Smart watch abnormity monitoring method, device and equipment and storage medium

Abstract

The invention discloses a smart watch abnormity monitoring method and device, equipment and a storage medium. The method comprises the following steps: generating a physical sign change curve according to physical sign parameters of a user; performing sign parameter anomaly detection based on the sign change curve, and when the sign parameter detection result is sign parameter anomaly, judging the health condition of the user according to the motion data of the user and the sign parameter detection result; and when the health condition meets a preset recognition condition, inputting the physical sign change curve into a preset health recognition model to obtain a user health monitoring result. According to the method, the physical sign parameter abnormity detection is firstly carried out, the health condition of the user is judged according to the motion data and the physical sign parameter detection result when the physical sign parameter is abnormal, and the user health prediction is carried out through the preset health recognition model when the health condition meets the preset recognition condition; compared with an existing mode of judging the health state of the user only according to the physical sign parameters, the above mode can improve the accuracy of user health monitoring.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for abnormality monitoring of a smart watch. Background Art

[0002] With the advancement of science and technology, smart wearable devices have developed rapidly, and many traditional electronic products have also begun to add mobile functions. Among them, smart watches have received widespread attention. Smart watches are watches with functions such as positioning, calling, recording monitoring, data transmission, etc. With the advancement of science and technology, smart watches can gradually perform health monitoring, such as monitoring the user's heart rate, sleep status and other physical signs. Health monitoring covers many aspects. Related health monitoring and early warning are usually statistically analyzed through manual experience or other single methods, such as indicator threshold early warning. Due to the singleness of data sources or monitoring and early warning methods, there are shortcomings such as low early warning accuracy, poor timeliness, and single monitoring dimension, and usually only one specific health problem can be monitored or warned. Therefore, more flexible and highly accurate health monitoring and early warning is an urgent problem to be solved. Summary of the invention

[0003] The main purpose of this application is to provide a smart watch abnormality monitoring method, device, equipment and storage medium, aiming to solve the technical problems of single monitoring dimension and low accuracy in existing health monitoring and early warning.

[0004] To achieve the above purpose, the present application proposes a smart watch abnormality monitoring method, the smart watch abnormality monitoring method comprising:

[0005] Monitor various physical sign parameters of the user, and generate a physical sign change curve according to the physical sign parameters;

[0006] Performing abnormality detection of physical sign parameters based on the physical sign change curve to obtain a physical sign parameter detection result;

[0007] When the physical sign parameter detection result is that the physical sign parameter is abnormal, obtaining the exercise data of the user;

[0008] Determining the health status of the user according to the motion data and the physical sign parameter detection results;

[0009] When the health condition meets the preset identification condition, the physical sign change curve is input into a preset health identification model to obtain the user health monitoring result output by the preset health identification model.

[0010] Optionally, the step of performing abnormality detection of physical sign parameters based on the physical sign change curve to obtain a physical sign parameter detection result includes:

[0011] Determining the physical sign change slope according to the physical sign change curve;

[0012] When the physical sign change slope is greater than a preset physical sign slope threshold, determining a target value range according to the parameter type corresponding to the physical sign change curve;

[0013] Determining whether the current physical sign parameter value is within the target value range according to the physical sign change curve;

[0014] If the current vital sign parameter value is not within the target value range, a vital sign parameter detection result indicating abnormal vital sign parameters is generated.

[0015] Optionally, the step of inputting the physical sign change curve into a preset health recognition model to obtain a user health monitoring result output by the preset health recognition model includes:

[0016] Preprocessing the physical sign change curve to obtain a target physical sign change curve;

[0017] Sequencing the target vital sign change curve by using a sliding window to obtain subsequences;

[0018] The subsequence is input into a preset health recognition model to obtain a user health monitoring result output by the preset health recognition model.

[0019] Optionally, after the step of obtaining the user's motion data, the method further includes:

[0020] Performing fall detection on the user based on the motion data to obtain a fall detection result;

[0021] When the fall detection result is that the user falls, obtaining current location information and current environment information;

[0022] Determine a target positioning method based on the current environmental information;

[0023] Determine the target location information according to the target positioning method;

[0024] Final position information is determined based on the target position information and the current position information, and a fall warning is performed according to the final position information.

[0025] Optionally, the step of performing fall detection on the user based on the motion data to obtain a fall detection result includes:

[0026] determining a motion curve of the user according to the motion data;

[0027] Determine the acceleration change value of the user according to the motion curve;

[0028] When the acceleration change value is greater than a preset acceleration, obtaining air pressure change information detected by a barometer sensor;

[0029] A current air pressure change value is determined according to the air pressure change information, and when the air pressure change value is greater than a preset change threshold, fall detection is performed on the user according to the air pressure change information to obtain a fall detection result.

[0030] Optionally, after the step of monitoring various vital sign parameters of the user, the method further includes:

[0031] Obtain the monitored user's heart rate information and heart rate variability;

[0032] determining an emotional change of the user according to the heart rate variability and the user heart rate information;

[0033] Emotional warning is performed based on the emotional changes.

[0034] Optionally, the smart watch abnormality monitoring method further includes:

[0035] Get the notification information received by the user;

[0036] Performing feature extraction on the notification information to obtain a feature extraction result;

[0037] Determine the to-do items of the user based on the feature extraction result;

[0038] Determine a target reminder time according to the to-do items;

[0039] Remind the user to process the to-do item based on the target reminder time.

[0040] In addition, to achieve the above purpose, the present application also proposes a smart watch abnormality monitoring device, the smart watch abnormality monitoring device comprising:

[0041] A monitoring module, used to monitor various physical sign parameters of the user and generate a physical sign change curve according to the physical sign parameters;

[0042] An abnormality detection module, used for performing abnormality detection of physical sign parameters based on the physical sign change curve to obtain a physical sign parameter detection result;

[0043] An acquisition module, used for acquiring the motion data of the user when the physical sign parameter detection result is that the physical sign parameter is abnormal;

[0044] A judgment module, used for judging the health status of the user according to the motion data and the physical sign parameter detection result;

[0045] The prediction module is used to input the physical sign change curve into a preset health recognition model when the health condition meets the preset recognition condition, and obtain the user health monitoring result output by the preset health recognition model.

[0046] In addition, to achieve the above-mentioned purpose, the present application also proposes a smart watch abnormality monitoring device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the smart watch abnormality monitoring method as described above.

[0047] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the smart watch abnormality monitoring method described above are implemented.

[0048] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the smart watch abnormality monitoring method as described above.

[0049] The present application monitors various vital sign parameters of the user, and generates a vital sign change curve based on the vital sign parameters; performs vital sign parameter abnormality detection based on the vital sign change curve to obtain a vital sign parameter detection result; when the vital sign parameter detection result is a vital sign parameter abnormality, obtains the user's motion data; judges the user's health status based on the motion data and the vital sign parameter detection result; when the health status meets the preset identification conditions, inputs the vital sign change curve into a preset health identification model to obtain the user health monitoring result output by the preset health identification model. Since the present application first performs vital sign parameter abnormality detection, and when the vital sign parameters are abnormal, judges the user's health status based on the motion data and the vital sign parameter detection results, and when the health status meets the preset identification conditions, predicts the user's health through the preset health identification model, compared with the existing method of judging the user's health status based only on the vital sign parameters, the above method of the present application can improve the accuracy of user health monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0051] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0052] Figure 1 A flowchart of the first embodiment of the method for monitoring abnormality of a smart watch according to the present application;

[0053] Figure 2 A flowchart of the second embodiment of the method for abnormal monitoring of a smart watch according to the present application;

[0054] Figure 3 A flowchart of the third embodiment of the method for monitoring abnormality of a smart watch according to the present application;

[0055] Figure 4 This is a schematic diagram of the module structure of the abnormality monitoring device for a smart watch according to an embodiment of the present application;

[0056] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the smart watch abnormality monitoring method in the embodiment of the present application.

[0057] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0058] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0059] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0060] The main solution of the embodiment of the present application is: monitor various vital sign parameters of the user, and generate a vital sign change curve according to the vital sign parameters; perform vital sign parameter abnormality detection based on the vital sign change curve to obtain a vital sign parameter detection result; when the vital sign parameter detection result is a vital sign parameter abnormality, obtain the user's motion data; judge the user's health status according to the motion data and the vital sign parameter detection result; when the health status meets the preset identification conditions, input the vital sign change curve into a preset health identification model to obtain the user health monitoring result output by the preset health identification model.

[0061] Since the present application first performs abnormal detection of vital sign parameters, when the vital sign parameters are abnormal, the user's health status is judged based on the motion data and the vital sign parameter detection results; when the health status meets the preset identification conditions, the user's health is predicted through a preset health identification model. Compared with the existing method of judging the user's health status only based on vital sign parameters, the above method of the present application can improve the accuracy of user health monitoring.

[0062] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a smart watch, etc. The following takes a smart watch as an example to illustrate this embodiment and the following embodiments.

[0063] Based on this, the present application embodiment provides a smart watch abnormality monitoring method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the abnormality monitoring method for a smart watch of the present application.

[0064] In this embodiment, the smart watch abnormality monitoring method includes steps S10 to S50:

[0065] Step S10, monitoring various physical sign parameters of the user, and generating a physical sign change curve according to the physical sign parameters;

[0066] It should be noted that the physical sign parameters may include heart rate, blood pressure, blood oxygen saturation, temperature, sleep, amount of exercise, etc. Generating a physical sign change curve according to the physical sign parameters may be to generate a curve that changes over time according to the values ​​of each physical sign parameter monitored, and obtain a physical sign change curve corresponding to each physical sign parameter.

[0067] Furthermore, in order to improve the user's health monitoring efficiency, after step S10, the method further includes: obtaining the monitored user's heart rate information and heart rate variability;

[0068] determining an emotional change of the user according to the heart rate variability and the user heart rate information;

[0069] Emotional warning is performed based on the emotional changes.

[0070] It should be noted that heart rate variability (HRV) refers to the degree to which the number of heartbeats changes with human activities. It reflects the activity of the cardiac autonomic nervous system and is an important indicator of whether the sympathetic and parasympathetic nerves are balanced. When a person is under stress, the sympathetic nervous system will be activated, resulting in an increase in heart rate and a decrease in heart rate variability. On the contrary, when a person is in a relaxed state, the parasympathetic nervous system will be activated, the heart rate will slow down, and the heart rate variability will increase. Therefore, the user's emotional changes can be determined by heart rate variability and the user's heart rate information. Specifically, when the heart rate is accelerated and the heart rate variability is reduced, the user's emotional state is determined to be in a stressful state. When the heart rate slows down and the heart rate variability increases, the user's emotional state is determined to be in a relaxed state. When the user's emotional changes are in a stressful state, the terminal device bound to the smart watch is prompted that the current user's emotional pressure is high. At the same time, you can search for content that users are usually interested in or related information that can adjust the user's mood for display.

[0071] Step S20, performing abnormal detection of physical sign parameters based on the physical sign change curve to obtain a physical sign parameter detection result;

[0072] It should be noted that the abnormal detection of physical sign parameters based on the physical sign change curve can be obtained by analyzing the fluctuation of the physical sign change curve and the physical sign threshold to obtain the physical sign parameter detection result. Specifically, the fluctuation of the physical sign change curve can be measured by the slope method or the standard deviation method. When the fluctuation of the physical sign change curve is greater than the preset fluctuation threshold, the physical sign parameter detection result is determined to be abnormal. It can also be to compare the current physical sign value in the physical sign change curve with the pre-set physical sign range. If the current physical sign value is not within the pre-set physical sign range, the physical sign parameter detection result is abnormal. Among them, the preset fluctuation threshold and the physical sign range are both values ​​pre-set according to prior knowledge, and the preset fluctuation threshold and physical sign range corresponding to different physical sign parameters may be different.

[0073] Further, in order to accurately predict the health status of the user, the abnormal detection of physical sign parameters based on the physical sign change curve can be performed based on the physical sign change curve. The physical sign parameter detection result can be obtained by performing year-on-year and month-on-month analysis of physical sign parameters based on the physical sign change curve, and obtaining month-on-month physical sign parameter detection results and year-on-year physical sign parameter detection results, wherein year-on-year refers to the comparison between the current period number and the same period of the previous year. That is, the physical sign change curves of this year are compared with the physical sign change curves of the previous year to obtain year-on-year physical sign parameter detection results. Month-on-month refers to the comparison between the current period number and the previous period number, and the cycle can be a month or a week. That is, the physical sign change curves of this month are compared with the physical sign change curves of last month to obtain month-on-month physical sign parameter detection results. By performing year-on-year and month-on-month analysis on physical sign parameters, it can be concluded whether the physical sign parameters of the user have an overall upward or downward fluctuation trend relative to the previous year or month. If the blood pressure of the user has an overall upward trend relative to the previous year, the user may be at risk of hypertension. If the user has a year-on-year upward trend in heart rate, the user may also have cardiovascular diseases such as hypertension and coronary heart disease. Through the year-on-year and month-on-month analysis of the physical sign parameters, the user can be given a health warning in time. Then, the physical sign parameter detection results are obtained based on the month-on-month physical sign parameter detection results and the year-on-year physical sign parameter detection results. Specifically, if the month-on-month physical sign parameter detection results and the year-on-year physical sign parameter detection results do not show an obvious fluctuation trend, the physical sign parameter detection results are normal physical sign parameters. If the month-on-month physical sign parameter detection results and / or the year-on-year physical sign parameter detection results show an obvious upward or downward trend, the physical sign parameter detection results are abnormal physical sign parameters. It is determined that further health diagnosis is needed. At this time, since the abnormalities appear year-on-year and month-on-month, they are less correlated with the user's current activity status, and health prediction can be directly performed through the preset health recognition model in step 50.

[0074] Step S30, when the physical sign parameter detection result is that the physical sign parameter is abnormal, obtaining the user's exercise data;

[0075] It should be noted that the exercise data may include information such as the user's exercise amplitude, step frequency, exercise mode, smart watch height, moving direction, etc. The exercise mode may include: running, swimming, cycling, etc. It may also include whether the user is in a eating state obtained through voice detection.

[0076] Step S40, judging the health status of the user according to the motion data and the physical sign parameter detection results;

[0077] It should be noted that judging the health status of the user according to the motion data and the vital sign parameter detection result may be judging whether the abnormality in the vital sign parameter detection result is a normal fluctuation caused by the user's activity according to the motion data. For example, when the abnormality in the vital sign parameter detection result is an accelerated heart rate, and the motion data indicates that the user is in a running state, it is considered that the abnormality of the accelerated heart rate in the vital sign parameter detection result is a normal fluctuation. Then the health status is normal, otherwise, the health status needs further detection.

[0078] Step S50, when the health condition meets the preset identification condition, the physical sign change curve is input into the preset health identification model to obtain the user health monitoring result output by the preset health identification model.

[0079] It should be noted that the preset identification condition may be that the health condition needs further testing. The preset health identification model may be a neural network model that is pre-trained with sample data and can perform correlation analysis on inputted physical sign change curves to obtain the user's health monitoring results.

[0080] Further, in order to improve the accuracy of the health monitoring result, the step S50 may include: preprocessing the physical sign change curve to obtain a target physical sign change curve;

[0081] Sequencing the target vital sign change curve by using a sliding window to obtain subsequences;

[0082] The subsequence is input into a preset health recognition model to obtain a user health monitoring result output by the preset health recognition model.

[0083] It should be noted that the preprocessing of the vital sign change curve to obtain the target vital sign change curve may be data cleaning and standardization of the vital sign change curve, and data cleaning may be removing or correcting noise, missing values ​​or outliers in the data to ensure the quality of the input data. Standardization may be converting the data to the same scale, which helps the model converge faster and improves prediction accuracy. The sequence division of the target vital sign change curve through a sliding window to obtain subsequences may be dividing the vital sign change curve into multiple subsequences of fixed length through a sliding window, each subsequence containing multiple continuous time points, which helps the model better capture the dependencies between sequences.

[0084] This embodiment monitors various vital sign parameters of the user, and generates a vital sign change curve based on the vital sign parameters; performs vital sign parameter abnormality detection based on the vital sign change curve to obtain a vital sign parameter detection result; when the vital sign parameter detection result is a vital sign parameter abnormality, obtains the user's motion data; judges the user's health status based on the motion data and the vital sign parameter detection result; when the health status meets the preset identification conditions, inputs the vital sign change curve into a preset health identification model to obtain the user health monitoring result output by the preset health identification model. Since this embodiment first performs vital sign parameter abnormality detection, when the vital sign parameters are abnormal, the user's health status is judged based on the motion data and the vital sign parameter detection results, and when the health status meets the preset identification conditions, the user's health prediction is performed through the preset health identification model, compared with the existing method of judging the user's health status based only on the vital sign parameters, the above method of this embodiment can improve the accuracy of user health monitoring.

[0085] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , Figure 2 A flow chart of the second embodiment of the method for monitoring abnormality of a smart watch provided in the present application; the step S20 further includes steps S201 to S204:

[0086] Step S201: determining the physical sign change slope according to the physical sign change curve;

[0087] It should be noted that determining the physical sign change slope according to the physical sign change curve may be determining the slope of the physical sign change curve, that is, the physical sign change slope.

[0088] Step S202: when the physical sign change slope is greater than a preset physical sign slope threshold, determining a target value range according to a parameter type corresponding to the physical sign change curve;

[0089] It should be noted that the preset vital sign slope threshold may be a pre-set slope threshold used to determine the fluctuation amplitude of the vital sign change parameter. The target value range may be the normal value range of the parameter type corresponding to the vital sign change curve. For example, when the parameter type corresponding to the vital sign change curve is heart rate, the target value range may be 60-100 times / minute; when the parameter type corresponding to the vital sign change curve is blood pressure, the target value range may be systolic pressure (high pressure) 90-140 mmHg, diastolic pressure (low pressure): 60-90 mmHg.

[0090] Step S203: determining whether the current physical sign parameter value is within the target value range according to the physical sign change curve;

[0091] It should be noted that determining whether the current vital sign parameter value is within the target numerical range according to the vital sign change curve may be determining the current vital sign parameter value according to the vital sign change curve, and judging whether the current vital sign parameter value is within the target numerical range.

[0092] Step S204: If the current vital sign parameter value is not within the target value range, a vital sign parameter detection result indicating abnormal vital sign parameters is generated.

[0093] In a specific implementation, if the current vital sign parameter value is not within the target numerical range, a vital sign parameter detection result indicating abnormal vital sign parameters is generated; if the current vital sign parameter value is within the target numerical range, a vital sign parameter detection result indicating normal vital sign parameters is generated.

[0094] This embodiment determines the slope of the sign change according to the sign change curve; when the sign change slope is greater than the preset sign slope threshold, determines the target value range according to the parameter type corresponding to the sign change curve; determines whether the current sign parameter value is within the target value range according to the sign change curve; if the current sign parameter value is not within the target value range, generates a sign parameter detection result indicating abnormal sign parameters. This embodiment first determines the user's sign parameter detection result through the sign change curve, and when the sign parameter detection result is abnormal, performs detection through the preset health recognition model, to avoid performing detection through the preset health recognition model every time, resulting in a large amount of data calculation and low timeliness.

[0095] Based on the above embodiments of the present application, the same or similar contents as those of the above embodiment 1 can be referred to the above introduction, and will not be described in detail later. Figure 3 , Figure 3 A flowchart of the third embodiment of the method for monitoring abnormality of a smart watch according to the present application is provided; after step S30, steps S301 to S305 are also included:

[0096] Step S301: performing fall detection on the user based on the motion data to obtain a fall detection result;

[0097] It should be noted that the fall detection of the user based on the motion data to obtain the fall detection result can be to determine the movement acceleration and height change information of the user based on the motion data, and when the movement acceleration is greater than a preset acceleration threshold and the height change information is a height drop greater than a preset height threshold, it is determined that the user has fallen, and a fall detection result of the user falling is generated. The preset acceleration threshold and the preset height threshold can be pre-set thresholds, wherein the preset acceleration threshold can be an acceleration threshold derived based on a large amount of experimental data and statistical analysis, and is used to distinguish between normal activities and fall events. The preset height threshold can be determined based on the user's height or the relative height when the user's arm is naturally perpendicular to the ground. For example, through calibration, the height of the user's arm when it is naturally perpendicular to the ground is 1 meter, then the preset height threshold can be 0.9 meters.

[0098] Further, in order to accurately perform fall detection, the step S301 may include: determining a motion curve of the user according to the motion data;

[0099] Determine the acceleration change value of the user according to the motion curve;

[0100] When the acceleration change value is greater than a preset acceleration, obtaining air pressure change information detected by a barometer sensor;

[0101] A current air pressure change value is determined according to the air pressure change information, and when the air pressure change value is greater than a preset change threshold, fall detection is performed on the user according to the air pressure change information to obtain a fall detection result.

[0102] It should be noted that the motion curve may be a detected height change curve of the smart watch over time. Determining the acceleration change value of the user according to the motion curve may be determining the acceleration change value of the user according to the height change in the motion curve, that is, the slope of the curve. The preset acceleration may be a preset acceleration value for detecting whether the user has fallen, which may be calibrated experimentally to be greater than the acceleration of the swinging arm during general running or other sports. The air pressure change information may include change information of the air pressure value collected by the air pressure sensor in the smart watch over time. Determining the current air pressure change value according to the air pressure change information may be determining the current air pressure drop or rise according to the air pressure change information. The preset change threshold may be a preset air pressure change threshold for detecting whether the user's height has dropped. The fall detection of the user is determined according to the air pressure change information, and the fall detection result can be that when the air pressure change value is greater than the preset change threshold, it indicates that there is a sudden change in the height of the user's arm, and the user's acceleration change value is greater than the preset acceleration. At this time, the user may be in a fall state. However, in order to more accurately determine whether the user has fallen, the air pressure average value of the user in a previous period of time (which can be one minute or 10 seconds) is determined according to the air pressure change information in this embodiment, and the air pressure average value can represent the user's previous height. The air pressure difference between the air pressure average value and the current air pressure value is calculated, and when the air pressure difference is greater than the preset air pressure difference threshold, it is determined that the user has fallen. The preset air pressure difference threshold can be a pre-set air pressure threshold, and the height change value corresponding to the preset air pressure difference threshold can be the height value when the user's arm is naturally perpendicular to the ground. In this embodiment, when the air pressure change value is greater than the preset change threshold, it is determined that the user is fall detected according to the air pressure change information, so as to avoid misjudgment of fall detection due to the user's arm swinging action, and improve the detection efficiency of fall detection.

[0103] Step S302: when the fall detection result is that the user falls, obtain current location information and current environment information;

[0104] It should be noted that the current location information may be the user's location information acquired in real time by the default positioning method in the smart watch, that is, the positioning information of the smart watch, which may be a GPS positioning method. The current environment information may include whether the current location is an indoor environment, an outdoor environment, and whether it is an urban or rural environment. The current environment information may be obtained by performing image analysis processing on the environment image collected by the smart watch.

[0105] Step S303: determining a target positioning method based on the current environment information;

[0106] It should be noted that the target positioning method determined based on the current environmental information may be a positioning method with the highest positioning accuracy in the current environment selected according to the current environmental information. For example, when the current environmental information is an outdoor environment, the target positioning method may be base station positioning, specifically, the signal arrival angle positioning method (AOA positioning) and the time advance positioning method (TA positioning); if it is a rural environment, the target positioning method may be A-GPS positioning, etc. When the current environmental information is an indoor environment, the target positioning method may be Wi-Fi positioning, Bluetooth positioning, etc.

[0107] Step S304: determining target location information according to the target positioning method;

[0108] It should be noted that determining the target location information according to the target positioning method may be performing positioning of the smart watch according to the target positioning method to obtain the target location information.

[0109] Step S305: determining final position information based on the target position information and the current position information, and performing a fall warning according to the final position information.

[0110] It should be noted that the determination of the final location information based on the target location information and the current location information, and the fall warning based on the final location information can be to determine whether the distance difference between the positioning positions corresponding to the target location information and the current location information is greater than a preset positioning position threshold. If it is greater, a redundant positioning method is randomly selected, and re-positioning is performed through the redundant positioning method, and it is determined which of the positioning positions corresponding to the redundant positioning method is closest to the target location information and the current location information, and the location information closest to the positioning position corresponding to the redundant positioning method is used as the final location information. If the distance difference between the positioning positions corresponding to the target location information and the current location information is less than or equal to the preset positioning position threshold, the target location information and the current location information can be displayed at the same time. That is, the final location information includes the target location information and the current location information.

[0111] Furthermore, in order to improve the user's experience of the smart watch, this embodiment also includes: obtaining notification information received by the user;

[0112] Performing feature extraction on the notification information to obtain a feature extraction result;

[0113] Determine the to-do items of the user based on the feature extraction result;

[0114] Determine a target reminder time according to the to-do items;

[0115] Remind the user to process the to-do item based on the target reminder time.

[0116] It should be noted that the notification information may include email information, SMS information, work software information, etc. Feature extraction is performed on the notification information to obtain the feature extraction result, which may be information about timestamp, sender / receiver, subject / title, content keywords and notification type extracted from the notification information. Determining the to-do items of the user based on the feature extraction result may be to determine whether there is a to-do item based on the timestamp, sender / receiver, subject / title, content keywords and other information in the feature extraction result, and if so, determine the specific item information of the to-do item, including the start time of the item. Determining the target reminder time based on the to-do item may be to determine the target reminder time based on the start time of the item, which may be ten minutes before the start time of the item or the day before. For items that require preparation of materials, the target reminder time may be 1-3 days earlier than the start time of the item. To determine whether the to-do item is an item that requires preparation of materials, the notification information corresponding to the to-do item may be semantically analyzed through natural language processing technology (NLP) to determine whether the user only participates or needs accurate information. Then the target reminder time is determined based on the start time of the item. The reminding the user to process the to-do item based on the target reminder time may be to remind the user by screen display, voice broadcast and / or ringing of a bell when the target reminder time is reached.

[0117] This embodiment performs fall detection on the user based on the motion data to obtain a fall detection result; when the fall detection result is that the user has fallen, obtain current location information and current environment information; determine a target positioning method based on the current environment information; determine target location information according to the target positioning method; determine final location information based on the target location information and the current location information, and issue a fall warning based on the final location information. This embodiment can detect a user's fall based on motion data, and can accurately obtain the user's location information for warning when the user falls, thereby improving the user's experience of using a smart watch.

[0118] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the abnormality monitoring method for smart watches of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0119] This application also provides a smart watch abnormality monitoring device, please refer to Figure 4 , the smart watch abnormality monitoring device comprises:

[0120] The monitoring module 10 is used to monitor various physical sign parameters of the user and generate a physical sign change curve according to the physical sign parameters;

[0121] An abnormality detection module 20, used to perform abnormality detection of physical sign parameters based on the physical sign change curve to obtain a physical sign parameter detection result;

[0122] An acquisition module 30, configured to acquire the user's motion data when the physical sign parameter detection result is that the physical sign parameter is abnormal;

[0123] A determination module 40, configured to determine the health condition of the user according to the motion data and the physical sign parameter detection result;

[0124] The prediction module 50 is used to input the physical sign change curve into a preset health recognition model when the health condition meets the preset recognition condition, so as to obtain the user health monitoring result output by the preset health recognition model.

[0125] This embodiment monitors various vital sign parameters of the user, and generates a vital sign change curve based on the vital sign parameters; performs vital sign parameter abnormality detection based on the vital sign change curve to obtain a vital sign parameter detection result; when the vital sign parameter detection result is a vital sign parameter abnormality, obtains the user's motion data; judges the user's health status based on the motion data and the vital sign parameter detection result; when the health status meets the preset identification conditions, inputs the vital sign change curve into a preset health identification model to obtain the user health monitoring result output by the preset health identification model. Since this embodiment first performs vital sign parameter abnormality detection, when the vital sign parameters are abnormal, the user's health status is judged based on the motion data and the vital sign parameter detection results, and when the health status meets the preset identification conditions, the user's health prediction is performed through the preset health identification model, compared with the existing method of judging the user's health status based only on the vital sign parameters, the above method of this embodiment can improve the accuracy of user health monitoring.

[0126] The smart watch abnormality monitoring device provided by the present application adopts the smart watch abnormality monitoring method in the above embodiment, which can solve the technical problems of single monitoring dimension and low accuracy in existing health monitoring and early warning. Compared with the prior art, the beneficial effects of the smart watch abnormality monitoring device provided by the present application are the same as the beneficial effects of the smart watch abnormality monitoring method provided by the above embodiment, and the other technical features in the smart watch abnormality monitoring device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0127] The present application provides a smart watch abnormality monitoring device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the smart watch abnormality monitoring method in the above-mentioned embodiment one.

[0128] Reference below Figure 5 , which shows a schematic diagram of the structure of a smart watch abnormality monitoring device suitable for implementing the embodiment of the present application. The smart watch abnormality monitoring device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The smart watch abnormality monitoring device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0129] like Figure 5 As shown, the smart watch abnormality monitoring device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Onl y Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the smart watch abnormality monitoring device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the smart watch abnormality monitoring device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a smart watch abnormality monitoring device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0130] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0131] The smart watch abnormality monitoring device provided by the present application adopts the smart watch abnormality monitoring method in the above embodiment, which can solve the technical problems of single monitoring dimension and low accuracy in existing health monitoring and early warning. Compared with the prior art, the beneficial effects of the smart watch abnormality monitoring device provided by the present application are the same as the beneficial effects of the smart watch abnormality monitoring method provided by the above embodiment, and the other technical features in the smart watch abnormality monitoring device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0132] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0133] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0134] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the smart watch abnormality monitoring method in the above-mentioned embodiment.

[0135] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0136] The above-mentioned computer-readable storage medium may be included in the smart watch abnormality monitoring device; or it may exist independently without being assembled into the smart watch abnormality monitoring device.

[0137] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the smart watch abnormality monitoring device, the smart watch abnormality monitoring device executes the smart watch abnormality monitoring method.

[0138] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0139] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0140] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0141] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned smart watch abnormality monitoring method, and can solve the technical problems of single monitoring dimension and low accuracy in existing health monitoring and early warning. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the smart watch abnormality monitoring method provided by the above-mentioned embodiment, and will not be repeated here.

[0142] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned smart watch abnormality monitoring method when executed by a processor.

[0143] The computer program product provided by this application can solve the technical problems of single monitoring dimension and low accuracy in existing health monitoring and early warning. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the smart watch abnormality monitoring method provided by the above embodiment, which will not be repeated here.

[0144] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for monitoring abnormality of a smart watch, characterized in that: The smart watch abnormality monitoring method comprises the following steps: Monitor various physical sign parameters of the user, and generate a physical sign change curve according to the physical sign parameters; Performing abnormality detection of physical sign parameters based on the physical sign change curve to obtain a physical sign parameter detection result; When the physical sign parameter detection result is that the physical sign parameter is abnormal, obtaining the exercise data of the user; Determining the health status of the user according to the motion data and the physical sign parameter detection results; When the health condition meets the preset identification condition, the physical sign change curve is input into a preset health identification model to obtain the user health monitoring result output by the preset health identification model.

2. The smart watch abnormality monitoring method according to claim 1, characterized in that: The step of performing abnormal detection of physical sign parameters based on the physical sign change curve to obtain physical sign parameter detection results includes: Determining the physical sign change slope according to the physical sign change curve; When the physical sign change slope is greater than a preset physical sign slope threshold, determining a target value range according to the parameter type corresponding to the physical sign change curve; Determining whether the current physical sign parameter value is within the target value range according to the physical sign change curve; If the current vital sign parameter value is not within the target value range, a vital sign parameter detection result indicating abnormal vital sign parameters is generated.

3. The method for monitoring abnormality of a smart watch according to claim 1, wherein: The step of inputting the physical sign change curve into a preset health recognition model to obtain the user health monitoring result output by the preset health recognition model includes: Preprocessing the physical sign change curve to obtain a target physical sign change curve; Sequencing the target vital sign change curve by using a sliding window to obtain subsequences; The subsequence is input into a preset health recognition model to obtain a user health monitoring result output by the preset health recognition model.

4. The method for monitoring abnormality of a smart watch according to claim 1, wherein: After the step of obtaining the user's motion data, the method further includes: Performing fall detection on the user based on the motion data to obtain a fall detection result; When the fall detection result is that the user falls, obtaining current location information and current environment information; Determine a target positioning method based on the current environmental information; Determine the target location information according to the target positioning method; Final position information is determined based on the target position information and the current position information, and a fall warning is performed according to the final position information.

5. The method for monitoring abnormality of a smart watch as claimed in claim 4, characterized in that: The step of performing fall detection on the user based on the motion data to obtain a fall detection result includes: determining a motion curve of the user according to the motion data; Determine the acceleration change value of the user according to the motion curve; When the acceleration change value is greater than a preset acceleration, obtaining air pressure change information detected by a barometer sensor; A current air pressure change value is determined according to the air pressure change information, and when the air pressure change value is greater than a preset change threshold, fall detection is performed on the user according to the air pressure change information to obtain a fall detection result.

6. The method for monitoring abnormality of a smart watch according to any one of claims 1 to 5, characterized in that: After the step of monitoring various vital sign parameters of the user, the method further includes: Obtain the monitored user's heart rate information and heart rate variability; determining an emotional change of the user according to the heart rate variability and the user heart rate information; Emotional warning is performed based on the emotional changes.

7. The method for monitoring abnormality of a smart watch according to any one of claims 1 to 5, characterized in that: The smart watch abnormality monitoring method also includes: Get the notification information received by the user; Performing feature extraction on the notification information to obtain a feature extraction result; Determine the to-do items of the user based on the feature extraction result; Determine a target reminder time according to the to-do items; Remind the user to process the to-do item based on the target reminder time.

8. A smart watch abnormality monitoring device, characterized in that: The smart watch abnormality monitoring device comprises: A monitoring module, used to monitor various physical sign parameters of the user and generate a physical sign change curve according to the physical sign parameters; An abnormality detection module, used for performing abnormality detection of physical sign parameters based on the physical sign change curve to obtain a physical sign parameter detection result; An acquisition module, used for acquiring the motion data of the user when the physical sign parameter detection result is that the physical sign parameter is abnormal; A judgment module, used for judging the health status of the user according to the motion data and the physical sign parameter detection result; The prediction module is used to input the physical sign change curve into a preset health recognition model when the health condition meets the preset recognition condition, and obtain the user health monitoring result output by the preset health recognition model.

9. A smart watch abnormality monitoring device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the smart watch abnormality monitoring method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the smart watch abnormality monitoring method according to any one of claims 1 to 7 are implemented.

Images