so that the electronic device can use the first analysis result corresponding to each sample feature to modify the weight corresponding to each sample feature when generating the measurement result. In this way, the deviation analysis can be used to locate abnormal points or links, optimize the acquisition process of obtaining the user's physical status through monitoring parameters, improve the electronic device's ability to handle abnormal problems, and improve the user's experience in monitoring the physical status.

[0050] In the data processing method proposed in the present application, a PPG sensor can be used to monitor the changes in physiological parameters such as PWV, heart rate, blood pressure and respiratory rate in real time, and then generate measurement results of the user's body based on the monitored physiological parameters in a timely manner or in response to instructions input by the user, so as to prompt the user of his or her current physical condition.

[0051] Figure 1 A schematic diagram of the structure of a communication system provided in an embodiment of the present application.

[0052] In some embodiments of the present application, the above data processing method can be applied to an electronic device, which can be connected and communicated with a wearable device. Figure 1 As shown in (a), the electronic device 2 can directly establish a connection with the wearable device 1 and communicate with it. The wearable device 1 is usually worn by the user for a long time on a certain part of the body, such as the wrist. A PPG sensor can be set in the wearable device 1. When the user wears the wearable device 1, the wearable device 1 can monitor the changes in physiological parameters such as PWV, heart rate, blood pressure and respiratory rate in real time through the PPG sensor. Then, the electronic device 2 can obtain the above-mentioned physiological parameters of the user from the wearable device 1 through the communication connection.

[0053] Then, the electronic device 2 can process the physiological parameters sent by the wearable device 1 to obtain measurement results corresponding to the physiological parameters to prompt the user of his current physical state.

[0054] In some embodiments, Figure 1 As shown in (b), the communication connection between the electronic device 2 and the wearable device 1 can also be realized based on the cloud server 3, that is, when the electronic device 2 and the wearable device 1 transmit data and send instructions, the data can be first sent to the cloud server 3, and then the cloud server 3 sends it to the other end. On this basis, the wearable device 1 can be used as a data acquisition end to collect the user's physiological parameters, and the cloud server 3 can be used as a data processing end to process the data collected by the wearable device 1 to obtain the corresponding measurement results, and the electronic device 2 acts as a data receiving end to receive the measurement results obtained after processing by the cloud server 3, and then prompt the user.

[0055] It should be understood that the communication connection method between the electronic device 2 and the wearable device 1 can be any one of the above examples or other methods that can achieve communication connection. The communication connection method between the electronic device 2 and the wearable device 1 is not limited in the embodiment of the present application.

[0056] Figure 2 A schematic diagram of an interactive process for generating measurement results provided in an embodiment of the present application.

[0057] In the embodiments of the present application, Figure 2 As shown, after the electronic device 2 receives an instruction input by the user to obtain the measurement results, the electronic device 2 may send a request to obtain the measurement results or physiological parameters to the wearable device 1 in response to the instruction, so as to send the physiological parameters of the user monitored by the wearable device 1 to the electronic device 2.

[0058] If the wearable device 1 is capable of processing the obtained physiological parameters, then after receiving the request sent by the electronic device 2, the wearable device 1 can call the processing module in the wearable device 1 to process the physiological parameters of the user collected by itself, obtain the measurement results corresponding to the physiological parameters, and then send them to the electronic device 2 for the user to query.

[0059] If the wearable device 1 cannot process the obtained physiological parameters, the electronic device 2 can call the built-in calculation module to process the received physiological parameters when receiving the physiological parameters, and then obtain the measurement results of the user at the current time.

[0060] In some embodiments, the wearable device 1 may also send the monitored physiological parameters or the measurement results obtained based on the physiological parameters to the electronic device 2 after monitoring the above-mentioned physiological parameters for a certain period of time (for example, 12 hours, 24 hours, etc.), so that the wearable device 1 can realize real-time monitoring of the user's physical state, while reducing the memory pressure of the wearable device 1 during monitoring.

[0061] In some embodiments of the present application, since the power of the wearable device 1 is limited, turning on the vascular monitoring function for a long time will increase the power consumption of the PPG sensor in the wearable device 1 and reduce the battery life of the wearable device 1. Therefore, the vascular monitoring function of the wearable device 1 can be turned on by setting corresponding function interfaces in the wearable device 1 and the electronic device 2 and by the user inputting instructions.

[0062] In some embodiments, the wearable device 1 can also directly respond to the instructions input by the user, call the PPG sensor, and turn on the vascular monitoring function to monitor the user's vascular status. After the monitoring time is over, the monitored physiological parameters can be sent to the electronic device 2 for processing, so that the measurement results of this time can be obtained through analysis by the electronic device 2.

[0063] In the embodiment of the present application, the wearable device 1 may also directly process the monitored physiological parameters to obtain the measurement results, and then send them to the electronic device 2. The present application does not impose any restrictions on this.

[0064] Figure 3 A display schematic diagram of an electronic device and a wearable device provided in an embodiment of the present application.

[0065] exist Figure 2In the monitoring mode shown, the electronic device 2 monitors the user's physiological parameters in response to the user's instructions. Figure 3 As shown, when the user performs blood vessel monitoring, the electronic device 2 can respond to the instructions input by the user and display the following Figure 3 The monitoring page 20 shown in the figure may display the previous measurement result 21 and the measurement control 22, wherein the previous measurement result 21 may include the measurement time, arterial elasticity, vascular age, health risks and prompt information, etc. The contents displayed in the previous measurement result 21 are all the measurement results obtained when the user sent an instruction for vascular monitoring last time.

[0066] The measurement control 22 can be used to generate a request to turn on the blood vessel monitoring function. In the embodiment of the present application, the electronic device 2 can trigger the measurement control 22 in response to the first operation 23 input by the user to the monitoring page 20, and send a request to turn on the blood vessel monitoring function to the wearable device 1, so that the wearable device 1 displays the monitoring process page 10.

[0067] In an embodiment of the present application, the monitoring process page 10 includes a monitoring waveform 11, prompt information 12 and monitoring time 13, wherein the monitoring waveform 11 is used to display the user's heart rate waveform, PWV waveform, etc. during the current monitoring process, the prompt information 12 is used to prompt the user to remain still, and the monitoring time 13 can display the time required for this monitoring. Specifically, the monitoring time 13 can be displayed in the form of a countdown.

[0068] When the timer in the monitoring time 13 ends, the wearable device 1 can stop displaying the monitoring process page 10, and send the monitored physiological parameters and / or the measurement results obtained based on the physiological parameters to the electronic device 2. After obtaining the current measurement result, the electronic device 2 can synchronously update the content of the previous measurement result 21 in the monitoring page 20 and replace it with the new measurement result, so that the user can view the measurement result of the current physiological parameter.

[0069] It should be noted that the waveform displayed in the monitoring waveform 11 may be the same as or different from the physiological parameters monitored during the current monitoring process. The monitoring waveform 11 is only a prompt information displayed to the user to remind the user that the current device is in the process of vascular monitoring. In conjunction with the prompt information 12, the user is prompted to maintain a still state to avoid strenuous activities during the monitoring process that may affect the measurement results.

[0070] In some embodiments of the present application, other contents may also be displayed at the location where the monitoring waveform 11 is displayed in the monitoring process page 10, and the present application does not impose any limitation on this.

[0071] It should be noted that when the above-mentioned electronic device 2 and wearable device 1 monitor blood vessels, the corresponding measurement results are obtained by processing the physiological parameters of the user collected by the wearable device 1. Therefore, the accuracy of the measurement results will be jointly affected by the monitored physiological parameters and the process of processing the physiological parameters.

[0072] In an embodiment of the present application, after receiving the measurement results, the user can obtain the gold standard results through hospital follow-up visits and other methods and input them into the electronic device 2. At this time, the electronic device 2 can analyze the measurement results obtained by monitoring the wearable device 1, locate the location where the problem occurs, and thus adjust the weights of different feature points in the physiological parameters, so that the measurement results obtained through monitoring of the wearable device 1 are more accurate.

[0073] It should be understood that the data processing method provided in the present application is mainly aimed at electronic devices that can process data collected by wearable devices. In some embodiments, the electronic device can be a mobile phone, a tablet computer, a handheld computer, a personal computer (PC), an ultra-mobile personal computer (UMPC), a netbook, and a cellular phone, a personal digital assistant (PDA), an augmented reality (AR) device, a virtual reality (VR) device, an artificial intelligence (AI) device, a wearable device, a vehicle-mounted device, a smart home device and / or a smart city device, etc., which have data processing functions. The embodiments of the present application do not impose any special restrictions on the specific type of the electronic device.

[0074] For example, taking the electronic device as a mobile phone as an example, Figure 4 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application.

[0075] like Figure 4As shown, the electronic device may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a display screen 193, a subscriber identification module (SIM) card interface 194, and a camera 195, etc. Among them, the sensor module 180 may include a pressure sensor, a gyroscope sensor, an air pressure sensor, a magnetic sensor, an acceleration sensor, a distance sensor, a proximity light sensor, a fingerprint sensor, a temperature sensor, a touch sensor, an ambient light sensor, a bone conduction sensor, etc.

[0076] It is to be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the electronic device. In other embodiments of the present application, the electronic device may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0077] The processor 110 may include one or more processing units, for example, the processor 110 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0078] The external memory interface 120 can be used to store computer executable program codes, and the executable program codes include instructions. The external memory interface 120 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc. The data storage area may store data created during the use of the electronic device (such as audio data, a phone book, etc.), etc. In addition, the external memory interface 120 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (Universal Flash Storage, UFS), etc. The processor 110 executes various functional applications and data processing of the electronic device by running instructions stored in the external memory interface 120 and / or instructions stored in a memory provided in the processor.

[0079] In some embodiments of the present application, the processor 110 may also include a Bluetooth chip, and the processor 110 may use the Bluetooth chip to process Bluetooth-related instructions of the electronic device to achieve Bluetooth connection and data transmission between the electronic device and other devices with Bluetooth connection functions. The Bluetooth chip may store Bluetooth protocol stacks, application programming interfaces (APIs), and other contents for achieving Bluetooth connection functions, or the external memory interface 120 may be used to store Bluetooth protocol stacks, APIs, and other contents that can achieve Bluetooth connection functions, so that the electronic device can use the Bluetooth chip to call software instructions corresponding to Bluetooth connection to control the Bluetooth connection function of the electronic device.

[0080] In an embodiment of the present application, the communication connection between the electronic device and the wearable device can be achieved through a Bluetooth connection. The electronic device establishes a connection with the wearable device through the Bluetooth chip in the processor 110, so that the electronic device and the wearable device can use Bluetooth to transmit instructions, requests, and monitored physiological parameters, measurement results, and other content.

[0081] The USB interface 130 is an interface that complies with the USB standard specification, and specifically can be a Mini USB interface, a Micro USB interface, a USB Type C interface, etc. The USB interface 130 can be used to connect a charger to charge an electronic device, and can also be used to transfer data between an electronic device and a peripheral device. It can also be used to connect headphones to play audio through the headphones. The interface can also be used to connect other electronic devices, such as AR devices, etc.

[0082] It is understandable that the interface connection relationship between the modules illustrated in the embodiments of the present application is only a schematic illustration and does not constitute a structural limitation on the electronic device. In other embodiments of the present application, the electronic device may also adopt different interface connection methods in the above embodiments, or a combination of multiple interface connection methods.

[0083] The charging management module 140 is used to receive charging input from a charger. The charger may be a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 140 may receive charging input from a wired charger through the USB interface 130. In some wireless charging embodiments, the charging management module 140 may receive wireless charging input through a wireless charging coil of an electronic device. While the charging management module 140 is charging the battery 142, it may also power the electronic device through the power management module 141.

[0084] The power management module 141 is used to connect the battery 142, the charging management module 140 and the processor 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140, and provides power to the processor 110, the external memory interface 120, the display screen 193, the camera 195, and the wireless communication module 160. The power management module 141 can also be used to monitor parameters such as battery capacity, battery cycle number, battery health status (leakage, impedance), etc. In some other embodiments, the power management module 141 can also be set in the processor 110. In other embodiments, the power management module 141 and the charging management module 140 can also be set in the same device.

[0085] The wireless communication function of the electronic device can be implemented through antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, modem processor and baseband processor.

[0086] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in the electronic device can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve the utilization of the antennas. For example, antenna 1 can be reused as a diversity antenna for a wireless local area network. In some other embodiments, the antenna can be used in combination with a tuning switch.

[0087] The mobile communication module 150 can provide solutions for wireless communications including 2G / 3G / 4G / 5G, etc., applied to electronic devices. The mobile communication module 150 may include at least one filter, a switch, a power amplifier, a low noise amplifier (LNA), etc. The mobile communication module 150 may receive electromagnetic waves from the antenna 1, and perform filtering, amplification, and other processing on the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 150 may also amplify the signal modulated by the modulation and demodulation processor, and convert it into electromagnetic waves for radiation through the antenna 1. In some embodiments, at least some of the functional modules of the mobile communication module 150 may be arranged in the processor 110. In some embodiments, at least some of the functional modules of the mobile communication module 150 may be arranged in the same device as at least some of the modules of the processor 110.

[0088] The modem processor may include a modulator and a demodulator. The modulator is used to modulate the low-frequency baseband signal to be sent into a medium-high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After the low-frequency baseband signal is processed by the baseband processor, it is passed to the application processor. The application processor outputs a sound signal through an audio device (not limited to a speaker 170A, a receiver 170B, etc.), or displays an image or video through a display screen 193. In some embodiments, the modem processor may be an independent device. In other embodiments, the modem processor may be independent of the processor 110 and may be set in the same device as the mobile communication module 150 or other functional modules.

[0089] The wireless communication module 160 can provide wireless communication solutions for electronic devices, including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc. The wireless communication module 160 can be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, modulates the frequency of the electromagnetic wave signal and filters it, and sends the processed signal to the processor 110. The wireless communication module 160 can also receive the signal to be sent from the processor 110, modulate the frequency of it, amplify it, and convert it into electromagnetic waves for radiation through the antenna 2.

[0090] In some embodiments, the antenna 1 of the electronic device is coupled to the mobile communication module 150, and the antenna 2 is coupled to the wireless communication module 160, so that the electronic device can communicate with the network and other devices through wireless communication technology. The wireless communication technology may include Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Time-Division Code Division Multiple Access (TD-SCDMA), Long Term Evolution (LTE), BT, GNSS, WLAN, NFC, FM, and / or IR technology, etc.

[0091] The electronic device implements the display function through a GPU, a display screen 193, and an application processor. The GPU is a microprocessor for image processing, which connects the display screen 193 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs that execute program instructions to generate or change display information.

[0092] The display screen 193 is used to display images, videos, etc. The display screen 193 includes a display panel.

[0093] The electronic device can realize the shooting function through ISP, camera 195, video codec, GPU, display screen 193 and application processor.

[0094] The ISP is used to process the data fed back by the camera 195. For example, when taking a photo, the shutter is opened, and the light is transmitted to the camera photosensitive element through the lens. The light signal is converted into an electrical signal, and the camera photosensitive element transmits the electrical signal to the ISP for processing and converts it into an image visible to the naked eye. The ISP can also perform algorithm optimization on the noise, brightness, and skin color of the image. The ISP can also optimize the exposure, color temperature and other parameters of the shooting scene. In some embodiments, the ISP can be set in the camera 195.

[0095] The camera 195 is used to capture still images or videos.

[0096] The touch sensor is also called a "touch control device". The touch sensor can be set on the display screen 193. The touch sensor and the display screen 193 form a touch screen, also called a "touch control screen". The touch sensor is used to detect touch operations acting on or near it.

[0097] The gyroscope sensor can be used to determine the motion posture of the electronic device. In some embodiments, the angular velocity of the electronic device around three axes (i.e., x, y, and z axes) can be determined by the gyroscope sensor. The gyroscope sensor can be used for anti-shake shooting. The gyroscope sensor can also be used for navigation and somatosensory game scenes.

[0098] The air pressure sensor is used to measure air pressure. In some embodiments, the electronic device calculates the altitude through the air pressure value measured by the air pressure sensor to assist positioning and navigation.

[0099] The geomagnetic sensor includes a Hall sensor. The electronic device can use the geomagnetic sensor to detect the opening and closing of the flip leather case. In some embodiments, when the electronic device is a flip phone, the electronic device can detect the opening and closing of the flip cover according to the geomagnetic sensor. Then, according to the detected opening and closing state of the leather case or the opening and closing state of the flip cover, the flip cover can be automatically unlocked.

[0100] Accelerometers can detect the magnitude of acceleration of electronic devices in various directions (generally three axes).

[0101] Distance sensor, used to measure distance.

[0102] The proximity light sensor may include, for example, a light emitting diode and a light detector, such as a photodiode.

[0103] The fingerprint sensor is used to collect fingerprints.

[0104] The temperature sensor is used to detect temperature. In some embodiments, the electronic device uses the temperature detected by the temperature sensor to execute a temperature processing strategy. For example, when the temperature reported by the temperature sensor exceeds a threshold, the electronic device reduces the performance of a processor located near the temperature sensor to reduce power consumption and implement thermal protection. In other embodiments, when the temperature is lower than another threshold, the electronic device heats the battery 142 to avoid abnormal shutdown of the electronic device due to low temperature. In other embodiments, when the temperature is lower than another threshold, the electronic device boosts the output voltage of the battery 142 to avoid abnormal shutdown due to low temperature.

[0105] The key 190 includes a power key, a volume key, etc. The key 190 can be a mechanical key or a touch key. The electronic device can receive key input and generate key signal input related to user settings and function control of the electronic device.

[0106] Motor 191 can generate vibration prompts. Motor 191 can be used for incoming call vibration prompts, and can also be used for touch vibration feedback. For example, touch operations acting on different applications (such as taking pictures, audio playback, etc.) can correspond to different vibration feedback effects. For touch operations acting on different areas of the display screen 193, motor 191 can also correspond to different vibration feedback effects. Different application scenarios (for example: time reminders, receiving messages, alarm clocks, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also support customization.

[0107] Of course, it can be understood that the above figure is only an exemplary description when the electronic device is in the form of a mobile phone. If the electronic device is a tablet computer, a handheld computer, a PC, a PDA, a wearable device (such as a smart watch, a smart bracelet) or other device forms, the structure of the electronic device may include fewer structures than shown in the figure, or may include more structures than shown in the figure, and this application does not limit it here.

[0108] Figure 5 A schematic diagram of the hardware structure of a wearable device provided in an embodiment of the present application.

[0109] For example, the wearable device involved in the embodiments of the present application may be a portable wearable electronic device such as a sports bracelet, a smart watch, a smart armband, etc. The embodiments of the present application do not impose any special restrictions on the specific form of the above-mentioned wrist-type wearable electronic device.

[0110] See also Figure 5As shown, the wearable device 200 may include a processor 210, a charging management module 220, a power management module 221, a battery 222, a USB interface 223, an audio module 230, a display screen 240, a motor 250, an internal memory 260, a button 270, a sensor module 280, and a wireless communication module 290, etc. Among them, the sensor module 280 may include a PPG sensor 280A, an acceleration sensor 280B, etc.

[0111] For an introduction to the processor 210, the charging management module 220, the power management module 221, the USB interface 223, the audio module 230, the display screen 240, the motor 250, the internal memory 260, the button 270, and the wireless communication module 290, please refer to Figure 2 Components of the same name in the electronic device 100 are shown.

[0112] It should be noted that, in order to achieve the communication connection between the electronic device 100 and the wearable device 200, the wireless communication module 160 of the electronic device 100 and the wireless communication module 290 of the wearable device support at least one of the same communication modes. Exemplarily, the processor 210 of the wearable device 200 is also provided with a Bluetooth chip, so that when the electronic device 100 sends a signal related to the Bluetooth connection, the wearable device 200 can respond to the signal and establish a Bluetooth connection with the electronic device, so that data can be transmitted between the electronic device 100 and the wearable device 200 via the Bluetooth connection.

[0113] The PPG sensor 280A is based on a light emitting diode (LED) light source and a photo detector (PD) to measure the attenuated light reflected and absorbed by human blood vessels and tissues, and record the pulsation state of blood vessels. In addition, it is used to monitor information such as heart rate, respiratory rate, and pulse wave velocity based on the frequency, rhythm, and waveform of the pulsation.

[0114] The acceleration sensor 280B is a meter for measuring the linear acceleration of the carrier. In the embodiment of the present application, the acceleration sensor 280B can be used to detect whether the user is in motion.

[0115] It is understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the wearable device 200. In other embodiments of the present application, the wearable device 200 may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0116] Figure 6 A software structure block diagram of an electronic device provided in an embodiment of the present application.

[0117] The layered architecture divides the software into several layers, each with clear roles and division of labor. The layers communicate with each other through software interfaces. In some embodiments, the Android system is divided into four layers, from top to bottom: the application layer, the application framework layer, the Android runtime and system library, and the kernel layer.

[0118] The application layer can include a series of application packages.

[0119] like Figure 6 As shown, the application package may include applications such as battery management, camera, gallery, calendar, call, map, navigation, music, video, short message, etc.

[0120] The application framework layer provides an application programming interface (API) and a programming framework for the applications in the application layer. The application framework layer includes some predefined functions.

[0121] In the embodiment of the present application, the API can encapsulate some functions of the private protocol for application program calls.

[0122] like Figure 6 As shown, for example, the application framework layer may include an activity manager, a window manager, a content provider, a camera service, an audio service (also referred to as an audio framework), a view system, a phone manager (also referred to as a phone framework), a Bluetooth service (also referred to as a Bluetooth framework), a resource manager, a notification manager, a package manager, etc., and the embodiments of the present application do not impose any restrictions on this.

[0123] The activity management service is the ActivityManagerService in the electronic device. The activity management service can be used to obtain the foreground activity, that is, the activity of the foreground application. The foreground application information may be included, including but not limited to: process, application name and other information.

[0124] The window manager is used to manage window programs. The window manager can obtain the display screen size, determine whether there is a status bar, lock the screen, capture the screen, etc.

[0125] Content providers are used to store and retrieve data and make it accessible to applications. This data can include videos, images, audio, calls made and received, browsing history and bookmarks, phone books, etc.

[0126] The main function of the camera service is to provide a unified interface and functions for applications to access and operate camera devices (i.e., cameras). The main function of the audio service is to provide a unified interface and functions for applications to access and operate audio modules in electronic devices.

[0127] The view system includes visual controls, such as controls for displaying text, controls for displaying pictures, etc. The view system can be used to build applications. The display interface can be composed of one or more views. For example, a display interface including a text notification icon can include a view for displaying text and a view for displaying pictures. In some embodiments, the view system can also include starting a rendering thread to complete operations such as drawing a frame buffer.

[0128] The phone manager is used to provide communication functions of the electronic device. For example, the phone manager can manage the call status of the call application (including initiation, connection, hang up, etc.).

[0129] The Bluetooth service is responsible for managing and controlling the interaction between Bluetooth hardware and software. It is responsible for discovering other Bluetooth devices, establishing and managing Bluetooth connections, handling Bluetooth data transmission, managing Bluetooth profiles, and Bluetooth-related settings and configurations.

[0130] The resource manager provides various resources for applications, such as localized strings, icons, images, layout files, video files, and so on.

[0131] The notification manager enables applications to display notification information in the status bar. It can be used to convey notification-type messages and can disappear automatically after a short stay without user interaction. For example, the notification manager is used to notify download completion, message reminders, etc. The notification manager can also be a notification that appears in the system top status bar in the form of a chart or scroll bar text, such as notifications of applications running in the background, or a notification that appears on the screen in the form of a dialog window. For example, a text message is displayed in the status bar, a prompt sound is emitted, an electronic device vibrates, an indicator light flashes, etc.

[0132] Android Runtime includes core libraries and virtual machines. Android runtime is responsible for scheduling and management of the Android system.

[0133] The core library consists of two parts: one part is the function that needs to be called by the Java language, and the other part is the Android core library.

[0134] The application layer and the application framework layer run in the virtual machine. The virtual machine executes the java files of the application layer and the application framework layer as binary files. The virtual machine is used to perform functions such as object life cycle management, stack management, thread management, security and exception management, and garbage collection. The system library can include multiple functional modules. For example: Surface Manager, Media Libraries, 3D graphics processing library (for example: OpenGLES), 2D graphics engine (for example: SGL), etc.

[0135] The surface manager is used to manage the display subsystem and provide the fusion of 2D and 3D layers for multiple applications.

[0136] The media library supports playback and recording of a variety of commonly used audio and video formats, as well as static image files, etc. The media library can support a variety of audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.

[0137] The 3D graphics processing library is used to implement 3D graphics drawing, image rendering, compositing, and layer processing.

[0138] A 2D graphics engine is a drawing engine for 2D drawings.

[0139] The kernel layer is the layer between hardware and software. The kernel layer contains at least display driver, camera driver, audio driver, sensor driver, power driver and Bluetooth driver.

[0140] In an embodiment of the present application, if a private protocol can interact with specific hardware, the software corresponding to the private protocol can be implemented at the kernel layer to control the hardware at the hardware layer.

[0141] It should be understood that in the above embodiments, although the software architecture of the electronic device is described using the Android system as an example, its basic principles are also applicable to electronic devices based on operating systems such as Hongmeng, iOS, and Windows, and this application does not impose any restrictions on the software architecture of the electronic device.

[0142] The technical solutions provided in the embodiments of the present application can be implemented in electronic devices having the above-mentioned hardware architecture or software architecture.

[0143] The data processing method proposed in the embodiment of the present application is described in detail below with reference to the accompanying drawings.

[0144] Figure 7 A flowchart of a data processing method provided in an embodiment of the present application.

[0145] The data processing method in the embodiment of the present application is applied to the electronic device as in the above embodiment, and the electronic device establishes a communication connection with the wearable device. In the embodiment of the present application, the electronic device is a mobile phone and the wearable device is a smart watch to illustrate the embodiment, and the present application does not limit the specific types of the electronic device and the wearable device.

[0146] like Figure 7 As shown, the data processing method may include steps S100 to S300.

[0147] S100: Acquire measurement results of user preset physiological parameters collected by the wearable device using PPG based on the communication connection.

[0148] From the above content, it can be known that when the PPG sensor in the wearable device monitors the user's physical condition, what is collected is the PPG waveform. The electronic device or wearable device can obtain the measurement results of the preset physiological parameters by extracting the features in the PPG waveform. For example, the measurement result can be obtained by the electronic device receiving the PPG waveform collected by the wearable device and then processing it, or it can be obtained by the wearable device directly processing the PPG waveform after collecting it. This application does not limit the method of obtaining the measurement result.

[0149] In an embodiment of the present application, the preset physiological parameters include at least PWV. The measurement result may include at least one sample feature, and the sample feature may be feature data corresponding to the preset physiological parameter. For example, the sample feature may be feature data corresponding to PWV. Specifically, in the process of processing the preset physiological parameters to generate the measurement result, there is more than one factor affecting the measurement result. These factors can be used as sample features, and the corresponding measurement results are formed according to different processing weights, that is, the sample feature can represent the specific value of an influencing factor in the measurement result.

[0150] The preset physiological parameters may include parameters corresponding to the user's physical state that need to be collected, for example, the preset physiological parameters may also include one or more parameters such as heart rate, respiratory rate, blood pressure, etc. The sample feature may represent the characteristic data of the influencing factor corresponding to one of the preset physiological parameters. In some embodiments, one of the preset physiological parameters, such as PWV, may correspond to multiple different sample features, which will not be described in detail in this application.

[0151] In some embodiments of the present application, the communication connection established between the electronic device and the wearable device may be a Bluetooth connection, a cloud-based communication connection, or a communication connection based on the same Wi-Fi local area network. The present application does not impose any restrictions on the communication connection method between the electronic device and the wearable device.

[0152] It should be noted that the measurement result obtained by the electronic device in the embodiment of the present application is a measurement result that is inconsistent with the gold standard result after the user verifies it with the gold standard result. In this way, by obtaining and processing the measurement result that is inconsistent with the gold standard result, the weight of the sample features that affect the measurement result is corrected, so that when an error occurs in the prediction, the location of the problem can be located in time and processed, thereby improving the accuracy of subsequent measurements.

[0153] Figure 8 A schematic diagram of a process for obtaining measurement results provided in an embodiment of the present application.

[0154] For example, after the wearable device collects the preset physiological parameters of the user, the collected information is sent to the electronic device for processing. Figure 8 As shown in (a), the process of the electronic device obtaining the measurement results of the preset physiological parameters collected by the wearable device from the user based on the communication connection may include steps S101 to S103.

[0155] S101: Acquire a first waveform collected by a wearable device based on a communication connection.

[0156] When the wearable device collects the preset physiological parameters, it collects the preset physiological parameters by emitting a light signal through the PPG sensor, receiving the transmitted and reflected light signals, and converting the feedback light signals into electrical signals. In the embodiment of the present application, the electrical signal may include information on changes in light intensity caused by changes in blood volume in the measured blood vessel. The wearable device can obtain at least one first waveform by continuously receiving the electrical signal converted from the light signal during the monitoring time. Therefore, the first waveform is the PPG waveform obtained by the PPG sensor monitoring the user's body.

[0157] For example, during the blood vessel monitoring process, after the wearable device collects the electrical signal, it can directly transmit it to the electronic device, and through continuous transmission during the monitoring process, the electronic device can obtain the first waveform corresponding to the collected electrical signal. Alternatively, the wearable device can also record the first waveform corresponding to the received electrical signal during the monitoring time. At the end of the monitoring, the electronic device can use the communication connection with the wearable device to request the wearable device to send the collected first waveform to the electronic device and perform subsequent steps.

[0158] It should be understood that the first waveform cannot directly reflect the user's blood vessel measurement results, and the user cannot obtain the corresponding blood vessel measurement results through the first waveform. On this basis, the wearable device or electronic device needs to be equipped with a processing or computing module to analyze and extract different feature points in the first waveform and integrate the measurement results corresponding to the different feature points to obtain the measurement results corresponding to the first waveform.

[0159] In the embodiment of the present application, the first waveform can be analyzed and processed in subsequent steps to obtain at least one characteristic point therein, and then the electronic device obtains the final measurement result through weighted analysis of the at least one characteristic point.

[0160] S102: intercepting at least one second waveform from the first waveform according to basic status data corresponding to the user and the collection time of the first waveform.

[0161] Taking the processing of the first waveform by an electronic device as an example, after obtaining the first waveform, the electronic device can intercept at least part of the waveform in the first waveform to obtain the second waveform. Among them, the second waveform is a waveform corresponding to any time period in the first waveform, and the electronic device can intercept a waveform of a period of time in the first waveform as the second waveform according to the corresponding acquisition time in the first waveform. The basic state data can be the basic state data of the body entered by the user into the electronic device or wearable device, such as height, weight, body shape, age, and heart rate, breathing rate and other information in a calm state.

[0162] In an embodiment of the present application, the basic status data may include physical status data, such as height, weight, age, etc., which the wearable device prompts the user to enter when the user first uses the vascular monitoring function of the wearable device. It may also include physical status data generated by the wearable device based on measurement results obtained during the monitoring process of the user, such as body shape, heart rate, respiratory rate, etc. This application does not limit the method for generating the basic status data.

[0163] Furthermore, the user's basic status data can be stored in the wearable device, or sent and stored in the electronic device through a communication connection. When the electronic device receives an instruction to call the basic status data, the corresponding basic status data can be obtained from the wearable device based on the storage status of the electronic device or based on the communication connection, so as to facilitate the subsequent waveform interception process.

[0164] In the embodiment of the present application, the basic status data may also include the golden data obtained by the user input, which refers to the deterministic physical status data obtained by the user through hospital examinations, etc. Taking the symptoms of arteriosclerosis monitored in the embodiment of the present application as an example, its golden data needs to be obtained by hospital surgery or examination such as arterial angiography, and its corresponding diagnosis includes multiple indicators. The numerical values ​​corresponding to the multiple indicators are combined to obtain the golden data.

[0165] In some embodiments of the present application, after the user inputs the acquired golden label data to the electronic device, and when the electronic device determines that the golden label data does not match the measurement data, the electronic device can obtain the first waveform based on the communication connection, and the measurement data generated according to the first waveform is different from the golden label data. In this way, the electronic device can obtain the measurement result according to the acquired first waveform, and then judge the deviation in the processing of the first waveform through the difference between the measurement result and the golden label data.

[0166] Taking the case where basic state data is stored in an electronic device and the basic state data includes first state data corresponding to preset physiological parameters of a user as an example, intercepting a portion of a first waveform as a second waveform is described.

[0167] In this embodiment, the first state data may be the gold mark data input by the user. If the measurement result does not match the first state data, the measurement result needs to be analyzed to locate the time when the measurement result does not match the first state data, so as to locate the problem band in the first waveform.

[0168] Specifically, the electronic device can obtain the first time period by querying the generation time of the measurement result and the monitoring time of the wearable device, wherein the first time period is any time period in which the measurement result is inconsistent with the first state data. By determining the problematic first time period, the first waveform obtained in the electronic device can be intercepted, thereby streamlining the waveform to be analyzed and reducing the difficulty of subsequent extraction of sample features.

[0169] After obtaining the first time period, the electronic device can intercept the first waveform according to the first time period, and intercept the waveform in the first time period in the first waveform to obtain at least one second waveform. It should be understood that the first waveform and the second waveform in the embodiment of the present application are both waveforms generated by electrical signals obtained by the wearable device using the PPG sensor to monitor the user's physiological state.

[0170] S103: Generate at least one sample feature according to at least one second waveform.

[0171] After obtaining at least one second waveform of the problem time period, at least one sample feature can be generated by analyzing and processing the second waveform. Then, through the sample features, the electronic device can analyze each sample feature to locate the sample features that have a greater impact on the measurement results when problems occur in the measurement results.

[0172] Because the wearable device sends and receives optical signals when collecting the user's physical state, it will be interfered by the external ambient light during the process of receiving the optical signal and converting it into an electrical signal. Therefore, after intercepting the second waveform, the interference signal in the second waveform can be identified and processed, and the interference signal can be filtered out from the second waveform, thereby reducing the impact of the interference signal on the generated measurement results during the acquisition process.

[0173] Furthermore, since there are multiple different indicators in the waveform of the electrical signal collected by the wearable device to indicate the state corresponding to the preset physiological parameters of the user, the intercepted second waveform also includes multiple indicators to indicate the user's physical state. On this basis, directly analyzing the second waveform will make it difficult to parse out the information in the second waveform.

[0174] For example, Figure 8 As shown in (b), the process of generating at least one sample feature according to at least one second waveform may include the following steps S103a to S103c.

[0175] S103a: Preprocess each second waveform respectively to obtain an AC component corresponding to each second waveform.

[0176] After the second waveform is intercepted, the alternating current (AC) component in the second waveform can be obtained through amplification, filtering and other processing operations. It should be understood that the alternating current component is an important component of the signal during the waveform processing of the signal. The alternating current component represents the alternating part of the signal that changes with time, and the alternating current component can also be a waveform.

[0177] A waveform signal may generally include an AC component and a DC component. Since the DC component does not change over time, and the characteristic data reflecting the user's physical state changes periodically over time, the DC component in the second waveform may interfere with the generation of sample features. In the embodiment of the present application, the DC component in the second waveform may be filtered out by high-pass filtering or the like, thereby improving the recognition efficiency of sample features.

[0178] In some embodiments of the present application, when the electronic device concludes that the measurement result does not match the gold standard data, it can check each processing link in turn according to the generation process of the measurement result to locate the location where the problem occurs and optimize the user's body monitoring experience.

[0179] Exemplarily, the process of obtaining the measurement result by the electronic device includes at least an acquisition process, a transmission process and a processing process. The acquisition process is the process in which the wearable device monitors the user's body to generate a first waveform, the transmission process is the process in which the wearable device sends the first waveform to the electronic device, and the processing process is the process in which the electronic device processes the first waveform into a measurement result. Therefore, when the measurement result is different from the gold standard data, the process in which the electronic device obtains the measurement result can be detected in sequence to determine the mitigation of the problem and modify the model weights accordingly to make the model more consistent with the user's personal physical condition.

[0180] In an embodiment of the present application, after executing step S103a, the electronic device may confirm the intercepted second waveform and AC component to determine whether the waveform is abnormal. After acquiring the AC component, the electronic device may detect the first waveform parameter corresponding to the second waveform and the AC component, wherein the first waveform parameter includes at least one of frequency, amplitude, waveform shape, and rate. The second waveform and the AC component are detected by detecting whether the first waveform parameter is within a first preset range. If the first waveform parameter is within the first preset range, the electronic device does not take any measures, but directly performs subsequent operations. If the first waveform parameter is outside the first preset range, a first alarm message is generated, and the first alarm message is used to prompt that the numerical acquisition error of the second waveform or the AC component is incorrect.

[0181] It should be understood that the first preset range can be a preset range corresponding to different waveform parameters generated by the electronic device based on the waveform data stored or acquired by the electronic device. In some embodiments of the present application, the first preset range used to determine whether the second waveform and the AC component are abnormal can be the physiological limit data range of the human body. Taking the frequency of the second waveform and the AC component as an example, the user's corresponding heart rate information can be obtained through the frequency information. Usually, the corresponding heart rate range can be obtained by monitoring the user's resting heart rate (i.e., the heart rate in a calm state) and data such as age provided by the user. On this basis, the heart rate range can be used as part of the first preset range to judge the first waveform parameter. When the frequency in the first waveform parameter exceeds the heart rate range, it means that the second waveform or the AC component is abnormal.

[0182] It should be noted that the purpose of confirming the second waveform and the AC component and determining whether there are any abnormalities is to troubleshoot problems that occur during the acquisition and transmission processes. For example, if there are no abnormalities in the second waveform and the AC component, then there are no problems in the process of the wearable device acquiring the first waveform and transmitting it to the electronic device; if there are abnormalities in the second waveform and the AC component, then there are abnormalities in at least part of the process of the wearable device acquiring the first waveform and transmitting it to the electronic device.

[0183] When the electronic device determines that the second waveform or the AC component is abnormal, the electronic device can send an instruction to the wearable device, prompting the wearable device to detect the acquisition process of the first waveform, so as to troubleshoot problems that may occur during the acquisition process, so as to reduce the impact of the waveform acquisition process on the final result and improve the accuracy of the generated measurement result.

[0184] In some embodiments, when the electronic device determines that the second waveform or the AC component is abnormal, the electronic device may also detect the communication connection between it and the wearable device, thereby troubleshooting possible problems that may occur during the transmission process to prevent the first waveform from being affected during the transmission process, thereby causing inaccurate measurement results generated by it.

[0185] It should be understood that the above embodiment is only an exemplary detection method of the second waveform and the AC component after the electronic device obtains the AC component. The above detection process can also be implemented in other ways, which will not be elaborated in this application.

[0186] S103b: Determine the waveform characteristics of each second waveform according to the AC component.

[0187] After obtaining the AC component, the electronic device can determine the waveform characteristics corresponding to each second waveform based on the AC component. In the embodiment of the present application, the waveform characteristics of the second waveform may include characteristic information such as the peak, trough, and inflection point corresponding to the AC component corresponding to the second waveform. Therefore, the method of determining the waveform characteristics of the second waveform in the embodiment of the present application is the process of obtaining characteristic information such as the peak, trough, and inflection point corresponding to the AC component using the second waveform.

[0188] Exemplarily, the electronic device can read and identify the AC component, determine the peaks and troughs of the AC component through the peak values ​​and trough values ​​in its waveform, and then the electronic device can mark the second waveform corresponding to the AC component according to the peaks and troughs.

[0189] Then the electronic device can obtain the first-order derivative corresponding to the waveform of the AC component, and thus determine the inflection point in the AC component through the first-order derivative of the waveform. Specifically, the inflection point of the AC component can be determined through the zero point of the first-order derivative and the sign change interval of the first-order derivative. For example, if the sign of the first-order derivative corresponding to the AC component changes from positive to negative in an interval, the waveform of the AC component changes from rising to falling in the interval. Similarly, if the sign of the first-order derivative corresponding to the AC component changes from negative to positive in an interval, the waveform of the AC component changes from falling to rising in the interval.

[0190] It should be noted that the above-mentioned methods of determining peaks, troughs and inflection points are all exemplary implementations in the present application. Other methods can also be used in the present application to determine peaks, troughs and inflection points. For example, when obtaining the inflection point, the second-order derivative corresponding to the AC component can be obtained based on the first-order derivative of the AC component, and then the position of the inflection point can be intuitively determined through the second-order derivative. The present application does not impose any restrictions on this.

[0191] In some embodiments of the present application, similar to the aforementioned determination of the operating status of the monitoring process and the transmission process, the electronic device can also determine the operating status of the waveform feature extraction process to determine whether it is abnormal. Exemplarily, the electronic device can determine the waveform feature extraction process by detecting the second waveform parameter corresponding to the waveform feature. If the electronic device detects that the second waveform parameter is outside the second preset range, a second alarm message is generated, and the second alarm message is used to prompt the electronic device that an error has occurred in the waveform feature extraction process. Among them, the second waveform parameter includes the peak, trough and inflection point determined by the electronic device in the aforementioned manner, and the second preset range is the value range of the second waveform parameter built into the electronic device or obtained based on a cloud server or other device.

[0192] S103c: Based on the waveform features, perform feature extraction processing on the second waveform to obtain sample features.

[0193] After obtaining the waveform features, the electronic device can perform feature extraction processing on the second waveform based on the waveform features to obtain corresponding sample features. The electronic device can obtain features corresponding to the second waveform based on the inflection point position, peak value, trough value, etc. in the waveform features, thereby obtaining sample features of the second waveform.

[0194] In some implementations, after obtaining the sample feature, the electronic device can obtain the feature type of the sample feature accordingly, and the feature type is a parameter used to describe the feature value type of the sample feature. Specifically, the feature type of the sample feature may include a binary feature and a regression feature, wherein the binary feature includes a feature whose feature value has two possible results, and these two possible results can be represented by 0 and 1, true and false, positive and negative, etc. This application does not limit the specific representation method of the binary feature.

[0195] Regression features include features whose feature values ​​can take any real value. The feature value corresponding to the regression feature can be any real number or real number range. In the embodiment of the present application, the regression features in the sample features obtained by the second waveform can be used to represent the heart rate, PWV and other data of the measured user.

[0196] S200: Perform deviation analysis on each sample feature to obtain a first analysis result.

[0197] After the electronic device obtains the sample feature in the second waveform, if the sample feature does not match the gold standard data, the electronic device can perform a deviation analysis on the sample feature to evaluate the difference between the sample feature and the gold standard data, thereby obtaining a first analysis result of the sample feature.

[0198] Fig. 9 A schematic diagram of a flow chart of deviation analysis of sample characteristics provided in an embodiment of the present application.

[0199] like Fig. 9 As shown, after the electronic device processes the input feature parameters and obtains the sample features, it can perform deviation analysis of the feature distribution according to the attributes of the sample features, that is, whether it belongs to a positive sample or a negative sample. Among them, since the pseudo-negative sample is actually a positive sample, when determining the feature deviation of the pseudo-negative sample, it is necessary to perform statistics based on the feature distribution of the positive sample; similarly, when determining the feature deviation of the pseudo-positive sample, it is necessary to perform statistics based on the feature distribution of the negative sample.

[0200] It should be understood that, because the data types of the feature values ​​corresponding to different types of sample features are different, the deviation analysis methods corresponding to different types of sample features can be set based on the type of sample features. Fig. 9 As shown, the process of performing deviation analysis on sample features by the electronic device may include the following steps S210 to S230 to implement deviation analysis of different types of sample features.

[0201] S210: Determine the feature type corresponding to each sample feature.

[0202] First, the electronic device may determine the feature type of each sample feature. The feature type may include a binary feature and a regression feature. In some embodiments of the present application, the feature type of the sample feature may be obtained in the process of the electronic device acquiring the sample feature using the waveform feature. Therefore, the electronic device may record the feature type of the sample feature in the process of acquiring the sample feature, and determine the feature type according to the corresponding relationship when the sample feature needs to be analyzed.

[0203] In another part of the embodiments of the present application, because the sample features obtained by the electronic device are based on the pre-set monitoring target, and the sample features corresponding to the monitoring target are obtained by extracting the waveform features, the corresponding sample type in each sample feature can be determined when the electronic device determines the monitoring target. Taking the electronic device monitoring the vascular health status of the user as an example, the data required for monitoring include at least the user's heart rate, PWV, etc., and the heart rate and PWV can correspond to at least one sample feature, such as a sample feature for characterizing the heart rate or PWV value, a sample feature for whether the heart rate or PWV is normal, etc. Correspondingly, the feature type of the sample feature used to characterize the heart rate or PWV value can be set to a regression feature, and the feature type of the sample feature used to characterize whether the heart rate or PWV is normal can be set to a binary feature.

[0204] In another embodiment of the present application, when the binary features acquired by the electronic device represent feature values ​​in the form of true and false, the electronic device can also read the specific feature values ​​in the sample features to determine the feature type before performing deviation analysis on the sample features.

[0205] It should be understood that the electronic device may determine the feature type corresponding to the sample feature by any of the above methods, and the electronic device may also determine the feature type corresponding to the sample feature by other methods, and the embodiments of the present application do not limit this.

[0206] In some embodiments of the present application, the electronic device can determine whether the sample feature has deviations before performing deviation analysis on the sample feature. Exemplarily, the electronic device can read the feature distribution of positive and negative samples pre-stored in the database of the cloud server or other device through a communication connection, so that the electronic device can determine whether each sample feature has deviations based on the feature values ​​in the sample feature and the feature distribution of the positive and negative samples.

[0207] Among them, positive samples are sample features obtained by the target object processed by the processing model in the electronic device, and negative samples are sample features used by the processing model to distinguish non-target objects. The difference between positive and negative samples is used to realize the processing of data obtained by the electronic device by the processing model, thereby improving the processing accuracy of the processing model.

[0208] Therefore, after the electronic device obtains the sample feature, whether the sample feature belongs to a positive sample or a negative sample can be determined by the decision boundary set in the processing model. Taking the sample feature as a binary feature as an example, the sample feature may also be a probability value between 0 and 1, indicating the probability that the sample feature belongs to a positive sample. The decision boundary of the processing model for the sample feature may be 0.5, that is, when the output probability is greater than the decision boundary, the processing module confirms that the sample feature belongs to a positive sample; otherwise, the processing module confirms that the sample feature belongs to a negative sample. Similarly, when the sample feature is a regression feature, the decision boundary may be one or more value ranges to limit the characteristic value of the sample feature. When the characteristic value of the sample feature is within the decision boundary, the processing module confirms that the sample feature belongs to a positive sample; otherwise, the processing module confirms that the sample feature belongs to a negative sample.

[0209] When the electronic device analyzes the output results that do not match the gold label data, if the electronic device determines that there are no problems with the data collection and transmission processes through the method in the aforementioned embodiment, it can analyze and determine whether there is a deviation in the sample characteristics by processing the feature distribution of the sample characteristics obtained by the model.

[0210] Exemplarily, the attributes of the sample features can be determined by comparing the mean, variance and other statistics of the feature distribution of the sample features with those of the positive and negative samples. The attributes of the sample features include whether the sample features belong to the positive sample and whether the sample features belong to the negative sample. In some embodiments, the attributes of the sample features can also be determined by comparing the feature distribution of the sample features with the feature distribution of the positive and negative samples. In another embodiment, the attributes of the sample features can also be determined by comparing with the feature values ​​in the gold standard data. The embodiments of the present application do not limit the method of redetermining the attributes of the sample features during the deviation analysis process.

[0211] It should be noted that the sample features processed in the embodiment of the present application are sample features that have been processed by the processing model, so the attributes of each sample feature are also in a determined state. The analysis method in the embodiment of the present application is to re-determine the attributes of the sample features whose attributes have been determined to confirm the deviation of the processing model. Furthermore, if the sample feature obtained by the processing model belongs to a positive sample and after the attribute is re-determined, if the sample feature belongs to a negative sample, then the sample feature is a pseudo-positive sample; similarly, if the sample feature obtained by the processing model belongs to a negative sample and after the attribute is re-determined, if the sample feature belongs to a positive sample, then the sample feature is a pseudo-negative sample.

[0212] S220: Analyze each sample feature separately according to the feature type to obtain a deviation level.

[0213] After obtaining the feature type, the electronic device can analyze different types of sample features based on different feature types to obtain the deviation level corresponding to each sample feature. In the embodiment of the present application, the deviation level includes three levels: low deviation level, high deviation level and no effect, wherein the low deviation level indicates that the deviation of the sample feature has a weak effect on the deviation of the measurement result, the high deviation level indicates that the deviation of the sample feature has a strong effect on the deviation of the measurement result, and no effect indicates that the sample feature does not have a deviation, or the deviation of the sample feature has no effect on the measurement result.

[0214] After obtaining the feature deviation of each pseudo-positive sample and pseudo-negative sample, the corresponding deviation level can be obtained based on the feature deviation. Exemplarily, if the sample feature to be processed is a binary feature, the electronic device can analyze the sample feature according to the first analysis method to obtain a second analysis result when analyzing the sample feature. If the sample feature to be processed is a regression feature, the electronic device can analyze the sample feature according to the second analysis method to obtain a third analysis result when analyzing the sample feature. After obtaining the second analysis result and the third analysis result, the deviation level corresponding to each sample feature can be determined according to the second analysis result or the third analysis result.

[0215] Fig.10 A schematic diagram of the process of the first analysis method provided in an embodiment of the present application.

[0216] like Fig.10 As shown, in the embodiment of the present application, when the electronic device performs deviation analysis on the binary classification features, it can be implemented based on the following steps S221 to S225.

[0217] S221: Obtain standard features and feature distribution data corresponding to sample features.

[0218] The feature distribution data may be the feature distribution corresponding to each positive and negative sample acquired by the electronic device in the aforementioned embodiment, and the standard feature may be the feature distribution corresponding to the sample feature in the feature distribution data obtained by the electronic device.

[0219] When obtaining the feature distribution corresponding to the positive and negative samples, the electronic device can obtain the standard feature corresponding to each sample feature through the obtained sample distribution according to the difference between each sample feature.

[0220] S222: Determine a first parameter according to a difference coefficient between the standard feature and the sample feature.

[0221] Among them, the first parameter is a parameter used to describe the difference between the standard feature and the sample feature. Because the standard feature is a feature distribution corresponding to the sample feature, and the feature value of the sample feature of the binary feature type can be a probability value from 0 to 1, when determining the first parameter, the electronic device can compare the mean value corresponding to the standard feature with the sample feature to determine the difference coefficient between the standard feature and the sample feature, and then determine the first parameter according to the value of the difference coefficient.

[0222] In the embodiment of the present application, after obtaining the standard feature, the electronic device can obtain the feature mean corresponding to the standard feature. For example, if the standard feature includes the feature values ​​of 100 data, the sum of the 100 data can be calculated and divided by 100 to obtain the mean of the standard feature, and then the absolute value of the difference obtained by subtracting the mean of the standard feature from the sample feature can be used as the coefficient of difference. It should be understood that the number of features in the standard feature is only an example, and the number of features corresponding to the standard feature can be more than 100 or less than 100, and the present application does not limit this.

[0223] It should be noted that the first parameter in the embodiment of the present application can be expressed in the form of true and false. When the difference coefficient exceeds or is equal to the first threshold, the first parameter can be true, and when the difference coefficient is less than the first threshold, the first parameter can be false. The first threshold can be 0.3. At this time, when the difference coefficient is less than 0.3, the first parameter is false, and when the difference parameter is greater than or equal to 0.3, the first parameter is true.

[0224] When the first parameter is true, it indicates that the difference between the sample feature and its corresponding standard feature is large. When the first parameter is false, it indicates that the difference between the sample feature and its corresponding standard feature is small. In the embodiment of the present application, when analyzing and obtaining the second analysis result, in addition to the value of the first parameter, the difference coefficient can also be used as a judgment criterion to implement deviation analysis.

[0225] S223: Determine a second parameter based on the correlation between the sample feature and the abnormal state.

[0226] Among them, the second parameter is a parameter used to describe the strength of the correlation between the sample feature and the abnormal state. It can be understood that among the multiple sample features obtained by the electronic device, the sample feature with a greater impact on the result obtained by the electronic device has a higher corresponding weight, and the sample feature with a smaller impact on the result obtained by the electronic device has a lower corresponding weight. Similarly, when the result output by the electronic device deviates, the sample feature with a higher weight may have a greater impact on the deviated measurement result, so the electronic device can determine the second parameter based on the weight of the sample feature.

[0227] In the embodiment of the present application, the second parameter can be obtained through the weight values ​​corresponding to different sample features built into the electronic device, and can also be obtained through the weight values ​​corresponding to different sample features in the processing model in the electronic device.

[0228] Exemplarily, when the absolute value of the weight value corresponding to the sample feature is greater than the second threshold, the second parameter may be true, and when the absolute value of the weight value corresponding to the sample feature is less than or equal to the second threshold, the second parameter may be false. In some embodiments, the second threshold may also be 0.3, and when the absolute value of the weight value is less than or equal to 0.3, the second parameter is false, and when the absolute value of the weight value is greater than 0.3, the second parameter is true.

[0229] It should be understood that the value of the second threshold of 0.3 is only a feasible implementation in the present application. The second threshold in the present application may also be other values, and the present application does not limit it here.

[0230] S224: Determine a third parameter according to the matching status of the sample feature and the feature distribution data.

[0231] Among them, the third parameter is a parameter used to describe the relationship between the sample feature and the feature distribution data. In some embodiments, the feature distribution data may be a standard feature corresponding to the sample feature, and the electronic device may determine whether the sample feature conforms to the feature distribution according to the orientation of the sample feature. When the orientation of the sample feature conforms to the feature distribution, the third parameter may be false, and when the orientation of the sample feature does not conform to the feature distribution, the third parameter may be true.

[0232] In some embodiments, when the electronic device determines whether the orientation of the sample feature conforms to the feature distribution, it may obtain whether the sample feature is within the feature distribution range by drawing a scatter plot of the sample feature and the standard feature. When the sample feature is within the feature distribution range, the orientation of the sample feature conforms to the feature distribution, and when the sample feature is outside the feature distribution range, the orientation of the sample feature does not conform to the feature distribution.

[0233] Furthermore, the central tendency and dispersion degree of the standard feature can be obtained through the statistics of the standard feature, such as the mean, standard deviation and other data, and the electronic device can judge whether the orientation of the sample feature conforms to the feature distribution based on the central tendency and dispersion degree. It should be understood that the above-mentioned way of judging whether the orientation of the sample feature conforms to the feature distribution by the electronic device is only an exemplary implementation in the embodiment of the present application, and the present application does not limit the way of judging whether the orientation of the sample feature conforms to the feature distribution.

[0234] S225: Obtain a second analysis result based on the first parameter, the second parameter and the third parameter.

[0235] After obtaining the first parameter, the second parameter and the third parameter, the electronic device can obtain a second analysis result according to the content included in the first parameter, the second parameter and the third parameter, wherein the second analysis result can include the deviation level corresponding to the sample feature.

[0236] In some embodiments of the present application, the first parameter, the second parameter and the third parameter all include a first feedback value or a second feedback value, wherein the first feedback value may be true and the second feedback value may be false. Based on the feedback values ​​in different parameters, the second analysis result can be determined, and the deviation level corresponding to the sample feature can be determined thereby.

[0237] Exemplarily, the electronic device can obtain the second analysis result according to the different contents included in the first parameter, the second parameter, and the third parameter. For example, when the third parameter includes the second feedback value, that is, false, the second analysis result of the sample feature is that the deviation level is the first level; on the basis that the third parameter includes the first feedback value, when at least two of the first parameter, the second parameter, and the third parameter include the first feedback value, that is, true, and the difference coefficient is less than or equal to the first preset threshold, the deviation level is the second level; when the first parameter, the second parameter, and the third parameter all include the first feedback value, or when the first parameter and the third parameter include the first feedback value and the difference coefficient is greater than the first preset threshold, the deviation level is the third level.

[0238] Among them, the first level in the deviation level is no effect, the second level is a low deviation level, and the third level is a high deviation level. The electronic device processes different sample features based on different deviation levels to adjust the process of the electronic device generating and outputting measurement results. In an embodiment of the present application, the first preset threshold is used to screen sample features whose sample distribution differs greatly from the standard features, so the specific value of the first preset threshold can be set larger, such as 0.6, that is, when the coefficient of difference is greater than 0.6 and the third parameter is true, the electronic device can confirm that the deviation level of the sample feature is the third level. It should be understood that the specific value of the first preset threshold is greater than the first threshold to avoid the situation where the first parameter includes true and can be determined by the first preset threshold. For example, the first preset threshold can also be 0.5, 0.55, etc., and the present application does not impose other restrictions on this.

[0239] In some embodiments of the present application, because when the third parameter is false, the electronic device can determine that the sample feature has no effect on the deviation of the measurement result, the electronic device can first verify the third parameter when analyzing the sample feature of the binary feature type. When the third parameter is false, the electronic device can determine that the sample feature has no effect on the deviation of the measurement result, end the processing of the current sample feature, and improve the speed of processing multiple sample features. Only when the electronic device detects that the third parameter is true, the first parameter and the second parameter can be verified in sequence. Exemplarily, the electronic device can first verify the content of the first parameter. When the first parameter includes false, the electronic device can verify the second parameter to determine whether the deviation level of the sample feature is the first level or the second level. When the second parameter includes false, the deviation level of the sample feature is the first level. If the second parameter includes true, the deviation level of the sample feature is the second level; or, when the first parameter includes true but the difference coefficient is less than or equal to the first preset threshold, the electronic device can verify the second parameter to determine whether the deviation level of the sample feature is the second level or the third level. When the second parameter includes false, the deviation level of the sample feature is the second level. If the second parameter includes true, the deviation level of the sample feature is the third level; and when the first parameter includes true and the difference coefficient is greater than the first preset threshold, the electronic device can determine that the deviation level of the sample feature is the third level, thereby reducing the number of parameter verifications and improving the analysis efficiency of the sample feature.

[0240] Fig.11 A schematic diagram of the process of the second analysis method provided in an embodiment of the present application.

[0241] like Fig.11 As shown, in the embodiment of the present application, when the electronic device performs deviation analysis on the regression features, it can be implemented based on the following steps S2201 to S2206.

[0242] S2201: Obtain a feature density map corresponding to sample features.

[0243] Fig.12 A feature density map provided in an embodiment of the present application.

[0244] Among them, Fig.12 As shown, the feature density map obtained by the electronic device is used to show the distribution of the numerical variables corresponding to the sample features, and the feature density map includes images corresponding to the positive samples and the negative samples. It should be understood that Fig.12 The content shown in is only an example, which is used to illustrate the content and function of the feature density map. Fig.12 The feature density map shown in does not limit the feature density map obtained by the electronic device.

[0245] The feature density map may also include the distribution of standard features obtained by the electronic device, and then obtain the feature density map based on the distribution of the sample features and the numerical variables corresponding to the standard features. And the feature density map has a variety of ways to achieve visualization, such as grayscale map, heat map, etc. In the embodiment of the present application, the kernel density estimation method is used to generate the feature density map to estimate and display the density distribution of the data. The feature density map to which the kernel density estimation method is applied can also be called a feature kernel density map.

[0246] S2202: Determine a fourth parameter according to an offset distance between the sample feature and a peak point in the feature density map.

[0247] After obtaining the feature density map corresponding to the sample feature, the electronic device can determine different parameters based on the relationship between the sample feature and the values ​​of each item in the feature density map, so as to analyze the influence of the sample feature on the deviation of the measurement result through different parameters.

[0248] In the embodiment of the present application, the fourth parameter is a parameter used to describe the offset relationship between the sample feature and the feature density map. The fourth parameter can be the X-axis distance between the sample feature and the positive sample peak point or the negative sample peak point in the feature density map. Using the fourth parameter, the electronic device can indicate the offset of the sample feature in the feature density map toward the positive sample or negative sample. The fourth parameter can also use true and false to indicate whether the sample feature meets the conditions, so that the electronic device can analyze the sample feature according to the fourth parameter and the subsequent steps.

[0249] For regression features, in the feature density map corresponding to the sample features, the range corresponding to the positive sample and the range corresponding to the negative sample may overlap, and sample features with different attributes need to be analyzed based on their attributes. Therefore, there are differences in the analysis methods for pseudo-positive samples and pseudo-negative samples.

[0250] Taking the sample feature belonging to a pseudo-negative sample as an example, when the sample feature is close to the negative sample peak point by less than 5%, and the distance to the positive sample peak point by more than 10%, the fourth parameter may be true, otherwise, the fourth parameter may be false. Wherein, close distance refers to the coefficient of the difference between the sample feature and the positive sample peak point or the negative sample peak point and the overall characteristic value range or standard deviation. The sample feature is close to the negative sample peak point by less than 5%, which means that the difference between the sample feature and the negative sample peak point is less than 5% of the characteristic value range or standard deviation of the negative sample, and the sample feature is close to the positive sample peak point by more than 10%, which means that the difference between the sample feature and the positive sample peak point is greater than 10% of the characteristic value range or standard deviation of the positive sample.

[0251] When the sample feature belongs to a pseudo-positive sample, when the distance between the sample feature and the peak point of the positive sample is less than 5%, and the distance between the sample feature and the peak point of the negative sample is greater than 10%, the electronic device may assign a true value to the fourth parameter; otherwise, the electronic device may assign a false value to the fourth parameter.

[0252] S2203: Determine the fifth parameter and the sixth parameter according to the density coefficient value of the sample feature in the feature density map.

[0253] The fifth parameter and the sixth parameter are parameters for describing the sample density around the sample feature on the feature density map, the fifth parameter has a first density coefficient value, the sixth parameter has a second density coefficient value, and the first density coefficient value is greater than the second density coefficient value. The values ​​of the fifth parameter and the sixth parameter can also be true or false.

[0254] In the present embodiment, the density coefficient value corresponds to Fig.12 The points on the curve or the area under the curve in the characteristic density graph shown in is used to quantify the density of data in different regions, based on which the difference in density coefficient values ​​between positive and negative samples refers to the Y-axis spacing of the peak points in the positive and negative samples. The fifth parameter has a first density coefficient value, and the sixth parameter has a second density coefficient value, which means that the electronic device determines the value of the fifth parameter based on the first density coefficient value, and determines the value of the sixth parameter based on the second density coefficient value, and because the first density coefficient value is greater than the second density coefficient value, when the fifth parameter is true, the sixth parameter is also true, and when the sixth parameter is false, the fifth parameter is also false.

[0255] Taking the sample feature as a pseudo-negative sample as an example, the fifth parameter can be determined by the density coefficient value of the negative sample on the feature kernel density map according to the eigenvalue of the sample feature being greater than 20% of the positive sample, and the first density coefficient value being 20%. The sixth parameter can be determined by the density coefficient value of the negative sample on the feature kernel density map being greater than 15% of the positive sample, and the second density coefficient value being 15%. Specifically, when the Y-axis spacing between the eigenvalue of the sample feature and the peak point of the negative sample is greater than 20% of the Y-axis value of the peak point of the positive sample, the fifth parameter and the sixth parameter are both true, when the Y-axis spacing between the eigenvalue of the sample feature and the peak point of the negative sample is less than or equal to 15% of the Y-axis value of the peak point of the positive sample, the fifth parameter and the sixth parameter are both false, and when the Y-axis spacing between the eigenvalue of the sample feature and the peak point of the negative sample is between 15% and 20% (not including 15%) of the Y-axis value of the peak point of the positive sample, the fifth parameter is false and the sixth parameter is true.

[0256] Correspondingly, when the sample feature is a pseudo-positive sample, the fifth parameter can be judged based on the density coefficient value of the positive sample on the feature kernel density map according to the characteristic value of the sample feature being greater than 20% of the negative sample, and the sixth parameter can be judged based on the density coefficient value of the positive sample on the feature kernel density map being greater than 15% of the negative sample.

[0257] In this way, the electronic device can analyze and evaluate the deviation of the sample features based on the distribution of the standard features corresponding to the sample features, so as to screen them out when the deviation is large, so that the subsequent electronic device can modify the processing model using the screened sample features to improve the monitoring accuracy of the processing model. It should be understood that the specific values ​​of the first density coefficient value and the second density coefficient value are exemplary descriptions. In the embodiments of the present application, both can also be other values, and the present application does not limit them here.

[0258] It should be understood that when the electronic device analyzes sample features with different correlations with the measurement results, the standards of the parameters used may be different. For example, the analysis parameter standards of the electronic device for sample features with strong correlations can be strengthened, and the analysis parameter standards of the electronic device for sample features with weak correlations can be relatively relaxed. In some embodiments, the second analysis method may include a determination operation of the deviation correlation of the sample feature. When the electronic device analyzes the sample features of the regression feature type, the weight corresponding to the sample feature can be obtained in the processing model, and based on the built-in weight threshold of the electronic device, the sample features with weights higher than the weight threshold are determined as sample features with strong deviation correlation, and other sample features are determined as sample features with weak deviation correlation. In some embodiments, the weight threshold can also be a percentage, and its value can be 30%, 35%, 40%, etc. For example, the top 30% of the sample features with the highest weights are determined as sample features with strong correlation, and the remaining sample features are sample features with weak correlation. The embodiment of the present application does not limit the specific value of the weight threshold.

[0259] Specifically, the results of the fifth parameter and the sixth parameter can be adjusted by adjusting the first density coefficient value and the second density coefficient value. For example, when the sample feature is a feature with strong correlation, the first density coefficient value can be 20%, and the second density coefficient value can be 15%, and when the sample feature is a feature with weak correlation, the first density coefficient value can be 30%, and the second density coefficient value can be 20%.

[0260] On this basis, the electronic device can determine the strength of the correlation of sample features before determining the parameters for analyzing regression features, so that different standards can be used to analyze sample features with different correlation strengths, thereby improving the accuracy of the electronic device in modifying weights.

[0261] S2204: Determine the seventh parameter according to the distance between the sample feature and the peak point in the feature density map.

[0262] In an embodiment of the present application, the seventh parameter is a parameter used to describe the relationship between the sample feature and the peak point in the feature density map. Specifically, the seventh parameter can be determined based on the position of the sample feature in the feature density map. Taking the sample feature as a pseudo-negative sample as an example, when the sample feature is close to the peak point of the negative sample by less than 5%, or the peak distance of the negative sample / the peak distance of the positive sample in the feature kernel density map is less than 0.8, the sample feature is closer to the peak point of the negative sample, and the peak points of the positive and negative samples are more similar. At this time, the electronic device can determine that the seventh parameter is true. In other cases, the seventh parameter is false.

[0263] Correspondingly, when the sample feature is a pseudo-positive sample, when the distance between the sample feature and the peak point of the positive sample is less than 5%, or the peak distance of the negative sample / the peak distance of the positive sample in the feature kernel density map is less than 0.8, the electronic device can determine that the seventh parameter is true. In other cases, the seventh parameter is false.

[0264] S2205: Obtain a third analysis result based on the fourth parameter, the fifth parameter and the sixth parameter.

[0265] In an embodiment of the present application, if the electronic device detects that the sample feature is a feature with weak correlation when acquiring the weight of the sample feature, the electronic device may execute step S2205 to obtain a third analysis result. It should be noted that the fourth parameter, the fifth parameter, and the sixth parameter may be used as the third analysis result, and the electronic device calls the third analysis result when executing subsequent steps, that is, to obtain the deviation level using the fourth parameter, the fifth parameter, and the sixth parameter; in another embodiment, the third analysis result may include the deviation level obtained based on the fourth parameter, the fifth parameter, and the sixth parameter on the basis of including the fourth parameter, the fifth parameter, and the sixth parameter, and the present application does not limit this.

[0266] Exemplarily, the fourth parameter, the fifth parameter, and the sixth parameter may include a third feedback value or a fourth feedback value, wherein the third feedback value is true and the fourth feedback value is false. Similar to the aforementioned binary features, the deviation levels obtained based on the third analysis result are also the first level, the second level, and the third level, and the first level, the second level, and the third level correspond to no influence, a low deviation level, and a high deviation level, respectively.

[0267] In the embodiment of the present application, when the fourth parameter, the fifth parameter and the sixth parameter all include the fourth feedback value, that is, when the fourth parameter, the fifth parameter and the sixth parameter are all false, the deviation level is the first level, and the sample feature has no effect on the deviation of the measurement result. When the sixth parameter value includes the third feedback value, that is, when the sixth parameter is true, the deviation level is the second level, and the sample feature has a lower effect on the deviation of the measurement result. When the fourth parameter or the fifth parameter includes the third feedback value, that is, when the fourth parameter or the fifth parameter is true, the deviation level is the third level, and the sample feature has a higher effect on the deviation of the measurement result.

[0268] S2206: Obtain a third analysis result based on the fourth parameter, the fifth parameter, the sixth parameter and the seventh parameter.

[0269] In some embodiments, if the electronic device detects that the sample feature is a feature with a strong correlation, the electronic device may execute step S2206 to obtain a third analysis result. Similar to the above embodiment, the third analysis result may include only the parameter value determined by the electronic device, or may include the deviation level obtained based on each parameter value in addition to each parameter value.

[0270] Exemplarily, the fourth parameter, the fifth parameter, the sixth parameter and the seventh parameter may include the third feedback value or the fourth feedback value, wherein the third feedback value is true and the fourth feedback value is false. When the fourth parameter, the fifth parameter, the sixth parameter and the seventh parameter all include the fourth feedback value, the deviation level is the first level; when the sixth parameter value or the seventh parameter includes the third feedback value, the deviation level is the second level; when the fourth parameter or the fifth parameter includes the third feedback value, the deviation level is the third level.

[0271] In this way, the electronic device can analyze different types of sample features based on the first analysis method and the second analysis method to obtain analysis results corresponding to the sample features, so that in subsequent steps the electronic device can correct different parts of the processing module based on different analysis results.

[0272] S230: Determine a first analysis result corresponding to the sample feature according to the deviation level.

[0273] After obtaining the second analysis result and / or the third analysis result according to the first analysis method or the second analysis method, the first analysis result corresponding to a sample feature can be determined based on the second analysis result and / or the third analysis result. Exemplarily, the first analysis result may include the sample feature, the second analysis result or the third analysis result corresponding to the sample feature, and the deviation level.

[0274] Therefore, if the second analysis result or the third analysis result does not include the deviation level, the electronic device may determine the deviation level based on the parameter information in the second analysis result or the third analysis result, and then determine the first analysis result corresponding to the sample feature.

[0275] S300: Based on the first analysis result, modify the weight corresponding to each sample feature when generating the measurement result.

[0276] After obtaining the first analysis result, the electronic device may modify the weight of the corresponding sample feature in the processing model for generating the measurement result based on the first analysis result.

[0277] In some embodiments of the present application, modifying the weight includes modifying the weight corresponding to the sample feature in the processing model and / or intercepting the sample feature with a higher deviation level. When generating a measurement result, the electronic device may intercept the sample feature with a deviation level greater than or equal to the second preset threshold, wherein the second preset threshold may be the second level, that is, the sample feature with a deviation level greater than or equal to the second level is intercepted at the measurement result generation stage to avoid the sample feature having a greater impact on the deviation of the measurement result from affecting the measurement result output by the electronic device, thereby achieving the purpose of modifying the weight corresponding to the sample feature in the processing model.

[0278] In some embodiments, intercepting some sample features at the stage of generating measurement results may result in insufficient sample features for generating measurement results. Therefore, the electronic device may also reduce the weight of sample features with deviation levels greater than or equal to the second preset threshold in the measurement results, thereby reducing the impact of sample features with larger deviations on the measurement results, reducing the deviation of the measurement results, and making the results measured by the electronic device through the wearable device closer to the gold standard results.

[0279] It should be noted that after adjusting the weight of the processing model, the electronic device can execute the corresponding test method according to the type of the processing model, so that the electronic device outputs the deviation level and the confidence corresponding to the modified weight. Among them, the confidence refers to the degree of trust of the processing model in the output result after the electronic device adjusts the weight in the processing model. The confidence can usually be a value between 0 and 1. The closer the value is to 1, the smaller the impact of the electronic device on the weight modification of the processing model on the stability of the model is, and the processing accuracy of the processing model for the current user is improved, reducing the deviation of the measurement results in subsequent monitoring.

[0280] It should be understood that the electronic device may adjust the weights multiple times when adjusting the weights so that the confidence of the adjusted processing model output reaches the threshold, thereby avoiding negative optimization of the processing model. The confidence output by the electronic device may be the confidence data output after the confidence of the processing model exceeds the threshold.

[0281] It is understandable that, in order to realize the above functions, the above terminal device includes a hardware structure and / or software module corresponding to each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the embodiments of the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiments of the present application.

[0282] The embodiment of the present application can divide the functional modules of the above-mentioned terminal device according to the above-mentioned method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0283] Based on the aforementioned data processing method, an embodiment of the present application further provides an electronic device, which includes: a display screen, a memory, and one or more processors; the display screen, the memory, and the processor are coupled; wherein the memory stores computer program code, and the computer program code includes computer commands, and when the computer commands are executed by the processor, the electronic device executes the data processing method provided in the aforementioned embodiment. The specific structure of the electronic device can be referred to Figure 4 The structure of the electronic device shown in .

[0284] Based on the aforementioned data processing method, the embodiment of the present application also provides a wearable device, which includes: a photoelectric volumetric pulse wave (PPG) sensor, a processor and a memory; the PPG sensor and the memory are respectively coupled to the processor; the PPG sensor is used to collect parameter values ​​corresponding to preset physiological parameters, and the preset physiological parameters at least include pulse wave velocity (PWV); the memory stores computer program code, and the computer program code includes computer instructions. When the computer instructions are executed by the processor, the wearable device controls the PPG sensor to collect preset physiological parameters and send the measurement results to the electronic device. The specific structure of the wearable device can be referred to Figure 5 The structure of the wearable device shown in .

[0285] An embodiment of the present application also provides a computer-readable storage medium, which includes computer commands. When the computer commands are executed on an electronic device, the electronic device executes the data processing method provided in the above embodiment.

[0286] An embodiment of the present application also provides a computer program product, which includes executable commands. When the computer program product is run on an electronic device, the electronic device executes the data processing method provided in the above embodiment.

[0287] Fig.13 A schematic diagram of the structure of a chip system provided in an embodiment of the present application.

[0288] The present application also provides a chip system, such as Fig.13 As shown, the chip system 1300 includes at least one processor 1301, a memory and at least one interface circuit 1302. The processor 1301 and the interface circuit 1302 can be interconnected through a line. For example, the interface circuit 1302 can be used to receive signals from other devices (such as target devices). For another example, the interface circuit 1302 can be used to send signals to other devices (such as target devices).

[0289] Exemplarily, the interface circuit 1302 can read the instruction or computer program stored in the memory and send the instruction or computer program to the processor 1301. When the instruction or computer program is executed by the processor 1301, each step of the communication method provided in the above embodiment can be implemented. Of course, the chip system can also include other discrete devices, which is not specifically limited in the embodiment of the present application.

[0290] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0291] In the several embodiments provided in the present application, it should be understood that the disclosed devices / equipment and methods can be implemented in other ways. For example, the device / equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0292] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0293] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0294] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several commands to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0295] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application shall be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A data processing method, characterized in that: Applied to an electronic device, the electronic device establishes a communication connection with a wearable device, and the method includes: Acquire, based on the communication connection, a measurement result of a preset physiological parameter of a user collected by the wearable device using photoplethysmography (PPG), wherein the preset physiological parameter at least includes pulse wave velocity (PWV), and the measurement result includes at least one sample feature, and the sample feature is feature data corresponding to the preset physiological parameter; Performing deviation analysis on each of the sample features to obtain a first analysis result; Based on the first analysis result, modifying the weight corresponding to each of the sample features when generating the measurement result; The step of performing deviation analysis on each of the sample features to obtain a first analysis result includes: Determine a feature type corresponding to each of the sample features, where the feature type includes at least one of a binary classification feature and a regression feature; According to the feature type, each of the sample features is analyzed to obtain a deviation level; If the sample feature is a binary feature, the sample feature is analyzed according to a first analysis method to obtain a second analysis result; the first analysis method is to determine the second analysis result based on the difference coefficient between the standard feature and the sample feature, the correlation between the sample feature and the abnormal state, and the conformity state between the sample feature and the feature distribution data; If the sample feature is a regression feature, the sample feature is analyzed according to a second analysis method to obtain a third analysis result, wherein the second analysis method includes a determination operation of the deviation correlation of the sample feature, and the second analysis method is based on the offset distance between the sample feature and the peak point in the feature density map, the density coefficient value of the sample feature in the feature density map, and the distance between the sample feature and the peak point in the feature density map to determine the third analysis result, and the feature density map is used to display the distribution of the numerical variable corresponding to the sample feature; Determining the deviation level of the sample feature based on the second analysis result or the third analysis result; The first analysis result corresponding to the sample feature is determined according to the deviation level.

2. The data processing method according to claim 1, characterized in that: The obtaining, based on the communication connection, a measurement result of a preset physiological parameter collected by the wearable device on the user includes: Acquire a first waveform acquired by the wearable device based on the communication connection, wherein the first waveform at least includes a PPG waveform obtained by monitoring the user using PPG; According to the basic status data corresponding to the user and the collection time of the first waveform, at least one second waveform is intercepted from the first waveform, where the second waveform is a waveform corresponding to any time period in the first waveform; At least one of the sample features is generated based on the at least one second waveform.

3. The data processing method according to claim 2, characterized in that: Generating at least one sample feature according to the at least one second waveform comprises: Preprocessing each of the second waveforms respectively to obtain an AC component corresponding to each of the second waveforms; determining a waveform feature of each of the second waveforms according to the AC component; Based on the waveform feature, feature extraction processing is performed on the second waveform to obtain the sample feature.

4. The data processing method according to claim 1, characterized in that: Analyzing the sample characteristics according to the first analysis method to obtain a second analysis result includes: Acquire the standard feature and the feature distribution data corresponding to the sample feature; Determine a first parameter according to a difference coefficient between the standard feature and the sample feature, where the first parameter is a parameter used to describe the difference between the standard feature and the sample feature; Determine a second parameter according to the correlation between the sample feature and the abnormal state, where the second parameter is a parameter used to describe the strength of the correlation between the sample feature and the abnormal state; Determine a third parameter according to a matching state between the sample feature and the feature distribution data, wherein the third parameter is a parameter used to describe a relationship between the sample feature and the feature distribution data; The second analysis result is obtained based on the first parameter, the second parameter and the third parameter.

5. The data processing method according to claim 4, characterized in that: The first parameter, the second parameter, and the third parameter all include a first feedback value or a second feedback value, and determining the deviation level of the sample feature based on the second analysis result or the third analysis result includes: If the third parameter includes the second feedback value, the deviation level is the first level; If at least two of the first parameter, the second parameter and the third parameter include a first feedback value, and the difference coefficient is less than or equal to a first preset threshold, the deviation level is a second level; If the first parameter, the second parameter and the third parameter all include a first feedback value, the deviation level is the third level; or, if the first parameter and the third parameter include a first feedback value and the difference coefficient is greater than the first preset threshold, the deviation level is the third level.

6. The data processing method according to claim 1, characterized in that: Analyzing the sample characteristics according to the second analysis method to obtain a third analysis result includes: Obtain the feature density map corresponding to the sample feature, wherein the feature density map includes the features corresponding to the positive sample and the negative sample; Determine a fourth parameter according to an offset distance between the sample feature and a peak point in the feature density map, wherein the fourth parameter is a parameter used to describe an offset relationship between the sample feature and the feature density map; Determine a fifth parameter and a sixth parameter according to the density coefficient value of the sample feature in the feature density map, wherein the fifth parameter and the sixth parameter are parameters for describing the sample density around the sample feature on the feature density map, the fifth parameter has a first density coefficient value, and the sixth parameter has a second density coefficient value, and the first density coefficient value is greater than the second density coefficient value; Determine a seventh parameter according to the distance between the sample feature and the peak point in the feature density map, wherein the seventh parameter is a parameter used to describe the relationship between the sample feature and the peak point in the feature density map; Based on the fourth parameter, the fifth parameter and the sixth parameter, the third analysis result is obtained; or, The third analysis result is obtained based on the fourth parameter, the fifth parameter, the sixth parameter and the seventh parameter.

7. The data processing method according to claim 6, characterized in that: The fourth parameter, the fifth parameter, the sixth parameter and the seventh parameter all include the third feedback value or the fourth feedback value, and determining the deviation level of the sample feature based on the second analysis result or the third analysis result includes: If the fourth parameter, the fifth parameter, the sixth parameter and the seventh parameter all include the fourth feedback value, the deviation level is the first level; If the sixth parameter value or the seventh parameter includes the third feedback value, the deviation level is the second level; If the fourth parameter or the fifth parameter includes the third feedback value, the deviation level is the third level.

8. The data processing method according to claim 1, characterized in that: The modifying, based on the first analysis result, the weight corresponding to each of the sample features when generating the measurement result includes: When generating the measurement result, intercepting the sample features whose deviation level is greater than or equal to a second preset threshold; or, When generating the measurement result, the weight of the sample features whose deviation level is greater than or equal to the second preset threshold in the measurement result is reduced.

9. The data processing method according to claim 8, characterized in that: After modifying the weight corresponding to each of the sample features when generating the measurement result based on the first analysis result, the method further includes: Obtain and output the confidence level corresponding to the deviation level and the weight.

10. The data processing method according to claim 3, characterized in that: The electronic device stores the basic state data, the basic state data includes first state data corresponding to the preset physiological parameter of the user, and intercepting at least one second waveform from the first waveform according to the basic state data corresponding to the user, comprising: If the measurement result does not match the first state data, a first time period is obtained, where the first time period is any time period in which the measurement result does not match the first state data; intercepting the waveform corresponding to the first time period in the first waveform to obtain the at least one second waveform; Preprocess each of the second waveforms to obtain an AC component corresponding to the second waveform.

11. The data processing method according to claim 10, characterized in that: After obtaining the AC component corresponding to each of the second waveforms, the method further includes: Detecting the second waveform and a first waveform parameter corresponding to the AC component, wherein the first waveform parameter includes at least one of frequency, amplitude, waveform shape, and rate; If the first waveform parameter is outside a first preset range, a first alarm message is generated, where the first alarm message is used to indicate that the numerical value collection of the second waveform or the AC component is wrong.

12. The data processing method according to claim 10, characterized in that: The waveform characteristics include a peak, a trough, and an inflection point corresponding to the AC component, and determining the waveform characteristics of each of the second waveforms according to the AC component includes: Determine the peaks and troughs in the AC component, and mark the second waveform corresponding to the AC component; Based on the first-order derivative of the AC component, obtaining an inflection point corresponding to the AC component; The step of performing feature extraction processing on the second waveform based on the waveform feature to obtain the sample feature includes: Based on the peaks, the troughs and the inflection points, the second waveform is processed to obtain the sample features.

13. The data processing method according to claim 12, characterized in that: After determining the waveform feature of each of the second waveforms according to the AC component, the method further includes: Detecting a second waveform parameter corresponding to the waveform feature, the second waveform parameter including the peak, the trough, and the inflection point; If the second waveform parameter is outside a second preset range, a second alarm message is generated, where the second alarm message is used to prompt that an error occurs in the waveform feature extraction process.

14. An electronic device, characterized in that: The electronic device comprises: a processor and a memory; the memory is coupled to the processor; a computer program code is stored in the memory, and the computer program code comprises computer instructions, and when the computer instructions are executed by the processor, the electronic device executes the method as described in any one of claims 1-13.

Images