Methods, systems, and media for monitoring and early warning of daily routines and health based on smartwatches
Through the dynamic evaluation and graph generation technology of smart watches, the technical maturity problem of smart watch routine health monitoring is solved, accurate routine health monitoring and early warning functions are realized, and users' health awareness and equipment trust are enhanced.
Patent Information
- Application Number
- CN202411087861.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-08-09
AI Technical Summary
The existing smart watches have not yet mature technology in operating and rest health monitoring, and it is difficult to ensure intelligence, comprehensiveness and accuracy, and face challenges such as technology, market verification and consumer trust.
By obtaining the monitoring information of the smart watch in the preset time period, extracting characteristic data and dynamic evaluation with environmental characteristic data, obtaining dynamic work and rest index, generating work and rest status information map, evaluating work and rest deviation index, and setting early warnings based on threshold comparison, reminding Users adjust their work and rest, evaluate sleep quality and exercise compliance, calculate health index, and generate alarm information.
Accurate work and rest health monitoring, early detection and early adjustment, improve users' awareness of work and rest health issues, and enhance smart watches' trust and market acceptance in health monitoring.
Smart Images

Figure CN118645246B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of work and rest health monitoring, and specifically, to a work and rest health monitoring and early warning method, system and medium based on a smart watch. Background Art
[0002] Due to the prevalence of bad living habits such as staying up late and sitting for long periods of time, as well as modern people's increasing attention to health, the demand for smart watches as portable health monitoring tools is increasing.
[0003] At present, although smart watches have great potential in health monitoring and early warning, the technology for using smart watches to monitor health and work schedules is not yet mature, and it is difficult to guarantee intelligence, comprehensiveness and accuracy. It still faces many challenges in technology, market verification and consumer trust.
[0004] In view of the above problems, effective technical solutions are urgently needed. Summary of the invention
[0005] The purpose of this application is to provide a method, system and medium for monitoring and early warning of work and rest health based on smart watches. It can obtain the user's work and rest deviation index to remind the user to adjust his or her work and rest. In addition, it can also obtain the user's health index. For those that do not meet the threshold requirements, an alarm message is generated and the user is reminded through a smart watch, so that the user's work and rest health problems can be discovered as early as possible, and accurate monitoring, early detection and early adjustment can be achieved, thus realizing the technology of work and rest health monitoring and early warning based on smart watches.
[0006] This application also provides a work and rest health monitoring and early warning method based on a smart watch, comprising the following steps:
[0007] Acquire monitoring information corresponding to multiple time periods of the smart watch within a preset time period and extract feature data, perform dynamic evaluation based on the feature data corresponding to the multiple time periods combined with corresponding environmental feature data, and obtain the user's work and rest dynamic index corresponding to the multiple time periods;
[0008] Comparing the work and rest dynamic indexes corresponding to the multiple time periods with the preset work and rest dynamic thresholds respectively, obtaining the sleep or non-sleep states corresponding to the multiple time periods according to the corresponding multiple comparison results, and obtaining the corresponding work and rest state information;
[0009] Generate a work and rest status information map of the user according to the work and rest status information corresponding to the multiple time periods, extract work and rest status change data according to the work and rest status information map, and evaluate the work and rest deviation degree in combination with the preset standard work and rest status change data of the user to obtain a work and rest deviation index;
[0010] Comparing the work-rest deviation index with a preset work-rest deviation threshold, if the threshold comparison result does not meet the preset threshold comparison requirement, setting the smart watch to issue an early warning and prompting the user to adjust his work-rest;
[0011] Acquire a set of sleep monitoring information of the user in a sleeping state within the preset time period, extract sleep characteristic data corresponding to multiple sleep time periods, evaluate the rationality of the user's sleep according to the sleep characteristic data, and obtain a sleep quality index of the user;
[0012] Acquire an activity monitoring information set of the user in a non-sleeping state within the preset time period, extract activity feature data corresponding to a plurality of activity time periods, and compare them with preset thresholds respectively to obtain a plurality of exercise time periods within the preset time period;
[0013] Acquire motion feature data of the multiple motion time periods, perform a user motion compliance assessment based on the motion feature data of the multiple motion time periods, and obtain a user motion compliance index;
[0014] Acquire the user's physical characteristic data, and process the data in combination with the environmental characteristic data corresponding to the multiple time periods to obtain a physical characteristic coefficient of the user;
[0015] According to the user sleep quality index and the user exercise compliance index, combined with the body characteristic coefficient, the user health evaluation is performed to obtain a user health index;
[0016] The user health index is compared with a preset work and rest health threshold. If the threshold comparison result does not meet the preset threshold comparison requirement, an alarm message is generated and the user is reminded through the smart watch.
[0017] Optionally, in the work and rest health monitoring and early warning method based on a smart watch described in the present application, the monitoring information corresponding to multiple time periods of the smart watch within a preset time period is obtained and feature data is extracted, and dynamic evaluation is performed according to the feature data corresponding to the multiple time periods in combination with corresponding environmental feature data to obtain the work and rest dynamic index of the user corresponding to the multiple time periods, including:
[0018] Obtain monitoring information corresponding to multiple time periods of the smart watch within a preset time period, including the user's steps, heart rate, body temperature, pressure, and blood oxygen saturation;
[0019] Extracting characteristic data according to the monitoring information, including acceleration data, heart rate change rate data, heart rate variability data, blood oxygen saturation change rate data and temperature change rate data;
[0020] Acquire environmental characteristic data corresponding to the multiple time periods according to the environmental monitoring platform database, including season information data, time information data, and room temperature data;
[0021] According to the characteristic data corresponding to the multiple time periods combined with the corresponding environmental characteristic data, a dynamic evaluation is performed through a preset user work and rest status evaluation model to obtain the user's work and rest dynamic index corresponding to the multiple time periods.
[0022] Optionally, in the work and rest health monitoring and early warning method based on a smart watch described in the present application, generating a work and rest status information map of the user according to the work and rest status information corresponding to the multiple time periods, extracting work and rest status change data according to the work and rest status information map, and performing work and rest deviation evaluation in combination with the user's preset standard work and rest status change data to obtain a work and rest deviation index, including:
[0023] Classify the work and rest status information corresponding to the multiple time periods, and perform distribution description according to the classified information, and generate a work and rest status information map of the user;
[0024] Extracting work and rest status change data according to the work and rest status information map;
[0025] Obtaining the user's standard work and rest status change data through a preset user work and rest monitoring platform database;
[0026] The work and rest state variation data is combined with the standard work and rest state variation data to perform work and rest deviation evaluation to obtain a work and rest deviation index.
[0027] Optionally, in the work and rest health monitoring and early warning method based on a smart watch described in the present application, the step of obtaining a sleep monitoring information set of the user in a sleep state within the preset time period, extracting sleep characteristic data corresponding to a plurality of sleep time periods, and performing a user sleep rationality assessment based on the sleep characteristic data to obtain a user sleep quality index includes:
[0028] Acquire a set of sleep monitoring information of the user in a sleeping state within the preset time period;
[0029] Extracting sleep characteristic data corresponding to multiple sleep time periods according to the sleep monitoring information set, including sleep duration data, light sleep duration data, deep sleep duration data, awakening frequency data, and rapid eye movement sleep duration data;
[0030] Performing a sleep rationality assessment on the user according to the sleep characteristic data corresponding to the multiple sleep time periods to obtain a sleep quality index of the user;
[0031] The calculation formula of the user sleep quality index is:
[0032] ;
[0033] in, is the user's sleep quality index, n is the number of sleep time periods within the preset time period, , , , , is the sleep duration data, light sleep duration data, deep sleep duration data, awakening times data, and rapid eye movement sleep duration data of the i-th sleep period, , , , , is the preset characteristic coefficient.
[0034] Optionally, in the work and rest health monitoring and early warning method based on a smart watch described in the present application, the obtaining of the activity monitoring information set of the user in a non-sleeping state within the preset time period, and extracting the activity feature data corresponding to the multiple activity time periods, and comparing them with the preset thresholds respectively, to obtain the multiple exercise time periods within the preset time period, includes:
[0035] Acquire an activity monitoring information set of the user in a non-sleeping state within the preset time period;
[0036] Extracting activity feature data corresponding to multiple activity time periods according to the activity monitoring information set, including activity cadence data, activity acceleration change data, activity blood oxygen saturation change rate data, and activity heart rate change rate data;
[0037] Acquire a user's motion characteristic threshold set, wherein the motion characteristic threshold set includes a step frequency characteristic threshold, an acceleration change characteristic threshold, a blood oxygen saturation change rate characteristic threshold, and a heart rate change rate characteristic threshold;
[0038] Comparing the activity feature data corresponding to the multiple activity time periods with the four thresholds of the motion characteristic threshold set;
[0039] If the four items of the activity feature data are all greater than the corresponding thresholds of the motion characteristic threshold set, the activity time period is a motion time period.
[0040] Optionally, in the work and rest health monitoring and early warning method based on a smart watch described in the present application, the acquiring of the motion characteristic data of the multiple motion time periods, performing a user motion compliance assessment based on the motion characteristic data of the multiple motion time periods, and obtaining a user motion compliance index includes:
[0041] Acquire motion characteristic data of the plurality of motion time periods, including motion step frequency data, motion acceleration change data, motion blood oxygen saturation change rate data, and motion heart rate change rate data;
[0042] Performing a user exercise compliance evaluation based on the exercise feature data of the multiple exercise time periods to obtain a user exercise compliance index;
[0043] The calculation formula of the user motion compliance index is:
[0044] ;
[0045] in, is the user's exercise compliance index, m is the number of exercise time periods within the preset time period, , , , The exercise step frequency data, exercise acceleration change data, exercise blood oxygen saturation change rate data, and exercise heart rate change rate data of the jth exercise time period, is the user motion state compensation coefficient, , , , is the preset characteristic coefficient.
[0046] Optionally, in the work and rest health monitoring and early warning method based on a smart watch described in the present application, the acquiring of the user's physical characteristic data and processing in combination with the environmental characteristic data corresponding to the multiple time periods to obtain the user's physical characteristic coefficient include:
[0047] Obtaining the user's physical characteristic data, including user weight data, user age data, and user gender information data, through a preset personal information monitoring platform database;
[0048] The physical characteristic data is combined with the environmental characteristic data corresponding to the multiple time periods and processed through a preset user health status assessment model to obtain the physical characteristic coefficient of the user.
[0049] Optionally, in the work and rest health monitoring and early warning method based on a smart watch described in the present application, the user health assessment is performed according to the user sleep quality index and the user exercise compliance index in combination with the body characteristic coefficient to obtain the user health index, including:
[0050] According to the user sleep quality index and the user exercise compliance index, combined with the physical characteristic coefficient, the user health is evaluated by using a preset user physical condition evaluation model to obtain a user health index;
[0051] The calculation formula of the user health index is:
[0052] ;
[0053] in, is the user health index, , , It is the user's sleep quality index, user's exercise compliance index, and body characteristic coefficient. , , is the preset characteristic coefficient.
[0054] In a second aspect, the present application provides a work and rest health monitoring and early warning system based on a smart watch, the system comprising: a memory and a processor, the memory comprising a program of a work and rest health monitoring and early warning method based on a smart watch, and the program of the work and rest health monitoring and early warning method based on a smart watch is executed by the processor to implement the following steps:
[0055] Acquire monitoring information corresponding to multiple time periods of the smart watch within a preset time period and extract feature data, perform dynamic evaluation based on the feature data corresponding to the multiple time periods combined with corresponding environmental feature data, and obtain the user's work and rest dynamic index corresponding to the multiple time periods;
[0056] Comparing the work and rest dynamic indexes corresponding to the multiple time periods with the preset work and rest dynamic thresholds respectively, obtaining the sleep or non-sleep states corresponding to the multiple time periods according to the corresponding multiple comparison results, and obtaining the corresponding work and rest state information;
[0057] Generate a work and rest status information map of the user according to the work and rest status information corresponding to the multiple time periods, extract work and rest status change data according to the work and rest status information map, and evaluate the work and rest deviation degree in combination with the preset standard work and rest status change data of the user to obtain a work and rest deviation index;
[0058] Comparing the work-rest deviation index with a preset work-rest deviation threshold, if the threshold comparison result does not meet the preset threshold comparison requirement, setting the smart watch to issue an early warning and prompting the user to adjust his work-rest;
[0059] Acquire a set of sleep monitoring information of the user in a sleeping state within the preset time period, extract sleep characteristic data corresponding to multiple sleep time periods, evaluate the rationality of the user's sleep according to the sleep characteristic data, and obtain a sleep quality index of the user;
[0060] Acquire an activity monitoring information set of the user in a non-sleeping state within the preset time period, extract activity feature data corresponding to a plurality of activity time periods, and compare them with preset thresholds respectively to obtain a plurality of exercise time periods within the preset time period;
[0061] Acquire motion feature data of the multiple motion time periods, perform a user motion compliance assessment based on the motion feature data of the multiple motion time periods, and obtain a user motion compliance index;
[0062] Acquire the user's physical characteristic data, and process the data in combination with the environmental characteristic data corresponding to the multiple time periods to obtain a physical characteristic coefficient of the user;
[0063] According to the user sleep quality index and the user exercise compliance index, combined with the body characteristic coefficient, the user health evaluation is performed to obtain a user health index;
[0064] The user health index is compared with a preset work and rest health threshold. If the threshold comparison result does not meet the preset threshold comparison requirement, an alarm message is generated and the user is reminded through the smart watch.
[0065] In the third aspect, the present application also provides a computer-readable storage medium, which stores a work and rest health monitoring and early warning method program based on a smart watch. When the work and rest health monitoring and early warning method program based on a smart watch is executed by a processor, the steps of the work and rest health monitoring and early warning method based on a smart watch as described in any one of the above items are implemented.
[0066] As can be seen from the above, the work and rest health monitoring and early warning method, system and medium based on smart watches provided in the present application obtain the monitoring information of the smart watch and extract the characteristic data, and perform dynamic evaluation in combination with the corresponding environmental characteristic data to obtain the work and rest dynamic index, and compare it with the preset threshold value respectively. According to the comparison result, the corresponding sleep or non-sleep state is obtained, and the corresponding work and rest state information is obtained, and then the user's work and rest state information map is generated, the work and rest state change data is extracted, and the work and rest deviation degree is evaluated to obtain the work and rest deviation index, and the threshold value is compared to prompt the user to adjust the work and rest, and the sleep characteristic data and the movement characteristic data are extracted respectively, and the user's sleep rationality evaluation and the user's movement compliance evaluation are respectively performed, and the user's sleep quality index and the user's movement compliance index are obtained accordingly; in addition, the user's body characteristic coefficient is obtained, and the user's health is evaluated according to the user's sleep quality index, the user's movement compliance index and the body characteristic coefficient, and the user's health index is obtained, and compared with the preset work and rest health threshold value. If the threshold comparison result does not meet the preset threshold comparison requirement, an alarm message is generated, and the user is reminded through the smart watch, thereby realizing the technology of work and rest health monitoring and early warning based on the smart watch.
[0067] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0068] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0069] Figure 1 A flowchart of a method for monitoring and warning of work and rest health based on a smart watch provided in an embodiment of the present application;
[0070] Figure 2 A flowchart of obtaining a work and rest dynamic index of a work and rest health monitoring and early warning method based on a smart watch provided in an embodiment of the present application;
[0071] Figure 3 A flow chart of obtaining a work-rest deviation index in a work-rest health monitoring and early warning method based on a smart watch provided in an embodiment of the present application;
[0072] Figure 4 A flowchart of obtaining a user's sleep quality index in a method for monitoring and warning of work and rest health based on a smart watch provided in an embodiment of the present application. DETAILED DESCRIPTION
[0073] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.
[0074] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0075] Please refer to Figure 1 , Figure 1 This is a flow chart of a work and rest health monitoring and early warning method based on a smart watch in some embodiments of the present application. The work and rest health monitoring and early warning method based on a smart watch is used in a terminal device, such as a computer, a mobile phone terminal, etc. The work and rest health monitoring and early warning method based on a smart watch includes the following steps:
[0076] S101, obtaining monitoring information corresponding to multiple time periods of the smart watch within a preset time period and extracting feature data, performing dynamic evaluation based on the feature data corresponding to the multiple time periods combined with corresponding environmental feature data, and obtaining the user's work and rest dynamic index corresponding to the multiple time periods;
[0077] S102, comparing the work and rest dynamic indexes corresponding to the multiple time periods with preset work and rest dynamic thresholds respectively, obtaining the sleep or non-sleep states corresponding to the multiple time periods according to the corresponding multiple comparison results, and obtaining corresponding work and rest state information;
[0078] S103, generating a work and rest status information map of the user according to the work and rest status information corresponding to the multiple time periods, extracting work and rest status change data according to the work and rest status information map, and performing work and rest deviation evaluation in combination with the preset standard work and rest status change data of the user to obtain a work and rest deviation index;
[0079] S104, comparing the work-rest deviation index with a preset work-rest deviation threshold, if the threshold comparison result does not meet the preset threshold comparison requirement, setting the smart watch to issue an early warning and prompting the user to adjust his work-rest;
[0080] S105, obtaining a sleep monitoring information set of the user in a sleeping state within the preset time period, and extracting sleep characteristic data corresponding to multiple sleep time periods, performing a sleep rationality assessment on the user according to the sleep characteristic data, and obtaining a sleep quality index of the user;
[0081] S106, obtaining an activity monitoring information set of the user in a non-sleeping state within the preset time period, extracting activity feature data corresponding to a plurality of activity time periods, and comparing the activity feature data with preset thresholds respectively to obtain a plurality of exercise time periods within the preset time period;
[0082] S107, acquiring motion feature data of the multiple motion time periods, and evaluating the user's motion compliance according to the motion feature data of the multiple motion time periods to obtain a user's motion compliance index;
[0083] S108, obtaining the user's physical characteristic data, and processing the data in combination with the environmental characteristic data corresponding to the multiple time periods to obtain the user's physical characteristic coefficient;
[0084] S109, evaluating the user's health according to the user's sleep quality index and the user's exercise compliance index in combination with the body characteristic coefficient to obtain a user health index;
[0085] S110, comparing the user health index with a preset work and rest health threshold, if the threshold comparison result does not meet the preset threshold comparison requirement, generating an alarm message and reminding the user through the smart watch.
[0086] It should be noted that in order to realize the monitoring of the user's work and rest health based on the smart watch and generate an early warning, so as to detect the user's work and rest health problems as early as possible and achieve accurate monitoring, early detection, and early adjustment technology, first, the monitoring information corresponding to multiple time periods of the smart watch within a preset time period is obtained and the feature data is extracted, wherein the preset time period and multiple time periods can be set according to the specific situation. In this embodiment, the time period is set to 24 hours and divided into 12 time periods. A dynamic evaluation is performed based on the extracted feature data combined with the corresponding environmental feature data to obtain a work and rest dynamic index, and the index is compared with the preset thresholds respectively. According to the comparison results, the corresponding sleep or non-sleep state is obtained, and the corresponding work and rest state information is obtained. Then, the user's work and rest state information map is generated, the work and rest state change data is extracted, the work and rest deviation degree is evaluated, and the work and rest deviation is obtained. Index, where the work and rest deviation index can reflect the user's work and rest regularity within a time period, and is compared with the user's historical regular work and rest. For users with irregular work and rest, the smart watch can prompt the user to adjust their work and rest. In addition, sleep characteristic data and motion characteristic data are extracted according to the different states of the user, and the user's sleep rationality and user's motion compliance are evaluated respectively, and the user's sleep quality index and user's motion compliance index are obtained accordingly; at the same time, the user's body characteristic coefficient is obtained, and the user's health is evaluated according to the user's sleep quality index, the user's motion compliance index and the body characteristic coefficient, and the user's health index is obtained. The user health index can accurately feedback the user's work and rest health status within a preset time period. For those who do not meet the expected health indicators, an alarm message is generated and the user is reminded through a smart watch.
[0087] Please refer to Figure 2 , Figure 2It is a flow chart of obtaining the work and rest dynamic index of the work and rest health monitoring and early warning method based on a smart watch in some embodiments of the present application. According to an embodiment of the present invention, the monitoring information corresponding to multiple time periods of the smart watch within a preset time period is obtained and feature data is extracted, and dynamic evaluation is performed based on the feature data corresponding to the multiple time periods combined with the corresponding environmental feature data to obtain the work and rest dynamic index corresponding to the user in the multiple time periods, including:
[0088] S201, obtaining monitoring information corresponding to multiple time periods of the smart watch within a preset time period, including the number of steps, heart rate, body temperature, pressure and blood oxygen saturation of the user;
[0089] S202, extracting characteristic data according to the monitoring information, including acceleration data, heart rate change rate data, heart rate variability data, blood oxygen saturation change rate data and temperature change rate data;
[0090] S203, acquiring environmental characteristic data corresponding to the multiple time periods according to the environmental monitoring platform database, including season information data, time information data and room temperature data;
[0091] S204, performing a dynamic evaluation based on the characteristic data corresponding to the multiple time periods in combination with the corresponding environmental characteristic data through a preset user work and rest status evaluation model to obtain a work and rest dynamic index corresponding to the multiple time periods of the user.
[0092] It should be noted that the user's work and rest dynamics can be fed back through the feature data extracted by monitoring information of the smart watch, including acceleration, heart rate change rate, heart rate variability, blood oxygen saturation change rate and temperature change rate. In addition, the user's work and rest dynamics are also affected by the environment in which the user is located. After obtaining the feature data extracted by the smart watch and the environmental feature data, the calculation formula of the preset user work and rest state evaluation model is input for dynamic evaluation to obtain the work and rest dynamic index corresponding to the multiple time periods of the user;
[0093] The calculation formula of the work and rest dynamic index is:
[0094] ;
[0095] in, is the work and rest dynamic index corresponding to the kth time period of multiple time periods within the preset time period, , , , , is the acceleration data, heart rate change rate data, heart rate variability data, blood oxygen saturation change rate data, and temperature change rate data corresponding to the kth time period, , , is the season information data, time information data, and room temperature data corresponding to the kth time period; , , , , , , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset user health monitoring platform database).
[0096] Please refer to Figure 3 , Figure 3 It is a flow chart of obtaining a work-rest deviation index of a work-rest health monitoring and early warning method based on a smart watch in some embodiments of the present application. According to an embodiment of the present invention, the work-rest status information map of the user is generated according to the work-rest status information corresponding to the multiple time periods, the work-rest status change data is extracted according to the work-rest status information map, and the work-rest deviation degree is evaluated in combination with the preset standard work-rest status change data of the user to obtain the work-rest deviation index, including:
[0097] S301, classifying and dividing the work and rest status information corresponding to the multiple time periods, and performing distribution description according to the classified and divided information, and generating a work and rest status information map of the user;
[0098] S302, extracting work and rest status change data according to the work and rest status information map;
[0099] S303, obtaining the standard work and rest status change data of the user through a preset user work and rest monitoring platform database;
[0100] S304, evaluating the work / rest deviation degree according to the work / rest status change data in combination with the standard work / rest status change data, to obtain a work / rest deviation index.
[0101] It should be noted that in order to obtain a work and rest deviation index that can reflect the user's work and rest regularity within a preset time period, it is first necessary to classify and divide the multiple work and rest status information that have been obtained, describe their distribution, and generate a work and rest status information map. The work and rest status information map is an information display map that reflects the distribution description of the sleep or non-sleep work and rest category information in each time period. The work and rest status information map is subjected to data extraction and processing to obtain work and rest status change data. At the same time, the work and rest deviation degree is evaluated in combination with the standard work and rest status change data to obtain the user's work and rest deviation index within the preset time period.
[0102] Please refer to Figure 4 , Figure 4This is a flowchart of obtaining a user's sleep quality index in a method for monitoring and warning work and rest health based on a smart watch in some embodiments of the present application. According to an embodiment of the present invention, the sleep monitoring information set of the user in the sleep state within the preset time period is obtained, and sleep characteristic data corresponding to multiple sleep time periods are extracted, and the user's sleep rationality is evaluated according to the sleep characteristic data to obtain the user's sleep quality index, including:
[0103] S401, obtaining a sleep monitoring information set of the user in a sleep state within the preset time period;
[0104] S402, extracting sleep characteristic data corresponding to multiple sleep time periods according to the sleep monitoring information set, including sleep duration data, light sleep duration data, deep sleep duration data, awakening frequency data, and rapid eye movement sleep duration data;
[0105] S403, evaluating the rationality of user sleep according to the sleep characteristic data corresponding to the multiple sleep time periods to obtain a user sleep quality index;
[0106] The calculation formula of the user sleep quality index is:
[0107] ;
[0108] in, is the user's sleep quality index, n is the number of sleep time periods within the preset time period, , , , , is the sleep duration data, light sleep duration data, deep sleep duration data, awakening times data, and rapid eye movement sleep duration data of the i-th sleep period, , , , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset user health monitoring platform database).
[0109] It should be noted that the user's state is either sleeping or non-sleeping. When the user is in a sleeping state, the quality of sleep will affect the user's health status. In order to accurately obtain the user's sleep quality index, the user's sleep rationality is evaluated based on the user's sleep duration data, light sleep duration data, deep sleep duration data, awakening times data, and rapid eye movement sleep duration data to obtain the user's sleep quality index. Rapid eye movement sleep, referred to as REM sleep, is a stage in the sleep cycle, and its characteristics include rapid eye movement, brain wave activity similar to the awake state, muscle relaxation, and difficulty in awakening.
[0110] According to an embodiment of the present invention, the step of obtaining an activity monitoring information set of the user in a non-sleeping state within the preset time period, extracting activity feature data corresponding to a plurality of activity time periods, and comparing the activity feature data with preset thresholds respectively to obtain a plurality of exercise time periods within the preset time period includes:
[0111] Acquire an activity monitoring information set of the user in a non-sleeping state within the preset time period;
[0112] Extracting activity feature data corresponding to multiple activity time periods according to the activity monitoring information set, including activity cadence data, activity acceleration change data, activity blood oxygen saturation change rate data, and activity heart rate change rate data;
[0113] Acquire a user's motion characteristic threshold set, wherein the motion characteristic threshold set includes a step frequency characteristic threshold, an acceleration change characteristic threshold, a blood oxygen saturation change rate characteristic threshold, and a heart rate change rate characteristic threshold;
[0114] Comparing the activity feature data corresponding to the multiple activity time periods with the four thresholds of the motion characteristic threshold set;
[0115] If the four items of the activity feature data are all greater than the corresponding thresholds of the motion characteristic threshold set, the activity time period is a motion time period.
[0116] It should be noted that when the user is not sleeping, the user may be in a state of resting, working or exercising. Since there will be a large deviation in identifying the user's further specific state through a single characteristic data, which affects the accuracy, in order to more accurately identify that the user is in a state of exercise, the activity cadence data, activity acceleration change data, activity blood oxygen saturation change rate data and activity heart rate change rate data are obtained at the same time, and compared with the corresponding exercise characteristic thresholds respectively to obtain the user's exercise time period.
[0117] According to an embodiment of the present invention, the acquiring of motion feature data of the multiple motion time periods, performing a user motion compliance assessment based on the motion feature data of the multiple motion time periods, and obtaining a user motion compliance index includes:
[0118] Acquire motion characteristic data of the plurality of motion time periods, including motion step frequency data, motion acceleration change data, motion blood oxygen saturation change rate data, and motion heart rate change rate data;
[0119] Performing a user exercise compliance evaluation based on the exercise feature data of the multiple exercise time periods to obtain a user exercise compliance index;
[0120] The calculation formula of the user motion compliance index is:
[0121] ;
[0122] in, is the user's exercise compliance index, m is the number of exercise time periods within the preset time period, , , , The exercise step frequency data, exercise acceleration change data, exercise blood oxygen saturation change rate data, and exercise heart rate change rate data of the jth exercise time period, is the user motion state compensation coefficient, , , , It is a preset characteristic coefficient (the user motion state compensation coefficient and characteristic coefficient are obtained by querying the preset user health monitoring platform database).
[0123] It should be noted that after confirming that the user is in a state of exercise, the motion characteristic data of the user in the state of exercise is obtained, including exercise cadence data, exercise acceleration change data, exercise blood oxygen saturation change rate data and exercise heart rate change rate data, and the user's motion compliance is evaluated based on the above motion characteristic data to obtain a user motion compliance index that can reflect the user's condition during exercise.
[0124] According to an embodiment of the present invention, the acquiring of the user's physical characteristic data and processing in combination with the environmental characteristic data corresponding to the multiple time periods to obtain the user's physical characteristic coefficient includes:
[0125] Obtaining the user's physical characteristic data, including user weight data, user age data, and user gender information data, through a preset personal information monitoring platform database;
[0126] The physical characteristic data is combined with the environmental characteristic data corresponding to the multiple time periods and processed through a preset user health status assessment model to obtain the physical characteristic coefficient of the user.
[0127] It should be noted that each user has his or her own physical characteristics. Therefore, before conducting a health assessment on the user, it is necessary to obtain the user's physical characteristic coefficient. First, it is necessary to obtain the user's physical characteristic data through the existing personal information monitoring platform database, including user weight data, user age data, and user gender information data, and then combine it with the corresponding environmental characteristic data, including season information data, time information data, and room temperature data, and process it through a preset user health status assessment model to obtain the user's physical characteristic coefficient. The user health status assessment model is a neural network model. The initialized user health status assessment model is trained according to a large amount of historical user physical data and environmental data to obtain a trained user health status assessment model.
[0128] According to an embodiment of the present invention, the user health assessment is performed based on the user sleep quality index and the user exercise compliance index in combination with the body characteristic coefficient to obtain the user health index, including:
[0129] According to the user sleep quality index and the user exercise compliance index, combined with the physical characteristic coefficient, the user health is evaluated by using a preset user physical condition evaluation model to obtain a user health index;
[0130] The calculation formula of the user health index is:
[0131] ;
[0132] in, is the user health index, , , It is the user's sleep quality index, user's exercise compliance index, and body characteristic coefficient. , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset user health monitoring platform database).
[0133] It should be noted that in order to obtain a user health index that can directly reflect the user's health status, the acquired user sleep quality index, user exercise compliance index and body characteristic coefficient need to be input into the calculation formula of the preset user physical condition assessment model for processing to obtain the user health index.
[0134] In a second aspect, the present invention further discloses a work and rest health monitoring and early warning system based on a smart watch, comprising a memory and a processor, wherein the memory comprises a work and rest health monitoring and early warning method program based on a smart watch, and when the work and rest health monitoring and early warning method program based on a smart watch is executed by the processor, the following steps are implemented:
[0135] Acquire monitoring information corresponding to multiple time periods of the smart watch within a preset time period and extract feature data, perform dynamic evaluation based on the feature data corresponding to the multiple time periods combined with corresponding environmental feature data, and obtain the user's work and rest dynamic index corresponding to the multiple time periods;
[0136] Comparing the work and rest dynamic indexes corresponding to the multiple time periods with the preset work and rest dynamic thresholds respectively, obtaining the sleep or non-sleep states corresponding to the multiple time periods according to the corresponding multiple comparison results, and obtaining the corresponding work and rest state information;
[0137] Generate a work and rest status information map of the user according to the work and rest status information corresponding to the multiple time periods, extract work and rest status change data according to the work and rest status information map, and evaluate the work and rest deviation degree in combination with the preset standard work and rest status change data of the user to obtain a work and rest deviation index;
[0138] Comparing the work-rest deviation index with a preset work-rest deviation threshold, if the threshold comparison result does not meet the preset threshold comparison requirement, setting the smart watch to issue an early warning and prompting the user to adjust his work-rest;
[0139] Acquire a set of sleep monitoring information of the user in a sleeping state within the preset time period, extract sleep characteristic data corresponding to multiple sleep time periods, evaluate the rationality of the user's sleep according to the sleep characteristic data, and obtain a sleep quality index of the user;
[0140] Acquire an activity monitoring information set of the user in a non-sleeping state within the preset time period, extract activity feature data corresponding to a plurality of activity time periods, and compare them with preset thresholds respectively to obtain a plurality of exercise time periods within the preset time period;
[0141] Acquire motion feature data of the multiple motion time periods, perform a user motion compliance assessment based on the motion feature data of the multiple motion time periods, and obtain a user motion compliance index;
[0142] Acquire the user's physical characteristic data, and process the data in combination with the environmental characteristic data corresponding to the multiple time periods to obtain a physical characteristic coefficient of the user;
[0143] According to the user sleep quality index and the user exercise compliance index, combined with the body characteristic coefficient, the user health evaluation is performed to obtain a user health index;
[0144] The user health index is compared with a preset work and rest health threshold. If the threshold comparison result does not meet the preset threshold comparison requirement, an alarm message is generated and the user is reminded through the smart watch.
[0145] It should be noted that in order to realize the monitoring of the user's work and rest health based on the smart watch and generate an early warning, so as to detect the user's work and rest health problems as early as possible and achieve accurate monitoring, early detection, and early adjustment technology, first, the monitoring information corresponding to multiple time periods of the smart watch within a preset time period is obtained and the feature data is extracted, wherein the preset time period and multiple time periods can be set according to the specific situation. In this embodiment, the time period is set to 24 hours and divided into 12 time periods. A dynamic evaluation is performed based on the extracted feature data combined with the corresponding environmental feature data to obtain a work and rest dynamic index, and the index is compared with the preset thresholds respectively. According to the comparison results, the corresponding sleep or non-sleep state is obtained, and the corresponding work and rest state information is obtained. Then, the user's work and rest state information map is generated, the work and rest state change data is extracted, the work and rest deviation degree is evaluated, and the work and rest deviation is obtained. Index, where the work and rest deviation index can reflect the user's work and rest regularity within a time period, and is compared with the user's historical regular work and rest. For users with irregular work and rest, the smart watch can prompt the user to adjust their work and rest. In addition, sleep characteristic data and motion characteristic data are extracted according to the different states of the user, and the user's sleep rationality and user's motion compliance are evaluated respectively, and the user's sleep quality index and user's motion compliance index are obtained accordingly; at the same time, the user's body characteristic coefficient is obtained, and the user's health is evaluated according to the user's sleep quality index, the user's motion compliance index and the body characteristic coefficient, and the user's health index is obtained. The user health index can accurately feedback the user's work and rest health status within a preset time period. For those who do not meet the expected health indicators, an alarm message is generated and the user is reminded through a smart watch.
[0146] According to an embodiment of the present invention, the monitoring information corresponding to multiple time periods of the smart watch within a preset time period is obtained and feature data is extracted, and dynamic evaluation is performed according to the feature data corresponding to the multiple time periods in combination with corresponding environmental feature data to obtain the work and rest dynamic index of the user corresponding to the multiple time periods, including:
[0147] Obtain monitoring information corresponding to multiple time periods of the smart watch within a preset time period, including the user's steps, heart rate, body temperature, pressure, and blood oxygen saturation;
[0148] Extracting characteristic data according to the monitoring information, including acceleration data, heart rate change rate data, heart rate variability data, blood oxygen saturation change rate data and temperature change rate data;
[0149] Acquire environmental characteristic data corresponding to the multiple time periods according to the environmental monitoring platform database, including season information data, time information data, and room temperature data;
[0150] According to the characteristic data corresponding to the multiple time periods combined with the corresponding environmental characteristic data, a dynamic evaluation is performed through a preset user work and rest status evaluation model to obtain the user's work and rest dynamic index corresponding to the multiple time periods.
[0151] It should be noted that the user's work and rest dynamics can be fed back through the feature data extracted by monitoring information of the smart watch, including acceleration, heart rate change rate, heart rate variability, blood oxygen saturation change rate and temperature change rate. In addition, the user's work and rest dynamics are also affected by the environment in which the user is located. After obtaining the feature data extracted by the smart watch and the environmental feature data, the calculation formula of the preset user work and rest state evaluation model is input for dynamic evaluation to obtain the work and rest dynamic index corresponding to the multiple time periods of the user;
[0152] The calculation formula of the work and rest dynamic index is:
[0153] ;
[0154] in, is the work and rest dynamic index corresponding to the kth time period of multiple time periods within the preset time period, , , , , is the acceleration data, heart rate change rate data, heart rate variability data, blood oxygen saturation change rate data, and temperature change rate data corresponding to the kth time period, , , is the season information data, time information data, and room temperature data corresponding to the kth time period; , , , , , , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset user health monitoring platform database).
[0155] According to an embodiment of the present invention, generating a work and rest status information map of the user according to the work and rest status information corresponding to the multiple time periods, extracting work and rest status change data according to the work and rest status information map, and performing work and rest deviation evaluation in combination with the preset standard work and rest status change data of the user to obtain a work and rest deviation index includes:
[0156] Classify the work and rest status information corresponding to the multiple time periods, and perform distribution description according to the classified information, and generate a work and rest status information map of the user;
[0157] Extracting work and rest status change data according to the work and rest status information map;
[0158] Obtaining the user's standard work and rest status change data through a preset user work and rest monitoring platform database;
[0159] The work and rest state variation data is combined with the standard work and rest state variation data to perform work and rest deviation evaluation to obtain a work and rest deviation index.
[0160] It should be noted that in order to obtain a work and rest deviation index that can reflect the user's work and rest regularity within a preset time period, it is first necessary to classify and divide the multiple work and rest status information that have been obtained, describe their distribution, and generate a work and rest status information map. The work and rest status information map is an information display map that reflects the distribution description of the sleep or non-sleep work and rest category information in each time period. The work and rest status information map is subjected to data extraction and processing to obtain work and rest status change data. At the same time, the work and rest deviation degree is evaluated in combination with the standard work and rest status change data to obtain the user's work and rest deviation index within the preset time period.
[0161] According to an embodiment of the present invention, the step of obtaining a set of sleep monitoring information of the user in a sleeping state within the preset time period, extracting sleep characteristic data corresponding to a plurality of sleep time periods, and evaluating the rationality of the user's sleep according to the sleep characteristic data to obtain a sleep quality index of the user includes:
[0162] Acquire a set of sleep monitoring information of the user in a sleeping state within the preset time period;
[0163] Extracting sleep characteristic data corresponding to multiple sleep time periods according to the sleep monitoring information set, including sleep duration data, light sleep duration data, deep sleep duration data, awakening frequency data, and rapid eye movement sleep duration data;
[0164] Performing a sleep rationality assessment on the user according to the sleep characteristic data corresponding to the multiple sleep time periods to obtain a sleep quality index of the user;
[0165] The calculation formula of the user sleep quality index is:
[0166] ;
[0167] in, is the user's sleep quality index, n is the number of sleep time periods within the preset time period, , , , , is the sleep duration data, light sleep duration data, deep sleep duration data, awakening times data, and rapid eye movement sleep duration data of the i-th sleep period, , , , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset user health monitoring platform database).
[0168] It should be noted that the user's state is either sleeping or non-sleeping. When the user is in a sleeping state, the quality of sleep will affect the user's health status. In order to accurately obtain the user's sleep quality index, the user's sleep rationality is evaluated based on the user's sleep duration data, light sleep duration data, deep sleep duration data, awakening times data, and rapid eye movement sleep duration data to obtain the user's sleep quality index. Rapid eye movement sleep, referred to as REM sleep, is a stage in the sleep cycle, and its characteristics include rapid eye movement, brain wave activity similar to the awake state, muscle relaxation, and difficulty in awakening.
[0169] According to an embodiment of the present invention, the step of obtaining an activity monitoring information set of the user in a non-sleeping state within the preset time period, extracting activity feature data corresponding to a plurality of activity time periods, and comparing the activity feature data with preset thresholds respectively to obtain a plurality of exercise time periods within the preset time period includes:
[0170] Acquire an activity monitoring information set of the user in a non-sleeping state within the preset time period;
[0171] Extracting activity feature data corresponding to multiple activity time periods according to the activity monitoring information set, including activity cadence data, activity acceleration change data, activity blood oxygen saturation change rate data, and activity heart rate change rate data;
[0172] Acquire a user's motion characteristic threshold set, wherein the motion characteristic threshold set includes a step frequency characteristic threshold, an acceleration change characteristic threshold, a blood oxygen saturation change rate characteristic threshold, and a heart rate change rate characteristic threshold;
[0173] Comparing the activity feature data corresponding to the multiple activity time periods with the four thresholds of the motion characteristic threshold set;
[0174] If the four items of the activity feature data are all greater than the corresponding thresholds of the motion characteristic threshold set, the activity time period is a motion time period.
[0175] It should be noted that when the user is not sleeping, the user may be in a state of resting, working or exercising. Since there will be a large deviation in identifying the user's further specific state through a single characteristic data, which affects the accuracy, in order to more accurately identify that the user is in a state of exercise, the activity cadence data, activity acceleration change data, activity blood oxygen saturation change rate data and activity heart rate change rate data are obtained at the same time, and compared with the corresponding exercise characteristic thresholds respectively to obtain the user's exercise time period.
[0176] According to an embodiment of the present invention, the acquiring of motion feature data of the multiple motion time periods, performing a user motion compliance assessment based on the motion feature data of the multiple motion time periods, and obtaining a user motion compliance index includes:
[0177] Acquire motion characteristic data of the plurality of motion time periods, including motion step frequency data, motion acceleration change data, motion blood oxygen saturation change rate data, and motion heart rate change rate data;
[0178] Performing a user exercise compliance evaluation based on the exercise feature data of the multiple exercise time periods to obtain a user exercise compliance index;
[0179] The calculation formula of the user motion compliance index is:
[0180] ;
[0181] in, is the user's exercise compliance index, m is the number of exercise time periods within the preset time period, , , , The exercise step frequency data, exercise acceleration change data, exercise blood oxygen saturation change rate data, and exercise heart rate change rate data of the jth exercise time period, is the user motion state compensation coefficient, , , , It is a preset characteristic coefficient (the user motion state compensation coefficient and characteristic coefficient are obtained by querying the preset user health monitoring platform database).
[0182] It should be noted that after confirming that the user is in a state of exercise, the motion characteristic data of the user in the state of exercise is obtained, including exercise cadence data, exercise acceleration change data, exercise blood oxygen saturation change rate data and exercise heart rate change rate data, and the user's motion compliance is evaluated based on the above motion characteristic data to obtain a user motion compliance index that can reflect the user's condition during exercise.
[0183] According to an embodiment of the present invention, the acquiring of the user's physical characteristic data and processing in combination with the environmental characteristic data corresponding to the multiple time periods to obtain the user's physical characteristic coefficient includes:
[0184] Obtaining the user's physical characteristic data, including user weight data, user age data, and user gender information data, through a preset personal information monitoring platform database;
[0185] The physical characteristic data is combined with the environmental characteristic data corresponding to the multiple time periods and processed through a preset user health status assessment model to obtain the physical characteristic coefficient of the user.
[0186] It should be noted that each user has his or her own physical characteristics. Therefore, before conducting a health assessment on the user, it is necessary to obtain the user's physical characteristic coefficient. First, it is necessary to obtain the user's physical characteristic data through the existing personal information monitoring platform database, including user weight data, user age data, and user gender information data, and then combine it with the corresponding environmental characteristic data, including season information data, time information data, and room temperature data, and process it through a preset user health status assessment model to obtain the user's physical characteristic coefficient. The user health status assessment model is a neural network model. The initialized user health status assessment model is trained according to a large amount of historical user physical data and environmental data to obtain a trained user health status assessment model.
[0187] According to an embodiment of the present invention, the user health assessment is performed based on the user sleep quality index and the user exercise compliance index in combination with the body characteristic coefficient to obtain the user health index, including:
[0188] According to the user sleep quality index and the user exercise compliance index, combined with the physical characteristic coefficient, the user health is evaluated by using a preset user physical condition evaluation model to obtain a user health index;
[0189] The calculation formula of the user health index is:
[0190] ;
[0191] in, is the user health index, , , It is the user's sleep quality index, user's exercise compliance index, and body characteristic coefficient. , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset user health monitoring platform database).
[0192] It should be noted that in order to obtain a user health index that can directly reflect the user's health status, the acquired user sleep quality index, user exercise compliance index and body characteristic coefficient need to be input into the calculation formula of the preset user physical condition assessment model for processing to obtain the user health index.
[0193] The third aspect of the present invention provides a readable storage medium, which stores a work and rest health monitoring and early warning method program based on a smart watch. When the work and rest health monitoring and early warning method program based on a smart watch is executed by a processor, the steps of the work and rest health monitoring and early warning method based on a smart watch as described in any one of the above items are implemented.
[0194] The work and rest health monitoring and early warning method, system and medium based on smart watches disclosed in the present invention obtain monitoring information of smart watches and extract characteristic data, perform dynamic evaluation in combination with corresponding environmental characteristic data, obtain work and rest dynamic index, and compare with preset threshold values respectively, obtain corresponding sleep or non-sleep state according to the comparison result, obtain corresponding work and rest state information, regenerate work and rest state information map of users, extract work and rest state change data, perform work and rest deviation evaluation, obtain work and rest deviation index, perform threshold comparison, prompt users to adjust their work and rest, extract sleep characteristic data and motion characteristic data respectively, perform user sleep rationality evaluation and user motion compliance evaluation respectively, and obtain user sleep quality index and user motion compliance index accordingly; in addition, obtain user's body characteristic coefficient, perform user health evaluation according to user sleep quality index, user motion compliance index and body characteristic coefficient, obtain user health index, compare with preset work and rest health threshold values, if the threshold comparison result does not meet the preset threshold comparison requirement, generate alarm information, and remind users through smart watches, thereby realizing the technology of work and rest health monitoring and early warning based on smart watches.
[0195] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the 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 can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.
[0196] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0197] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0198] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, the aforementioned program can be stored in a readable storage medium, and when the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.
[0199] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.
Claims
1. A work and rest health monitoring and early warning method based on a smart watch, characterized in that: The following steps are involved: Acquire monitoring information corresponding to multiple time periods of the smart watch within a preset time period and extract feature data, perform dynamic evaluation based on the feature data corresponding to the multiple time periods combined with corresponding environmental feature data, and obtain the user's work and rest dynamic index corresponding to the multiple time periods; Comparing the work and rest dynamic indexes corresponding to the multiple time periods with the preset work and rest dynamic thresholds respectively, obtaining the sleep or non-sleep states corresponding to the multiple time periods according to the corresponding multiple comparison results, and obtaining the corresponding work and rest state information; Generate a work and rest status information map of the user according to the work and rest status information corresponding to the multiple time periods, extract work and rest status change data according to the work and rest status information map, and evaluate the work and rest deviation degree in combination with the preset standard work and rest status change data of the user to obtain a work and rest deviation index; Comparing the work-rest deviation index with a preset work-rest deviation threshold, if the threshold comparison result does not meet the preset threshold comparison requirement, setting the smart watch to issue an early warning and prompting the user to adjust his work-rest; Acquire a set of sleep monitoring information of the user in a sleeping state within the preset time period, extract sleep characteristic data corresponding to multiple sleep time periods, evaluate the rationality of the user's sleep according to the sleep characteristic data, and obtain a sleep quality index of the user; Acquire an activity monitoring information set of the user in a non-sleeping state within the preset time period, extract activity feature data corresponding to a plurality of activity time periods, and compare them with preset thresholds respectively to obtain a plurality of exercise time periods within the preset time period; Acquire motion feature data of the multiple motion time periods, perform a user motion compliance assessment based on the motion feature data of the multiple motion time periods, and obtain a user motion compliance index; Acquire the user's physical characteristic data, and process the data in combination with the environmental characteristic data corresponding to the multiple time periods to obtain a physical characteristic coefficient of the user; According to the user sleep quality index and the user exercise compliance index, combined with the body characteristic coefficient, the user health evaluation is performed to obtain a user health index; Comparing the user health index with a preset work and rest health threshold, if the threshold comparison result does not meet the preset threshold comparison requirement, generating an alarm message and reminding the user through the smart watch; The step of acquiring monitoring information corresponding to multiple time periods of the smart watch within a preset time period and extracting feature data, and performing dynamic evaluation based on the feature data corresponding to the multiple time periods in combination with corresponding environmental feature data, to obtain the work and rest dynamic index of the user corresponding to the multiple time periods, includes: Obtain monitoring information corresponding to multiple time periods of the smart watch within a preset time period, including the user's steps, heart rate, body temperature, pressure, and blood oxygen saturation; Extracting characteristic data according to the monitoring information, including acceleration data, heart rate change rate data, heart rate variability data, blood oxygen saturation change rate data and temperature change rate data; Acquire environmental characteristic data corresponding to the multiple time periods according to the environmental monitoring platform database, including season information data, time information data, and room temperature data; According to the characteristic data corresponding to the multiple time periods combined with the corresponding environmental characteristic data, a dynamic evaluation is performed through a preset user work and rest state evaluation model to obtain the work and rest dynamic index corresponding to the multiple time periods of the user; The calculation formula of the work and rest dynamic index is: ; in, is the work and rest dynamic index corresponding to the kth time period of multiple time periods within the preset time period, , , , , is the acceleration data, heart rate change rate data, heart rate variability data, blood oxygen saturation change rate data, and temperature change rate data corresponding to the kth time period, , , is the season information data, time information data, and room temperature data corresponding to the kth time period; , , , , , , , is the preset characteristic coefficient; The step of obtaining a sleep monitoring information set of the user in a sleep state within the preset time period, extracting sleep characteristic data corresponding to a plurality of sleep time periods, and evaluating the rationality of the user's sleep according to the sleep characteristic data to obtain a sleep quality index of the user includes: Acquire a set of sleep monitoring information of the user in a sleeping state within the preset time period; Extracting sleep characteristic data corresponding to multiple sleep time periods according to the sleep monitoring information set, including sleep duration data, light sleep duration data, deep sleep duration data, awakening frequency data, and rapid eye movement sleep duration data; Performing a sleep rationality assessment on the user according to the sleep characteristic data corresponding to the multiple sleep time periods to obtain a sleep quality index of the user; The calculation formula of the user sleep quality index is: ; in, is the user's sleep quality index, n is the number of sleep time periods within the preset time period, , , , , is the sleep duration data, light sleep duration data, deep sleep duration data, awakening times data, and rapid eye movement sleep duration data of the i-th sleep period, , , , , is the preset characteristic coefficient; The step of obtaining the activity monitoring information set of the user in a non-sleeping state within the preset time period, extracting activity feature data corresponding to a plurality of activity time periods, and comparing the activity feature data with preset thresholds respectively to obtain a plurality of exercise time periods within the preset time period includes: Acquire an activity monitoring information set of the user in a non-sleeping state within the preset time period; Extracting activity feature data corresponding to multiple activity time periods according to the activity monitoring information set, including activity cadence data, activity acceleration change data, activity blood oxygen saturation change rate data, and activity heart rate change rate data; Acquire a user's motion characteristic threshold set, wherein the motion characteristic threshold set includes a step frequency characteristic threshold, an acceleration change characteristic threshold, a blood oxygen saturation change rate characteristic threshold, and a heart rate change rate characteristic threshold; Comparing the activity feature data corresponding to the multiple activity time periods with the four thresholds of the motion characteristic threshold set; If the four items of the activity characteristic data are all greater than the corresponding thresholds of the motion characteristic threshold set, then the activity time period is a motion time period; The acquiring the motion feature data of the multiple motion time periods, and performing a user motion compliance evaluation based on the motion feature data of the multiple motion time periods to obtain a user motion compliance index includes: Acquire motion characteristic data of the plurality of motion time periods, including motion step frequency data, motion acceleration change data, motion blood oxygen saturation change rate data, and motion heart rate change rate data; Performing a user exercise compliance evaluation based on the exercise feature data of the multiple exercise time periods to obtain a user exercise compliance index; The calculation formula of the user motion compliance index is: ; in, is the user's exercise compliance index, m is the number of exercise time periods within the preset time period, , , , The exercise step frequency data, exercise acceleration change data, exercise blood oxygen saturation change rate data, and exercise heart rate change rate data of the jth exercise time period, is the user motion state compensation coefficient, , , , is the preset characteristic coefficient.
2. The work and rest health monitoring and early warning method based on a smart watch according to claim 1 is characterized in that: Generating the work and rest state information map of the user according to the work and rest state information corresponding to the multiple time periods, extracting the work and rest state change data according to the work and rest state information map, and performing work and rest deviation evaluation in combination with the preset standard work and rest state change data of the user to obtain the work and rest deviation index, including: Classify the work and rest status information corresponding to the multiple time periods, and perform distribution description according to the classified information, and generate a work and rest status information map of the user; Extracting work and rest status change data according to the work and rest status information map; Obtaining the user's standard work and rest status change data through a preset user work and rest monitoring platform database; The work and rest state variation data is combined with the standard work and rest state variation data to perform work and rest deviation evaluation to obtain a work and rest deviation index.
3. The method for monitoring and warning of work and rest health based on a smart watch according to claim 2, characterized in that: The acquiring the user's physical characteristic data and processing the data in combination with the environmental characteristic data corresponding to the multiple time periods to obtain the user's physical characteristic coefficient includes: Obtaining the user's physical characteristic data, including user weight data, user age data, and user gender information data, through a preset personal information monitoring platform database; The physical characteristic data is combined with the environmental characteristic data corresponding to the multiple time periods and processed through a preset user health status assessment model to obtain the physical characteristic coefficient of the user.
4. The work and rest health monitoring and early warning method based on a smart watch according to claim 3 is characterized in that: The step of evaluating the user's health according to the user's sleep quality index and the user's exercise compliance index in combination with the body characteristic coefficient to obtain the user's health index includes: According to the user sleep quality index and the user exercise compliance index, combined with the physical characteristic coefficient, the user health is evaluated by using a preset user physical condition evaluation model to obtain a user health index; The calculation formula of the user health index is: ; in, is the user health index, is the body characteristic coefficient, , , is the preset characteristic coefficient.
5. The work and rest health monitoring and early warning system based on smart watches is characterized by: The system includes: a memory and a processor, wherein the memory includes a program of a work and rest health monitoring and early warning method based on a smart watch, and when the program of the work and rest health monitoring and early warning method based on a smart watch is executed by the processor, the steps of the work and rest health monitoring and early warning method based on a smart watch as described in any one of claims 1 to 4 are implemented.
6. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a work and rest health monitoring and early warning method program based on a smart watch. When the work and rest health monitoring and early warning method program based on a smart watch is executed by a processor, the steps of the work and rest health monitoring and early warning method based on a smart watch as described in any one of claims 1 to 4 are implemented.
Citation Information
Patent Citations
User health assessment method and device, storage medium and electronic equipment
CN111798978A
Behavior recommendation method and apparatus, storage medium, and electronic device
CN113168596A
Human body health index condition monitoring and analyzing method and system and storage medium
CN115083607A
Health target recommendation record tracking method and device based on smart watch
CN116741377A
Health monitoring management method and system based on intelligent equipment platform, and medium
CN118230953A
