Sleep quality evaluation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a sleep quality evaluation method and device, electronic equipment and a storage medium, and can obtain current sleep parameters of a target person under the condition that the target person is in a sleep state. And inputting the current sleep parameters, the exercise amount data of the target person in the pre-sleep preset time period and the current health condition data of the target person into a pre-trained neural network model for processing, so that the duration of a core sleep stage, the duration of a deep sleep stage and the duration of a rapid eye movement sleep stage can be determined. According to the method and the device, the duration ratio of the three sleep stages can be determined by combining the total sleep duration of the target person, so that the sleep quality of the target person can be determined, and the technical problem that the sleep quality of the user cannot be effectively evaluated in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the technical field of sleep quality assessment, and in particular to a sleep quality assessment method, device, electronic device and storage medium. Background Art

[0002] About one-third of a person's life is spent sleeping, and the quality of sleep is closely related to human health. Good sleep quality plays a vital role in maintaining a healthy state of the human body. On the contrary, when the quality of sleep is poor, the incidence of various diseases will increase. Specifically, insomnia can easily cause endocrine disorders, mental disorders, harm physical health, affect memory, cause depression, and even affect the nervous system and cause cardiovascular diseases. According to statistics, 35% of the population in my country suffer from insomnia, and 17% are in a more serious state. It can be seen that insomnia has become a common disease, which has seriously affected people's normal life and work.

[0003] Therefore, the inability to effectively evaluate the user's sleep quality has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The embodiments of the present application provide a sleep quality assessment method, device, electronic device, and storage medium, which can effectively assess the sleep quality of a user.

[0005] In a first aspect, an embodiment of the present application provides a method for evaluating sleep quality, comprising:

[0006] When the target person is in a sleeping state, obtaining the current sleep parameters of the target person; the sleep parameters include the following parameters: turning over frequency, heart rate and brain wave signal;

[0007] Input the current sleep parameters, the target person's exercise data in a preset time period before going to bed, and the target person's current health status data into a pre-trained neural network model for processing to determine the duration of the core sleep stage, the duration of the deep sleep stage, and the duration of the rapid eye movement sleep stage; wherein the neural network model is pre-trained by the historical data of the sleep parameters in the core sleep stage, the historical data of the sleep parameters in the deep sleep stage, the historical data of the sleep parameters in the rapid eye movement sleep stage, the historical exercise data of the target person in a preset time period before going to bed, and the historical health status data of the target person;

[0008] Determine the duration ratio of the core sleep stage, the duration ratio of the deep sleep stage, and the duration ratio of the rapid eye movement sleep stage according to the total sleep duration of the target person, the duration of the core sleep stage, the duration of the deep sleep stage, and the duration ratio of the rapid eye movement sleep stage;

[0009] The sleep quality of the target person is determined based on the total sleep duration of the target person, the duration ratio of the core sleep stage, the duration ratio of the deep sleep stage, and the duration ratio of the rapid eye movement sleep stage.

[0010] Optionally, determining the sleep quality of the target person according to the total sleep duration of the target person, the duration ratio of the core sleep stage, the duration ratio of the deep sleep stage, and the duration ratio of the rapid eye movement sleep stage includes:

[0011] Comparing the total sleep duration of the target person with a first preset duration to determine first sleep quality data;

[0012] Comparing the duration ratio of the core sleep stage with the first preset duration ratio to determine second sleep quality data;

[0013] Comparing the duration ratio of the deep sleep stage with the second preset duration ratio to determine third sleep quality data;

[0014] Comparing the duration ratio of the rapid eye movement sleep stage with a third preset duration ratio to determine fourth sleep quality data;

[0015] The sleep quality of the target person is determined according to the first sleep quality data, the second sleep quality data, the third sleep quality data, and the fourth sleep quality data.

[0016] Optionally, determining the sleep quality of the target person according to the first sleep quality data, the second sleep quality data, the third sleep quality data, and the fourth sleep quality data includes:

[0017] Multiplying the first sleep quality data by a preset first weight coefficient to obtain a first parameter;

[0018] Multiplying the second sleep quality data by a preset second weight coefficient to obtain a second parameter;

[0019] multiplying the third sleep quality data by a preset third weight coefficient to obtain a third parameter;

[0020] multiplying the fourth sleep quality data by a preset fourth weight coefficient to obtain a fourth parameter;

[0021] The first parameter, the second parameter, the third parameter and the fourth parameter are summed to determine the sleep quality of the target person.

[0022] Optionally, the neural network model is an LSTM neural network model.

[0023] Optionally, before or after obtaining the current sleep parameters of the target person, the method further includes: detecting the external environment condition where the target person is located;

[0024] After determining the sleep quality of the target person, the method further includes:

[0025] The sleep anti-interference ability of the target person is determined according to the external environment conditions and the sleep quality of the target person.

[0026] Optionally, the external environmental conditions include ambient temperature, ambient humidity, ambient noise level, and ambient visible light intensity.

[0027] Optionally, before or after obtaining the current sleep parameters of the target person, the method further includes: detecting the sleeping posture of the target person; the sleeping posture is a supine sleeping posture, a left side sleeping posture, a right side sleeping posture or a prone sleeping posture;

[0028] After determining the sleep quality of the target person according to the total sleep duration of the target person, the duration ratio of the core sleep stage, the duration ratio of the deep sleep stage, and the duration ratio of the rapid eye movement sleep stage, the method further includes:

[0029] Determining a first sleeping position with the highest sleep quality according to the sleep quality of the target person in various sleeping positions;

[0030] The first sleeping position is recommended to the target person.

[0031] In a second aspect, an embodiment of the present application provides a sleep quality assessment device, comprising:

[0032] An acquisition unit, used for acquiring current sleep parameters of the target person when the target person is in a sleeping state; the sleep parameters include the following parameters: turning over frequency, heart rate frequency and brain wave signal;

[0033] A first determination unit is used to input the current sleep parameters, the exercise data of the target person in a preset time period before going to bed, and the current health status data of the target person into a pre-trained neural network model for processing to determine the duration of the core sleep stage, the duration of the deep sleep stage, and the duration of the rapid eye movement sleep stage; wherein the neural network model is pre-trained by the historical data of the sleep parameters in the core sleep stage, the historical data of the sleep parameters in the deep sleep stage, the historical data of the sleep parameters in the rapid eye movement sleep stage, the historical exercise data of the target person in a preset time period before going to bed, and the historical health status data of the target person;

[0034] A second determining unit is used to determine the duration ratio of the core sleep stage, the duration ratio of the deep sleep stage, and the duration ratio of the rapid eye movement sleep stage according to the total sleep duration of the target person, the duration of the core sleep stage, the duration of the deep sleep stage, and the duration of the rapid eye movement sleep stage;

[0035] The third determination unit is used to determine the sleep quality of the target person according to the total sleep time of the target person, the proportion of the core sleep stage, the proportion of the deep sleep stage and the proportion of the rapid eye movement sleep stage.

[0036] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device implements the aforementioned sleep quality assessment method.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the aforementioned sleep quality assessment method when executed by a processor.

[0038] The embodiments of the present application provide a sleep quality assessment method, device, electronic device and storage medium, which can obtain the current sleep parameters of the target person when the target person is in a sleeping state. The current sleep parameters, the target person's exercise data in a preset period before going to bed, and the target person's current health status data are input into a pre-trained neural network model for processing, and the duration of the core sleep stage, the duration of the deep sleep stage, and the duration of the rapid eye movement sleep stage can be determined. Combined with the total sleep duration of the target person, the duration ratio of the above three sleep stages can be determined, and then the sleep quality of the target person can be determined, which solves the technical problem that the user's sleep quality cannot be effectively assessed in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 A schematic diagram of a flow chart of a sleep quality assessment method provided in an embodiment of the present application;

[0041] Figure 2 A flow chart of a method for determining the sleep quality of a target person provided in an embodiment of the present application;

[0042] Figure 3 Another flowchart of a method for determining the sleep quality of a target person provided in an embodiment of the present application;

[0043] Figure 4 A schematic flow chart of a method for recommending sleeping positions provided in an embodiment of the present application;

[0044] Figure 5 A schematic diagram of the structure of a sleep quality assessment device provided in an embodiment of the present application;

[0045] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The term "and / or" in this article is a description of the association relationship of 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. The symbol " / " in this article indicates that the associated objects are in an or relationship, for example, A / B means A or B.

[0047] The terms "first" and "second" in the specification and claims herein are used to distinguish different objects rather than to describe a specific order of the objects. For example, a first response message and a second response message are used to distinguish different response messages rather than to describe a specific order of the response messages.

[0048] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0049] In the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more than two. For example, multiple processors means two or more processors, etc.; multiple elements means two or more elements, etc.

[0050] In a first aspect, an embodiment of the present application provides a method for evaluating sleep quality, which can be performed by a sleep quality evaluation device implemented by software and / or hardware, see Figure 1 , the method may include:

[0051] S11, when the target person is in a sleeping state, obtaining the current sleep parameters of the target person; the sleep parameters include the following parameters: turning over frequency, heart rate frequency and brain wave signal.

[0052] In this step, the target person is the person to be detected, and specifically can be any user. The embodiment of the present application does not impose any restriction on the category of the user.

[0053] The sleep quality assessment device may include a pillow with a built-in pressure sensor, and the pressure value detected by the pressure sensor can be used to detect whether the target person has entered a sleeping state. Specifically, when the pressure value is greater than a preset threshold, it indicates that the user's head is located on the pillow and the user is in a sleeping state. When the pressure value is less than the preset threshold, it indicates that the user's head is not located on the pillow and the user is not in a sleeping state. By determining the time when the target person begins to enter a sleeping state and the time when the target person ends the sleeping state, the specific time period when the target person is in a sleeping state can be determined.

[0054] For example, the user falls asleep at 10 pm and ends sleeping at 6 am the next day. It can be determined that the user is asleep from 10 pm to the next morning, which lasts for 8 hours.

[0055] After the target person falls asleep, the turning over action of the target person can be determined based on the pressure change detected by the pressure sensor. The turning over frequency of the target person, that is, the turning over times of the target person in a unit time, can be determined by counting the number of turning over actions of the target person in a preset period of time (e.g., 3 minutes).

[0056] In addition, when the target person is in a sleeping state, the heart rate of the target person can be detected by a related device (such as a heart rate detector). Similarly, the brain wave signal of the target person can be detected by a brain wave detector.

[0057] It should be noted that the embodiment of the present application can continuously obtain the current sleep parameters of the target person according to a preset frequency. Specifically, the above three sleep parameters can be obtained according to three different preset frequencies.

[0058] S12, inputting the current sleep parameters, the exercise data of the target person within a preset period before going to bed, and the current health status data of the target person into a pre-trained neural network model for processing to determine the duration of the core sleep stage, the duration of the deep sleep stage, and the duration of the rapid eye movement sleep stage; wherein the neural network model is pre-trained by the historical data of the sleep parameters of the core sleep stage, the historical data of the sleep parameters of the deep sleep stage, the historical data of the sleep parameters of the rapid eye movement sleep stage, the historical exercise data of the target person, and the historical health status data of the target person.

[0059] In this step, the total sleep duration may include different sleep stages, for example, the total sleep duration may include three sleep stages, core sleep (also known as light sleep) stage, deep sleep stage and rapid eye movement sleep stage. Before entering the sleep state is the sleep latency stage, and the brain wave signals of the target person have different characteristics in different sleep stages.

[0060] Specifically, the sleep latency stage is the transition period before entering sleep, when the brain begins to relax and the body gradually enters a drowsy state. In the core sleep stage, the brain will occasionally react to try to stay awake, but overall the user has begun to fall asleep. In the deep sleep stage, the user loses consciousness, physiological activity is reduced to the lowest stage, and the brain and body get the deepest rest. In the REM sleep stage, the user's brain is very active and may dream.

[0061] Brainwave signals are bioelectric signals generated when information is transmitted between neuronal cells. This signal can accurately transmit brain activity information. In different sleep stages, the user's brainwaves have different characteristics. The use of an electroencephalograph can monitor and record the target person's brainwave signals. The five common brainwave signals are alpha waves, theta waves, delta waves, sleep spindles, and K complex waves. Specifically, alpha waves are a type of brainwave that can occur between alertness and sleep. They are the main brainwave patterns produced when a person is drowsy and transitions from a wakeful state to a sleeping state. They last in the early stages of sleep until they are replaced by slower theta waves. Abnormalities in alpha waves may cause people to suffer from insomnia and feel sleepy during the day. Theta waves appear when the target person is asleep or dreaming, but they do not appear in the deepest stages of sleep. They may occur when the target person is asleep, or in light sleep before the target person wakes up, representing creativity, insight, deep relaxation, dreaming, deep meditation, and decreased consciousness. Delta waves are the slowest brainwaves recorded by humans and are associated with the deepest levels of relaxation and restorative sleep. If this fluctuation is suppressed, it can lead to a body that is not able to rejuvenate, a brain that is not able to rejuvenate, and poor sleep. Sleep spindles are an indicator of non-REM sleep, which includes core sleep and deep sleep. Individual sleep spindles typically last 0.5 to 3 seconds and occur every 3 to 6 seconds. Sleep spindles are thought to play a role in brain plasticity, or the process of learning and consolidating new memories. During sleep, it may reduce our response to external stimuli while we sleep, helping to maintain the status quo of sleep. K-complexes are the longest and most distinctive of all brain waves, occurring approximately every 1 to 2 seconds. They are characterized by prominent negative sharp waves followed by a positive wave, which can be easily distinguished from an EEG. It represents an internal alert system that allows you to wake up when needed. K-complexes can be caused by sounds or other stimuli in the environment, such as touch or interruptions in breathing.

[0062] In this step, the target person's exercise data for a preset period of time (e.g., 4 hours) before going to bed can be obtained in advance. Specifically, a sports bracelet or smart watch can be used to monitor the calories consumed by the target person during the aforementioned preset period of time, and use it as exercise data. The accelerometer can also be worn on a specific part of the target person's body, such as the wrist, waist, etc., which can more accurately measure the intensity, frequency, and duration of physical activity, so that the target person's exercise data during the preset period can be calculated.

[0063] The health status data of the target person may be data of the target person's illness, for example, whether the target person has a cold. The identification code corresponding to the current illness of the target person may be input through the display interface in the sleep quality assessment device.

[0064] In the embodiment of the present application, an initial neural network model may be established before step S11, and the present application does not limit the specific type of the neural network model. Exemplarily, the neural network model may be a convolutional neural network model.

[0065] Sleep parameters will be different in different sleep stages of the target person. For example, when the target person is in the deep sleep stage, physiological activity is reduced to the lowest, and the target person's turning frequency and heart rate are at the lowest. Similarly, when the target person is in the core sleep stage or the rapid eye movement sleep stage, the target person's turning frequency and heart rate also have their own unique characteristics.

[0066] Similarly, when the target person is in different sleep stages, the target person's brain wave signals will also have different characteristics. Specifically, in the rapid eye movement sleep stage, the target person's brain wave signal frequency becomes faster and the amplitude becomes lower. In the target person's core sleep stage and deep sleep stage, the target person's brain wave signals also have their own unique characteristics.

[0067] The amount of activity of the target person in the preset time period before going to bed will also affect the heart rate and brain wave signal characteristics of the target person in each sleep stage. When the amount of activity of the target person in the preset time period before going to bed is different, the heart rate and brain wave signal of the target person will also be different in the same sleep stage. For example, when the amount of activity of the target person in the preset time period before going to bed is large, the heart rate of the target person will be higher in each sleep stage.

[0068] When the target person's health condition is different, the target person's heart rate and brain wave signal will also be different when they are in the same sleep stage. For example, when the target person has a cold, the inflammatory response and physical discomfort caused by the cold will stimulate the sympathetic nervous system and increase the heart rate. This makes the target person's heart rate increase to varying degrees when they are in each sleep stage compared to a healthy state.

[0069] Therefore, in the process of training the neural network model, the target person's sleep parameters can be counted in advance when the target person enters different sleep stages, and the target person's exercise data in the preset time period and the target person's health status data at that time can be obtained. The above data are the various historical data of the target person at that time. A historical data of the target person's exercise volume in a preset time period (for example, 4 hours), a historical data of the target person's health status, and a historical data of various sleep parameters of the corresponding target person in different sleep stages are used as a training sample data. According to this method, multiple training sample data can be obtained, and multiple training data in different training sample data can be partially the same, but not completely the same, so as to fully train the neural network model. Based on the above multiple training sample data, a training sample set is generated.

[0070] Then, each training sample in the training sample set is input into the neural network model in turn, and iterative training is performed until the training process is completed to obtain a trained neural network model. Exemplarily, the above initial neural network model can be trained using a loss function, or the neural network model can be determined to have completed training when the training reaches a preset number of iterations.

[0071] Specifically, when training the aforementioned neural network model, the historical data of the health status of the target person, the historical data of the amount of exercise of the target person in the preset time period before going to bed, and the historical data of various sleep parameters of the corresponding target person in different sleep stages are used as training sets. Therefore, after the current sleep parameters of the target person, the amount of exercise of the target person in the preset time period before going to bed, and the current health status data of the target person are input into the pre-trained neural network model for processing, the pre-trained neural network model can determine whether the target person enters core sleep according to the above input data, so as to determine the time when the target person enters core sleep. Similarly, the pre-trained neural network model can determine whether the target person enters deep sleep according to the above input data, so as to determine the time when the target person enters deep sleep. The pre-trained neural network model can determine whether the target person enters rapid eye movement sleep according to the above input data, so as to determine the time when the target person enters rapid eye movement sleep. Similarly, the pre-trained neural network model can determine the time when the target person ends core sleep, the time when deep sleep ends, and the time when rapid eye movement sleep ends, and then the duration of the above three sleep stages can be determined.

[0072] S13, determining the duration ratio of the core sleep stage, the duration ratio of the deep sleep stage, and the duration ratio of the rapid eye movement sleep stage according to the total sleep duration of the target person, the duration of the core sleep stage, the duration of the deep sleep stage, and the duration ratio of the rapid eye movement sleep stage.

[0073] In this step, the duration of the three sleep stages and the total sleep duration of the target person can be used to determine the proportion of the three sleep stages in the total sleep duration. For example, if the total sleep duration is 10 hours, the duration of deep sleep, core sleep, and REM sleep are 2 hours, 5 hours, and 3 hours, respectively, then the duration proportions of the three stages can be determined to be 20%, 50%, and 30%, respectively.

[0074] S14, determining the sleep quality of the target person according to the total sleep time of the target person, the duration ratio of the core sleep stage, the duration ratio of the deep sleep stage, and the duration ratio of the rapid eye movement sleep stage.

[0075] In this step, the target person's sleep quality depends on whether the sleep is sufficient and whether the duration of the three sleep stages is reasonable. Specifically, when the target person's total sleep duration is less than a specific value, the target person cannot get enough rest, which will reduce the sleep quality. When the duration of the three sleep stages is unreasonable, the sleep quality will also be reduced. Therefore, based on the target person's total sleep duration and the time proportion of the three sleep stages, the target person's sleep quality can be determined.

[0076] The embodiment of the present application provides a sleep quality assessment method, which can obtain the current sleep parameters of the target person when the target person is in a sleeping state. The current sleep parameters, the target person's exercise data in a preset period before going to bed, and the target person's current health status data are input into a pre-trained neural network model for processing, and the duration of the core sleep stage, the duration of the deep sleep stage, and the duration of the rapid eye movement sleep stage can be determined. Combined with the total sleep duration of the target person, the duration ratio of the above three sleep stages can be determined, and then the sleep quality of the target person can be determined, which solves the technical problem that the user's sleep quality cannot be effectively assessed in the prior art.

[0077] In some embodiments of the present application, Figure 2 As shown, determining the sleep quality of the target person according to the total sleep duration of the target person, the duration ratio of the core sleep stage, the duration ratio of the deep sleep stage, and the duration ratio of the rapid eye movement sleep stage (step S14) may include:

[0078] S141, comparing the total sleep duration of the target person with a first preset duration to determine first sleep quality data;

[0079] S142, comparing the duration ratio of the core sleep stage with the first preset duration ratio to determine second sleep quality data;

[0080] S143, comparing the duration ratio of the deep sleep stage with a second preset duration ratio to determine third sleep quality data;

[0081] S144, comparing the duration ratio of the rapid eye movement sleep stage with a third preset duration ratio to determine fourth sleep quality data;

[0082] S145: Determine the sleep quality of the target person according to the first sleep quality data, the second sleep quality data, the third sleep quality data, and the fourth sleep quality data.

[0083] In an embodiment of the present application, the total sleep duration of the target person can be compared with the first preset duration (for example, 8 hours) to determine whether the total sleep duration of the target person is sufficient, or whether the total sleep duration of the target person is too long. And according to the comparison result, a score can be performed to obtain the first sleep quality data. Among them, the first preset duration can be a reference value of sleep duration given by a medical institution for the target person. When the target person is a different user, the length of the first preset duration may not be equal, and the larger the first sleep quality data, the closer the total sleep duration of the target person is to the first preset duration. Exemplarily, the first preset duration can be 8 hours.

[0084] Similarly, the core sleep duration ratio can be compared with the first preset duration ratio to determine whether the target person's core sleep duration ratio is reasonable, and a score can be given based on the comparison result to obtain the second sleep quality data. Among them, the first preset duration ratio can be a reference value given by a medical institution for the target person. The larger the second sleep quality data, the closer the target person's core sleep duration ratio is to the first preset duration ratio. Exemplarily, the first preset duration ratio can be 62%.

[0085] Similarly, the duration ratio of deep sleep can be compared with the second preset duration ratio to determine whether the duration ratio of deep sleep of the target person is reasonable, and a score can be given based on the comparison result to obtain the third sleep quality data. Among them, the second preset duration ratio can be a reference value given by a medical institution for the target person. The larger the third sleep quality data, the closer the duration ratio of deep sleep of the target person is to the second preset duration ratio. Exemplarily, the second preset duration ratio can be 20%.

[0086] Similarly, the REM sleep duration ratio can be compared with the third preset duration ratio to determine whether the target person's REM sleep duration ratio is reasonable, and based on the comparison result, a score can be given to obtain the fourth sleep quality data. Among them, the third preset duration ratio can be a reference value given by a medical institution for the target person. The larger the fourth sleep quality data, the closer the target person's REM sleep duration ratio is to the third preset duration ratio. Exemplarily, the third preset duration ratio can be 18%.

[0087] Since the first sleep quality data reflects whether the total sleep time of the target person is reasonable, the second sleep quality data reflects whether the core sleep time ratio of the target person is reasonable, the third sleep quality data reflects whether the deep sleep time ratio of the target person is reasonable, and the fourth sleep quality data reflects whether the rapid eye movement sleep time ratio of the target person is reasonable, therefore, the sleep quality of the target person can be determined according to the first sleep quality data, the second sleep quality data, the third sleep quality data and the fourth sleep quality data.

[0088] In some embodiments of the present application, Figure 3 As shown, determining the sleep quality of the target person according to the first sleep quality data, the second sleep quality data, the third sleep quality data and the fourth sleep quality data (step S145) includes:

[0089] S1451, multiplying the first sleep quality data by a preset first weight coefficient to obtain a first parameter;

[0090] S1452, multiplying the second sleep quality data by a preset second weight coefficient to obtain a second parameter;

[0091] S1453, multiplying the third sleep quality data by a preset third weight coefficient to obtain a third parameter;

[0092] S1454, multiplying the fourth sleep quality data by a preset fourth weight coefficient to obtain a fourth parameter;

[0093] S1455, summing the first parameter, the second parameter, the third parameter and the fourth parameter to determine the sleep quality of the target person.

[0094] In the embodiment of the present application, a first weight value can be assigned to the first sleep quality data, a second weight value can be assigned to the second sleep quality data, a third weight value can be assigned to the third sleep quality data, and a fourth weight value can be assigned to the fourth sleep quality data according to the importance of the total sleep duration, the duration ratio of the core sleep stage, the duration ratio of the deep sleep stage, and the duration ratio of the rapid eye movement. The embodiment of the present application does not limit the specific method for determining the first weight value, the second weight value, the third weight value, and the fourth weight value.

[0095] By multiplying the first sleep quality data with the preset first weight coefficient, a first parameter can be obtained, which is used to characterize the rationality of the total sleep time of the target person. By multiplying the second sleep quality data with the preset second weight coefficient, a second parameter can be obtained, which is used to characterize the rationality of the duration ratio of the core sleep stage of the target person. By multiplying the third sleep quality data with the preset third weight coefficient, a third parameter can be obtained, which is used to characterize the rationality of the duration ratio of the deep sleep stage of the target person. By multiplying the fourth sleep quality data with the preset fourth weight coefficient, a fourth parameter can be obtained, which is used to characterize the rationality of the duration ratio of the rapid eye movement sleep stage of the target person.

[0096] The first parameter, the second parameter, the third parameter and the fourth parameter are summed up, and the total value obtained can reflect the overall sleep quality of the target person.

[0097] In some embodiments of the present application, the neural network model is an LSTM neural network model.

[0098] In an embodiment of the present application, the Long Short-Term Memory (LSTM) neural network model is a special recurrent neural network (RNN) architecture, which is mainly used to process and predict time series data.

[0099] The LSTM neural network model is good at processing time series data and can remember long-term dependencies, making it suitable for analyzing continuous physiological data such as heart rate and brain wave signals. The LSTM neural network model can more accurately process the target person's sleep parameters and thus more accurately identify which sleep stage the target person is in.

[0100] In some embodiments of the present application, before or after obtaining the current sleep parameters of the target person (step S11), the method may further include: detecting the external environment condition where the target person is located;

[0101] After determining the sleep quality of the target person, the method further includes: determining the sleep anti-interference ability of the target person according to the external environment conditions and the sleep quality of the target person.

[0102] In an embodiment of the present application, the external environmental condition where the target person is located refers to the condition of the environment where the target person is in a sleeping state. Specifically, the external environmental condition may include ambient temperature, ambient humidity, ambient noise level, and ambient visible light intensity. The above four environmental conditions all have an optimal interval, for example, the optimal ambient temperature range is 18 to 23 degrees, which can be called the ambient reference temperature. The ambient temperature can be evaluated using the ambient reference temperature. The closer the ambient temperature is to the ambient reference temperature, the higher the score of the ambient temperature, indicating that the better the ambient temperature is, the more conducive it is for the target person to sleep. The greater the gap between the ambient temperature and the ambient reference temperature, the lower the score of the ambient temperature, indicating that the worse the ambient temperature is, the more unfavorable it is for the target person to sleep.

[0103] Similarly, the smaller the difference between the ambient humidity and the ambient baseline humidity, the higher the ambient humidity score, indicating that the ambient humidity is better and more conducive to the target person's sleep. The larger the difference between the ambient humidity and the ambient baseline humidity, the lower the ambient humidity score, indicating that the ambient humidity is worse and less conducive to the target person's sleep. The louder the ambient noise, the lower the ambient noise score, indicating that the ambient noise conditions are worse and less conducive to the target person's sleep. The smaller the ambient noise, the higher the ambient noise score, indicating that the ambient noise conditions are better and more conducive to the target person's sleep. The greater the ambient visible light intensity, the lower the ambient visible light score, indicating that the ambient visible light conditions are worse and less conducive to the target person's sleep.

[0104] The sleep anti-interference ability of the target person can be judged by comprehensively considering the sleep quality of the target person and the external environment conditions where the target person is located. Under the condition that the sleep quality of the target person is the same, the worse the external environment conditions are, the stronger the sleep anti-interference ability of the target person is.

[0105] Specifically, the target person's sleep quality can be expressed in the form of a score, and the target person's external environment conditions can also be expressed in the form of a score. The result obtained by dividing the score value of the target person's sleep quality by the score value of the external environment conditions can be used to characterize the target person's sleep anti-interference ability. The larger the result value, the stronger the target person's sleep anti-interference ability is, and the smaller the result value, the worse the target person's sleep anti-interference ability is.

[0106] In some embodiments of the present application, before or after obtaining the current sleep parameters of the target person, the method further includes: detecting the sleeping posture of the target person, and determining the start and end time of each sleeping posture of the target person; the sleeping posture is a supine sleeping posture, a left side sleeping posture, a right side sleeping posture, or a prone sleeping posture;

[0107] like Figure 4 As shown, after determining the sleep quality of the target person according to the total sleep duration of the target person, the duration ratio of the core sleep stage, the duration ratio of the deep sleep stage, and the duration ratio of the rapid eye movement sleep stage, the method further includes:

[0108] S15, determining a first sleeping position with the highest sleeping quality according to the sleep quality of the target person in various sleeping positions;

[0109] S16: recommending the first sleeping position to the target person.

[0110] In the embodiment of the present application, before or after obtaining the current sleep parameters of the target person (step S11), it is also possible to detect whether the target person's sleeping position is supine, left-side, right-side, or prone. Specifically, a camera can be used to shoot a video of the target person, so as to distinguish which sleeping position the target person adopts throughout the entire sleeping state.

[0111] The target person's sleep quality can be determined in various sleeping positions, and then the target person's sleep quality in various sleeping positions can be compared, and then the sleeping position with the highest sleep quality (i.e., the first sleeping position) can be determined. The first sleeping position is recommended to the target user. Specifically, the target user can be sent information related to the first sleeping position in the form of text messages or other information. After receiving the first sleeping position, the target person can sleep in the first sleeping position, thereby improving the sleep quality.

[0112] In a second aspect, the present application provides a sleep quality assessment device, see Figure 5 , the device may include:

[0113] The acquisition unit 51 is used to acquire the current sleep parameters of the target person when the target person is in a sleeping state; the sleep parameters include the following parameters: turning over frequency, heart rate frequency and brain wave signal;

[0114] The first determination unit 52 is used to input the current sleep parameters, the exercise data of the target person in a preset time period before going to bed, and the current health status data of the target person into a pre-trained neural network model for processing to determine the duration of the core sleep stage, the duration of the deep sleep stage, and the duration of the rapid eye movement sleep stage; wherein the neural network model is pre-trained by the historical data of the sleep parameters of the core sleep stage, the historical data of the sleep parameters of the deep sleep stage, the historical data of the sleep parameters of the rapid eye movement sleep stage, the historical exercise data of the target person in a preset time period before going to bed, and the historical health status data of the target person;

[0115] A second determining unit 53 is used to determine the duration ratio of the core sleep stage, the duration ratio of the deep sleep stage, and the duration ratio of the rapid eye movement sleep stage according to the total sleep duration of the target person, the duration of the core sleep stage, the duration of the deep sleep stage, and the duration of the rapid eye movement sleep stage;

[0116] The third determination unit 54 is used to determine the sleep quality of the target person according to the total sleep time of the target person, the duration ratio of the core sleep stage, the duration ratio of the deep sleep stage and the duration ratio of the rapid eye movement sleep stage.

[0117] The embodiment of the present application provides a sleep quality assessment device, which can obtain the current sleep parameters of the target person when the target person is in a sleeping state. The current sleep parameters, the target person's exercise data in a preset period before going to bed, and the target person's current health status data are input into a pre-trained neural network model for processing, and the duration of the core sleep stage, the duration of the deep sleep stage, and the duration of the rapid eye movement sleep stage can be determined. Combined with the total sleep duration of the target person, the duration ratio of the above three sleep stages can be determined, and then the sleep quality of the target person can be determined, which solves the technical problem that the user's sleep quality cannot be effectively assessed in the prior art.

[0118] The sleep quality assessment device provided in the embodiment of the present application belongs to the same inventive concept as the aforementioned sleep quality assessment method. The technical details not described in the sleep quality assessment device can be found in the relevant description of the aforementioned sleep quality assessment method and will not be repeated here.

[0119] Thirdly, Figure 6 As shown, an embodiment of the present application also provides an electronic device, which includes a memory and a processor, wherein the memory is used to store a computer program. When the computer program is executed by the processor, the sleep quality assessment method as described above can be implemented. For details, please refer to the description of the aforementioned embodiment.

[0120] Specifically, at the hardware level, the electronic device may include a processor, an internal bus, and a memory. The memory may include a memory and a non-volatile memory. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it. It can be understood by those skilled in the art that Figure 6 The structure shown is only for illustration and does not limit the structure of the electronic device. Figure 6More or fewer components shown in the figure may also include other processing hardware, such as a GPU (Graphics Processing Unit), or an external communication port, etc. Of course, in addition to the software implementation, this application does not exclude other implementations, such as logic devices or a combination of software and hardware, etc.

[0121] In this embodiment, the processor may include a central processing unit (CPU) or a graphics processing unit (GPU), and of course may also include other single-chip microcomputers, logic gate circuits, integrated circuits, etc. with logic processing capabilities, or appropriate combinations thereof. The memory described in this embodiment may be a memory device for storing information. In a digital system, a device that can store binary data may be a memory; in an integrated circuit, a circuit with a storage function without a physical form may also be a memory, such as a RAM, FIFO, etc.; in a system, a storage device with a physical form may also be called a memory, etc. When implemented, the memory may also be implemented in the form of a cloud storage, and the specific implementation method is not limited in this specification.

[0122] In a fourth aspect, the present application further provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the above sleep quality assessment method can be implemented.

[0123] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0124] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for evaluating sleep quality, characterized in that: include: When the target person is in a sleeping state, obtaining the current sleeping parameters of the target person; The sleep parameters include the following parameters: turning over frequency, heart rate and brain wave signal; Input the current sleep parameters, the target person's exercise data in a preset time period before going to bed, and the target person's current health status data into a pre-trained neural network model for processing to determine the duration of the core sleep stage, the duration of the deep sleep stage, and the duration of the rapid eye movement sleep stage; wherein the neural network model is pre-trained by the historical data of the sleep parameters in the core sleep stage, the historical data of the sleep parameters in the deep sleep stage, the historical data of the sleep parameters in the rapid eye movement sleep stage, the historical exercise data of the target person in a preset time period before going to bed, and the historical health status data of the target person; Determine the duration ratio of the core sleep stage, the duration ratio of the deep sleep stage, and the duration ratio of the rapid eye movement sleep stage according to the total sleep duration of the target person, the duration of the core sleep stage, the duration of the deep sleep stage, and the duration ratio of the rapid eye movement sleep stage; The sleep quality of the target person is determined based on the total sleep duration of the target person, the duration ratio of the core sleep stage, the duration ratio of the deep sleep stage, and the duration ratio of the rapid eye movement sleep stage.

2. The method according to claim 1, characterized in that: Determining the sleep quality of the target person according to the total sleep duration of the target person, the duration ratio of the core sleep stage, the duration ratio of the deep sleep stage, and the duration ratio of the rapid eye movement sleep stage, including: Comparing the total sleep duration of the target person with a first preset duration to determine first sleep quality data; Comparing the duration ratio of the core sleep stage with the first preset duration ratio to determine second sleep quality data; Comparing the duration ratio of the deep sleep stage with the second preset duration ratio to determine third sleep quality data; Comparing the duration ratio of the rapid eye movement sleep stage with a third preset duration ratio to determine fourth sleep quality data; The sleep quality of the target person is determined according to the first sleep quality data, the second sleep quality data, the third sleep quality data, and the fourth sleep quality data.

3. The method according to claim 2, characterized in that The determining the sleep quality of the target person according to the first sleep quality data, the second sleep quality data, the third sleep quality data, and the fourth sleep quality data includes: Multiplying the first sleep quality data by a preset first weight coefficient to obtain a first parameter; Multiplying the second sleep quality data by a preset second weight coefficient to obtain a second parameter; multiplying the third sleep quality data by a preset third weight coefficient to obtain a third parameter; multiplying the fourth sleep quality data by a preset fourth weight coefficient to obtain a fourth parameter; The first parameter, the second parameter, the third parameter and the fourth parameter are summed to determine the sleep quality of the target person.

4. The method according to claim 1, characterized in that The neural network model is an LSTM neural network model.

5. The method according to claim 1, characterized in that Before or after obtaining the current sleep parameters of the target person, the method further includes: detecting the external environment conditions where the target person is located; After determining the sleep quality of the target person, the method further includes: The sleep anti-interference ability of the target person is determined according to the external environment conditions and the sleep quality of the target person.

6. The method according to claim 5, characterized in that The external environmental conditions include ambient temperature, ambient humidity, ambient noise level, and ambient visible light intensity.

7. The method according to claim 1, characterized in that Before or after obtaining the current sleep parameters of the target person, the method further includes: detecting the sleeping position of the target person; the sleeping position is a supine sleeping position, a left side sleeping position, a right side sleeping position or a prone sleeping position; After determining the sleep quality of the target person according to the total sleep duration of the target person, the duration ratio of the core sleep stage, the duration ratio of the deep sleep stage, and the duration ratio of the rapid eye movement sleep stage, the method further includes: Determining a first sleeping position with the highest sleep quality according to the sleep quality of the target person in various sleeping positions; The first sleeping position is recommended to the target person.

8. A sleep quality assessment device, characterized in that: include: an acquisition unit, used for acquiring current sleep parameters of the target person when the target person is in a sleeping state; The sleep parameters include the following parameters: turning over frequency, heart rate and brain wave signal; A first determination unit is used to input the current sleep parameters, the exercise data of the target person in a preset time period before going to bed, and the current health status data of the target person into a pre-trained neural network model for processing to determine the duration of the core sleep stage, the duration of the deep sleep stage, and the duration of the rapid eye movement sleep stage; wherein the neural network model is pre-trained by the historical data of the sleep parameters in the core sleep stage, the historical data of the sleep parameters in the deep sleep stage, the historical data of the sleep parameters in the rapid eye movement sleep stage, the historical exercise data of the target person in a preset time period before going to bed, and the historical health status data of the target person; A second determining unit is used to determine the duration ratio of the core sleep stage, the duration ratio of the deep sleep stage, and the duration ratio of the rapid eye movement sleep stage according to the total sleep duration of the target person, the duration of the core sleep stage, the duration of the deep sleep stage, and the duration of the rapid eye movement sleep stage; The third determination unit is used to determine the sleep quality of the target person according to the total sleep time of the target person, the proportion of the core sleep stage, the proportion of the deep sleep stage and the proportion of the rapid eye movement sleep stage.

9. An electronic device, characterized in that: The electronic device comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images