Methods, devices, equipment and storage media for processing sleep guidance information
By acquiring users' raw sleep data and target health status, querying correlations to determine target data for sleep influencing factors, and pushing sleep change data, this solves the problem of the inability to quantify sleep guidance in existing technologies and improves the effectiveness of sleep guidance.
Patent Information
- Application Number
- CN202110982640.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-08-25
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2041-08-25
AI Technical Summary
Existing sleep guidance methods cannot quantify the guidance plan, resulting in poor sleep guidance effectiveness.
By acquiring the original sleep data and target sleep health of the users to be guided, querying the correlation between health and sleep influencing factors, determining the target sleep data for sleep influencing factors, and pushing sleep change data as guidance information based on the differences.
This approach quantifies sleep guidance programs and improves the effectiveness of sleep guidance.
Smart Images

Figure CN115938538B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of deep learning technology, and in particular to a method, apparatus, device and storage medium for processing sleep guidance information. Background Technology
[0002] Sleep is essential for life; good sleep helps the body and mind recover and relieves psychological stress. However, with technological advancements and a faster pace of life, many people suffer from sleep problems such as difficulty falling asleep at night, insomnia, excessive dreaming and sweating, daytime fatigue, and the need to rely on sleep aids. Over time, these issues affect physical health and increase the risk of chronic diseases such as sleep apnea, hypertension, hyperlipidemia, hyperglycemia, and obesity.
[0003] Most sleep problems are caused by long-term poor sleep habits. For example, many people stay up late playing on their phones or other electronic devices, causing them to miss the optimal sleep time and resulting in difficulty falling asleep and insufficient sleep duration. Others play online games all night and then try to catch up on sleep during the day, leading to irregular sleep patterns and difficulty falling asleep at night.
[0004] In related technologies, sleep guidance courses are usually used to improve users' theoretical knowledge of sleep and thus provide sleep guidance, or sleep guidance is provided from a physical perspective through sleep-aiding diets or medications to improve users' sleep problems. However, neither of these methods can quantify the guidance plan when providing sleep guidance, so the sleep guidance effect is poor. Summary of the Invention
[0005] The purpose of this application is to at least partially solve one of the technical problems in the related art.
[0006] The first aspect of this application proposes a method for processing sleep guidance information, comprising: obtaining raw sleep data of various sleep influencing factors for a user to be guided, and obtaining a set target sleep health score; querying a first correlation between the health score and each sleep influencing factor based on the target sleep health score to obtain target sleep data of each sleep influencing factor; determining sleep change data of each sleep influencing factor based on the difference between the target sleep data of each sleep influencing factor and the raw sleep data of the corresponding sleep influencing factor; and pushing the sleep change data of each sleep influencing factor as sleep guidance information to the user terminal.
[0007] Optionally, before guiding the user to obtain the original sleep data of each sleep influencing factor, the method further includes: obtaining multiple candidate sleep influencing factors and multiple sleep problems; determining the correlation between each candidate sleep influencing factor and the multiple sleep problems; and selecting each sleep influencing factor from the multiple candidate sleep influencing factors based on the correlation between each candidate sleep influencing factor and the multiple sleep problems.
[0008] Optionally, determining the correlation between each candidate sleep influencing factor and the plurality of sleep problems includes: acquiring first sample data, wherein the first sample data includes sample sleep data of each candidate sleep influencing factor corresponding to a plurality of first sample users and the corresponding sleep problems; using the sample sleep data of the candidate sleep influencing factors corresponding to the plurality of first sample users and the corresponding sleep problems as training data for an association model, wherein the association model has corresponding candidate sleep influencing factors and sleep problems; training the association model using the training data to obtain parameters of the association model; and determining the correlation between the candidate sleep influencing factor and the sleep problem based on the parameters of the association model.
[0009] Optionally, selecting each sleep influencing factor from the plurality of candidate sleep influencing factors based on the correlation between each candidate sleep influencing factor and the plurality of sleep problems includes: for each candidate sleep influencing factor, obtaining the target sleep problems with a correlation greater than a preset correlation threshold and the number of the target sleep problems; determining the average correlation between the same candidate sleep influencing factor and each target sleep problem; and determining at least one sleep influencing factor from the plurality of candidate sleep influencing factors, wherein the average value corresponding to the sleep influencing factor is greater than a preset threshold, and the number of the corresponding target sleep problems is greater than a preset number threshold.
[0010] Optionally, before querying the first correlation between the health score and each sleep influencing factor based on the target sleep health score to obtain the target sleep data of each sleep influencing factor, the method further includes: obtaining a second correlation between each sleep influencing factor and the health score; performing an inverse operation on the second correlation to obtain the first correlation between the health score and each sleep influencing factor.
[0011] Optionally, obtaining the second correlation between the sleep influencing factors and the health score includes: obtaining second sample data, wherein the second sample data includes sample sleep data and corresponding sample sleep health scores for each sleep influencing factor for multiple second sample users; constructing an initial second correlation between the sleep influencing factors and the health score; and adjusting the initial second correlation using the second sample data to obtain the second correlation.
[0012] Optionally, obtaining the set target sleep health score includes: querying the second correlation between each sleep influencing factor and the health score based on the original sleep data of each sleep influencing factor of the user to be guided, to obtain the original sleep health score of the user to be guided; and determining the target sleep health score based on the original sleep health score.
[0013] The sleep guidance information processing method of this application embodiment involves obtaining the original sleep data of each sleep influencing factor and the set target sleep health level for the user to be guided. Based on the target sleep health level, a first correlation relationship is queried between the health level and each sleep influencing factor to obtain the target sleep data for each sleep influencing factor. Then, based on the difference between the target sleep data of each sleep influencing factor and the original sleep data of the corresponding sleep influencing factor, the sleep change data of each sleep influencing factor is determined. Finally, the sleep change data of each sleep influencing factor is pushed to the user as sleep guidance information. This allows for guidance on changing sleep habits based on the sleep change data of each sleep influencing factor, quantifying the sleep guidance plan and improving the effectiveness of sleep guidance.
[0014] A second aspect of this application provides a sleep guidance information processing device, comprising: a first acquisition module, configured to acquire raw sleep data of various sleep influencing factors and acquire a set target sleep health score for a user to be guided; a query module, configured to query a first correlation between the health score and the various sleep influencing factors based on the target sleep health score, and obtain target sleep data of the various sleep influencing factors; a first determination module, configured to determine sleep change data of the various sleep influencing factors based on the difference between the target sleep data of the various sleep influencing factors and the raw sleep data of the corresponding sleep influencing factors; and a sending module, configured to push the sleep change data of the various sleep influencing factors as sleep guidance information to the user terminal.
[0015] Optionally, the device further includes: a second acquisition module, configured to acquire multiple candidate sleep influencing factors and multiple sleep problems; a second determination module, configured to determine the correlation degree between each candidate sleep influencing factor and the multiple sleep problems; and a selection module, configured to select each sleep influencing factor from the multiple candidate sleep influencing factors based on the correlation degree between each candidate sleep influencing factor and the multiple sleep problems.
[0016] Optionally, the second determining module includes: a first acquiring unit, configured to acquire first sample data, wherein the first sample data includes sample sleep data of each candidate sleep influencing factor corresponding to a plurality of first sample users and corresponding sleep problems; a processing unit, configured to use the sample sleep data of the candidate sleep influencing factors corresponding to the plurality of first sample users and the sleep problems corresponding to the plurality of first sample users as training data for an association model, wherein the association model has corresponding candidate sleep influencing factors and sleep problems; a training unit, configured to train the association model using the training data of the association model to obtain parameters of the association model; and a first determining unit, configured to determine the correlation degree between the candidate sleep influencing factors and the sleep problems based on the parameters of the association model.
[0017] Optionally, the selection module includes: a second acquisition unit, configured to acquire, for each candidate sleep influencing factor, target sleep problems with a correlation degree greater than a preset correlation degree threshold and the number of target sleep problems; a second determination unit, configured to determine the average value of the correlation degree between the same candidate sleep influencing factor and each target sleep problem; and a third determination unit, configured to determine at least one sleep influencing factor from the plurality of candidate sleep influencing factors, wherein the average value corresponding to the sleep influencing factor is greater than a preset threshold, and the number of target sleep problems corresponding to it is greater than a preset number threshold.
[0018] Optionally, the device further includes:
[0019] The third acquisition module is used to acquire the second correlation between each sleep influencing factor and the health score; the processing module is used to perform an inverse operation on the second correlation to obtain the first correlation between the health score and each sleep influencing factor.
[0020] Optionally, the third acquisition module includes: a third acquisition unit, configured to acquire second sample data, wherein the second sample data includes sample sleep data of each sleep influencing factor corresponding to multiple second sample users and sample sleep health scores corresponding to each; a construction unit, configured to construct an initial second correlation relationship between each sleep influencing factor and the health score; and an adjustment unit, configured to adjust the initial second correlation relationship using the second sample data to obtain the second correlation relationship.
[0021] Optionally, the first acquisition module includes: a query unit, configured to query a second correlation between each sleep influencing factor and the health score based on the original sleep data of each sleep influencing factor of the user to be guided, and obtain the original sleep health score of the user to be guided; and a fourth determination unit, configured to determine the target sleep health score based on the original sleep health score.
[0022] The sleep guidance information processing device of this application embodiment obtains the original sleep data of each sleep influencing factor and the set target sleep health level for the user to be guided. Based on the target sleep health level, it queries the first correlation between the health level and each sleep influencing factor to obtain the target sleep data for each sleep influencing factor. Then, based on the difference between the target sleep data of each sleep influencing factor and the original sleep data of the corresponding sleep influencing factor, it determines the sleep change data of each sleep influencing factor, and then pushes the sleep change data of each sleep influencing factor as sleep guidance information to the user. This enables the user to change their sleep behavior habits based on the sleep change data of each sleep influencing factor, quantifying the sleep guidance plan and thus improving the effectiveness of sleep guidance.
[0023] A third aspect of this application provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the sleep guidance information processing method described in the above embodiments.
[0024] A fourth aspect of this application provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to perform a method for processing sleep guidance information as described in the above embodiments.
[0025] A fifth aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the sleep guidance information processing method described in the above embodiments.
[0026] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description
[0027] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein,
[0028] Figure 1 A flowchart illustrating a method for processing sleep guidance information provided in an embodiment of this application;
[0029] Figure 2 This is a schematic diagram illustrating an application scenario of a method for processing sleep guidance information provided in an embodiment of this application.
[0030] Figure 3 A flowchart illustrating another method for processing sleep guidance information provided in an embodiment of this application;
[0031] Figure 4 A flowchart illustrating another method for processing sleep guidance information provided in an embodiment of this application;
[0032] Figure 5 A schematic diagram of a sleep guidance information processing device provided in an embodiment of this application;
[0033] Figure 6 This is a schematic block diagram of an example electronic device used to implement embodiments of the present disclosure. Detailed Implementation
[0034] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.
[0035] Sleep is essential for life; good sleep helps the body and mind recover and relieves psychological stress. However, with technological advancements and a faster pace of life, many people suffer from sleep problems such as difficulty falling asleep at night, insomnia, excessive dreaming and sweating, daytime fatigue, and the need to rely on sleep aids. Over time, these issues affect physical health and increase the risk of chronic diseases such as sleep apnea, hypertension, hyperlipidemia, hyperglycemia, and obesity.
[0036] Most sleep problems are caused by long-term poor sleep habits. For example, many people stay up late playing on their phones or other electronic devices, causing them to miss the optimal sleep time and resulting in difficulty falling asleep and insufficient sleep duration. Others play online games all night and then try to catch up on sleep during the day, leading to irregular sleep patterns and difficulty falling asleep at night.
[0037] In related technologies, sleep guidance courses are usually used to improve users' theoretical knowledge of sleep and thus provide sleep guidance, or sleep guidance is provided from a physical perspective through sleep-aiding diets or medications to improve users' sleep problems. However, neither of these methods can quantify the guidance plan when providing sleep guidance, so the sleep guidance effect is poor.
[0038] This application addresses the problem that existing sleep guidance methods cannot quantify guidance plans, resulting in poor sleep guidance effectiveness. It proposes a method for processing sleep guidance information. This method involves obtaining the original sleep data of each sleep influencing factor and a set target sleep health level from the user. Based on the target sleep health level, a first correlation relationship is queried between the health level and each sleep influencing factor to obtain the target sleep data for each factor. Then, based on the difference between the target sleep data and the original sleep data of each factor, the sleep change data for each factor is determined. This sleep change data is then pushed to the user as sleep guidance information. This allows for guidance on changing sleep habits based on the sleep change data of each influencing factor, quantifying the sleep guidance plan and improving the effectiveness of sleep guidance.
[0039] The following description, with reference to the accompanying drawings, describes a method, apparatus, electronic device, and storage medium for processing sleep guidance information according to embodiments of this application.
[0040] Figure 1 This is a flowchart illustrating a method for processing sleep guidance information provided in an embodiment of this application.
[0041] It should be noted that the sleep guidance information processing method provided in this application embodiment, hereinafter referred to as the processing method, is executed by the sleep guidance information processing device provided in this application embodiment, hereinafter referred to as the processing device. The sleep guidance information processing device can be an electronic device or can be configured within an electronic device to quantify the sleep guidance scheme and improve the effectiveness of sleep guidance.
[0042] Among these, electronic devices can include personal computers, cloud devices, mobile devices, wearable devices, etc. Wearable devices can include smartwatches, smart bracelets, etc.
[0043] This application uses the example of a processing device being configured in an electronic device, where the electronic device is a cloud device corresponding to a wearable device, for illustration.
[0044] like Figure 1 As shown, the method for processing this sleep guidance information includes the following steps:
[0045] Step 101: Guide the user to obtain the raw sleep data of each sleep influencing factor, and obtain the set target sleep health level.
[0046] Among them, sleep-influencing factors can be understood as factors related to sleep that affect sleep quality, such as "sleep start time", "sleep duration", and "sleep rhythm index".
[0047] The raw sleep data for sleep influencing factors are calculated based on the current baseline sleep data of the user to be guided, according to the strategy for determining sleep influencing factors. Baseline sleep data can be understood as any sleep-related data, such as whether the user to be guided was asleep or awake at a certain time on a certain day, or whether the user talked in their sleep, turned over, or made other movements while asleep.
[0048] Taking the collection of basic sleep data from a user to be guided through a wearable device as an example, the wearable device can enable all-day heart rate monitoring, recording the user's heart rate value every minute of each day. Based on this heart rate value, it can determine whether the user is sleeping at any given minute of each day, thus obtaining the user's sleep state (whether they are asleep or awake). This sleep state of the user every minute of each day constitutes a type of basic sleep data for the user.
[0049] Referring to Table 1 below, in this embodiment of the application, the original sleep data of each sleep influencing factor can be calculated based on the current basic sleep data of the user to be guided, according to the determination strategy of each sleep influencing factor in Table 1. It should be noted that the sleep influencing factors shown in Table 1 are only illustrative examples and should not be construed as limiting the technical solution of this application. Each sleep influencing factor in the embodiment of this application can be any sleep influencing factor, and this application does not impose any restrictions on it.
[0050] Table 1. Factors affecting sleep and their corresponding explanations
[0051]
[0052] Taking the "sleep rhythm index" as an example, the original sleep data of the "sleep rhythm index" over N days can be obtained by using the determination strategy shown in the following formula (1).
[0053]
[0054] Where N is the number of days, and M is the number of minutes in a day. i,j For the sleep state at minute j on day i, s i+1,j This represents the sleep state at minute j on day i+1. When s i,j =s i+1,j At that time, δ(s) i,j ,s i+1,j ) = 1; when s i,j ≠s i+1,j At that time, δ(s) i,j ,s i+1,j ) = 0.
[0055] Assuming the wearable device is enabled to monitor heart rate all day, and records the heart rate value of the user to be guided per minute over 42 days, i.e. N is 42 and M is 1440, and the user to be guided has the same daily routine over 42 days, then according to the determination strategy shown in formula (1), the original sleep data of the sleep influencing factor "sleep rhythmicity index" of the user to be guided over 42 days can be determined to be 100.
[0056] Among them, sleep health score is used to measure the quality of a user's sleep. Target sleep health score is the level of sleep health that the user is to be guided to achieve.
[0057] In an exemplary embodiment, the current sleep health of the user to be guided can be determined based on the raw sleep data of each sleep influencing factor. Based on this current sleep health, a target sleep health level can be set for the user. The specific method for obtaining the set target sleep health level will be described in the following embodiments and will not be repeated here.
[0058] Step 102: Based on the target sleep health score, query the first correlation between the health score and each sleep influencing factor to obtain the target sleep data for each sleep influencing factor.
[0059] The target sleep data for each sleep influencing factor refers to the sleep data for each sleep influencing factor when the user is to achieve the target sleep health score. For example, when the target sleep health score is 0.8, the sleep data for sleep influencing factors such as "sleep start time" and "sleep duration" represent the time and frequency of sleep that the user needs to go to bed.
[0060] In an exemplary embodiment, a first correlation between health status and each sleep influencing factor can be predetermined. After obtaining the set target sleep health status, the first correlation between health status and each sleep influencing factor can be queried based on the target sleep health status to obtain the target sleep data of each sleep influencing factor.
[0061] In an exemplary embodiment, a second correlation between each sleep-influencing factor and health status can be predetermined, and then a first correlation between health status and each sleep-influencing factor can be determined based on the second correlation between the sleep-influencing factors and health status. The second correlation and the first correlation are inverse relationships.
[0062] For example, in the embodiments of this application, the second correlation between each sleep-affecting factor and health can be determined as the relationship represented by the logistic regression model shown in the following formulas (2) and (3).
[0063]
[0064]
[0065] Where n is the number of sleep-influencing factors, f(x) i Let w be the density function of the i-th sleep-influencing factor. i Let be the weight vector of the i-th sleep influencing factor, F(x) be the distribution function of each sleep influencing factor, and y be the sleep health score.
[0066] Where, f(x) i The function form of ) can be any function from a user-defined function family. These function families include: linear function families, polynomial function families, exponential function families, logarithmic function families, and trigonometric function families.
[0067] In this embodiment of the disclosure, the first correlation between health and each sleep influencing factor can be determined by inverse operation according to formulas (2) and (3), and the first correlation between health and each sleep influencing factor can be queried according to the target sleep health to obtain the target sleep data of each sleep influencing factor.
[0068] Specifically, for any j-th sleep influencing factor, we can assume that the values of the other sleep influencing factors remain unchanged. Since the function family in formula (3) is an elementary function, we can calculate its inverse function. Substituting the target sleep health y' into formula (2), we can obtain the following formulas (4) and (5):
[0069]
[0070]
[0071] Where, x' j represents the target sleep data for the j-th sleep influencing factor.
[0072] Furthermore, It can be regarded as a constant, denoted by C. Accordingly, formula (5) can be transformed into the following formula (6):
[0073] G -1 (y′)=w j *f(x' j )+C (6)
[0074] Based on formula (6), we can obtain the following formula (7), and then obtain formula (8):
[0075]
[0076]
[0077] The target sleep data x' of the j-th sleep influencing factor can be obtained according to formula (8). j .
[0078] It should be noted that the relationship represented by the logistic regression model in the above embodiments as the first correlation between health and various sleep influencing factors is only an example and should not be construed as a limitation on the technical solution of this application. In practical applications, those skilled in the art can use any other interpretable binary classification machine learning model, such as support vector machine model or neural network model, as needed to determine the first correlation between health and various sleep influencing factors. This application does not impose any restrictions on this.
[0079] Step 103: Determine the sleep change data of each sleep influencing factor based on the difference between the target sleep data of each sleep influencing factor and the original sleep data of the corresponding sleep influencing factor.
[0080] Step 104: Push the sleep change data of each sleep influencing factor as sleep guidance information to the user terminal.
[0081] In an exemplary embodiment, after determining the sleep change data of each sleep influencing factor, for each sleep influencing factor, the sleep change data of the sleep influencing factor can be determined based on the difference between the target sleep data and the original sleep data of the sleep influencing factor, thereby pushing the sleep change data of each sleep influencing factor as sleep guidance information to the user terminal.
[0082] Among them, the sleep change data of sleep influencing factors can be specifically the amount of change of sleep influencing factors. For example, for the sleep influencing factor of "sleep start time", if the target sleep data is 9 o'clock and the original sleep data is 11 o'clock, the sleep change data of this sleep influencing factor can be 2 hours earlier.
[0083] In an exemplary embodiment, the user terminal may be an electronic device such as a mobile phone belonging to the user to be guided, a wearable device worn by the user to be guided, or other devices, and this disclosure does not limit it.
[0084] For example, suppose the original sleep data for the sleep factor "sleep start time" is 11 PM, and the target sleep data for this factor is 10 PM. This means the target sleep data differs from the original data by one hour, a change of one hour. For the sleep factor "sleep duration," the original sleep data is 9 hours, and the target sleep data is also 9 hours. This means the target sleep data for this factor is the same as the original sleep data, a change of 0. Then, a sleep guidance message can be sent to the user's mobile phone: "It is recommended to go to bed one hour earlier tonight and keep the sleep duration consistent with yesterday." This quantifies the sleep guidance plan; users only need to follow the guidance to improve sleep quality, thus enhancing the effectiveness of sleep guidance.
[0085] It should be noted that, for each sleep influencing factor, after determining the sleep change data, when pushing the sleep change data of each sleep influencing factor to the user as sleep guidance information, the sleep influencing factors can also be sorted according to the sleep change data of each sleep influencing factor, and a preset number of sleep influencing factors' sleep change data can be selected from the sorting results to push to the user. The preset number can be set arbitrarily as needed, for example, it can be 3 or 5, and this application does not impose any restrictions on it.
[0086] For example, assuming the preset quantity is 3, and the changes in 15 sleep-influencing factors are determined, if the changes in sleep-influencing factors x1, x2, and x3 are smaller than the changes in other sleep-influencing factors, then the changes in sleep-influencing factors x1, x2, and x3 can be pushed to the user as sleep guidance information.
[0087] In an exemplary embodiment, reference is made to Figure 2As shown in the scenario diagram, wearable device 220 can collect sleep-related data of the user to be guided to obtain basic sleep data, and send the basic sleep data to cloud device 210 where the processing device is located. Cloud device 210 can obtain the original sleep data of each sleep influencing factor of the user to be guided and obtain the set target sleep health score based on the basic sleep data of the user to be guided. Based on the target sleep health score, it queries the first correlation between the health score and each sleep influencing factor to obtain the target sleep data of each sleep influencing factor. Based on the difference between the target sleep data of each sleep influencing factor and the original sleep data of the corresponding sleep influencing factor, it determines the sleep change data of each sleep influencing factor, and then pushes the sleep change data of each sleep influencing factor as sleep guidance information to the mobile phone or other electronic device 230 of the user to be guided, so as to realize the sleep guidance of the user to be guided.
[0088] The sleep guidance information processing method of this application embodiment involves obtaining the original sleep data of each sleep influencing factor and the set target sleep health level for the user to be guided. Based on the target sleep health level, a first correlation relationship is queried between the health level and each sleep influencing factor to obtain the target sleep data for each sleep influencing factor. Then, based on the difference between the target sleep data of each sleep influencing factor and the original sleep data of the corresponding sleep influencing factor, the sleep change data of each sleep influencing factor is determined. Finally, the sleep change data of each sleep influencing factor is pushed to the user as sleep guidance information. This allows for guidance on changing sleep habits based on the sleep change data of each sleep influencing factor, quantifying the sleep guidance plan and improving the effectiveness of sleep guidance.
[0089] As can be seen from the above analysis, in this embodiment of the disclosure, the sleep change data of each sleep influencing factor can be determined based on the original sleep data of each sleep influencing factor and the target sleep health of the user to be guided, and then the sleep change data of each sleep influencing factor can be pushed to the user as sleep guidance information. The following is in conjunction with... Figure 3 The method for determining each sleep-influencing factor in the embodiments of this application will be described.
[0090] Figure 3 This is a flowchart illustrating another method for processing sleep guidance information provided in an embodiment of this application.
[0091] like Figure 3 As shown, the method for processing sleep guidance information, including the method for obtaining various sleep influencing factors, may include the following steps:
[0092] Step 301: Obtain multiple candidate sleep influencing factors and multiple sleep problems.
[0093] In an exemplary embodiment, candidate sleep impact factors can be extracted from medical literature. For example, highly cited literature related to "sleep" can be searched in a browser to obtain candidate sleep impact factors. Alternatively, candidate sleep impact factors can be obtained by searching high-ranking sleep-related journals in the medical field using keywords such as "factor" or "survey".
[0094] Sleep problems can be identified through questionnaires. For example, a questionnaire may include multiple candidate sleep problems such as: frequent awakenings, waking up early, insomnia, vivid dreams, fatigue upon waking, needing to urinate at night, difficulty falling asleep at night, headaches and dizziness upon waking, daytime fatigue and drowsiness, excessive sleepiness, difficulty falling back asleep after waking, waking up early and having difficulty falling back asleep, frequent snoring or being awakened by snoring during sleep, currently taking sleep aids (not health supplements), insomnia, irritability, and excessive sweating. Questionnaires can be distributed to multiple users, allowing them to select corresponding sleep problems based on their physical condition. There is no limit to the number of sleep problems that can be selected, thus obtaining multiple sleep problems as described in this application embodiment based on the user's choices.
[0095] It should be noted that the above-mentioned sleep problems are merely illustrative examples and should not be construed as limiting the technical solutions of this application. The multiple sleep problems in the embodiments of this application can be any sleep problems, and this application does not impose any restrictions on them.
[0096] Step 302: Determine the association degree between each candidate sleep influencing factor and multiple sleep problems.
[0097] Among them, the correlation degree is used to characterize the degree of association between candidate sleep influencing factors and sleep problems.
[0098] In an exemplary embodiment, for each candidate sleep influencing factor, the correlation between the candidate sleep influencing factor and multiple sleep problems can be determined separately.
[0099] In an exemplary embodiment, the correlation between each candidate sleep influencing factor and each sleep problem can be obtained in the following manner: First sample data is obtained, wherein the first sample data includes sample sleep data of each candidate sleep influencing factor corresponding to multiple first sample users and their respective corresponding sleep problems; the sample sleep data of the candidate sleep influencing factors corresponding to multiple first sample users and their respective corresponding sleep problems are used as training data for an association model, wherein the association model has corresponding candidate sleep influencing factors and sleep problems; the association model is trained using the training data to obtain the parameters of the association model; and the correlation between the candidate sleep influencing factors and sleep problems is determined based on the parameters of the association model.
[0100] Among them, the sample sleep data of each candidate sleep influencing factor corresponding to multiple first sample users can be calculated according to the determination strategy of each candidate sleep influencing factor based on the basic sleep data corresponding to multiple first sample users; the sleep problems corresponding to multiple first sample users can be obtained through questionnaire surveys.
[0101] The association between candidate sleep influencing factors and sleep problems can be characterized by the AOR (Adjusted Odds Ratio) between candidate sleep influencing factors and sleep problems, or by any other variable that can characterize the degree of association between candidate sleep influencing factors and sleep problems. This application does not impose any restrictions on this.
[0102] The correlation model can be, for example, a logistic regression model, or other types of models; this application does not limit this.
[0103] In an exemplary embodiment, for each candidate sleep influencing factor and each sleep problem, a correlation model can be constructed. The sample sleep data of the candidate sleep influencing factor corresponding to multiple first sample users, and the data of the sleep problem corresponding to the multiple first sample users (e.g., whether the sleep problem exists; if the sleep problem exists, the data is 1; if the sleep problem does not exist, the data is 0) are used as training data to train the correlation model. The correlation model is then trained using this training data to obtain its parameters. Based on these parameters, the correlation degree between the candidate sleep influencing factor and the sleep problem is determined. A similar method can be used to determine the correlation degree between each candidate sleep influencing factor and multiple sleep problems.
[0104] For example, suppose a correlation model is constructed for a candidate sleep influencing factor x1 and a sleep problem Y1, and the correlation model takes the form shown in the following formula (9):
[0105] Y1=f'(ax1+by1+cz1) (9)
[0106] Where a is the weight corresponding to candidate sleep influencing factor x1, b is the weight corresponding to age y1, and z is the weight corresponding to gender z1. f1(ax+by+cz) can be, for example, a sigmoid function.
[0107] In this embodiment, the sample sleep data of candidate sleep influencing factors x1 corresponding to multiple first sample users and the sleep problem Y1 data of multiple first sample users in the first sample data can be used as training data for the association model shown in formula (9). Specifically, for each first sample user, when the first sample user has sleep problem Y1, the data of sleep problem Y1 of the first sample user is 1, and when the first sample user does not have sleep problem Y1, the data of sleep problem Y1 of the first sample user is 0.
[0108] Furthermore, the training data of the association model shown in formula (9) can be used to train the association model and obtain the parameters of the association model, namely the values of a, b, and c in formula (9). Then, the weight a corresponding to the candidate sleep influencing factor x1 can be exponentially transformed, i.e., e a The AOR value between candidate sleep influence factor x1 and sleep problem Y1 is obtained. Using a similar method, the AOR values between each candidate sleep influence factor and multiple sleep problems can be determined.
[0109] Step 303: Select each sleep influencing factor from multiple candidate sleep influencing factors based on the correlation between each candidate sleep influencing factor and multiple sleep problems.
[0110] In an exemplary embodiment, after determining the correlation between each candidate sleep influencing factor and multiple sleep problems, each sleep influencing factor can be selected from the multiple candidate sleep influencing factors in the following manner:
[0111] For each candidate sleep influencing factor, obtain the target sleep problems with a correlation degree greater than a preset correlation degree threshold and the number of target sleep problems;
[0112] Determine the average correlation between the same candidate sleep influencing factor and each target sleep problem;
[0113] At least one sleep influencing factor is determined from multiple candidate sleep influencing factors, wherein the average value of the sleep influencing factor is greater than a preset threshold, and the number of target sleep problems corresponding to the sleep influencing factor is greater than a preset number threshold.
[0114] The correlation threshold can be set as needed, and this application does not impose any restrictions on it. For example, when using the AOR value as the correlation, the correlation threshold can be set to 1, so that when the correlation between the candidate sleep influencing factor and sleep problems is greater than 1, it can be determined that the candidate sleep influencing factor and sleep problems are significantly correlated.
[0115] The preset threshold and preset quantity threshold can be set as needed, and this application does not impose any restrictions on them.
[0116] For example, suppose we use the AOR value as the correlation coefficient, the correlation coefficient threshold is 1, the number of candidate sleep influencing factors is 65, and the number of sleep problems is 15.
[0117] In this embodiment, the correlation between 65 candidate sleep influencing factors and 15 sleep problems can be determined. For each candidate sleep influencing factor, the target sleep problems with an AOR value greater than 1 are identified, and the number of target sleep problems is counted. For each candidate sleep influencing factor, when the number of target sleep problems with an AOR value greater than 1 is greater than 1, the average correlation between the candidate sleep influencing factor and each target sleep problem is determined. For example, assuming that the AOR values between candidate sleep influencing factor x1 and sleep problems Y1, Y2, and Y3 are all greater than 1, the average AOR values between candidate sleep influencing factor x1 and sleep problem Y1, between candidate sleep influencing factor x1 and sleep problem Y2, and between candidate sleep influencing factor x1 and sleep problem Y3 can be determined.
[0118] Furthermore, among multiple candidate sleep influencing factors, the candidate sleep influencing factors whose average value is greater than a preset threshold and whose number of target sleep problems is greater than a preset number threshold can be identified as each sleep influencing factor in this application embodiment.
[0119] After identifying each sleep influencing factor, when providing sleep guidance to the user, the system can obtain the original sleep data of each sleep influencing factor and the set target sleep health score. Based on the target sleep health score, the system can query the first correlation between the health score and each sleep influencing factor to obtain the target sleep data of each sleep influencing factor. Then, based on the difference between the target sleep data of each sleep influencing factor and the original sleep data of the corresponding sleep influencing factor, the system can determine the sleep change data of each sleep influencing factor. Finally, the sleep change data of each sleep influencing factor is pushed to the user as sleep guidance information.
[0120] The sleep guidance information processing method provided in this application obtains multiple candidate sleep influencing factors and multiple sleep problems, determines the correlation between each candidate sleep influencing factor and multiple sleep problems, and selects each sleep influencing factor from the multiple candidate sleep influencing factors based on the correlation between each candidate sleep influencing factor and multiple sleep problems. This achieves the selection of candidate sleep influencing factors with a high degree of correlation with sleep problems as each sleep influencing factor, thereby making the sleep change data determined based on the original sleep data of each sleep influencing factor of the user to be guided more accurate, and thus improving the accuracy of the sleep guidance information pushed to the user.
[0121] The following is combined Figure 4 The processing method for sleep guidance information provided in the embodiments of this application will be further explained.
[0122] Figure 4 This is a flowchart illustrating another method for processing sleep guidance information provided in an embodiment of this application.
[0123] like Figure 4 As shown, the method for processing sleep guidance information provided in this application embodiment may include the following steps:
[0124] Step 401: Obtain the second correlation between each sleep-influencing factor and health status.
[0125] Step 402: Perform the inverse operation on the second correlation to obtain the first correlation between health and each sleep influencing factor.
[0126] Specifically, we can first obtain the second correlation between each sleep-influencing factor and health, and then perform an inverse operation on the second correlation to obtain the first correlation between health and each sleep-influencing factor.
[0127] In an exemplary embodiment, the second correlation between various sleep-influencing factors and health can be obtained through the following methods:
[0128] Obtain second sample data, which includes sample sleep data of each sleep influencing factor for multiple second sample users and their corresponding sample sleep health scores.
[0129] Construct an initial second association between various sleep-influencing factors and health status;
[0130] Using the second sample data, the initial second association relationship is adjusted to obtain the second association relationship.
[0131] In an exemplary embodiment, the sample sleep data of each candidate sleep influencing factor corresponding to each of the multiple second sample users can be calculated based on the basic sleep data corresponding to each of the multiple second sample users, according to the determination strategy of each candidate sleep influencing factor.
[0132] The sleep health scores of multiple second sample users can be obtained in the following way: the sleep problems of multiple second sample users are obtained through questionnaires. For each second sample user, if the second sample user has any sleep problems, the sleep health score of the second sample user is marked as 0, and if the second sample user does not have any sleep problems, the sleep health score of the second sample user is marked as 1.
[0133] In an exemplary embodiment, after constructing the initial second association between each sleep influencing factor and health status, the initial second association can be trained using deep learning with the second sample data to adjust its parameters, resulting in a trained second association. When training the initial second association using deep learning, sample sleep data of each sleep influencing factor corresponding to multiple second sample users in the second sample data can be used as input, and sample sleep health status of multiple second sample users in the training data can be used as output. The initial second association is iteratively trained by continuously adjusting its parameters until the accuracy of the sleep health status predicted based on the parameter-adjusted second association meets a pre-set threshold. Training then ends, and the trained second association is obtained.
[0134] Taking the initial second association between the constructed sleep influencing factors and health as the logistic regression model represented by formulas (2) and (3) as an example, in this embodiment of the application, when adjusting the initial second association using second sample data, the sample sleep data of each sleep influencing factor corresponding to a second sample user can be substituted into formulas (2) and (3), and the obtained y value can be compared with the sample sleep health corresponding to the second sample user. Based on the difference between the two, the w in formula (3) can be adjusted. i Adjustments can be made. Furthermore, the sleep data of each sleep influencing factor corresponding to another second sample user can be substituted into formulas (2) and (3), and the obtained y value can be compared with the sleep health score corresponding to that second sample user. The w value in formula (3) can be adjusted based on the difference between the two. i Further adjustments were made. Therefore, by utilizing sample sleep data of various sleep influencing factors and corresponding sample sleep health scores from multiple second-sample users, w was continuously iteratively adjusted. i The value, until according to w i If the accuracy of the sleep health prediction obtained by the adjusted second association meets the preset threshold, then w can be set at this point. i The value is used as a parameter for the second association, resulting in the final second association.
[0135] It should be noted that the relationship represented by the logistic regression model in the above embodiments as the initial second association between each sleep influencing factor and health is only an example and should not be construed as a limitation on the technical solution of this application. In practical applications, when constructing the initial second association between each sleep influencing factor and health, those skilled in the art can use any other interpretable binary classification machine learning model as needed, such as support vector machine model or neural network model. This application does not impose any restrictions on this.
[0136] Step 403: Guide the user to obtain the raw sleep data of each sleep influencing factor.
[0137] The specific implementation process and principle of step 403 can be referred to the description of the above embodiments, and will not be repeated here.
[0138] It should be noted that steps 401 and 402 can be executed before step 403, after step 403, or simultaneously with step 403. This application does not restrict the timing of the execution of steps 401 and 402, as long as they are executed before step 404.
[0139] Step 404: Based on the original sleep data of each sleep influencing factor of the user to be guided, query the second correlation between each sleep influencing factor and health score to obtain the original sleep health score of the user to be guided.
[0140] Step 405: Determine the target sleep health score based on the original sleep health score.
[0141] In an exemplary embodiment, the original sleep health of the user can be obtained by querying the second correlation between each sleep influencing factor and the health score based on the original sleep data of each sleep influencing factor of the user to be guided.
[0142] The original sleep health score is the current sleep health score of the user to be guided.
[0143] In an exemplary embodiment, after obtaining the user's initial sleep health status, the processing device can determine a target sleep health status based on the user's actions. For example, the processing device can display the initial sleep health status on the screen of the user's electronic device, allowing the user to understand their current sleep health status and determine the target sleep health status to be achieved based on the current status. The user can input the target sleep health status into the electronic device through interactive methods such as touch selection or direct input, so that the processing device in the electronic device can obtain the user-set target sleep health status.
[0144] In an exemplary embodiment, after obtaining the user's initial sleep health status, the processing device can also set a target sleep health status based on that initial status. For example, the processing device can, based on the "zone of proximal development" theory, provide the user with a target sleep health status that is challenging yet achievable through gradual improvement of sleep behavior. The core idea of the "zone of proximal development" theory is to provide the user with challenging behavioral guidance based on their initial sleep health status to motivate their participation, gradually improve their sleep behavior, and ultimately reach the target sleep behavior habit level, before moving on to a higher level.
[0145] By querying the second correlation between each sleep influencing factor and the health score of the user to be guided based on the original sleep data of each sleep influencing factor, the original sleep health score of the user to be guided can be obtained. Then, based on the original health score, the target sleep health score can be determined, so that a more suitable target sleep health score can be set for the user to be guided based on the current sleep quality.
[0146] Step 406: Based on the target sleep health score, query the first correlation between the health score and each sleep influencing factor to obtain the target sleep data for each sleep influencing factor.
[0147] Step 407: Determine the sleep change data of each sleep influencing factor based on the difference between the target sleep data of each sleep influencing factor and the original sleep data of the corresponding sleep influencing factor.
[0148] Step 408: Push the sleep change data of each sleep influencing factor as sleep guidance information to the user terminal.
[0149] The specific implementation process and principle of steps 406-408 can be referred to the description of the above embodiments, and will not be repeated here.
[0150] Understandably, after pushing sleep guidance information to the user's device, the processing device can continue to acquire sleep data for various sleep influencing factors of the user, query the secondary correlation between each sleep influencing factor and health status, and obtain the user's sleep health status. This allows for real-time assessment of the user's sleep quality and the quantification of changes in sleep quality. Furthermore, the sleep health status can be pushed to the user's device, enabling them to objectively understand the quantified changes in sleep quality, thereby increasing user participation in changing sleep habits and further improving the effectiveness of sleep guidance.
[0151] The sleep guidance information processing method provided in this application involves obtaining a second correlation between each sleep influencing factor and health status, performing an inverse operation on the second correlation to obtain a first correlation between health status and each sleep influencing factor, obtaining the original sleep data of each sleep influencing factor for the user to be guided, querying the second correlation between each sleep influencing factor and health status based on the original sleep data of the user to be guided to obtain the original sleep health status of the user to be guided, determining the target sleep health status based on the original sleep health status, querying the first correlation between health status and each sleep influencing factor based on the target sleep health status to obtain the target sleep data of each sleep influencing factor, determining the sleep change data of each sleep influencing factor based on the difference between the target sleep data of each sleep influencing factor and the original sleep data of the corresponding sleep influencing factor, and then pushing the sleep change data of each sleep influencing factor as sleep guidance information to the user. This enables guidance for users to change their sleep habits based on the sleep change data of each sleep influencing factor, quantifying the sleep guidance plan and thus improving the effectiveness of sleep guidance.
[0152] To implement the above embodiments, this application proposes a sleep guidance information processing device.
[0153] Figure 5 This is a schematic diagram of a sleep guidance information processing device provided in an embodiment of this application.
[0154] like Figure 5 As shown, the sleep guidance information processing device 500 may include: a first acquisition module 510, a query module 520, a first determination module 530, and a sending module 540.
[0155] The first acquisition module 510 is used to acquire the original sleep data of each sleep influencing factor for the user to be guided, and to acquire the set target sleep health level.
[0156] The query module 520 is used to query the first correlation between the target sleep health score and each sleep influencing factor, and obtain the target sleep data for each sleep influencing factor;
[0157] The first determining module 530 is used to determine the sleep change data of each sleep influencing factor based on the difference between the target sleep data of each sleep influencing factor and the original sleep data of the corresponding sleep influencing factor.
[0158] The sending module 540 is used to push sleep change data of various sleep influencing factors as sleep guidance information to the user terminal.
[0159] It should be noted that the sleep guidance information processing device provided in this application embodiment, hereinafter referred to as the processing device, can execute the sleep guidance information processing method provided in this application embodiment. The sleep guidance information processing device can be an electronic device or can be configured within an electronic device to quantify the sleep guidance scheme and improve the effectiveness of sleep guidance.
[0160] Among these, electronic devices can include personal computers, cloud devices, mobile devices, wearable devices, etc. Wearable devices can include smartwatches, smart bracelets, etc.
[0161] As one possible scenario, the sleep guidance information processing device 500 may further include:
[0162] The second acquisition module is used to acquire multiple candidate sleep influencing factors and multiple sleep problems;
[0163] The second determination module is used to determine the correlation between each candidate sleep influencing factor and multiple sleep problems;
[0164] The selection module is used to select each sleep influencing factor from multiple candidate sleep influencing factors based on the correlation between each candidate sleep influencing factor and multiple sleep problems.
[0165] As another possible scenario, the second determining module includes:
[0166] The first acquisition unit is used to acquire first sample data, wherein the first sample data includes sample sleep data of each candidate sleep influencing factor corresponding to multiple first sample users and their corresponding sleep problems;
[0167] The processing unit is used to take the sample sleep data of the candidate sleep influencing factors corresponding to multiple first sample users, and the sleep problems corresponding to multiple first sample users, as training data for the association model, wherein the association model has corresponding candidate sleep influencing factors and sleep problems.
[0168] The training unit is used to train the association model using the training data of the association model to obtain the parameters of the association model.
[0169] The first determining unit is used to determine the degree of association between candidate sleep influencing factors and sleep problems based on the parameters of the association model.
[0170] As another possible scenario, the selected module includes:
[0171] The second acquisition unit is used to acquire, for each candidate sleep influencing factor, the target sleep problems with a correlation degree greater than a preset correlation degree threshold and the number of target sleep problems;
[0172] The second determining unit is used to determine the average value of the correlation between the same candidate sleep influencing factor and each target sleep problem;
[0173] The third determining unit is used to determine at least one sleep influencing factor from multiple candidate sleep influencing factors, wherein the average value of the sleep influencing factor is greater than a preset threshold, and the number of corresponding target sleep problems is greater than a preset number threshold.
[0174] As another possible scenario, the sleep guidance information processing device 500 also includes:
[0175] The third acquisition module is used to obtain the second correlation between various sleep-influencing factors and health status;
[0176] The processing module is used to perform the inverse operation on the second correlation to obtain the first correlation between health and each sleep influencing factor.
[0177] As another possible scenario, the third acquisition module includes:
[0178] The third acquisition unit is used to acquire the second sample data, which includes sample sleep data of each sleep influencing factor corresponding to multiple second sample users and their corresponding sample sleep health.
[0179] The building blocks are used to construct the initial secondary association between various sleep-influencing factors and health status;
[0180] The adjustment unit is used to adjust the initial second association relationship using the second sample data to obtain the first association relationship.
[0181] As another possible scenario, the first acquisition module includes:
[0182] The query unit is used to query the second correlation between each sleep influencing factor and the health score based on the original sleep data of each sleep influencing factor of the user to be guided, so as to obtain the original sleep health score of the user to be guided.
[0183] The fourth determining unit is used to determine the target sleep health score based on the original sleep health score.
[0184] It should be noted that the explanation of the above-mentioned method for processing sleep guidance information also applies to the sleep information guidance device of this embodiment, and will not be repeated here.
[0185] The sleep guidance information processing device of this application embodiment obtains the original sleep data of each sleep influencing factor and the set target sleep health level for the user to be guided. Based on the target sleep health level, it queries the first correlation between the health level and each sleep influencing factor to obtain the target sleep data for each sleep influencing factor. Then, based on the difference between the target sleep data of each sleep influencing factor and the original sleep data of the corresponding sleep influencing factor, it determines the sleep change data of each sleep influencing factor, and then pushes the sleep change data of each sleep influencing factor as sleep guidance information to the user. This enables the user to change their sleep behavior habits based on the sleep change data of each sleep influencing factor, quantifying the sleep guidance plan and thus improving the effectiveness of sleep guidance.
[0186] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.
[0187] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.
[0188] like Figure 6 As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 602 or a computer program loaded from storage unit 608 into random access memory (RAM) 603. RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.
[0189] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0190] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as the method for processing sleep guidance information. For example, in some embodiments, the method for processing sleep guidance information may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the method for processing sleep guidance information described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the method for processing sleep guidance information by any other suitable means (e.g., by means of firmware).
[0191] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0192] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0193] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0194] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0195] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.
[0196] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.
[0197] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
[0198] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0199] Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.
Claims
1. A method for processing sleep guidance information, characterized in that, include: The task involves guiding users to obtain raw sleep data for various sleep-influencing factors, as well as to achieve a set target sleep health level. Based on the target sleep health score, the first correlation between the health score and each sleep influencing factor is queried to obtain the target sleep data of each sleep influencing factor. The first correlation is obtained by performing an inverse operation on the second correlation between each sleep influencing factor and the health score. The first correlation is represented by a binary classification machine learning model. Based on the difference between the target sleep data of each sleep influencing factor and the original sleep data of the corresponding sleep influencing factor, the sleep change data of each sleep influencing factor are determined. The sleep change data of each sleep influencing factor will be pushed to the user as sleep guidance information.
2. The method according to claim 1, characterized in that, Before guiding users to obtain raw sleep data for each sleep-influencing factor, the process also includes: We obtained multiple candidate sleep influencing factors and multiple sleep problems; For each candidate sleep influencing factor, determine its correlation with the multiple sleep problems; Based on the correlation between each candidate sleep influencing factor and the multiple sleep problems, the sleep influencing factors are selected from the multiple candidate sleep influencing factors.
3. The method according to claim 2, characterized in that, The step of determining the correlation between each candidate sleep influencing factor and the plurality of sleep problems includes: Obtain first sample data, wherein the first sample data includes sample sleep data of each candidate sleep influencing factor corresponding to multiple first sample users and their corresponding sleep problems; The sample sleep data of the candidate sleep influencing factors corresponding to the plurality of first sample users, and the sleep problems corresponding to the plurality of first sample users, are used as training data for the association model, wherein the association model has the corresponding candidate sleep influencing factors and the sleep problems; The parameters of the association model are obtained by training the association model using the training data of the association model. Based on the parameters of the association model, the degree of association between the candidate sleep influencing factors and the sleep problem is determined.
4. The method according to claim 2, characterized in that, The step of selecting each sleep influencing factor from the multiple candidate sleep influencing factors based on the correlation between each candidate sleep influencing factor and the multiple sleep problems includes: For each candidate sleep influencing factor, obtain the target sleep problems with a correlation degree greater than a preset correlation degree threshold and the number of the target sleep problems; Determine the average correlation between the same candidate sleep influencing factor and each target sleep problem; At least one sleep influencing factor is determined from the plurality of candidate sleep influencing factors, wherein the average value of the sleep influencing factor is greater than a preset threshold, and the number of the target sleep problems corresponding to the sleep influencing factor is greater than a preset number threshold.
5. The method according to claim 1, characterized in that, The step of obtaining the second correlation between each sleep-influencing factor and the health status includes: Obtain second sample data, wherein the second sample data includes sample sleep data of each sleep influencing factor corresponding to multiple second sample users and sample sleep health scores corresponding to each factor; Construct an initial second correlation between each sleep-influencing factor and the health status; Using the second sample data, the initial second association relationship is adjusted to obtain the second association relationship.
6. The method according to claim 1, characterized in that, The process of obtaining the set target sleep health score includes: Based on the original sleep data of each sleep influencing factor of the user to be guided, the second correlation between each sleep influencing factor and the health score is queried to obtain the original sleep health score of the user to be guided. The target sleep health score is determined based on the original sleep health score.
7. A device for processing sleep guidance information, characterized in that, include: The first acquisition module is used to obtain the raw sleep data of each sleep influencing factor for the user to be guided, as well as to obtain the set target sleep health level; The query module is used to query the first correlation between the target sleep health score and each sleep influencing factor, and obtain the target sleep data of each sleep influencing factor; The first determining module is used to determine the sleep change data of each sleep influencing factor based on the difference between the target sleep data of each sleep influencing factor and the original sleep data of the corresponding sleep influencing factor. The first correlation is obtained by performing an inverse operation on the second correlation between each sleep influencing factor and the health status. The first correlation is represented by a binary classification machine learning model. The sending module is used to push the sleep change data of each sleep influencing factor as sleep guidance information to the user terminal.
8. The apparatus according to claim 7, characterized in that, Also includes: The second acquisition module is used to acquire multiple candidate sleep influencing factors and multiple sleep problems; The second determining module is used to determine the correlation degree between each candidate sleep influencing factor and the plurality of sleep problems; The selection module is used to select each sleep influencing factor from the multiple candidate sleep influencing factors based on the correlation between each candidate sleep influencing factor and the multiple sleep problems.
9. The apparatus according to claim 8, characterized in that, The second determining module includes: The first acquisition unit is used to acquire first sample data, wherein the first sample data includes sample sleep data of each candidate sleep influencing factor corresponding to multiple first sample users and their corresponding sleep problems; The processing unit is used to take the sample sleep data of the candidate sleep influencing factors corresponding to the plurality of first sample users, and the sleep problems corresponding to the plurality of first sample users, as training data for the association model, wherein the association model has the corresponding candidate sleep influencing factors and the sleep problems; The training unit is used to train the association model using the training data of the association model to obtain the parameters of the association model. The first determining unit is used to determine the degree of correlation between the candidate sleep influencing factors and the sleep problem based on the parameters of the correlation model.
10. The apparatus according to claim 8, characterized in that, The selection module includes: The second acquisition unit is used to acquire, for each candidate sleep influencing factor, target sleep problems with a correlation degree greater than a preset correlation degree threshold and the number of target sleep problems; The second determining unit is used to determine the average value of the correlation between the same candidate sleep influencing factor and each target sleep problem; The third determining unit is used to determine at least one sleep influencing factor from the plurality of candidate sleep influencing factors, wherein the average value corresponding to the sleep influencing factor is greater than a preset threshold, and the number of the corresponding target sleep problems is greater than a preset number threshold.
11. The apparatus according to claim 7, characterized in that, The third acquisition module includes: The third acquisition unit is used to acquire second sample data, wherein the second sample data includes sample sleep data of each sleep influencing factor corresponding to multiple second sample users and sample sleep health scores corresponding to each factor. A construction unit is used to construct an initial second correlation relationship between each sleep-influencing factor and the health status; The adjustment unit is used to adjust the initial second association relationship using the second sample data to obtain the second association relationship.
12. The apparatus according to claim 7, characterized in that, The first acquisition module includes: The query unit is used to query the second correlation between each sleep influencing factor and the health score based on the original sleep data of each sleep influencing factor of the user to be guided, so as to obtain the original sleep health score of the user to be guided. The fourth determining unit is used to determine the target sleep health score based on the original sleep health score.
13. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; characterized in that, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the sleep guidance information processing method according to any one of claims 1-6.
14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to execute the method for processing sleep guidance information according to any one of claims 1-6.
Citation Information
Patent Citations
Processing method and system for sleep quality report
CN110491468A
Sleep quality prediction method and device
CN111489019A
