Sleep quality quantification method, system, equipment and medium

Abstract

The invention provides a sleep quality quantification method, system and device and a medium. According to the method, a multi-dimensional sleep data acquisition module is used for acquiring multi-dimensional sleep data; the multi-dimensional sleep feature extraction module is used for performing feature extraction on the sleep data to obtain multi-dimensional sleep features; the multi-dimensional sleep feature vector determination module is used for inputting the multi-dimensional sleep features into a multi-dimensional sleep feature quantification model to obtain multi-dimensional sleep feature vectors; wherein the multi-dimensional sleep feature quantification model comprises a basic quantification model and an optimized quantification model; the sleep quality quantification result determination module is used for calculating and obtaining a sleep quality quantification result based on the multi-dimensional sleep feature vector, performing feature extraction on the multi-dimensional sleep data, obtaining the multi-dimensional sleep feature vector corresponding to the multi-dimensional sleep data, quantifying the sleep quality based on the multi-dimensional sleep feature vector, and determining the sleep quality quantification result. The accuracy of sleep quality quantification is improved, association with the corresponding disease is carried out, and accurate risk prompt of the disease in the early stage can be achieved.

Description

Technical Field

[0001] The present application belongs to the field of sleep monitoring technology and relates to a sleep quality quantification method, system, device and medium. Background Art

[0002] Currently, complex and significant associations exist between various dimensions of sleep data and disease risk. This extends beyond sleep duration to encompass multiple dimensions, including sleep architecture (such as the proportion of REM and non-REM sleep), sleep continuity (such as the number and duration of awakenings), sleep timing (such as bedtime and waking time, and circadian rhythm), subjective perception of sleep quality, and daytime functional status (such as daytime sleepiness and fatigue). However, despite initial insights into these associations, accurately and individually linking these dispersed, multidimensional sleep characteristic data with specific disease risks remains a significant challenge.

[0003] Therefore, how to associate multidimensional sleep characteristics with diseases and achieve accurate early warning of diseases based on multidimensional sleep characteristics has become one of the technical problems that need to be solved urgently. Summary of the Invention

[0004] The present application provides a sleep quality quantification method, system, device and medium for improving the accuracy of disease early warning based on multidimensional sleep characteristics.

[0005] In a first aspect, the present application provides a sleep quality quantification method. The method includes: a multidimensional sleep data acquisition module for acquiring multidimensional sleep data, wherein the multidimensional sleep data includes circadian rhythm data, sleep duration data, sleep stability data, sleep debt data, and / or sleep schedule data; a multidimensional sleep feature extraction module for extracting features from the sleep data to obtain multidimensional sleep features; a multidimensional sleep feature vector determination module for inputting the multidimensional sleep features into a multidimensional sleep feature quantification model to obtain a multidimensional sleep feature vector; wherein the multidimensional sleep feature quantification model includes a basic quantification model and an optimized quantification model; and a sleep quality quantification result determination module for calculating a sleep quality quantification result based on the multidimensional sleep feature vector.

[0006] In the sleep quality quantification method of the present application, feature extraction is performed on the sleep data to obtain multidimensional sleep features, and multidimensional sleep feature vectors corresponding to the multidimensional sleep features are obtained based on a multidimensional sleep feature quantification model. A correlation matrix between the multidimensional sleep feature vectors and disease risks is established, and a correlation model is established based on the correlation matrix and the disease types. The disease warning results are output based on the correlation model, which greatly improves the accuracy of disease warning based on multidimensional sleep features.

[0007] In an implementation of the first aspect, the multidimensional sleep feature is input into a basic quantitative model to obtain a score quantification effect of each dimension of the sleep feature, including: the multidimensional sleep feature quantification model determines the first The expression for the score quantification effect of the dimensional sleep feature is: in, Indicates the The score quantifies the effect of dimensional sleep characteristics. Indicates the Dimensional sleep data The original score of the data, Indicates the Dimensional sleep data The weight of the data, Indicates the The number of elements in the sleep data dimension.

[0008] In an implementation of the first aspect, the plurality of score effects are input into an optimization quantification model to obtain a multidimensional sleep feature vector, including: The expression for determining the optimal quantization effect is: in, represents the optimal quantization effect, Indicates whether there is Optimization conditions, when the first When the conditions for an optimization task are ;otherwise, , represents the optimization objective function, Indicates the A weight set of all questions under the dimension; if the optimal quantization effect is less than the preset quantization effect, adjusting the weight of at least one parameter among the clustering / classification model, the subjective reference correlation, the physiological indicator correlation, and the classic scale correlation to update the optimal quantization effect; if the optimal quantization effect is greater than or equal to the preset quantization effect, normalizing the optimal quantization effect to obtain the multidimensional sleep feature vector output by the multidimensional sleep feature quantization model.

[0009] In an implementation of the first aspect, the method also includes: obtaining a first quantitative effect of the score quantification effect based on a clustering / classification model; obtaining a second quantitative effect of the score quantification effect based on a subjective reference correlation; obtaining a third quantitative effect of the score quantification effect based on a physiological indicator correlation; obtaining a fourth quantitative effect of the optimal quantitative effect based on a classic scale correlation; and weighting the first quantitative effect, the second quantitative effect, the third quantitative effect, and the fourth quantitative effect to obtain an optimal quantitative effect.

[0010] In an implementation of the first aspect, the feature extraction of the sleep data to obtain multidimensional sleep features includes: obtaining rhythm morning and evening features based on rhythm morning and evening data; obtaining sleep duration features based on sleep duration data; obtaining sleep stability features based on sleep stability data; obtaining sleep debt features based on sleep debt data; obtaining work and rest regularity features based on work and rest regularity data; the multidimensional sleep features include rhythm morning and evening features, sleep duration features, sleep stability features, sleep debt features, and work and rest regularity features.

[0011] In an implementation of the first aspect, the method further includes: determining the distribution of sleep feature scores for each dimension in the multidimensional sleep feature vector using a multidimensional classification model; determining a classification threshold based on the distribution characteristics of the sleep feature score distribution for each dimension using the multidimensional classification model; and inputting the optimal quantitative effect corresponding to the multidimensional sleep feature vector into the multidimensional classification model to obtain a sleep quality classification label output by the multidimensional classification model.

[0012] In an implementation of the first aspect, the step of calculating the sleep quality quantification result based on the multidimensional sleep feature vector includes: determining an association matrix between the multidimensional sleep feature vector and the disease risk; if the matrix element in the association matrix is is greater than the preset threshold, then Sleep characteristics increase disease risks; If the matrix elements in the incidence matrix is less than or equal to the preset threshold, then Maintaining sleep characteristics reduces disease risk.

[0013] In an implementation of the first aspect, determining the association matrix between the multidimensional sleep feature vector and the disease risk includes: extracting the odds ratio of each dimension of sleep feature and the corresponding disease risk based on the database; The odds ratio of the three-dimensional sleep characteristic is logarithmically processed to obtain a log odds ratio corresponding to the odds ratio; a variance value corresponding to the log odds ratio is determined; a random effect weight is determined based on the variance value; a combined effect size is determined based on the random effect weight and the log odds ratio; and the association matrix is ​​determined based on the combined effect size.

[0014] In a second aspect, the present application provides a sleep quality quantification system, which includes: a multidimensional sleep feature acquisition module, used to extract features from the sleep data to obtain multidimensional sleep features; a multidimensional sleep feature vector determination module, used to input the multidimensional sleep features into a multidimensional sleep feature quantification model to obtain a multidimensional sleep feature vector; an association matrix establishment module, used to establish an association matrix between the multidimensional sleep feature vector and disease risk; an association model establishment module, used to establish an association model based on the association matrix and disease type; and a disease warning result determination module, used to output a disease warning result based on the association model.

[0015] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the sleep quality quantification method described in any one of the first aspects of the embodiments of the present application is implemented.

[0016] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising: a memory storing a computer program; and a processor communicatively connected to the memory, for executing the sleep quality quantification method described in any one of the first aspects of the embodiments of the present application when the computer program is called.

[0017] As described above, the sleep quality quantification method, system, device and medium described in the present application have the following beneficial effects: in the sleep quality quantification method of the present application, by extracting features from the sleep data, multidimensional sleep features are obtained, and multidimensional sleep feature vectors corresponding to the multidimensional sleep features are obtained based on a multidimensional sleep feature quantification model, and an association matrix between the multidimensional sleep feature vectors and disease risks is established. An association model is established based on the association matrix and the disease types, and a disease warning result is output based on the association model, which greatly improves the accuracy of disease warning based on multidimensional sleep features.

[0018] In this application, different sleep characteristics corresponding to different sleep data are obtained through deep neural networks and other methods, providing a sufficient sleep feature foundation for the subsequent establishment of a correlation matrix between multidimensional sleep feature vectors and disease risks.

[0019] When determining the optimal quantitative effect, the present application obtains the first quantitative effect, the second quantitative effect, the third quantitative effect and the fourth quantitative effect respectively through the clustering / classification model, the subjective reference correlation, the physiological index correlation and the classic scale correlation, and performs weighted processing on the first quantitative effect, the second quantitative effect, the third quantitative effect and the fourth quantitative effect to obtain the optimal quantitative effect, rather than directly determining the optimal quantitative effect based on a single method. In this method, the comprehensiveness, robustness, adaptability and objectivity of the quantification are improved through a multi-dimensional weighted quantification method, and the interpretability and decision support capabilities of the optimal quantitative effect are enhanced. This method is particularly suitable for comprehensive quantification problems in complex scenarios, and its quantification results are more accurate.

[0020] In this application, the classification thresholds corresponding to different sleep feature score distributions can be determined separately, and the classification thresholds can be determined adaptively, which can significantly improve the accuracy of the sleep quality classification labels of each sleep feature vector.

[0021] In this application, the correlation matrix between multidimensional sleep feature vectors and disease risks is determined, and the corresponding disease risks are determined based on the relationship between each matrix element in the correlation matrix and the preset threshold. The preset thresholds corresponding to each matrix element can be the same or different, and the specific values ​​of the preset thresholds corresponding to each matrix element can be determined based on actual conditions. This method is suitable for determining multi-dimensional and multi-level disease risks, and can significantly improve the accuracy of determining disease risks.

[0022] In the present application, logarithmic processing is performed on the odds ratio of each dimension of sleep characteristics to the corresponding disease risk, and the variance value corresponding to the log odds ratio is determined; random effect weights are determined based on the variance values; a combined effect size is determined based on the random effect weights and the log odds ratio; and the association matrix is ​​determined based on the combined effect size. By performing the above-mentioned multiple data processing on the odds ratio of each dimension of sleep characteristics to the corresponding disease risk, the accuracy of the association matrix is ​​greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1A Shown is a hardware application scenario diagram of the sleep quality quantification method provided by an embodiment of the present application.

[0024] Figure 1B Shown is a flowchart of a sleep quality quantification method provided by an embodiment of the present application.

[0025] Figure 2 Shown is a flowchart of extracting features from sleep data to obtain multi-dimensional sleep features according to an embodiment of the present application.

[0026] Figure 3 Shown is a flowchart of determining the optimal quantization effect provided by an embodiment of the present application.

[0027] Figure 4 Shown is a flowchart of determining a sleep quality classification label provided by an embodiment of the present application.

[0028] Figure 5 Shown is a flowchart of determining a sleep quality quantification result provided by an embodiment of the present application.

[0029] Figure 6 Shown is a flowchart of determining a correlation matrix between multi-dimensional sleep feature vectors and disease risks provided by an embodiment of the present application.

[0030] Figure 7 Shown is a flowchart of another sleep quality quantification method provided by an embodiment of the present application.

[0031] Figure 8 Shown is a structural diagram of a sleep quality quantification system provided by an embodiment of the present application.

[0032] Figure 9 Shown is a structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0033] The following describes the embodiments of the present application through specific examples. Those skilled in the art can easily understand the other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other unless they conflict.

[0034] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. Therefore, the illustrations only show components related to the present application and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0035] The following embodiments of this application provide sleep quality quantification methods, systems, devices, and media, including but not limited to the hardware application scenarios listed in this embodiment.

[0036] like Figure 1AAs shown, this embodiment provides a hardware application scenario diagram for a sleep quality quantification method, specifically including: a user to be detected, a sleep data acquisition device, and an electronic device. The sleep data acquisition device is used to acquire sleep data from the user to be detected and transmit the sleep data to the electronic device. The electronic device processes the received sleep data to obtain multidimensional sleep features, inputs the multidimensional sleep features into a multidimensional sleep feature quantification model to obtain a multidimensional sleep feature vector, and calculates the sleep quality quantification result based on the multidimensional sleep feature vector.

[0037] The technical solutions in the embodiments of the present application will be described in detail below with reference to the accompanying drawings in the embodiments of the present application.

[0038] like Figure 1B As shown, the embodiment of the present application provides a flowchart of a sleep quality quantification method, as shown in FIG. Figure 1B As shown, the sleep quality quantification method provided in the embodiment of the present application includes the following steps S11 to S14.

[0039] S11, a multi-dimensional sleep data acquisition module, configured to extract features from the sleep data to obtain multi-dimensional sleep features.

[0040] Among them, multidimensional sleep characteristics include rhythm characteristics, sleep duration characteristics, sleep stability characteristics, sleep debt characteristics, and regular work and rest characteristics.

[0041] S12, a multi-dimensional sleep feature extraction module, configured to extract features from the sleep data to obtain multi-dimensional sleep features.

[0042] S13, a multi-dimensional sleep feature vector determination module, configured to input the multi-dimensional sleep feature into a multi-dimensional sleep feature quantification model to obtain a multi-dimensional sleep feature vector.

[0043] The multi-dimensional sleep feature quantification model includes a basic quantification model and an optimized quantification model.

[0044] For example, a multi-dimensional sleep feature vector can be used express.

[0045] In some embodiments, the multidimensional sleep characteristics are input into a basic quantitative model to obtain a score quantification effect of each dimension of the sleep characteristics, including: the multidimensional sleep characteristics quantitative model determines the first The expression for the score quantification effect of the dimensional sleep feature is: in, Indicates the The score quantifies the effect of dimensional sleep characteristics. Indicates the Dimensional sleep data The original score of the data, Indicates the Dimensional sleep data The weight of the data, Indicates the The number of elements in the sleep data.

[0046] In some embodiments, multiple score effects are input into an optimized quantitative model to obtain a multi-dimensional sleep feature vector, including: The expression for determining the optimal quantization effect is: in, represents the optimal quantization effect, Indicates whether there is Optimization conditions, when the first When the conditions for an optimization task are ;otherwise, , represents the optimization objective function, Indicates the A weight set of all questions under the dimension; if the optimal quantization effect is less than the preset quantization effect, adjusting the weight of at least one parameter among the clustering / classification model, the subjective reference correlation, the physiological indicator correlation, and the classic scale correlation to update the optimal quantization effect; if the optimal quantization effect is greater than or equal to the preset quantization effect, normalizing the optimal quantization effect to obtain the multidimensional sleep feature vector output by the multidimensional sleep feature quantization model.

[0047] S14, a sleep quality quantification result determination module, configured to obtain a sleep quality quantification result based on the multi-dimensional sleep feature vector.

[0048] The sleep quality quantification results can be expressed as scores and / or types.

[0049] For example, the vector Predicting disease Probability .

[0050] in, Represents a covariate vector, which is a set of confounding factors that require statistical adjustment or predictor variables, used to separate the independent effects of sleep characteristics on disease risk, such as age, gender, ethnicity, smoking, drinking, exercise habits, education level, income, etc. Its core role is to control confounding bias and ensure that the sleep characteristics effect estimated by the model is Closer to true causal relationship.

[0051] For example, the sleep quality quantification results can be obtained based on a logistic regression model with covariates. Specifically, (1) Feature standardization in, Indicates the The standardized scores of dimensional sleep characteristics quantify the effect, express The mean of express The standard deviation of Indicates the The scores of the three-dimensional sleep characteristics quantify the effects.

[0052] (2) Model construction in, represents the intercept obtained by maximum likelihood estimation, Indicates the Coefficients of dimensional sleep characteristics (comparable after standardization), represents the coefficient of covariates (such as age, gender), represents the covariate vector, , represents the covariate vector The number of elements in , .

[0053] (3) Risk probability prediction in, represents the intercept obtained by maximum likelihood estimation, Indicates the Coefficients of dimensional sleep characteristics (comparable after standardization), represents the coefficient of covariates (such as age, gender), represents the covariate vector, , represents the covariate vector The number of elements in , .

[0054] For example, when predicting a user's coronary heart disease risk based on the above logistic regression model, if the input is: (Among them, the rhythm is 54 for morning and evening, the sleep duration is 12, etc.), output: ,If the preset threshold of coronary heart disease is 0.3, the user is judged to be at high risk.

[0055] An embodiment of the present application provides a sleep quality quantification method, the method comprising a multidimensional sleep data acquisition module for acquiring multidimensional sleep data, the multidimensional sleep data comprising circadian rhythm data, sleep duration data, sleep stability data, sleep debt data, and / or work and rest regularity data; a multidimensional sleep feature extraction module for performing feature extraction on the sleep data to obtain multidimensional sleep features; a multidimensional sleep feature vector determination module for inputting the multidimensional sleep features into a multidimensional sleep feature quantification model to obtain a multidimensional sleep feature vector; wherein the multidimensional sleep feature quantification model comprises a basic quantification model and an optimized quantification model; and a sleep quality quantification result determination module for calculating a sleep quality quantification result based on the multidimensional sleep feature vector. By performing feature extraction on the multidimensional sleep data and obtaining a multidimensional sleep feature vector corresponding to the multidimensional sleep data, sleep quality is quantified based on the multidimensional sleep feature vector, thereby improving the accuracy of sleep quality quantification and associating it with corresponding diseases, thereby providing accurate risk warnings for early-stage diseases.

[0056] like Figure 2 As shown, the embodiment of the present application provides a flowchart for extracting features from sleep data to obtain multi-dimensional sleep features, as shown in FIG. Figure 2 As shown, the method for extracting features from the sleep data to obtain multi-dimensional sleep features provided in the embodiment of the present application includes the following steps S21 to S25.

[0057] S21, obtaining rhythm morning and evening features based on rhythm morning and evening data.

[0058] For example, the rhythmic morning and evening data include the time of getting up or going to bed on weekdays, the time of getting up or going to bed on weekends, the time of being awake, the time of being in the best condition, and the heart rate, blood pressure, core body temperature, etc. in the above different time periods.

[0059] For example, by obtaining the heart rate, blood pressure, core body temperature, etc. of the person to be tested in different time periods, and based on the changing patterns of the heart rate, blood pressure, and core body temperature of the person to be tested in different time periods, the morning and evening rhythm characteristics are obtained.

[0060] As another example, the rhythm morning and evening data can be input into a deep neural network (DNN) to obtain the rhythm morning and evening features output by the deep neural network.

[0061] Specifically, deep neural networks can efficiently identify the time series patterns of gene expression and extract the characteristics of rhythmic early and late periods by training on a large amount of rhythmic early and late period data.

[0062] It should be noted that the rhythm early-late feature based on the rhythm early-late data is only used for illustrative description, and the rhythm early-late feature corresponding to the rhythm early-late data can also be determined by any other suitable method in actual application, which is not limited in the present application.

[0063] S22, obtaining a sleep duration feature based on the sleep duration data.

[0064] For example, the sleep duration feature includes short sleep time, medium sleep time and long sleep time.

[0065] For example, if the sleep duration data is less than the first sleep duration, the sleep duration feature is short sleep time; if the sleep duration data is greater than or equal to the first sleep duration and less than the second sleep duration, the sleep duration feature is medium sleep time; if the sleep duration data is greater than or equal to the second sleep duration, the sleep duration feature is long sleep time.

[0066] It should be noted that the specific values of the first sleep duration and the second sleep duration can be determined based on specific application scenarios, which are not limited in the present application.

[0067] It should be noted that the sleep duration feature and the determination method of the sleep duration feature are only used for illustrative description, and any other suitable sleep duration data can also be included in actual application, which is not limited in the present application.

[0068] S23, obtaining a sleep stability feature based on the sleep stability data.

[0069] For example, the sleep stability data includes the time length from starting to sleep to entering deep sleep, the frequency of waking up at night, the frequency of waking up at midnight and being difficult to sleep, the frequency of nightmares, etc.

[0070] Specifically, the sleep stability feature includes sleep stability and sleep instability.

[0071] For example, if the time length from starting to sleep to entering deep sleep is less than the preset first time length, the frequency of waking up at night is less than the preset first frequency, the frequency of waking up at midnight and being difficult to sleep is less than the preset second frequency, and the frequency of nightmares is less than the preset third frequency, the corresponding sleep stability feature is sleep stability. Conversely, if the time length from starting to sleep to entering deep sleep is greater than or equal to the preset first time length, or the frequency of waking up at night is greater than or equal to the preset first frequency, or the frequency of waking up at midnight and being difficult to sleep is greater than or equal to the preset second frequency, or the frequency of nightmares is greater than or equal to the preset third frequency, the corresponding sleep stability feature is sleep instability.

[0072] It should be noted that the above-mentioned methods of obtaining sleep stability characteristics based on sleep stability data are only for illustrative purposes. In actual applications, any other appropriate methods can be selected according to specific application scenarios to determine the sleep stability characteristics corresponding to the sleep stability data. This application does not impose any restrictions on this.

[0073] S24, obtaining sleep debt features based on the sleep debt data.

[0074] Specifically, sleep debt data includes the difference between ideal sleep and actual sleep duration, the probability of daytime naps, etc.

[0075] Among them, the characteristics of sleep debt include sleep debt and sleep non-debt.

[0076] For example, if the difference between ideal sleep and actual sleep duration is greater than a preset sleep difference, and the probability of daytime naps is greater than a preset probability, then the sleep debt feature corresponding to the sleep debt data is sleep debt. Conversely, if the difference between ideal sleep and actual sleep duration is less than or equal to the preset sleep difference, or the probability of daytime naps is less than or equal to the preset probability, then the sleep debt feature corresponding to the sleep debt data is sleep debt-free.

[0077] S25, obtaining work and rest pattern characteristics based on the work and rest pattern data.

[0078] Among them, the data on work and rest patterns include the time of getting up and going to bed on weekdays, the time of getting up and going to bed on weekends, the number of times you wake up in the middle of the night, etc.

[0079] Among them, the characteristics of regular work and rest include regular work and rest and irregular work and rest.

[0080] For example, if the sleep time each night is within a first preset time range, the wake-up time in the morning is within a second preset time range, and the number of midnight awakenings is within a preset range, then the sleep pattern data corresponding to the sleep pattern characteristic is regular. Conversely, if the sleep time each night is not within the first preset time range, or the wake-up time in the morning is not within the second preset time range, or the number of midnight awakenings is within a preset range, then the sleep pattern data corresponding to the sleep pattern characteristic is irregular.

[0081] It should be noted that this application does not limit the specific values ​​of the above-mentioned first preset time range, second preset time range and preset number range.

[0082] Among them, the sleep data includes rhythm morning and evening data, sleep duration data, sleep stability data, sleep debt data, and work and rest regularity data, and the multidimensional sleep characteristics include rhythm morning and evening characteristics, sleep duration characteristics, sleep stability characteristics, sleep debt characteristics, and work and rest regularity characteristics.

[0083] The embodiment of the present application provides a method for extracting features of the sleep data and obtaining multi-dimensional sleep features, in which different sleep features corresponding to different sleep data are obtained by a deep neural network or the like, thereby providing sufficient sleep feature basis for subsequent establishment of an association matrix between a multi-dimensional sleep feature vector and a disease risk.

[0084] As shown in Figure 3 The embodiment of the present application provides a flowchart for determining an optimal quantization effect, as shown in Figure 3 The method for determining an optimal quantization effect provided by the embodiment of the present application includes the following steps S31 to S35.

[0085] S31, obtaining a first quantization effect of the score quantization effect based on a clustering / classification model.

[0086] The clustering / classification model includes SVM, K-means, etc.

[0087] Exemplarily, an expression of the first quantization effect of the score quantization effect obtained based on the clustering / classification model is as follows: Wherein, The first quantization effect is represented by Q1, The score quantization effect of the i-th sleep feature is represented by Q1(i), The distance between sample groups is represented by D, The distance within a sample group is represented by D, The quantization effect makes the feature of the population have the largest classification effect.

[0088] S32, obtaining a second quantization effect of the score quantization effect based on a subjective reference correlation.

[0089] Exemplarily, an expression of the second quantization effect of the score quantization effect obtained based on the subjective reference correlation is as follows: Wherein, The second quantization effect is represented by Q2, The Pearson correlation coefficient is represented by r, The subjective evaluation score of a subject on a certain dimension of sleep feature is represented by S.

[0090] S33, obtaining a third quantization effect of the score quantization effect based on a physiological index correlation.

[0091] Exemplarily, an expression of the third quantization effect of the score quantization effect obtained based on the physiological index correlation is as follows: Wherein, The third quantization effect is represented by Q3, represents the Pearson correlation coefficient, Represents a physiological indicator measured by a device (such as an actiwatch). For example, the Pearson correlation coefficient is calculated between the average number of awakenings over the past month measured by the actiwatch and the third dimension, sleep stability.

[0092] S34, obtaining a fourth quantization effect of the optimal quantization effect based on the classic scale correlation.

[0093] Exemplarily, the expression of the fourth quantization effect of the optimal quantization effect obtained based on the classic scale correlation is: in, represents the fourth quantization effect, represents the Pearson correlation coefficient, This represents the Pearson correlation coefficient between scores on classic unidimensional sleep assessment scales, such as the 19-item Morning and Evening Questionnaire-19 (MEQ-19) developed by Horne and Ostberg, and the second dimension, morningness or eveningness.

[0094] S35 , performing weighted processing on the first quantization effect, the second quantization effect, the third quantization effect, and the fourth quantization effect to obtain an optimal quantization effect.

[0095] In some embodiments, weighted processing is performed on the first quantization effect, the second quantization effect, the third quantization effect, and the fourth quantization effect, and the weight under the optimal quantization effect is obtained as follows: in, represents the optimal quantization effect, Indicates whether there is Optimization conditions, when the first When the conditions for an optimization task are ;otherwise, , represents the optimization objective function, Indicates the The weight set of all questions under the dimension.

[0096] The embodiment of the present application provides a method for determining the optimal quantitative effect, in which the first quantitative effect, the second quantitative effect, the third quantitative effect and the fourth quantitative effect are obtained respectively by clustering / classification model, subjective reference correlation, physiological index correlation and classic scale correlation, and the first quantitative effect, the second quantitative effect, the third quantitative effect and the fourth quantitative effect are weighted to obtain the optimal quantitative effect, rather than directly determining the optimal quantitative effect based on a single method. The multi-dimensional weighted quantification method in this method improves the comprehensiveness, robustness, adaptability and objectivity of quantification, and also enhances the interpretability and decision support capabilities of the optimal quantitative effect. This method is particularly suitable for comprehensive quantification problems in complex scenarios, and its quantification results are more accurate.

[0097] like Figure 4 As shown, the embodiment of the present application provides a flow chart for determining a sleep quality classification label, such as Figure 4 As shown, the method for determining the sleep quality classification label provided in the embodiment of the present application includes the following steps S41 to S43.

[0098] S41 , using a multidimensional classification model to determine the distribution of sleep feature scores for each dimension in the multidimensional sleep feature vector.

[0099] Among them, the multidimensional classification model includes a rhythm morning and evening classification model, a sleep duration classification model, a sleep stability classification model, a sleep debt classification model and a work and rest regularity classification model.

[0100] S42: The multidimensional classification model determines a classification threshold based on the distribution characteristics of each dimension of sleep characteristic score distribution.

[0101] Specifically, if the sleep feature score distribution of one dimension in the multi-dimensional sleep feature vector is unimodal or uniform, a classification threshold for an optimal quantification effect of the sleep data is determined based on the score ratio.

[0102] For example, the fractional ratio may be any suitable value such as 0.5, 0.6, etc., and the present application does not impose any limitation on the specific value of the fractional ratio.

[0103] For example, if the score distribution of the rhythmic morning and evening sleep characteristics is unimodal or uniformly distributed, and the score ratio is 0.5, the optimal quantitative effect of the rhythmic morning and evening sleep data between 0 and 0.5 is determined as "early type", and the optimal quantitative effect of the rhythmic morning and evening sleep data between 0.5 and 1 is determined as "evening type".

[0104] It should be noted that the method for determining the classification thresholds corresponding to the sleep duration feature score distribution, sleep stability feature score distribution, and sleep debt feature score distribution in the multidimensional sleep characteristics is similar to the method for determining the classification thresholds corresponding to the above-mentioned rhythm morning and evening vectors, and this application will not go into details about this.

[0105] Specifically, if the multi-dimensional sleep feature vector is multimodal distributed, the classification threshold of the sleep data is determined based on the peaks and valleys of the multimodal distribution.

[0106] S43 , inputting the optimal quantization effect corresponding to the multidimensional sleep feature vector into the multidimensional classification model to obtain a sleep quality classification label output by the multidimensional classification model.

[0107] An embodiment of the present application provides a method for determining a sleep quality classification label. In this method, the distribution of sleep feature scores for each dimension in a multidimensional sleep feature vector is determined, and a classification threshold is determined based on the distribution characteristics of the sleep feature score distribution for each dimension. The optimal quantitative effect corresponding to the multidimensional sleep feature vector is input into the multidimensional classification model, and the multidimensional classification model outputs a sleep quality classification label. The method fully considers the distribution of different sleep feature scores, and determines the classification thresholds corresponding to the different sleep feature score distributions. The classification thresholds can be adaptively determined, which can significantly improve the accuracy of the sleep quality classification labels for each sleep feature vector.

[0108] like Figure 5 As shown, the embodiment of the present application provides a flow chart for determining the quantitative result of sleep quality, such as Figure 5 As shown, the method for determining the quantified result of sleep quality provided in the embodiment of the present application includes the following steps S51 to S53.

[0109] S51, determining a correlation matrix between the multi-dimensional sleep feature vector and disease risk.

[0110] S52, if the matrix element in the incident matrix is greater than the preset threshold, then Sleep characteristics increase disease risk.

[0111] For example, the preset threshold value may be set to a suitable value such as 1 or 0.8.

[0112] It should be noted that the specific values ​​of the preset thresholds listed above are only for illustrative purposes. In actual applications, any other appropriate values ​​can be selected as the preset thresholds, and this application does not impose any restrictions on this.

[0113] It should be noted that the preset thresholds corresponding to the matrix elements in the correlation matrix may be the same or different.

[0114] S53, if the matrix element in the incident matrix is less than or equal to the preset threshold, then Maintaining sleep characteristics reduces disease risk.

[0115] An embodiment of the present application provides a method for determining the quantitative results of sleep quality. In this method, the corresponding disease risk is determined by determining the correlation matrix between the multidimensional sleep feature vector and the disease risk, and based on the relationship between each matrix element in the correlation matrix and the preset threshold, the corresponding disease risk is determined, wherein the preset threshold corresponding to each matrix element can be the same or different, and the specific value of the preset threshold corresponding to each matrix element can be determined based on the actual situation. This method is suitable for determining multi-dimensional and multi-level disease risks, and can significantly improve the accuracy of determining disease risks.

[0116] like Figure 6 As shown, the embodiment of the present application provides a flow chart for determining the association matrix between multi-dimensional sleep feature vectors and disease risks, as shown in FIG. Figure 6 As shown, the method for determining the correlation matrix between multi-dimensional sleep feature vectors and disease risks provided by the embodiment of the present application includes the following steps S61 to S66.

[0117] S61, extracting the odds ratio of each dimension of sleep characteristics to the corresponding disease risk based on the database.

[0118] Among them, the odds ratio of disease risk is available OR Indicates that, and OR It represents the incidence rate ratio of the exposed group / the incidence rate ratio of the control group.

[0119] S62, for The odds ratio of the 2-dimensional sleep feature is logarithmically processed to obtain a logarithmic odds ratio corresponding to the odds ratio.

[0120] For example, The expression of the logarithmic processing of the odds ratio of the dimensional sleep characteristics is: in, Indicates the Disease Study Log odds ratios of dimensional sleep characteristics, Indicates the Disease Study Odds ratios for sleep characteristics.

[0121] in, , Indicates the total number of disease studies.

[0122] For example, if the third study reports “short sleep duration vs normal sleep” OR =1.85, then: ,in, =1 indicates the sleep duration.

[0123] S63, determining the variance value corresponding to the log odds ratio.

[0124] Exemplarily, the expression for determining the variance value corresponding to the log odds ratio is: in, , Respectively represent The first study Sleep characteristics OR The lower and upper limits of the 95% confidence interval for the value; 3.92 = 2 × 1.96 (97.5% quantile of the standard normal distribution × 2).

[0125] S64, determining a random effect weight based on the variance value.

[0126] Exemplarily, the expression for determining the random effect weight based on the variance value is: in, Indicates the Variance of between-study heterogeneity of dimensional sleep characteristics (e.g., DerSimonian-Laird estimator).

[0127] S65, determining a combined effect size based on the random effect weight and the log odds ratio.

[0128] Exemplarily, the expression for determining the combined effect size based on the random effect weight and the log odds ratio is: in, Indicates that for any disease Calculation of the pooled effect size for dimensional sleep characteristics.

[0129] S66, determining the correlation matrix based on the combined effect size.

[0130] For example, M diseases and 5-dimensional sleep feature vectors, the corresponding association matrix is:

[0131] An embodiment of the present application provides a method for determining an association matrix between multidimensional sleep feature vectors and disease risks. In this method, logarithmic processing is performed on the odds ratio of each dimensional sleep feature to the corresponding disease risk, and the variance value corresponding to the log odds ratio is determined; random effect weights are determined based on the variance values; a combined effect size is determined based on the random effect weights and the log odds ratio; and the association matrix is ​​determined based on the combined effect size. By performing the above-mentioned multiple data processing on the odds ratio of each dimensional sleep feature to the corresponding disease risk, the accuracy of the association matrix is ​​greatly improved.

[0132] The protection scope of the sleep quality quantification method described in the embodiment of the present application is not limited to the execution order of the steps listed in this embodiment. All solutions implemented by adding, subtracting, or replacing steps in the prior art based on the principles of the present application are included in the protection scope of the present application.

[0133] See also Figure 7 , Figure 7 Shown is a flowchart of another sleep quality quantification method provided by an embodiment of the present application. Figure 7 The steps in Figures 1B to 6 Detailed description is given in , and this application will not go into details here.

[0134] See also Figure 8 In one embodiment, the sleep quality quantification system 80 of the present application includes: a multidimensional sleep feature acquisition module 81, a multidimensional sleep feature vector determination module 82, an association matrix establishment module 83, an association model establishment module 84, and a disease warning result determination module 85.

[0135] The multi-dimensional sleep feature acquisition module 81 is used to extract features from the sleep data to obtain multi-dimensional sleep features.

[0136] The multi-dimensional sleep feature vector determination module 82 is configured to input the multi-dimensional sleep feature into a multi-dimensional sleep feature quantification model to obtain a multi-dimensional sleep feature vector.

[0137] The association matrix building module 83 is used to build an association matrix between the multi-dimensional sleep feature vector and disease risk.

[0138] The association model building module 84 is used to build an association model based on the association matrix and disease types.

[0139] The disease warning result determination module 85 is used to output the disease warning result based on the association model.

[0140] Among them, the structures and principles of the multidimensional sleep feature acquisition module 81, the multidimensional sleep feature vector determination module 82, the association matrix establishment module 83, the association model establishment module 84, and the disease warning result determination module 85 correspond one-to-one to the steps in the above-mentioned sleep quality quantification method, and therefore will not be repeated here.

[0141] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices or methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules / units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules or units, which can be electrical, mechanical or other forms.

[0142] The modules / units described as separate components may or may not be physically separate, and the components displayed as modules / units may or may not be physical modules, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules / units may be selected according to actual needs to achieve the purpose of the embodiments of the present application. For example, the functional modules / units in the various embodiments of the present application may be integrated into a processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into a single module / unit.

[0143] Those skilled in the art should further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0144] An embodiment of the present application also provides an electronic device. Figure 9 The structure diagram of the electronic device 90 in one embodiment of the present application is shown as follows: Figure 9 The electronic device 90 shown is, but not limited to, Figure 9As shown, the electronic device 90 includes a processor 91 , a memory, a system bus 93 , and a network interface 95 , wherein the memory may include a non-volatile storage medium 92 and an internal memory 94 .

[0145] The non-volatile storage medium 92 can store an operating system and a computer program. The computer program includes program instructions, which, when executed, can cause the processor to execute any one of the sleep quality quantification methods provided in the embodiments of the present application.

[0146] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0147] The internal memory 94 provides an environment for running the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any one of the sleep quality quantification methods provided in the embodiments of the present application.

[0148] The network interface 95 is used for network communication, such as sending assigned tasks, etc. It will be understood by those skilled in the art that Figure 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0149] It should be understood that the processor 91 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0150] The electronic device 90 in the embodiment of the present application may include terminal devices such as tablet computers, laptop computers, mobile phones, supercomputers, smart wearable devices, etc., and can also be applied to databases, servers, and service response systems based on terminal artificial intelligence. The embodiment of the present application does not impose any restrictions on the specific type of electronic device.

[0151] For example, the electronic device can be a station (STAION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, a computer, a laptop computer, a handheld communication device, a handheld computing device, and / or other devices for communicating on a wireless system and a next-generation communication system, such as a mobile terminal in a 5G network, a mobile terminal in a future-evolved Public Land Mobile Network (PLMN), or a mobile terminal in a future-evolved Non-terrestrial Network (NTN).

[0152] The present application also provides a computer-readable storage medium. Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments can be performed by instructing a processor through a program. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, a hard disk, a solid-state drive, magnetic tape, a floppy disk, an optical disc, or any combination thereof. The storage medium can be any available medium accessible by a computer, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a digital video disc (DVD)), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0153] The embodiments of the present application may also provide a computer program product, which includes one or more computer instructions. When the computer instructions are loaded and executed on a computing device, the process or function described in the embodiments of the present application is generated in whole or in part. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, or data center to another website, computer, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0154] When the computer program product is executed by a computer, the computer executes the method described in the above method embodiment. The computer program product can be a software installation package. When the above method is needed, the computer program product can be downloaded and executed on the computer.

[0155] The descriptions of the processes or structures corresponding to the above figures have different emphases. For parts that are not described in detail in a certain process or structure, please refer to the relevant descriptions of other processes or structures.

[0156] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by one of ordinary skill in the art without departing from the spirit and technical concepts disclosed in this application shall be covered by the claims of this application.

Claims

1. A sleep quality quantification method, characterized in that: The method comprises: A multidimensional sleep data acquisition module, configured to acquire multidimensional sleep data, wherein the multidimensional sleep data includes circadian rhythm data, sleep duration data, sleep stability data, sleep debt data, and / or work and rest regularity data; A multidimensional sleep feature extraction module, configured to extract features from the sleep data to obtain multidimensional sleep features; a multidimensional sleep feature vector determination module, configured to input the multidimensional sleep feature into a multidimensional sleep feature quantification model to obtain a multidimensional sleep feature vector; wherein the multidimensional sleep feature quantification model includes a basic quantification model and an optimized quantification model; The sleep quality quantification result determination module is configured to calculate and obtain the sleep quality quantification result based on the multi-dimensional sleep feature vector.

2. The sleep quality quantification method according to claim 1, characterized in that: The multi-dimensional sleep characteristics are input into the basic quantitative model to obtain the score quantitative effect of each dimension of the sleep characteristics, including: the multi-dimensional sleep characteristics quantitative model determines the first The expression for the score quantification effect of the dimensional sleep feature is: in, Indicates the The score quantifies the effect of dimensional sleep characteristics. Indicates the Dimensional sleep data The original score of the data, Indicates the Dimensional sleep data The weight of the data, Indicates the The number of elements in the sleep data dimension.

3. The sleep quality quantification method according to claim 2, characterized in that: Input the multiple score effects into the optimization quantification model to obtain a multi-dimensional sleep feature vector, including: The expression for determining the optimal quantization effect is: in, represents the optimal quantization effect, Indicates whether there is Optimization conditions, when the first When the conditions for an optimization task are ;otherwise, , represents the optimization objective function, Indicates the A weight set of all questions under the dimension; if the optimal quantization effect is less than the preset quantization effect, adjusting the weight of at least one parameter among the clustering / classification model, the subjective reference correlation, the physiological indicator correlation, and the classic scale correlation to update the optimal quantization effect; if the optimal quantization effect is greater than or equal to the preset quantization effect, normalizing the optimal quantization effect to obtain the multidimensional sleep feature vector output by the multidimensional sleep feature quantization model.

4. The sleep quality quantification method according to claim 3, characterized in that: The method further comprises: Obtaining a first quantitative effect of the score quantitative effect based on a clustering / classification model; Obtaining a second quantization effect of the score quantization effect based on the subjective reference correlation; Obtaining a third quantitative effect of the score quantitative effect based on the correlation of the physiological indicators; A fourth quantization effect of obtaining the optimal quantization effect based on the classic scale correlation; The first quantization effect, the second quantization effect, the third quantization effect, and the fourth quantization effect are weighted to obtain an optimal quantization effect.

5. The sleep quality quantification method according to claim 1, characterized in that: The step of extracting features from the sleep data to obtain multi-dimensional sleep features includes: Obtain rhythm morning and evening characteristics based on rhythm morning and evening data; Obtaining sleep duration characteristics based on sleep duration data; obtaining a sleep stability feature based on the sleep stability data; Obtain sleep debt features based on sleep debt data; Obtaining work and rest pattern characteristics based on work and rest pattern data; The multidimensional sleep characteristics include the rhythm morning and evening characteristics, the sleep duration characteristics, the sleep stability characteristics, the sleep debt characteristics, and the work and rest regularity characteristics.

6. The sleep quality quantification method according to claim 1, characterized in that: The method further comprises: Determining the distribution of sleep characteristic scores for each dimension in the multidimensional sleep characteristic vector using a multidimensional classification model; The multidimensional classification model determines a classification threshold based on the distribution characteristics of each dimension of sleep characteristic score distribution; The optimal quantization effect corresponding to the multidimensional sleep feature vector is input into the multidimensional classification model to obtain a sleep quality classification label output by the multidimensional classification model.

7. The sleep quality quantification method according to claim 6, characterized in that: The step of calculating and obtaining a sleep quality quantification result based on the multi-dimensional sleep feature vector includes: Determining a correlation matrix between the multidimensional sleep feature vector and disease risk; If the matrix elements in the incidence matrix is greater than the preset threshold, then Sleep characteristics increase disease risks; If the matrix elements in the incidence matrix is less than or equal to the preset threshold, then Maintaining sleep characteristics reduces disease risk.

8. The sleep quality quantification method according to claim 7, characterized in that: Determining the association matrix between the multidimensional sleep feature vector and disease risk includes: Based on the database, the odds ratio of each dimension of sleep characteristics and the corresponding disease risk was extracted; For the first Taking logarithm processing on the odds ratio of the dimensional sleep feature to obtain the log odds ratio corresponding to the odds ratio; determining a variance value corresponding to the log odds ratio; determining random effect weights based on the variance values; determining a pooled effect size based on the random effects weight and the log odds ratio; The association matrix is ​​determined based on the combined effect size.

9. A sleep quality quantification system, comprising: A multi-dimensional sleep feature acquisition module, configured to extract features from the sleep data to obtain multi-dimensional sleep features; a multidimensional sleep feature vector determination module, configured to input the multidimensional sleep feature into a multidimensional sleep feature quantification model to obtain a multidimensional sleep feature vector; A correlation matrix establishment module, used to establish a correlation matrix between the multi-dimensional sleep feature vector and disease risk; An association model building module, used to build an association model based on the association matrix and disease types; The disease warning result determination module is used to output the disease warning result based on the association model.

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 sleep quality quantification method according to any one of claims 1 to 8 is implemented.

11. An electronic device, characterized in that: The electronic device comprises: a memory storing a computer program; A processor is communicatively connected to the memory, and executes the sleep quality quantification method according to any one of claims 1 to 8 when calling the computer program.

Images