A system and method for analyzing sleep state by collecting data through a wearable device
By collecting and analyzing users' pulse data in smart wearable devices, combined with skin color and light factor correction, and using wrist motion sensors and PPG sensors to acquire data, and incorporating knowledge of traditional Chinese medicine pulse diagnosis, accurate monitoring of users' sleep status and organ function has been achieved, solving the error problem of existing devices and improving the quality of sleep detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING XUEYANG TECH CO LTD
- Filing Date
- 2023-01-10
- Publication Date
- 2026-06-05
AI Technical Summary
Existing smart wearable devices cannot effectively monitor the functional status of various organs in the human body when monitoring sleep, resulting in significant errors and failing to fully utilize the collected vital signs data.
The system collects the user's raw pulse data through wearable devices, corrects it by combining factors such as skin color and external light, analyzes basic body parameters, establishes organ status, and determines the user's sleep status. It also uses wrist motion sensors and PPG sensors to acquire data and makes estimations by combining traditional Chinese medicine pulse diagnosis knowledge.
It reduces the error of sleep detection and improves the quality of sleep detection, allowing users to understand their sleep status and physical health status in real time.
Smart Images
Figure CN116807394B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of smart wearable technology, and in particular to a system and method for analyzing sleep states by collecting data through wearable devices. Background Technology
[0002] Currently, with the continuous development of portable human feature detection technology, the use of human vital sign collection devices in smart wearable devices for data collection has become widespread. However, existing wearable devices generally only provide an overall health status for users through vital sign monitoring, without actually utilizing the data. Maintaining a normal amount of sleep each day is crucial for humans. Current smart wearable devices can only measure whether the body has entered a sleep state; they cannot effectively monitor the functional status of various organs, resulting in significant errors.
[0003] Therefore, the present invention provides a system and method for analyzing sleep states by collecting data through wearable devices. Summary of the Invention
[0004] This invention discloses a system and method for collecting and analyzing sleep status data through wearable devices. By analyzing the sleep of the user's organs, the system comprehensively judges the user's sleep status, thereby reducing the error of sleep detection and improving the quality of sleep detection by smart devices.
[0005] This invention provides a method for analyzing sleep states by collecting data through wearable devices, comprising:
[0006] The acquisition module is used to acquire the user's raw pulse data through the wearable device, and adjust the raw pulse data according to the user's skin color and the ambient light to obtain raw waveform data;
[0007] The analysis module is used to parse the raw waveform data to obtain the user's basic body parameters, and analyze the user's physical health status based on the basic body parameters;
[0008] The determination module is used to establish the organ status corresponding to each target organ of the user based on the physical health status, and to obtain the user's sleep status at the same time based on the changes in the organ status.
[0009] In one feasible approach
[0010] The wearable device is equipped with a wrist motion sensor, which is used to acquire the user's wrist motion data in real time, generate a wrist motion line graph corresponding to the user at different times, and transmit it to a designated terminal for display.
[0011] The wearable device is also equipped with a PPG sensor, which is used to acquire the user's raw pulse data and transmit the raw pulse data to the acquisition module.
[0012] In one feasible approach
[0013] The acquisition module includes:
[0014] The data acquisition unit is used to collect the user's raw pulse data through wearable devices;
[0015] A light acquisition unit is used to acquire the user's skin color and establish a first external influence factor based on the skin color; and to acquire the external light in the user's environment and establish a second external influence factor based on the external light.
[0016] The data correction unit is used to correct the original pulse data based on the first external influence factor and the second external influence factor, and input the corrected original pulse data into a rectangular coordinate system to obtain the user's original waveform data.
[0017] In one feasible approach
[0018] The analysis module includes:
[0019] The data analysis unit is used to treat the original waveform data as initial data, sort the initial data in chronological order to obtain a first data sequence, sample the first data sequence at a preset time interval to obtain multiple target initial data, and obtain a weighted average of the multiple target initial data.
[0020] The data processing unit is used to smooth the first data sequence using the weighted average to obtain a second data sequence, draw a waveform diagram based on the second data sequence, and when there are waveform breakpoints in the waveform diagram, obtain the breakpoint target data corresponding to each waveform breakpoint in the second data sequence, and perform interpolation processing on the breakpoint target data to obtain a third data sequence.
[0021] The data determination unit is used to parse the third data sequence to obtain the user's basic physical parameters, and analyze the user's physical health status based on the basic physical parameters.
[0022] In one feasible approach
[0023] The determining module includes:
[0024] The sleep simulation unit is used to build a corresponding user model in a preset virtual space based on the physical health status. When the model attributes of the user model belong to preset attributes, the user model is input into a preset sleep environment to perform sleep simulation and obtain simulation results.
[0025] The feature analysis unit is used to establish a feature filtering network based on the organ features corresponding to each target organ, and input the simulation results into the feature filtering network for filtering to obtain the sub-simulation results corresponding to each target organ.
[0026] The sleep analysis unit is used to parse the corresponding sub-simulation results to obtain the current features of each target organ, analyze the organ sleep features of each organ based on the current features, and determine the organ state of the corresponding target organ based on the organ sleep features.
[0027] The sleep statistics unit is used to obtain the common sleep characteristics of different target organs at the same time based on the organ states of different target organs at the same time, and generate the user's sleep state at that time.
[0028] In one feasible approach
[0029] Also includes:
[0030] The pulse analysis module is used to establish an estimation model based on preset TCM pulse diagnosis knowledge, acquire and input the wrist movement data into the estimation model to perform sleep estimation, and obtain the estimation result;
[0031] Based on the estimation results, the user's sleep level is determined and transmitted to a preset terminal for display.
[0032] This invention provides a method for analyzing sleep states by collecting data through a wearable device, comprising:
[0033] S1: Collect the user's raw pulse data through a wearable device, and adjust the raw pulse data according to the user's skin color and ambient light to obtain raw waveform data;
[0034] S2: Analyze the original waveform data to obtain the user's basic body parameters, and analyze the user's physical health status based on the basic body parameters;
[0035] S3: Based on the physical health status, establish the organ status corresponding to each target organ of the user, and obtain the user's sleep status at the same time based on the changes in the organ status.
[0036] In one feasible approach
[0037] S1 includes:
[0038] S11: Collect the user's raw pulse data;
[0039] S12: Collect the user's skin color, establish a first external influence factor based on the skin color, collect the external light of the user's environment, and establish a second external influence factor based on the external light.
[0040] S13: Correct the original pulse data based on the first external influence factor and the second external influence factor, and input the corrected original pulse data into a rectangular coordinate system to obtain the user's original waveform data.
[0041] The beneficial effects achievable by this invention are as follows: In order to detect the user's sleep state in real time, the user's original pulse data is first collected. During the collection process, the influence of the external environment is eliminated to obtain the original waveform data. Then, the user's basic body parameters can be obtained, thereby analyzing the user's physical health status and establishing the organ status corresponding to each target organ. Finally, the user's sleep state at the same time can be obtained. In this way, the user's organ sleep is analyzed to comprehensively judge the user's sleep state, thereby reducing the error of sleep detection, improving the quality of sleep detection by smart devices, and allowing users to understand their sleep status after waking up the next day.
[0042] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.
[0043] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description
[0044] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:
[0045] Figure 1 This is a schematic diagram of the composition of a system for collecting and analyzing sleep states through a wearable device, according to an embodiment of the present invention.
[0046] Figure 2 This is a schematic diagram of the data acquisition module of a system for collecting and analyzing sleep states through wearable devices, according to an embodiment of the present invention.
[0047] Figure 3 This is a schematic diagram illustrating the workflow of a method for collecting and analyzing sleep states using wearable devices, as described in an embodiment of the present invention. Detailed Implementation
[0048] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.
[0049] Example 1
[0050] This embodiment provides a system for collecting and analyzing sleep states through wearable devices, such as... Figure 1 As shown, it includes:
[0051] The acquisition module is used to acquire the user's raw pulse data through the wearable device, and adjust the raw pulse data according to the user's skin color and the ambient light to obtain raw waveform data;
[0052] The analysis module is used to parse the raw waveform data to obtain the user's basic body parameters, and analyze the user's physical health status based on the basic body parameters;
[0053] The determination module is used to establish the organ status corresponding to each target organ of the user based on the physical health status, and to obtain the user's sleep status at the same time based on the changes in the organ status.
[0054] In this example, the sampling rate of the pulse wave data was increased when collecting the user's raw pulse data, thereby obtaining the best raw pulse data;
[0055] In this example, the original waveform data can be PPG data;
[0056] In this example, the basic body parameters include the user's heart rate, blood pressure, blood oxygen, and heart rate variability.
[0057] In this example, physical health status includes three types: healthy status, sub-healthy status, and unhealthy status.
[0058] In this example, sleep states include: wakefulness, rapid eye movement (REM) sleep, and non-rapid eye movement (NREM) sleep. REM sleep is also known as REM sleep, and NREM sleep is also known as NREM sleep. When a human falls asleep, REM sleep and NREM sleep alternate.
[0059] In this example, the target organ could be the heart, lungs, or brain;
[0060] In this example, organ status refers to the working status of different body organs in the user's current physical health state.
[0061] The working principle and beneficial effects of the above technical solution are as follows: In order to detect the user's sleep status in real time, the user's raw pulse data is first collected. During the collection process, the influence of the external environment is eliminated to obtain the raw waveform data. Then, the user's basic body parameters can be obtained, thereby analyzing the user's physical health status and establishing the organ status corresponding to each target organ. Finally, the user's sleep status at the same time can be obtained. In this way, the user's organ sleep is analyzed to comprehensively judge the user's sleep status, thereby reducing the error of sleep detection, improving the quality of sleep detection of smart devices, and allowing users to understand their sleep status after waking up the next day.
[0062] Example 2
[0063] Based on Example 1, the system for collecting and analyzing sleep states through wearable devices is as follows:
[0064] The wearable device is equipped with a wrist motion sensor, which is used to acquire the user's wrist motion data in real time, generate a wrist motion line graph corresponding to the user at different times, and transmit it to a designated terminal for display.
[0065] The wearable device is also equipped with a PPG sensor, which is used to acquire the user's raw pulse data and transmit the raw pulse data to the acquisition module.
[0066] The working principle and beneficial effects of the above technical solution are as follows: By setting up a wrist motion sensor and a PPG sensor on the wearable device, the user's wrist motion data and raw pulse data are acquired respectively, laying the foundation for subsequent sleep detection.
[0067] Example 3
[0068] Based on Example 1, the system for collecting and analyzing sleep states through wearable devices, such as... Figure 2 As shown, the acquisition module includes:
[0069] The data acquisition unit is used to collect the user's raw pulse data through wearable devices;
[0070] A light acquisition unit is used to acquire the user's skin color and establish a first external influence factor based on the skin color; and to acquire the external light in the user's environment and establish a second external influence factor based on the external light.
[0071] The data correction unit is used to correct the original pulse data based on the first external influence factor and the second external influence factor, and input the corrected original pulse data into a rectangular coordinate system to obtain the user's original waveform data.
[0072] In this example, the darker the user's skin tone, the less impact it has on the raw pulse data; the weaker the ambient light, the less impact it has on the raw pulse data.
[0073] In this example, the first external influence factor represents the impact of user skin color on the accuracy of data collection by the data collection unit. The greater the influence, the lower the accuracy, and vice versa.
[0074] In this example, the second external influence factor represents the impact of external light intensity on the data acquisition accuracy of the data acquisition unit. The greater the influence, the lower the accuracy, and vice versa.
[0075] In this example, because the wearable device collects the user's raw pulse data in real time, the raw waveform data is updated in real time.
[0076] The working principle and beneficial effects of the above technical solution are as follows: By collecting the user's original pulse data and correcting the original pulse data according to the actual situation, the corrected original pulse data is then input into the teaching coordinate system to obtain the user's original waveform data. In this way, the user can not only understand his / her pulse data in real time, but also lay the foundation for subsequent sleep detection.
[0077] Example 4
[0078] Based on Embodiment 1, the system for collecting and analyzing sleep states through wearable devices, wherein the analysis module includes:
[0079] The data analysis unit is used to treat the original waveform data as initial data, sort the initial data in chronological order to obtain a first data sequence, sample the first data sequence at a preset time interval to obtain multiple target initial data, and obtain a weighted average of the multiple target initial data.
[0080] The data processing unit is used to smooth the first data sequence using the weighted average to obtain a second data sequence, draw a waveform diagram based on the second data sequence, and when there are waveform breakpoints in the waveform diagram, obtain the breakpoint target data corresponding to each waveform breakpoint in the second data sequence, and perform interpolation processing on the breakpoint target data to obtain a third data sequence.
[0081] The data determination unit is used to parse the third data sequence to obtain the user's basic physical parameters, and analyze the user's physical health status based on the basic physical parameters.
[0082] In this example, since each initial data point has a collection time, the initial data are sorted in chronological order.
[0083] In this example, the first data sequence list is the result of sorting the initial data in chronological order;
[0084] In this example, the preset time interval is 10 seconds;
[0085] In this example, the target initial data represents the data extracted from the first data sequence, and the time interval between adjacent target initial data is a preset time interval;
[0086] In this example, the second data sequence represents the result of smoothing the first data sequence using a weighted average;
[0087] In this example, smoothing can remove interfering data from the first data sequence;
[0088] In this example, the waveform diagram represents the waveform formed by connecting all the data in the second data sequence in chronological order;
[0089] In this example, a waveform breakpoint represents a point on the second waveform where the data is 0 and none of the adjacent data are 0;
[0090] In this example, the third data sequence represents the result of interpolating the second data sequence;
[0091] In this example, interpolation can correct data breaks in the second data sequence.
[0092] The working principle and beneficial effects of the above technical solution are as follows: In order to accurately analyze the user's physical health status, the original waveform is first regarded as the initial data, and then sorted according to time to obtain the first data sequence. Then, data sampling is performed in the first data sequence to obtain a weighted average value that can be used for smoothing. This weighted average value is then used to smooth the first data sequence, and a waveform graph is drawn. Based on the correspondence between the waveform breakpoints on the waveform graph and the data in the data sequence, the breakpoint target data is eliminated using the difference method to obtain the third sequence. Finally, the user's basic physical parameters can be obtained by parsing the third data sequence, thereby obtaining the user's physical health status.
[0093] Example 5
[0094] Based on Embodiment 1, the system for collecting and analyzing sleep states through wearable devices, wherein the determining module includes:
[0095] The sleep simulation unit is used to build a corresponding user model in a preset virtual space based on the physical health status. When the model attributes of the user model belong to preset attributes, the user model is input into a preset sleep environment to perform sleep simulation and obtain simulation results.
[0096] The feature analysis unit is used to establish a feature filtering network based on the organ features corresponding to each target organ, and input the simulation results into the feature filtering network for filtering to obtain the sub-simulation results corresponding to each target organ.
[0097] The sleep analysis unit is used to parse the corresponding sub-simulation results to obtain the current features of each target organ, analyze the organ sleep features of each organ based on the current features, and determine the organ state of the corresponding target organ based on the organ sleep features.
[0098] The sleep statistics unit is used to obtain the common sleep characteristics of different target organs at the same time based on the organ states of different target organs at the same time, and generate the user's sleep state at that time.
[0099] In this example, the default attribute represents the sleep attribute;
[0100] In this example, the user model's attributes include three categories: movement attributes, sedentary attributes, and sleep attributes.
[0101] In this example, sleep simulation means simulating the user's sleep process in a virtual space;
[0102] In this example, organ features represent the differences between this organ and other organs; they are distinguishable characteristics.
[0103] In this example, the feature filtering network represents a simulation tool used to filter simulation results for different organs;
[0104] In this example, the current feature represents the working characteristics of the target organ at the current moment. For example, the working characteristic of the heart at the current moment is 70 beats per minute.
[0105] In this example, organ sleep characteristics refer to the features exhibited by an organ during different sleep stages in humans.
[0106] In this example, co-sleep characteristics represent the user's sleep characteristics under the coordination of different target organs.
[0107] The working principle and beneficial effects of the above technical solution are as follows: In order to analyze the user's sleep state in greater depth, a user model is first established in a virtual space based on the user's physical health status. Then, a sleep simulation is performed on the user model, and the simulation results are input into a feature filtering network for differentiation and filtering to obtain the sub-simulation results corresponding to each target organ. In this way, the current features of each target organ can be obtained, thereby determining the organ state of each target organ at that moment, and thus obtaining the user's sleep state.
[0108] Example 6
[0109] Based on Embodiment 2, the system for collecting and analyzing sleep states through wearable devices further includes:
[0110] The pulse analysis module is used to establish an estimation model based on preset TCM pulse diagnosis knowledge, acquire and input the wrist movement data into the estimation model to perform sleep estimation, and obtain the estimation result;
[0111] Based on the estimation results, the user's sleep level is determined and transmitted to a preset terminal for display.
[0112] The working principle and beneficial effects of the above technical solution are as follows: By estimating the user's sleep level through traditional Chinese medicine pulse diagnosis, the user's sleep can be analyzed in a comprehensive manner, achieving the goal of joint detection by multiple methods and improving the accuracy of sleep detection.
[0113] Example 7
[0114] This invention provides a method for analyzing sleep states by collecting data through wearable devices, such as... Figure 3 As shown, it includes:
[0115] S1: Collect the user's raw pulse data through a wearable device, and adjust the raw pulse data according to the user's skin color and ambient light to obtain raw waveform data;
[0116] S2: Analyze the original waveform data to obtain the user's basic body parameters, and analyze the user's physical health status based on the basic body parameters;
[0117] S3: Based on the physical health status, establish the organ status corresponding to each target organ of the user, and obtain the user's sleep status at the same time based on the changes in the organ status.
[0118] In this example, the sampling rate of the pulse wave data was increased when collecting the user's raw pulse data, thereby obtaining the best raw pulse data;
[0119] In this example, the original waveform data can be PPG data;
[0120] In this example, the basic body parameters include the user's heart rate, blood pressure, blood oxygen, and heart rate variability.
[0121] In this example, physical health status includes three types: healthy status, sub-healthy status, and unhealthy status.
[0122] In this example, sleep states include: wakefulness, rapid eye movement (REM) sleep, and non-rapid eye movement (NREM) sleep. REM sleep is also known as REM sleep, and NREM sleep is also known as NREM sleep. When a human falls asleep, REM sleep and NREM sleep alternate.
[0123] In this example, the target organ could be the heart, lungs, or brain;
[0124] In this example, organ status refers to the working status of different body organs in the user's current physical health state.
[0125] The working principle and beneficial effects of the above technical solution are as follows: In order to detect the user's sleep status in real time, the user's raw pulse data is first collected. During the collection process, the influence of the external environment is eliminated to obtain the raw waveform data. Then, the user's basic body parameters can be obtained, thereby analyzing the user's physical health status and establishing the organ status corresponding to each target organ. Finally, the user's sleep status at the same time can be obtained. In this way, the user's organ sleep is analyzed to comprehensively judge the user's sleep status, thereby reducing the error of sleep detection, improving the quality of sleep detection of smart devices, and allowing users to understand their sleep status after waking up the next day.
[0126] Example 8
[0127] Based on Example 7, the method for collecting and analyzing sleep states through wearable devices, S1 includes:
[0128] S11: Collect the user's raw pulse data;
[0129] S12: Collect the user's skin color, establish a first external influence factor based on the skin color, collect the external light of the user's environment, and establish a second external influence factor based on the external light.
[0130] S13: Correct the original pulse data based on the first external influence factor and the second external influence factor, and input the corrected original pulse data into a rectangular coordinate system to obtain the user's original waveform data.
[0131] In this example, the darker the user's skin tone, the less impact it has on the raw pulse data; the weaker the ambient light, the less impact it has on the raw pulse data.
[0132] In this example, the first external influence factor represents the impact of user skin color on the accuracy of data collection by the data collection unit. The greater the influence, the lower the accuracy, and vice versa.
[0133] In this example, the second external influence factor represents the impact of external light intensity on the data acquisition accuracy of the data acquisition unit. The greater the influence, the lower the accuracy, and vice versa.
[0134] In this example, because the wearable device collects the user's raw pulse data in real time, the raw waveform data is updated in real time.
[0135] The working principle and beneficial effects of the above technical solution are as follows: By collecting the user's original pulse data and correcting the original pulse data according to the actual situation, the corrected original pulse data is then input into the teaching coordinate system to obtain the user's original waveform data. In this way, the user can not only understand his / her pulse data in real time, but also lay the foundation for subsequent sleep detection.
[0136] Example 9
[0137] Based on Example 7, the method for collecting and analyzing sleep states through wearable devices, S2 includes:
[0138] S21: The original waveform data is regarded as initial data, and the initial data is sorted in time order to obtain a first data sequence. The first data sequence is sampled at a preset time interval to obtain multiple target initial data, and the weighted average of the multiple target initial data is obtained.
[0139] S22: The first data sequence is smoothed using the weighted average to obtain the second data sequence. A waveform diagram is drawn based on the second data sequence. When there are waveform breakpoints in the waveform diagram, the breakpoint target data corresponding to each waveform breakpoint in the second data sequence is obtained. The breakpoint target data is interpolated to obtain the third data sequence.
[0140] S23: Parse the third data sequence to obtain the user's basic physical parameters, and analyze the user's physical health status based on the basic physical parameters.
[0141] In this example, since each initial data point has a collection time, the initial data are sorted in chronological order.
[0142] In this example, the first data sequence list is the result of sorting the initial data in chronological order;
[0143] In this example, the preset time interval is 10 seconds;
[0144] In this example, the target initial data refers to the data extracted from the first data sequence, and the time interval between adjacent target initial data is a preset time interval;
[0145] In this example, the second data sequence represents the result of smoothing the first data sequence using a weighted average;
[0146] In this example, smoothing can remove interfering data from the first data sequence;
[0147] In this example, the waveform diagram represents the waveform formed by connecting all the data in the second data sequence in chronological order;
[0148] In this example, a waveform breakpoint represents a point on the second waveform where the data is 0 and none of the adjacent data are 0;
[0149] In this example, the third data sequence represents the result of interpolating the second data sequence;
[0150] In this example, interpolation can correct data breaks in the second data sequence.
[0151] The working principle and beneficial effects of the above technical solution are as follows: In order to accurately analyze the user's physical health status, the original waveform is first regarded as the initial data, and then sorted according to time to obtain the first data sequence. Then, data sampling is performed in the first data sequence to obtain a weighted average value that can be used for smoothing. This weighted average value is then used to smooth the first data sequence, and a waveform graph is drawn. Based on the correspondence between the waveform breakpoints on the waveform graph and the data in the data sequence, the breakpoint target data is eliminated using the difference method to obtain the third sequence. Finally, the user's basic physical parameters can be obtained by parsing the third data sequence, thereby obtaining the user's physical health status.
[0152] Example 10
[0153] Based on Example 7, the method for analyzing sleep states by collecting data through a wearable device, S3 includes:
[0154] S31: Based on the physical health status, establish a corresponding user model in a preset virtual space. When the model attribute of the user model belongs to a preset attribute, input the user model into a preset sleep environment to perform sleep simulation and obtain the simulation result.
[0155] S32: Based on the organ characteristics corresponding to each target organ, establish a feature filtering network, input the simulation results into the feature filtering network for filtering, and obtain the sub-simulation results corresponding to each target organ;
[0156] S33: Analyze the corresponding sub-simulation results to obtain the current features of each target organ, analyze the organ sleep features of each organ based on the current features, and determine the organ state of the corresponding target organ based on the organ sleep features.
[0157] S34: Based on the organ states of different target organs at the same time, obtain the common sleep characteristics of different target organs at that time, and generate the sleep state of the user at that time.
[0158] In this example, the default attribute represents the sleep attribute;
[0159] In this example, the user model's attributes include three categories: movement attributes, sedentary attributes, and sleep attributes.
[0160] In this example, sleep simulation means simulating the user's sleep process in a virtual space;
[0161] In this example, organ features represent the differences between this organ and other organs; they are distinguishable features.
[0162] In this example, the feature filtering network represents a simulation tool used to filter simulation results for different organs;
[0163] In this example, the current feature represents the working characteristics of the target organ at the current moment. For example, the working characteristic of the heart at the current moment is 70 beats per minute.
[0164] In this example, organ sleep characteristics refer to the features exhibited by an organ during different sleep stages in humans.
[0165] In this example, co-sleep characteristics refer to the user's sleep characteristics under the coordination of different target organs.
[0166] The working principle and beneficial effects of the above technical solution are as follows: In order to analyze the user's sleep state in greater depth, a user model is first established in a virtual space based on the user's physical health status. Then, a sleep simulation is performed on the user model, and the simulation results are input into a feature filtering network for differentiation and filtering to obtain the sub-simulation results corresponding to each target organ. In this way, the current features of each target organ can be obtained, thereby determining the organ state of each target organ at that moment, and thus obtaining the user's sleep state.
[0167] Example 11
[0168] Based on Example 9, the method for collecting and analyzing sleep states through wearable devices includes:
[0169] Step a: Obtain the second data sequence and the target initial data;
[0170] Step b: Sort the initial data of each target according to the order of their positions in the second data sequence to obtain the initial data sequence of the target;
[0171] Step c: Map the target initial data sequence to the third data sequence to obtain the mapping data corresponding to each target initial data sequence;
[0172] Step d: Calculate the user's current heart rate index according to formula (1);
[0173]
[0174] Where T represents the user's current heart rate index, C represents the preset time interval and sampling interval, and y n Let m represent the nth mapping data. n Let [a, b] represent the initial data for the nth target, where [a, b] represents the range of normal human heart rate per unit time, a represents the lower limit of normal human heart rate per unit time, and b represents the upper limit of normal human heart rate per unit time.
[0175] Step e: Obtain the calculation result of formula (1) to get the current heart rate index of the user. When the current heart rate index is within the preset heart rate index range, it is determined that the current heart rate of the user is normal.
[0176] The working principle and beneficial effects of the above technical solution are as follows: In order to further improve the practicality of smart wearable devices, the user's heart rate is analyzed based on the user's original waveform data, so that the user can understand his / her physical condition in real time, and can also remind the user to pay attention to his / her health and protect the user.
[0177] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.
Claims
1. A system for collecting and analyzing sleep states using wearable devices, characterized in that, include: The acquisition module is used to acquire the user's raw pulse data through the wearable device, and adjust the raw pulse data according to the user's skin color and the ambient light to obtain raw waveform data; The analysis module is used to parse the raw waveform data to obtain the user's basic body parameters, and analyze the user's physical health status based on the basic body parameters; The determination module is used to establish the organ status corresponding to each target organ of the user based on the physical health status, and to obtain the user's sleep status at the same time based on the changes in the organ status. The determining module includes: The sleep simulation unit is used to build a corresponding user model in a preset virtual space based on the physical health status. When the model attributes of the user model belong to preset attributes, the user model is input into a preset sleep environment to perform sleep simulation and obtain simulation results. The feature analysis unit is used to establish a feature filtering network based on the organ features corresponding to each target organ, and input the simulation results into the feature filtering network for filtering to obtain the sub-simulation results corresponding to each target organ. The sleep analysis unit is used to parse the corresponding sub-simulation results to obtain the current features of each target organ, analyze the organ sleep features of each organ based on the current features, and determine the organ state of the corresponding target organ based on the organ sleep features. The sleep statistics unit is used to obtain the common sleep characteristics of different target organs at the same time based on the organ states of different target organs at the same time, and generate the user's sleep state at that time.
2. The system for collecting and analyzing sleep states via wearable devices as described in claim 1, characterized in that: The wearable device is equipped with a wrist motion sensor, which is used to acquire the user's wrist motion data in real time, generate a wrist motion line graph corresponding to the user at different times, and transmit it to a designated terminal for display. The wearable device is also equipped with a PPG sensor, which is used to acquire the user's raw pulse data and transmit the raw pulse data to the acquisition module.
3. The system for collecting and analyzing sleep states via wearable devices as described in claim 1, characterized in that, The acquisition module includes: The data acquisition unit is used to collect the user's raw pulse data through wearable devices; A light acquisition unit is used to acquire the user's skin color and establish a first external influence factor based on the skin color; and to acquire the external light in the user's environment and establish a second external influence factor based on the external light. The data correction unit is used to correct the original pulse data based on the first external influence factor and the second external influence factor, and input the corrected original pulse data into a rectangular coordinate system to obtain the user's original waveform data.
4. The system for collecting and analyzing sleep states via wearable devices as described in claim 1, characterized in that, The analysis module includes: The data analysis unit is used to treat the original waveform data as initial data, sort the initial data in chronological order to obtain a first data sequence, sample the first data sequence at a preset time interval to obtain multiple target initial data, and obtain a weighted average of the multiple target initial data. The data processing unit is used to smooth the first data sequence using the weighted average to obtain a second data sequence, draw a waveform diagram based on the second data sequence, and when there are waveform breakpoints in the waveform diagram, obtain the breakpoint target data corresponding to each waveform breakpoint in the second data sequence, and perform interpolation processing on the breakpoint target data to obtain a third data sequence. The data determination unit is used to parse the third data sequence to obtain the user's basic physical parameters, and analyze the user's physical health status based on the basic physical parameters.
5. The system for collecting and analyzing sleep states via wearable devices as described in claim 2, characterized in that, Also includes: The pulse analysis module is used to establish an estimation model based on preset TCM pulse diagnosis knowledge, acquire and input the wrist movement data into the estimation model to perform sleep estimation, and obtain the estimation result; Based on the estimation results, the user's sleep level is determined and transmitted to a preset terminal for display.
6. A method for collecting and analyzing sleep states using wearable devices, characterized in that, include: S1: Collect the user's raw pulse data through a wearable device, and adjust the raw pulse data according to the user's skin color and ambient light to obtain raw waveform data; S2: Analyze the original waveform data to obtain the user's basic body parameters, and analyze the user's physical health status based on the basic body parameters; S3: Based on the physical health status, establish the organ status corresponding to each target organ of the user, and obtain the user's sleep status at the same time based on the changes in the organ status; S3 includes: S31: Based on the physical health status, establish a corresponding user model in a preset virtual space. When the model attribute of the user model belongs to a preset attribute, input the user model into a preset sleep environment to perform sleep simulation and obtain the simulation result. S32: Based on the organ characteristics corresponding to each target organ, establish a feature filtering network, input the simulation results into the feature filtering network for filtering, and obtain the sub-simulation results corresponding to each target organ; S33: Analyze the corresponding sub-simulation results to obtain the current features of each target organ, analyze the organ sleep features of each organ based on the current features, and determine the organ state of the corresponding target organ based on the organ sleep features. S34: Based on the organ states of different target organs at the same time, obtain the common sleep characteristics of different target organs at that time, and generate the sleep state of the user at that time.
7. The method for collecting and analyzing sleep states using wearable devices as described in claim 6, characterized in that, S1 includes: S11: Collect the user's raw pulse data; S12: Collect the user's skin color, establish a first external influence factor based on the skin color, collect the external light of the user's environment, and establish a second external influence factor based on the external light. S13: Correct the original pulse data based on the first external influence factor and the second external influence factor, and input the corrected original pulse data into a rectangular coordinate system to obtain the user's original waveform data.
8. A method for analyzing sleep states by collecting data through a wearable device as described in claim 6, characterized in that, S2 include: S21: The original waveform data is regarded as initial data, and the initial data is sorted in time order to obtain a first data sequence. The first data sequence is sampled at a preset time interval to obtain multiple target initial data, and the weighted average of the multiple target initial data is obtained. S22: The first data sequence is smoothed using the weighted average to obtain the second data sequence. A waveform diagram is drawn based on the second data sequence. When there are waveform breakpoints in the waveform diagram, the breakpoint target data corresponding to each waveform breakpoint in the second data sequence is obtained. The breakpoint target data is interpolated to obtain the third data sequence. S23: Parse the third data sequence to obtain the user's basic physical parameters, and analyze the user's physical health status based on the basic physical parameters.