A sleep aiding method, apparatus, device and medium

Abstract

The application discloses a sleep-aiding method, device, equipment and medium, and relates to the technical field of sleep-aiding, which comprises the following steps: collecting electroencephalogram data, physiological parameter data and noise data when a user is sleeping; performing sleep state discrimination on the electroencephalogram data and the physiological parameter data to obtain user sleep state information; generating a sleep-aiding sound signal according to the user sleep state information and the noise data; and playing the sleep-aiding sound signal in the user's sleeping environment. The application reduces the cost of sleep-aiding while improving the timeliness of sleep-aiding.

Description

Technical Field

[0001] This application relates to the field of sleep aid technology, and in particular to a sleep aid method, device, equipment and medium. Background Technology

[0002] In the current social context, due to the pressures of life and work, as well as external noise signals such as construction, operation of home appliances, and crowds, people's sleep quality has declined sharply, making it difficult for them to fall asleep normally and seriously affecting their physical and mental health.

[0003] For seafarers, ship cabins are typically semi-enclosed spaces. Environmental issues such as physical, chemical, and microbial contamination severely disrupt their sleep. Studies show that over 50% of seafarers report chronic sleep problems, with an average sleep duration of only 6.6 hours, lower than the 7-9 hours typical for the general population. Sleep deprivation is a significant cause of seafarer fatigue, and prolonged sleep deprivation is associated with decreased attention span, increased error judgment, and reduced work efficiency. This increases the risk of ship accidents. Existing shipboard sleep technology primarily relies on rotating the outer and inner cabins to effectively reduce turbulence in the sleep pods. However, this method is costly and lacks timely feedback on the seafarer's sleep status and other characteristics. Summary of the Invention

[0004] The purpose of this application is to provide a sleep aid method, device, equipment, and medium that reduces the cost of sleep aids while improving the timeliness of sleep aids.

[0005] To achieve the above objectives, this application provides the following solution:

[0006] Firstly, this application provides a sleep aid method, the sleep aid method comprising:

[0007] Collects EEG signal data, physiological parameter data, and noise data from users during sleep;

[0008] The user's sleep state information is obtained by analyzing the electroencephalogram (EEG) signal data and the physiological parameter data to determine the sleep state.

[0009] Based on the user's sleep state information and the noise data, a sleep aid sound signal is generated;

[0010] The sleep-aid sound signal is played in the user's sleep environment.

[0011] Optionally, sleep state determination is performed on the electroencephalogram (EEG) signal data and the physiological parameter data to obtain user sleep state information, specifically including:

[0012] The electroencephalogram (EEG) signal data and the physiological parameter data are preprocessed; the preprocessing includes data cleaning.

[0013] Sleep discrimination processing was performed on the preprocessed EEG signal data to obtain the first discrimination result;

[0014] The preprocessed physiological parameter data were subjected to sleep discrimination processing to obtain a second discrimination result.

[0015] The first discrimination result and the second discrimination result are weighted and fused to obtain the user's sleep state value;

[0016] Based on a preset range of user sleep state values ​​for falling asleep, light sleep, and deep sleep, the user sleep state information is determined according to the user sleep state values; the user sleep state information is falling asleep, light sleep, or deep sleep.

[0017] Optionally, sleep discrimination processing is performed on the preprocessed EEG signal data to obtain a first discrimination result, specifically including:

[0018] The difference between the preprocessed EEG signal data and the standard EEG signal under the preset deep sleep state is calculated to obtain the first discrimination result.

[0019] Optionally, the preprocessed EEG signal data is compared with the standard EEG signal under a preset deep sleep state to calculate the difference and obtain the first discrimination result, which specifically includes:

[0020] The preprocessed EEG signal data is represented as an EEG signal matrix; the EEG signal data is a collection of multiple EEG signals, and each row vector in the EEG signal matrix represents a preprocessed EEG signal;

[0021] Each row vector of the EEG signal matrix is ​​subtracted from the standard EEG signal in a preset deep sleep state, and the first difference vector after each subtraction constitutes the EEG difference matrix.

[0022] The first discrimination calculation is performed on the EEG difference matrix and the EEG signal matrix to obtain the first discrimination result;

[0023] The expression for the first discrimination calculation is:

[0024]

[0025] Among them, c ij Let be the element in the i-th row and j-th column of the EEG difference matrix. The i-th element of the first difference vector. p is the i-th element of the second difference vector. The first difference vector is the vector formed by the largest element in each row of the EEG difference matrix, and the second difference vector is the vector formed by the smallest element in each row of the EEG difference matrix. i Let A be the i-th element of the first eigenvector, M and N be the row and column dimensions of the EEG difference matrix, respectively. ij Let A be the element in the i-th row and j-th column of the EEG signal matrix. i denoted as the mean of the i-th row of the EEG signal matrix, and ND as the first discrimination result.

[0026] Optionally, the preprocessed physiological parameter data undergoes sleep discrimination processing to obtain a second discrimination result, specifically including:

[0027] The preprocessed physiological parameter data is represented as a physiological parameter matrix; each row vector in the physiological parameter matrix represents a physiological parameter; the physiological parameter data includes multiple physiological parameters, including blood pressure, pulse, and respiratory rate.

[0028] Subtract the preset standard value of the physiological parameter for each row vector in the physiological parameter matrix from the preset standard value of the corresponding type to obtain the corresponding second difference vector. The second difference vectors constitute the physiological difference matrix.

[0029] A second discrimination calculation is performed on the physiological difference matrix and the physiological parameter matrix to obtain the second discrimination result.

[0030] Optionally, a second discriminant calculation is performed on the physiological difference matrix and the physiological parameter matrix to obtain a second discriminant result, specifically including:

[0031] Cross-correlation calculation is performed on the row vectors of the physiological difference matrix to obtain a cross-correlation matrix; the elements of the i'th row and j'th column of the cross-correlation matrix are the cross-correlation values ​​of the i'th row vector and the j'th row vector of the cross-correlation matrix;

[0032] The physiological parameter matrix is ​​transformed to obtain the transformation matrix;

[0033] The transformation matrix is ​​decomposed into eigenvalues ​​to obtain eigenvalue vectors;

[0034] Singular value decomposition is performed on the cross-correlation matrix to obtain the singular value vector;

[0035] Perform a vector dot product on the singular value vector and the eigenvalue vector to obtain a second discrimination result;

[0036] The expression for transforming the physiological parameter matrix is ​​as follows:

[0037]

[0038] Where, p kh f is the element in the k-th row and h-th column of the transformation matrix. kh Let m be the element in the k-th row and h-th column of the physiological parameter matrix, where m and n are the row and column dimensions of the transformation matrix, respectively.

[0039] Optionally, a sleep-aid sound signal is generated based on the user's sleep state information and the noise data, specifically including:

[0040] Obtain the multiplication factor corresponding to the user's sleep state information; each type of user sleep state information corresponds to a multiplication factor;

[0041] The noise data is inverted to obtain an inverted waveform signal;

[0042] The sleep aid sound signal is obtained by multiplying the inverted waveform signal with the multiplication factor corresponding to the user's sleep state information.

[0043] Secondly, this application provides a sleep aid device, which applies the sleep aid method described in any of the above claims, the sleep aid device comprising:

[0044] The sleep data acquisition module is used to collect the user's electroencephalogram (EEG) signal data, physiological parameter data, and noise data during sleep.

[0045] The sleep state discrimination module is used to discriminate the sleep state based on the electroencephalogram signal data and the physiological parameter data to obtain the user's sleep state information.

[0046] A sleep aid sound signal generation module is used to generate a sleep aid sound signal based on the user's sleep state information and the noise data;

[0047] A sleep aid sound signal playback module is used to play the sleep aid sound signal in the user's sleep environment.

[0048] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the sleep aid method described in any of the above claims.

[0049] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the sleep aid method described in any one of the above descriptions.

[0050] According to the specific embodiments provided in this application, the following technical effects are disclosed:

[0051] This application provides a sleep aid method, device, equipment, and medium that collects electroencephalogram (EEG) signal data, physiological parameter data, and noise data during a user's sleep; performs sleep state discrimination on the EEG signal data and physiological parameter data to obtain the user's sleep state information; and generates a sleep aid sound signal based on the user's sleep state information and the noise data. By collecting data from the user's current sleep state to generate the sleep aid sound signal in a timely manner, the timeliness of sleep aid is improved. This application generates the sleep aid sound signal through data processing, without requiring any modification to the user's sleep environment, making it easy to implement and reducing the cost of sleep aid. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a flowchart illustrating a sleep aid method provided in one embodiment of this application.

[0054] Figure 2 This is a schematic diagram of the functional modules of a sleep aid device provided in another embodiment of this application.

[0055] Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0056] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0057] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0058] In one exemplary embodiment, this application provides a sleep aid method, such as... Figure 1 As shown, the sleep aid method includes steps 101 to 104.

[0059] Step 101: Collect EEG signal data, physiological parameter data, and noise data during the user's sleep.

[0060] Step 102: Perform sleep state discrimination on the electroencephalogram (EEG) signal data and the physiological parameter data to obtain the user's sleep state information.

[0061] Step 103: Generate a sleep aid sound signal based on the user's sleep state information and the noise data.

[0062] Step 104: Play the sleep aid sound signal in the user's sleep environment.

[0063] In step 101, the EEG signal data is a set of EEG signal sequences, i.e., the EEG signal set; the physiological parameter data is a set of physiological parameter signal sequences, i.e., the physiological parameter signal set; and the noise data is a set of noise data sequences, i.e., the noise data set.

[0064] Physiological parameter signal sequences include blood pressure measurement sequences, pulse measurement sequences, and respiratory rate measurement sequences.

[0065] The noise data specifically refers to the noise data around the user's ears, in order to accurately extract the user's sleep noise data.

[0066] Blood pressure measurement sequences were acquired using a blood pressure sensor, pulse measurement sequences were acquired using a pulse sensor, and respiratory rate measurement sequences were acquired using a respiratory rate sensor.

[0067] This application achieves a sleep-aiding function by generating sleep-inducing sound signals to counteract the impact of noise data on the user's sleep.

[0068] In another exemplary embodiment, step 102 specifically includes:

[0069] Step 201: Preprocess the EEG signal data and the physiological parameter data; the preprocessing includes data cleaning.

[0070] Step 202: Perform sleep discrimination processing on the preprocessed EEG signal data to obtain the first discrimination result.

[0071] Step 203: Perform sleep discrimination processing on the preprocessed physiological parameter data to obtain the second discrimination result.

[0072] Step 204: Perform a weighted fusion of the first discrimination result and the second discrimination result to obtain the user's sleep state value.

[0073] Step 205: Based on preset user sleep state value ranges for falling asleep, light sleep, and deep sleep, determine the user's sleep state information according to the user's sleep state values; the user's sleep state information is falling asleep, light sleep, or deep sleep. That is, each sleep state corresponds to a range of user sleep state values, and the user's sleep state information, i.e., which sleep state the user is in, is determined according to each range.

[0074] In another exemplary embodiment, step 201 specifically includes the following steps:

[0075] Step 2011: Perform data cleaning and processing on the EEG signal data and physiological parameter data to obtain the first signal set.

[0076] Step 2012: Perform category discrimination processing on the first signal set to obtain the second signal set. The categories include electroencephalogram (EEG) signals and physiological parameters.

[0077] Step 2013: Perform pattern detection on the second signal set to obtain a preprocessed signal set; the preprocessed signal set includes preprocessed EEG signal data and preprocessed physiological parameter data.

[0078] The category discrimination process involves judging the attributes of each data in the signal set and determining whether its attributes are consistent with preset attributes (categories). Data that are inconsistent are deleted from the signal set.

[0079] The data cleaning process includes filling in missing values, smoothing noisy data, and smoothing or deleting outliers. Smoothing noisy data involves first identifying the noisy data, and then smoothing it based on the data preceding and following it. The noisy data refers to data whose values ​​are less than the detection sensitivity of the sensor (the sensor that collects EEG signals and physiological parameter signals) used to collect the observed data, or greater than the upper limit of the sensor's measurement range. Outlier identification can be performed using Kalman filtering. The filling values ​​for missing values ​​can be obtained by averaging the measurements within a certain sampling interval before and after the missing value.

[0080] Step 2013 specifically includes the following steps:

[0081] Step 20131: For each category of data (each data attribute) in the second signal set, using the data acquisition information of the category data as the independent variable and the data value of the category data (the value of an element in the EEG signal sequence or physiological parameter signal sequence) as the dependent variable, perform autoregressive-moving average modeling to obtain the first approximation model for each category of data. The category data (data attribute) is either an EEG signal or a physiological parameter.

[0082] Step 20132: Using all the information sequences in the information sequence set of each type of data attribute as row vectors, construct the information matrix of the data attribute of the type.

[0083] Step 20133: Perform singular value calculation on the information matrix to obtain a singular value sequence.

[0084] Step 20134: Using the element values ​​of the singular value sequence as known dependent variables and the element indices of the singular value sequence as known independent variables, construct the curve to be approximated using the known independent and dependent variables; perform polynomial fitting on the curve to be approximated to obtain the second approximation model of the data class attribute.

[0085] Step 20135: Multiply the second approximation model and the first approximation model to obtain the fusion verification model of the class data attributes.

[0086] Step 20136: Using the fusion test model for each type of data attribute, calculate and process the data collection information of the data attribute to obtain an approximate dependent variable.

[0087] Step 20137: Determine whether the absolute value of the difference between the approximate dependent variable and the corresponding data is greater than the set first regression discrimination threshold; if it is greater than the first regression discrimination threshold, delete the data from the second signal set; if it is less than or equal to the first regression discrimination threshold, do not process the data.

[0088] Step 20138: Perform fusion processing on all data in the second signal set according to steps 20136 to 20137 to obtain a preprocessed signal set.

[0089] In another exemplary embodiment, step 202 specifically includes: calculating the difference between the preprocessed EEG signal data and the standard EEG signal under a preset deep sleep state to obtain a first discrimination result.

[0090] The difference between the preprocessed EEG signal data and the standard EEG signal under a preset deep sleep state is calculated to obtain the first discrimination result, which specifically includes:

[0091] Step 2021: Represent the preprocessed EEG signal data as an EEG signal matrix; the EEG signal data is a collection of multiple EEG signals, and each row vector in the EEG signal matrix represents a preprocessed EEG signal.

[0092] Step 2022: Subtract each row vector of the EEG signal matrix from the standard EEG signal under the preset deep sleep state. The first difference vector after each subtraction constitutes the EEG difference matrix.

[0093] The standard EEG signal in deep sleep is preset to a preset value.

[0094] Step 2023: Perform a first discrimination calculation on the EEG difference matrix and the EEG signal matrix to obtain a first discrimination result.

[0095] The expression for the first discrimination calculation is:

[0096]

[0097] Among them, c ij Let be the element in the i-th row and j-th column of the EEG difference matrix. The first difference vector is the first

[0098] i elements, Let p be the i-th element of the second difference vector. The first difference vector is the vector formed by the largest element in each row of the EEG difference matrix, and the second difference vector is the vector formed by the smallest element in each row of the EEG difference matrix. i Let A be the i-th element of the first eigenvector, M and N be the row and column dimensions of the EEG difference matrix, respectively. ij Let A be the element in the i-th row and j-th column of the EEG signal matrix. i denoted as the mean of the i-th row of the EEG signal matrix, and ND as the first discrimination result.

[0099] The expression for the first discrimination calculation, by calculating the maximum and minimum values ​​of the rows of the EEG difference matrix, can capture the changing characteristics of EEG signals from multiple perspectives, thus more comprehensively reflecting the user's current sleep state. By introducing sine and tangent functions to nonlinearly fuse the EEG signal matrix and the EEG difference matrix, this nonlinear processing method can better capture complex patterns and subtle changes in EEG signals, improving the accuracy of sleep state discrimination. Furthermore, by introducing p... i The two weighted discriminant indicators, ND and ND, take into account both the mean and difference of the EEG signal, which can more accurately assess the difference between the EEG signal and the preset deep sleep state standard EEG signal, thus providing a more reliable basis for sleep state discrimination.

[0100] The expression for the first discrimination calculation can dynamically adjust the discrimination result according to the real-time data of the EEG signal matrix, which has strong adaptability and can be applied to the EEG signal feature changes of different users and different sleep stages. By calculating the difference matrix and feature vector of physiological parameter data, the user's physiological state, such as heart rate and respiratory rate, can be analyzed from multiple dimensions, thereby more comprehensively reflecting the user's current sleep state.

[0101] The expression for the first discrimination calculation, by weightedly fusing the discrimination results of EEG signals and physiological parameter data, comprehensively considers the user's brain activity and physiological state, thereby more comprehensively reflecting the user's sleep state and improving the accuracy and reliability of sleep state discrimination. By introducing weighting coefficients, the weights of EEG signals and physiological parameter data can be dynamically adjusted according to actual application scenarios and user needs, making the discrimination results more in line with actual requirements. Weighted fusion can fully utilize the advantages of EEG signals and physiological parameter data, making up for the shortcomings of a single data source, thereby improving the accuracy and robustness of sleep state discrimination.

[0102] In another exemplary embodiment, step 203 specifically includes:

[0103] Step 2031: Represent the preprocessed physiological parameter data as a physiological parameter matrix; each row vector in the physiological parameter matrix represents a physiological parameter; the physiological parameter data includes multiple physiological parameters, including blood pressure, pulse and respiratory rate.

[0104] Step 2032: Subtract the preset standard value of the physiological parameter of the corresponding type from each row vector in the physiological parameter matrix to obtain the corresponding second difference vector. The second difference vectors constitute the physiological difference matrix.

[0105] Step 2033: Perform a second discriminant calculation on the physiological difference matrix and the physiological parameter matrix to obtain the second discriminant result.

[0106] In another exemplary embodiment, step 2033 specifically includes:

[0107] Step 20331: Perform cross-correlation calculation on the row vectors of the physiological difference matrix to obtain a cross-correlation matrix; the elements of the i'th row and j'th column of the cross-correlation matrix are the cross-correlation values ​​of the i'th row vector and the j'th row vector of the cross-correlation matrix. The cross-correlation values ​​can be calculated using the corr function.

[0108] Step 20332: Transform the physiological parameter matrix to obtain the transformation matrix.

[0109] Step 20333: Perform eigenvalue decomposition on the transformation matrix to obtain the eigenvalue vector. Eigenvalue decomposition can be achieved using an eigenvalue decomposition algorithm for a matrix.

[0110] Step 20334: Perform singular value decomposition on the cross-correlation matrix to obtain the singular value vector.

[0111] Step 20335: Perform a vector dot product on the singular value vector and the eigenvalue vector to obtain the second discrimination result.

[0112] The expression for transforming the physiological parameter matrix is ​​as follows:

[0113]

[0114] Where, p kh f is the element in the k-th row and h-th column of the transformation matrix. kh Let m be the element in the k-th row and h-th column of the physiological parameter matrix, where m and n are the row and column dimensions of the transformation matrix, respectively.

[0115] In another exemplary embodiment, step 204 specifically includes: when performing weighted fusion processing on the first discrimination result and the second discrimination result, the weighting coefficient of the first discrimination result is 0.2 and the weighting coefficient of the second discrimination result is 0.5.

[0116] In another exemplary embodiment, step 103 specifically includes:

[0117] Step 1031: Obtain the multiplication factor corresponding to the user's sleep state information; each type of user sleep state information corresponds to a multiplication factor.

[0118] The preset multiplication factors for the sleep state, light sleep state, and deep sleep state are 0.7, 0.5, and 0.3, respectively.

[0119] Step 1032: Perform an inverse phase transformation on the noise data to obtain an inverse waveform signal.

[0120] Step 1033: Multiply the inverted waveform signal with the multiplication factor corresponding to the user's sleep state information to obtain the sleep aid sound signal.

[0121] This application generates sleep-aid sound signals in real time by collecting data from the user's current sleep state, thus improving the timeliness of sleep aid. This application generates sleep-aid sound signals through data processing, without requiring any modification to the user's sleep environment, making it easy to implement, reducing the cost of sleep aid, and suitable for sleep aid in enclosed spaces, such as ship cabins.

[0122] Based on the same inventive concept, this application also provides a sleep aid device for implementing the sleep aid method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more sleep aid device embodiments provided below can be found in the limitations of the sleep aid method above, and will not be repeated here.

[0123] In another exemplary embodiment, such as Figure 2 As shown, a sleep aid device is provided, which applies any of the sleep aid methods described above, and the sleep aid device includes:

[0124] The sleep data acquisition module is used to collect the user's electroencephalogram (EEG) signal data, physiological parameter data, and noise data during sleep.

[0125] The sleep state discrimination module is used to discriminate the sleep state based on the electroencephalogram (EEG) signal data and the physiological parameter data to obtain the user's sleep state information.

[0126] The sleep aid sound signal generation module is used to generate sleep aid sound signals based on the user's sleep state information and the noise data.

[0127] The sleep aid sound signal playback module is used to play the sleep aid sound signal in the user's sleep environment, that is, to send a sleep aid sound signal to the user.

[0128] The sleep data acquisition module includes a noise acquisition unit, an electroencephalogram (EEG) acquisition unit, and a physiological parameter acquisition unit. The physiological parameter acquisition unit includes a blood pressure sensor, a respiratory rate sensor, and a pulse sensor.

[0129] The noise acquisition unit is used to acquire noise data, and the EEG acquisition unit is used to acquire EEG signal data.

[0130] The respiratory rate sensor is used to measure the user's respiratory rate.

[0131] The blood pressure sensor is used to measure the user's blood pressure sequence.

[0132] The pulse sensor is used to measure the user's pulse sequence.

[0133] The sleep aid sound signal generation module includes a non-recursive lateral filtering unit, an inverting processor, an audio amplifier, and a player.

[0134] A non-recursive transverse filter unit is used to adjust the weight coefficients of the non-recursive transverse filter according to the adjustment parameters, so that the output of the non-recursive transverse filter unit is a noise waveform signal that matches the indoor noise data.

[0135] An inverting processor is used to invert the noise waveform signal to obtain an inverted waveform signal.

[0136] An audio amplifier is used to amplify the power of the inverted waveform signal and drive the player to convert the amplified inverted waveform signal into a noise-reduced wave (sleep-aid sound signal).

[0137] A player is used to play the noise-reduced wave to superimpose and cancel the indoor noise data.

[0138] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 3As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores sleep-aid data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a sleep-aid method.

[0139] Those skilled in the art will understand that Figure 3 The structures shown are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0140] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0141] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0142] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0143] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0144] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units, etc., and are not limited to these.

[0145] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0146] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A sleep aid method, characterized in that, The sleep aid methods include: Collects EEG signal data, physiological parameter data, and noise data from users during sleep; The user's sleep state information is obtained by analyzing the electroencephalogram (EEG) signal data and the physiological parameter data to determine the sleep state. Based on the user's sleep state information and the noise data, a sleep aid sound signal is generated; Play the sleep-aid sound signal in the user's sleep environment; Specifically, sleep state determination is performed on the electroencephalogram (EEG) signal data and the physiological parameter data to obtain user sleep state information, including: The electroencephalogram (EEG) signal data and the physiological parameter data are preprocessed; the preprocessing includes data cleaning. Sleep discrimination processing was performed on the preprocessed EEG signal data to obtain the first discrimination result; The preprocessed physiological parameter data were subjected to sleep discrimination processing to obtain a second discrimination result. The first discrimination result and the second discrimination result are weighted and fused to obtain the user's sleep state value; Based on a preset range of user sleep state values ​​for falling asleep, light sleep, and deep sleep, the user's sleep state information is determined according to the user's sleep state values; the user's sleep state information is falling asleep, light sleep, or deep sleep. Specifically, the process of performing sleep discrimination processing on the preprocessed EEG signal data to obtain the first discrimination result includes: calculating the difference between the preprocessed EEG signal data and the standard EEG signal under a preset deep sleep state to obtain the first discrimination result; The process involves calculating the difference between the preprocessed EEG signal data and the standard EEG signal under a preset deep sleep state to obtain the first discrimination result, which specifically includes: The preprocessed EEG signal data is represented as an EEG signal matrix; the EEG signal data is a collection of multiple EEG signals, and each row vector in the EEG signal matrix represents a preprocessed EEG signal; Each row vector of the EEG signal matrix is ​​subtracted from the standard EEG signal in a preset deep sleep state, and the first difference vector after each subtraction constitutes the EEG difference matrix. The first discrimination calculation is performed on the EEG difference matrix and the EEG signal matrix to obtain the first discrimination result; The expression for the first discrimination calculation is: ， ； ； ； in, Let be the element in the i-th row and j-th column of the EEG difference matrix. The i-th element of the first difference vector. Let be the i-th element of the second difference vector. The first difference vector is the vector formed by the largest element in each row of the EEG difference matrix, and the second difference vector is the vector formed by the smallest element in each row of the EEG difference matrix. Let be the i-th element of the first eigenvector, and M and N be the row and column dimensions of the EEG difference matrix, respectively. Let be the element in the i-th row and j-th column of the EEG signal matrix. denoted as the mean of the i-th row of the EEG signal matrix, and ND as the first discrimination result.

2. The sleep-aiding method according to claim 1, characterized in that, The preprocessed physiological parameter data are subjected to sleep discrimination processing to obtain a second discrimination result, which specifically includes: The preprocessed physiological parameter data is represented as a physiological parameter matrix; each row vector in the physiological parameter matrix represents a physiological parameter; the physiological parameter data includes multiple physiological parameters, including blood pressure, pulse, and respiratory rate. Subtract the preset standard value of the physiological parameter for each row vector in the physiological parameter matrix from the preset standard value of the corresponding type to obtain the corresponding second difference vector. The second difference vectors constitute the physiological difference matrix. A second discrimination calculation is performed on the physiological difference matrix and the physiological parameter matrix to obtain the second discrimination result.

3. The sleep-aiding method according to claim 2, characterized in that, A second discriminant calculation is performed on the physiological difference matrix and the physiological parameter matrix to obtain the second discriminant result, specifically including: Cross-correlation calculation is performed on the row vectors of the physiological difference matrix to obtain a cross-correlation matrix; the elements of the i'th row and j'th column of the cross-correlation matrix are the cross-correlation values ​​of the i'th row vector and the j'th row vector of the cross-correlation matrix; The physiological parameter matrix is ​​transformed to obtain the transformation matrix; The transformation matrix is ​​decomposed into eigenvalues ​​to obtain eigenvalue vectors; Singular value decomposition is performed on the cross-correlation matrix to obtain the singular value vector; Perform a vector dot product on the singular value vector and the eigenvalue vector to obtain a second discrimination result; The expression for transforming the physiological parameter matrix is ​​as follows: in, Let be the element in the k-th row and h-th column of the transformation matrix. Let m be the element in the k-th row and h-th column of the physiological parameter matrix, where m and n are the row and column dimensions of the transformation matrix, respectively.

4. The sleep-aiding method according to claim 1, characterized in that, Based on the user's sleep state information and the noise data, a sleep-aid sound signal is generated, specifically including: Obtain the multiplication factor corresponding to the user's sleep state information; each type of user sleep state information corresponds to a multiplication factor; The noise data is inverted to obtain an inverted waveform signal; The sleep aid sound signal is obtained by multiplying the inverted waveform signal with the multiplication factor corresponding to the user's sleep state information.

5. A sleep aid device, characterized in that, The sleep aid device applies the sleep aid method according to any one of claims 1-4, and the sleep aid device comprises: The sleep data acquisition module is used to collect the user's electroencephalogram (EEG) signal data, physiological parameter data, and noise data during sleep. The sleep state discrimination module is used to discriminate the sleep state based on the electroencephalogram signal data and the physiological parameter data to obtain the user's sleep state information. A sleep aid sound signal generation module is used to generate a sleep aid sound signal based on the user's sleep state information and the noise data; A sleep aid sound signal playback module is used to play the sleep aid sound signal in the user's sleep environment.

6. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the sleep aid method according to any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the sleep aid method according to any one of claims 1-4.

Images