Sleep monitoring system and method

Abstract

The embodiment of the invention provides a sleep monitoring system and method, and is applied to the technical field of intelligent sensing and medical health. The system comprises a pulse measurement bracelet based on a flexible piezoelectric electret sensor and terminal equipment, the pulse measurement bracelet is used for collecting pulse signals of a user in a sleep period to obtain pulse signal data and transmitting the pulse signal data to the terminal equipment; and the terminal equipment performs data cleaning and feature extraction on the pulse signal data to obtain pulse signal features, inputs the pulse signal features into a pre-trained sleep monitoring model, processes the pulse signal features to obtain sleep features of the user, and then displays the sleep features. Obviously, the system can detect the sleep condition of the user based on the pulse signal, assess the sleep quality and improve the sleep quality of the user, and meanwhile has the advantages of being simple in structure, convenient to use, comfortable to wear, low in cost and friendly in sleep.

Description

Technical Field

[0001] The present invention relates to the field of intelligent sensing and medical health technology, and in particular to a sleep monitoring system and method. Background Art

[0002] Sleep quality can reflect many potential diseases of the human body and is closely related to many physiological and psychological indicators. In addition to physical and mental health, sleep quality is directly related to the mental state of the next day. A high-quality sleep is very helpful for improving work efficiency, and sleep quality is inseparable from lifestyle habits. A healthy body is inseparable from healthy lifestyle habits, and even more inseparable from healthy sleep conditions.

[0003] There are many sleep detection systems available today, and their technologies and principles vary. Traditional sleep detection systems mainly include PPG-based smart watches or bracelets, and their technology requires green light to flash during measurement, which causes great trouble for people who are photosensitive during sleep. Moreover, as a smart watch with complex functions, its size and weight are a burden for people who need to wear it for sleep detection, not to mention issues such as battery life.

[0004] Therefore, how to provide a sleep monitoring system that is simple in structure, easy to use, comfortable to wear, low in cost and sleep-friendly is a technical problem that needs to be urgently solved by those skilled in the art. Summary of the invention

[0005] In a first aspect, an embodiment of the present invention provides a sleep monitoring system, the system comprising: a pulse measurement bracelet based on a flexible piezoelectric electret sensor, and a terminal device;

[0006] The pulse measurement bracelet is used to collect the pulse signal of the user during sleep, obtain pulse signal data, and transmit the pulse signal data to the terminal device;

[0007] The terminal device is used to clean and extract features of the pulse signal data to obtain pulse signal features, and input the pulse signal features into a pre-trained sleep monitoring model. The sleep monitoring model processes the pulse signal features to obtain the user's sleep characteristics, and then displays the sleep characteristics.

[0008] In some implementations of the first aspect, the pulse measurement bracelet includes: a signal acquisition unit and a signal transmission unit; the terminal device includes: a signal preprocessing unit, an intelligent computing unit, and a result display unit;

[0009] The signal acquisition unit is used to collect the pulse signal of the user to obtain pulse signal data;

[0010] The signal transmission unit is used to transmit the pulse signal data to the signal preprocessing unit;

[0011] The signal preprocessing unit is used to perform data cleaning and feature extraction on the pulse signal data to obtain pulse signal features;

[0012] The intelligent computing unit is used to input the pulse signal characteristics into a pre-trained sleep monitoring model, and the sleep monitoring model processes the pulse signal characteristics to obtain the user's sleep characteristics;

[0013] The result display unit is used to display sleep characteristics.

[0014] In some implementations of the first aspect, the result display unit is further configured to display sleep guidance suggestions matching the sleep characteristics.

[0015] In some implementations of the first aspect, the signal acquisition unit is composed of a flexible piezoelectric electret sensor and a nylon canvas material covering the surface of the flexible piezoelectric electret sensor.

[0016] In some possible implementations of the first aspect, the signal transmission unit is composed of a Bluetooth transmission module and a microcircuit, and the Bluetooth transmission module and the microcircuit are packaged on the same circuit board; the Bluetooth transmission module refers to a basic circuit set of a chip with integrated Bluetooth function; the microcircuit includes a battery, a battery charging and discharging element and circuit, and a signal temporary storage element and circuit, which are used to power the signal transmission unit and the signal acquisition unit.

[0017] In some implementations of the first aspect, the signal transmission unit is encapsulated in a plastic housing and fixedly connected to the signal acquisition unit.

[0018] In some implementations of the first aspect, the sleep monitoring model is trained by the following steps:

[0019] Obtain a pre-training data set, the pre-training data set includes a plurality of samples and their corresponding labels; the samples include pulse signal features of the subject during sleep; the labels include sleep features of the subject during sleep;

[0020] The initial sleep monitoring model is trained according to the pre-training data set to obtain a sleep monitoring model.

[0021] In some implementations of the first aspect, the pre-training dataset is generated by the following steps:

[0022] Obtaining a pulse signal public data set and a pulse signal offline collection data set; the data in the pulse signal public data set and the pulse signal offline collection data set include pulse signal data of the subject during sleep and PSG polysomnography data;

[0023] Performing data cleaning and feature extraction on the pulse signal data of the subject during sleep to obtain the pulse signal features of the subject during sleep;

[0024] The sleep stages of the subjects' PSG polysomnogram data during sleep were annotated to obtain the subjects' sleep characteristics during sleep;

[0025] Samples are generated according to the pulse signal characteristics of the subjects during sleep, and corresponding labels are generated according to the sleep characteristics of the subjects during sleep, so as to generate a pre-training data set.

[0026] In some implementations of the first aspect, the sleep monitoring model is a random forest.

[0027] In a second aspect, an embodiment of the present invention provides a sleep monitoring method, which is applied to the system as described above, and includes:

[0028] The pulse measurement bracelet collects the pulse signal of the user during sleep, obtains pulse signal data, and transmits the pulse signal data to the terminal device;

[0029] The terminal device performs data cleaning and feature extraction on the pulse signal data to obtain the pulse signal characteristics, and inputs the pulse signal characteristics into a pre-trained sleep monitoring model. The sleep monitoring model processes the pulse signal characteristics to obtain the user's sleep characteristics, and then displays the sleep characteristics.

[0030] In an embodiment of the present invention, a sleep monitoring system and method are provided. The sleep monitoring system includes: a pulse measurement bracelet with a sensor made of a new material (flexible piezoelectric electret) and a terminal device. During sleep monitoring, the user only needs to wear the pulse measurement bracelet on the wrist, and the pulse measurement bracelet will automatically record the user's pulse signal data and send it to the terminal device for processing to obtain the user's sleep characteristics, and then display it. Compared with the prior art, the present invention can detect the user's sleep condition based on the pulse signal, evaluate the sleep quality, and improve the user's sleep quality. At the same time, it has the advantages of simple structure, easy use, comfortable wearing, low cost and sleep-friendly.

[0031] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are provided for a better understanding of the present invention and do not constitute a limitation of the present invention. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0033] Figure 1 A schematic diagram of the structure of a sleep monitoring system provided by an embodiment of the present invention is shown;

[0034] Figure 2 A schematic structural diagram of a flexible piezoelectric electret sensor provided by an embodiment of the present invention is shown;

[0035] Figure 3 A schematic diagram of an example of a sleep monitoring system provided by an embodiment of the present invention is shown;

[0036] Figure 4 A flow chart of a sleep monitoring method provided by an embodiment of the present invention is shown.

[0037] Explanation of the accompanying drawings: Pulse measurement bracelet based on flexible piezoelectric electret sensor (also known as sleep monitoring bracelet based on flexible piezoelectric electret sensor) 1, terminal device 2 (such as mobile phone, tablet computer), signal acquisition unit 3, signal transmission unit 4, signal preprocessing unit 5, intelligent computing unit 6, result display unit 7, metal electrode 8, piezoelectric electret film 9, wire 10, data processing mechanism 11, flexible piezoelectric electret sensor 12, nylon canvas material 13, circuit button 14, Bluetooth transmission module 15, terminal device Bluetooth function 16, sleep characteristic chart 17. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] In addition, the term "and / or" in the present invention is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects before and after are in an "or" relationship.

[0040] In order to solve the technical problems in the background technology, the embodiments of the present invention provide a sleep monitoring system and method. During sleep monitoring, the user only needs to wear the pulse measurement bracelet on the wrist, and the pulse measurement bracelet will automatically record the user's pulse signal data and send it to the terminal device for processing to obtain the user's sleep characteristics, and then display it.

[0041] Compared with the prior art, the present invention can detect the user's sleeping condition based on the pulse signal, evaluate the sleep quality, and improve the user's sleep quality. At the same time, it has the advantages of simple structure, easy use, comfortable wearing, low cost and sleep-friendly.

[0042] A sleep monitoring system and method provided by an embodiment of the present invention will be described in detail below with reference to the accompanying drawings through specific embodiments.

[0043] Figure 1 FIG. 4 shows a schematic diagram of a sleep monitoring system provided by an embodiment of the present invention. Figure 1 As shown, the sleep monitoring system may include: a sleep monitoring bracelet and a pulse measurement bracelet 1 based on a flexible piezoelectric electret sensor, and a terminal device 2.

[0044] The pulse measurement bracelet 1 is used to collect the pulse signal of the user during sleep, obtain pulse signal data, and transmit the pulse signal data to the terminal device 2.

[0045] Terminal device 2 is used to perform data cleaning and feature extraction on the pulse signal data to obtain pulse signal features, and input the pulse signal features into a pre-trained sleep monitoring model. The sleep monitoring model processes the pulse signal features to obtain the user's sleep characteristics, and then displays the sleep characteristics and their matching sleep guidance suggestions.

[0046] Furthermore, if Figure 1 As shown, the pulse measurement bracelet 1 may include: a signal acquisition unit 3, a signal transmission unit 4; the terminal device 2 may include: a signal preprocessing unit 5, an intelligent calculation unit 6, and a result display unit 7, wherein each unit of the terminal device 2 is encapsulated in the APP.

[0047] The signal acquisition unit 3 is used to collect the pulse signal of the user to obtain pulse signal data.

[0048] The signal transmission unit 4 is used to transmit the pulse signal data to the signal preprocessing unit 5 .

[0049] The signal preprocessing unit 5 is used to perform data cleaning and feature extraction on the pulse signal data to obtain pulse signal features.

[0050] The intelligent operation unit 6 is used to input the pulse signal characteristics into the pre-trained sleep monitoring model, and the sleep monitoring model processes the pulse signal characteristics to obtain the user's sleep characteristics.

[0051] The result display unit 7 is used to display the sleep characteristics and the matching sleep guidance suggestions.

[0052] Figure 2 FIG. 4 shows a schematic structural diagram of a flexible piezoelectric electret sensor provided by an embodiment of the present invention. Figure 2 As shown, the flexible piezoelectric electret sensor may include: a metal electrode 8, a piezoelectric electret film 9, a wire 10, and a data processing mechanism 11.

[0053] The metal electrode 8 and the piezoelectric electret film 9 are the main parts of the flexible piezoelectric electret sensor. The piezoelectric electret film 9 is a porous film made of piezoelectric electret, which contains a large number of honeycomb holes inside. A large number of positive and negative charges are deposited on the upper and lower surfaces of the holes. When the film is subjected to pressure, the electrons on the surface of the holes move, and then form a potential difference on the metal electrode 8, thereby sensing pressure.

[0054] Optionally, the piezoelectric electret film 9 can be made of cross-linked polypropylene (IXPP) or other materials. After the piezoelectric electret film 9 is analyzed and calibrated in a three-dimensional force loading platform test system, it can be used in the present invention. Compared with other sensors, flexible piezoelectric electret sensors have many advantages, such as: (1) light weight and thin thickness, (2) soft and bendable, (3) high sensitivity, (4) sensitive to vertical forces, and (5) low material cost. The above advantages determine its advantages as a pulse measurement bracelet: easy to use, comfortable to wear, low cost and sleep-friendly.

[0055] Figure 3 FIG. 4 shows a schematic diagram of an example of a sleep monitoring system provided by an embodiment of the present invention. Figure 3 As shown, the left side is the pulse measurement bracelet 1, and the right side is the terminal device 2.

[0056] The signal acquisition unit 3 of the pulse measurement bracelet 1 is composed of a flexible piezoelectric electret sensor 12 and a nylon canvas material 13 covering the surface of the flexible piezoelectric electret sensor 12. It is worth noting that the nylon canvas material has the characteristics of strong durability, soft material, comfortable wearing, good air permeability, affordable price and easy cleaning, which can improve the comfort of wearing the pulse measurement bracelet. Furthermore, there is a Velcro (not shown in the figure) on the surface of the nylon canvas material for easy wearing.

[0057] The signal transmission unit 4 of the pulse measurement bracelet 1 is encapsulated in a plastic shell, here referred to as a circuit button 14, and is fixedly connected to the signal acquisition unit 3. It is composed of a Bluetooth transmission module 15 and a microcircuit (not shown in the figure), and the Bluetooth transmission module 15 and the microcircuit are encapsulated on the same circuit board; the Bluetooth transmission module 15 refers to a basic circuit set of a chip with integrated Bluetooth function, which can be used for wireless network communication; the microcircuit includes a battery, a battery charging and discharging element and circuit, a signal temporary storage element and circuit, and other necessary elements and circuits, which are used to power the signal transmission unit 4 and the signal acquisition unit 3.

[0058] The signal preprocessing unit 5, the intelligent computing unit 6 and the result display unit 7 of the terminal device are all encapsulated in the APP of the terminal device.

[0059] During sleep monitoring, the signal acquisition unit 3 of the pulse measurement bracelet 1 collects the pulse signal of the user during sleep to obtain pulse signal data, and then the signal transmission unit 4 transmits the pulse signal data to the signal preprocessing unit 5 of the terminal device 2 through the connection between the Bluetooth transmission module 15 and the terminal device Bluetooth module 16.

[0060] The signal preprocessing unit 5 performs data cleaning and feature extraction on the pulse signal data to obtain the pulse signal characteristics, that is, to detect whether the user's pulse measurement bracelet 1 has fallen off during sleep, and to detect whether there is any data loss. If the above situation occurs, the corresponding data needs to be eliminated and then feature extraction is performed to obtain the corresponding characteristics. Thereafter, the intelligent computing unit 6 inputs the pulse signal characteristics into a pre-trained sleep monitoring model, and the sleep monitoring model processes the pulse signal characteristics to obtain the user's sleep characteristics. Then, the result display unit 7 displays the sleep characteristics in the form of a sleep characteristic chart 17, and can also be combined with AI to give relevant sleep guidance suggestions.

[0061] It is worth noting that the above sleep monitoring model can be trained through the following steps:

[0062] A pre-training data set is obtained, wherein the pre-training data set includes a plurality of samples and corresponding labels; the samples include pulse signal features of the subject during sleep; and the labels include sleep features of the subject during sleep.

[0063] Exemplarily, a pulse signal public data set and a pulse signal offline collection data set may be obtained, wherein the data include pulse signal data of the subject during sleep and PSG polysomnography data.

[0064] Data cleaning and feature extraction are performed on the pulse signal data of the subject during sleep to obtain the pulse signal features of the subject during sleep. Optionally, the pulse signal features extracted here include but are not limited to:

[0065] (1) Standard deviation of the time interval between two adjacent normal heartbeats (SDNN)

[0066]

[0067] (2) The root mean square difference (RMSSD) between two adjacent peaks

[0068]

[0069] (3) Low frequency power (LF) (power in the range of 0.04-0.15 Hz)

[0070] LF=0.04Hz <Frequency<0.15Hz (3)

[0071] (4) High frequency power (HF) (power in the range of 0.15-0.40 Hz)

[0072] HF=0.15Hz <Frequency<0.40Hz (4)

[0073] (5) Low frequency / high frequency ratio (LF / HF)

[0074]

[0075] The sleep stages of the subjects' PSG polysomnogram data during sleep were annotated to obtain the subjects' sleep characteristics during sleep. Specifically, the sleep stages (N1, N2, N3, REM) were annotated and labeled with corresponding labels (0 for awake, 1 for N1, 2 for N2, 3 for N3, and 4 for REM).

[0076] Samples are generated according to the pulse signal characteristics of the subjects during sleep, and corresponding labels are generated according to the sleep characteristics of the subjects during sleep, so as to generate a pre-training data set.

[0077] The initial sleep monitoring model is trained according to the pre-training data set to obtain a sleep monitoring model.

[0078] As an example, the sleep monitoring model can be a random forest. Here, the pre-trained data set can be divided into a training set and a test set in a ratio of 4:1, and imported into the random forest trainer for training. Here, the parameters are selected as n_estimators=100, random_state=42. As the training progresses, the model will automatically evaluate the training results according to the test set and automatically adjust the relevant parameters according to the initial parameters to maximize the accuracy of the model. In this example, the model training parameters cannot be increased after reaching 96.3%, so this model is taken as the final model. It is understandable that the final model can be encapsulated, and there is no need to train it again for subsequent use. You only need to input the data required by the model into the model to output the user's sleep characteristics.

[0079] The above is an introduction to the system embodiment. The following is a method embodiment to further illustrate the solution of the present invention.

[0080] Figure 4 A flowchart of a sleep monitoring method provided by an embodiment of the present invention is shown. Figure 4 As shown, the sleep monitoring method can be applied to the above sleep monitoring system, including:

[0081] S410, the pulse measurement bracelet collects the pulse signal of the user during sleep to obtain pulse signal data, and transmits the pulse signal data to the terminal device;

[0082] S420, the terminal device performs data cleaning and feature extraction on the pulse signal data to obtain pulse signal features, and inputs the pulse signal features into a pre-trained sleep monitoring model. The sleep monitoring model processes the pulse signal features to obtain the user's sleep features, and then displays the sleep features and their matching sleep guidance suggestions.

[0083] The above steps are described below in conjunction with a specific embodiment, as shown below:

[0084] During sleep monitoring, the user wears a pulse measuring bracelet to sleep, and the signal acquisition unit of the pulse measuring bracelet collects the pulse signal of the user during sleep to obtain pulse signal data. Then, the signal transmission unit transmits the pulse signal data to the signal preprocessing unit of the terminal device through the connection between the Bluetooth transmission module and the Bluetooth module of the terminal device.

[0085] The signal preprocessing unit cleans and extracts features of the pulse signal data to obtain pulse signal features. The intelligent computing unit then inputs the pulse signal features into a pre-trained sleep monitoring model, which processes the pulse signal features to obtain the user's sleep characteristics. For example, the user's wakefulness time is 2 minutes, the N1 stage is 29 minutes, the N2 stage is 156 minutes, the N3 stage is 95 minutes, and the REM stage is 115 minutes, which means that the user has undergone multiple stage transitions during sleep. The result display unit then displays the sleep characteristics in the form of a sleep characteristics chart, and can also be combined with AI to give relevant sleep guidance suggestions.

[0086] In summary, according to the embodiments of the present invention, at least the following technical effects are achieved:

[0087] The present invention can detect the user's sleeping condition based on the pulse signal, evaluate the sleep quality, and improve the user's sleep quality. At the same time, it has the advantages of simple structure, easy use, comfortable wearing, low cost and sleep-friendly.

[0088] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the order of the actions described, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0089] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present invention can be achieved, and the present invention is not limited here.

[0090] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A sleep monitoring system, It is characterized in that The system comprises: a pulse measurement bracelet based on a flexible piezoelectric electret sensor and a terminal device; The pulse measurement bracelet is used to collect the pulse signal of the user during sleep, obtain pulse signal data, and transmit the pulse signal data to the terminal device; The terminal device is used to perform data cleaning and feature extraction on the pulse signal data to obtain pulse signal features, and input the pulse signal features into a pre-trained sleep monitoring model. The sleep monitoring model processes the pulse signal features to obtain the user's sleep features, and then displays the sleep features.

2. The system according to claim 1, It is characterized in that The pulse measurement bracelet includes: a signal acquisition unit and a signal transmission unit; the terminal device includes: a signal preprocessing unit, an intelligent computing unit, and a result display unit; The signal acquisition unit is used to collect the pulse signal of the user to obtain pulse signal data; The signal transmission unit is used to transmit the pulse signal data to the signal preprocessing unit; The signal preprocessing unit is used to perform data cleaning and feature extraction on the pulse signal data to obtain pulse signal features; The intelligent computing unit is used to input the pulse signal characteristics into a pre-trained sleep monitoring model, and the sleep monitoring model processes the pulse signal characteristics to obtain the sleep characteristics of the user; The result display unit is used to display the sleep characteristics.

3. The system according to claim 2, It is characterized in that The result display unit is also used to display sleep guidance suggestions matching the sleep characteristics.

4. The system according to claim 2, It is characterized in that The signal acquisition unit is composed of the flexible piezoelectric electret sensor and a nylon canvas material covering the surface of the flexible piezoelectric electret sensor.

5. The system according to claim 2, It is characterized in that The signal transmission unit is composed of a Bluetooth transmission module and a microcircuit, and the Bluetooth transmission module and the microcircuit are packaged on the same circuit board; the Bluetooth transmission module refers to a basic circuit set of a chip with integrated Bluetooth function; the microcircuit includes a battery, a battery charging and discharging element and circuit, and a signal temporary storage element and circuit, which are used to power the signal transmission unit and the signal acquisition unit.

6. The system according to claim 5, It is characterized in that The signal transmission unit is encapsulated in a plastic shell and fixedly connected to the signal acquisition unit.

7. The system according to any one of claims 1 to 6, It is characterized in that The sleep monitoring model is trained by the following steps: Acquire a pre-training data set, the pre-training data set comprising a plurality of samples and their corresponding labels; the samples comprising pulse signal features of the subject during sleep; the labels comprising sleep features of the subject during sleep; The initial sleep monitoring model is trained according to the pre-training data set to obtain a sleep monitoring model.

8. The system according to claim 7, It is characterized in that The pre-training dataset is generated by the following steps: Acquire a pulse signal public data set and a pulse signal offline collection data set; the data in the pulse signal public data set and the pulse signal offline collection data set include pulse signal data of the subject during sleep and PSG polysomnography data; Performing data cleaning and feature extraction on the pulse signal data of the subject during sleep to obtain the pulse signal features of the subject during sleep; The sleep stages of the subjects' PSG polysomnogram data during sleep were annotated to obtain the subjects' sleep characteristics during sleep; Samples are generated according to the pulse signal characteristics of the subjects during sleep, and corresponding labels are generated according to the sleep characteristics of the subjects during sleep, so as to generate a pre-training data set.

9. The system according to claim 7, It is characterized in that The sleep monitoring model is a random forest.

10. A sleep monitoring method, It is characterized in that The method is applied to the system according to any one of claims 1 to 9, comprising: The pulse measurement bracelet collects the pulse signal of the user during sleep to obtain pulse signal data, and transmits the pulse signal data to the terminal device; The terminal device performs data cleaning and feature extraction on the pulse signal data to obtain pulse signal features, and inputs the pulse signal features into a pre-trained sleep monitoring model. The sleep monitoring model processes the pulse signal features to obtain the user's sleep features, and then displays the sleep features.

Images