A method, device and storage medium for intelligently adjusting a sleep state

Abstract

The application discloses a method, device and storage medium for intelligently adjusting a sleep state. The method for intelligently adjusting the sleep state comprises the following steps: obtaining a historical sleep staging model, a standard sleep cycle of a user and a first heart impact signal; determining first sleep state information of the user and predicting second sleep state information according to the first heart impact signal and the historical sleep staging model; judging whether sleep state adjustment is needed according to the second sleep state information and the standard sleep cycle; if yes, outputting a corresponding adjustment scheme according to the first sleep state information, the second sleep state information and physiological parameters of the user. According to the technical scheme of the application, the heart impact signal in the sleep process of the user is collected in real time, the sleep state information is judged and the sleep state information is predicted according to the heart impact signal, the sleep state of the user is adjusted and intervened, the sleep state of the user reaches the standard sleep cycle, the sleep quality of the user is improved, and the user is helped to sleep healthily.

Description

Technical Field

[0001] This invention relates to the field of sleep regulation technology, and in particular to a method, apparatus and storage medium for intelligently regulating sleep state. Background Technology

[0002] Human sleep cycles (wakefulness / dreaming / light sleep I / light sleep II / deep sleep) alternate cyclically. A regular sleep cycle ensures sufficient energy throughout the day. Each part of the sleep cycle has distinct characteristics, and by collecting sleep characteristics from different stages, a person's sleep state can be regulated. Current sleep state recognition technologies are inaccurate and cannot predict a user's sleep state, leading to inaccurate sleep regulation and failing to achieve the goal of improving sleep quality. Summary of the Invention

[0003] This invention provides a method, apparatus, and storage medium for intelligently regulating sleep state, which predicts the user's sleep state information and compares and adjusts it according to a standard sleep cycle to improve the user's sleep quality.

[0004] According to one aspect of the present invention, a method for intelligently regulating sleep state is provided, comprising:

[0005] Acquire historical sleep staging models, the user's standard sleep cycle, and the first cardiac impact signal, where the first cardiac impact signal is the user's cardiac impact signal in the current time segment;

[0006] The user's first sleep state information is determined based on the first cardiac impact signal and the historical sleep stage model, and the second sleep state information is predicted. The first sleep state information is the sleep state information under the current time segment, and the second sleep state information is the sleep state information under the next time segment.

[0007] Determine whether sleep state adjustment is needed based on second sleep state information and standard sleep cycle;

[0008] If so, the corresponding adjustment scheme is output based on the first sleep state information, the second sleep state information, the user's physiological parameters, and the user's sleeping position. Optionally, obtaining the historical sleep staging model includes:

[0009] Extracting historical temporal and frequency domain features of historical cardiac impact signals;

[0010] Obtain a sleep stage label model, which includes the correspondence between time-domain features, frequency-domain features, and sleep stage labels;

[0011] Based on historical time-domain characteristics, historical frequency-domain characteristics, and sleep stage labeling models, the historical sleep stage model corresponding to historical cardiac impact signals is determined.

[0012] Optionally, obtaining the user's standard sleep cycle includes:

[0013] Obtain the current user's physiological and sleep parameters;

[0014] The standard sleep cycle of the current user is determined based on physiological parameters, sleep parameters, and standard sleep state parameters.

[0015] Optional physiological parameters include: sex, age, height, weight, and physical condition;

[0016] Sleep parameters include sleep duration.

[0017] Optionally, the user's first sleep state information and second sleep state information are determined based on the first cardiac impulse signal and historical sleep staging model, including:

[0018] The first sleep state information corresponding to the first heart impact signal is determined based on the first heart impact signal and the historical sleep stage model.

[0019] The second cardiac impact signal is predicted based on the first cardiac impact signal, and the second cardiac impact signal is the cardiac impact signal in the next time segment.

[0020] Second sleep state information is determined based on the second cardiac impact signal and historical sleep stage model.

[0021] Optionally, predicting the second cardiac impact signal based on the first cardiac impact signal includes:

[0022] The functional correspondence between the cardiac impact signal and the time segment is calculated using nonlinear interpolation based on the first cardiac impact signal;

[0023] Calculate the cardiac impact signal for the next time segment based on the function correspondence.

[0024] Optionally, determine whether sleep state regulation is needed based on second sleep state information and the standard sleep cycle, including:

[0025] Obtain the sleep start time and determine the first moment information corresponding to the second sleep state information based on the second sleep state information;

[0026] The sleep duration information is determined based on the first moment information and the sleep onset time.

[0027] Determine the standard sleep state information corresponding to the sleep duration information within the standard sleep cycle based on the sleep duration information;

[0028] Whether sleep state adjustment is needed is determined based on whether the second sleep state information and the standard sleep state information are the same.

[0029] Optionally, an adjustment scheme can be output based on the first sleep state information, the second sleep state information, the user's physiological parameters, and the user's sleeping position, including:

[0030] The user's sleep comfort is adjusted based on the first sleep state information, the user's physiological parameters, and the user's sleeping position, so that the second sleep state information is adjusted to the standard sleep state information.

[0031] According to another aspect of the present invention, an apparatus for intelligently regulating sleep state is provided, the apparatus being used to perform a method for intelligently regulating sleep state, the apparatus comprising:

[0032] The sleep parameter acquisition module is used to acquire historical sleep stage models, the user's standard sleep cycle, and the first cardiac impact signal. The first cardiac impact signal is the user's cardiac impact signal in the current time segment.

[0033] The sleep state determination module is used to determine the user's first sleep state information and predict the second sleep state information based on the first cardiac impact signal and the historical sleep staging model. The first sleep state information is the sleep state information under the current time segment, and the second sleep state information is the sleep state information under the next time segment.

[0034] The sleep regulation judgment module is used to determine whether sleep regulation is needed based on the second sleep state information and the standard sleep cycle.

[0035] The sleep regulation module is used to output corresponding regulation schemes based on the first sleep state information, the second sleep state information, the user's physiological parameters, and the user's sleeping posture when sleep state regulation is required.

[0036] According to another aspect of the present invention, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements a method for intelligently regulating a sleep state.

[0037] The technical solution of this invention collects cardiac impact signals during the user's sleep process in real time, judges and predicts sleep state information based on the cardiac impact signals, and compares the predicted sleep state information with the standard sleep cycle. When the predicted sleep state information is inconsistent with the standard sleep cycle, the user's sleep state is adjusted and intervened to make the user's sleep state reach the standard sleep cycle, thereby improving the user's sleep quality and helping the user sleep healthily.

[0038] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a flowchart of a first method for intelligently regulating sleep state provided by an embodiment of the present invention;

[0041] Figure 2 This is a flowchart of obtaining a historical sleep staging model according to an embodiment of the present invention;

[0042] Figure 3 This is a flowchart for obtaining a user's standard sleep cycle according to an embodiment of the present invention;

[0043] Figure 4 This is a flowchart of a second method for intelligently regulating sleep state provided by an embodiment of the present invention;

[0044] Figure 5 This is a flowchart of a third method for intelligently regulating sleep state provided by an embodiment of the present invention;

[0045] Figure 6 This is a flowchart of a fourth method for intelligently regulating sleep state provided by an embodiment of the present invention;

[0046] Figure 7 This is a flowchart of a fifth method for intelligently regulating sleep state provided by an embodiment of the present invention;

[0047] Figure 8 This is a schematic diagram of the structure of a device for intelligently regulating sleep state according to an embodiment of the present invention. Detailed Implementation

[0048] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0049] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in sequences other than those illustrated or described herein.

[0050] Figure 1 This is a flowchart of a first method for intelligently regulating sleep state according to an embodiment of the present invention. This embodiment is applicable to situations involving sleep state regulation, such as... Figure 1 As shown, the method includes:

[0051] S10. Obtain the historical sleep staging model, the user's standard sleep cycle, and the first cardiac impact signal. The first cardiac impact signal is the user's cardiac impact signal in the current time segment.

[0052] Among them, the cardiac impact signal can be a weak change signal of external pressure on the human body surface caused by the human heart pulsation and arterial flow; the cardiac impact signal can include heart rate signal, respiratory signal and body movement signal, among which the heart rate signal, respiratory signal and body movement signal are related to sleep state information, and the user's sleep state can be judged by comprehensively judging the heart rate signal, respiratory signal and body movement signal in the cardiac impact signal.

[0053] The historical sleep staging model can be a pre-established relationship model between cardiac impact signals and user sleep state information. Based on the real-time cardiac impact signal and the historical sleep staging model, the current user's sleep state information can be obtained. The first cardiac impact signal is the cardiac impact signal collected during the current time segment in the user's sleep state. The current time segment can be one minute, which is the sleep state information corresponding to the user within the current minute. The time segment can also be other durations, such as thirty seconds, five minutes, or ten minutes. The embodiments of this invention do not specifically limit the duration of the time segment.

[0054] Among them, the user's standard sleep cycle can be the user's ideal sleep cycle based on the user's physiological parameters and sleep status. Based on this ideal sleep cycle, the user's sleep quality and health can be guaranteed.

[0055] S11. Determine the user's first sleep state information and predict the second sleep state information based on the first cardiac impact signal and the historical sleep stage model. The first sleep state information is the sleep state information under the current time segment, and the second sleep state information is the sleep state information under the next time segment.

[0056] For example, the sleep state information for the current time segment is obtained based on the cardiac impact signal (i.e., the first cardiac impact signal) and the historical sleep staging model; and the sleep state information for the next time segment is predicted based on the sleep state information for the current time segment. Here, the current time segment can be one minute, meaning that the sleep state information for the current minute is obtained based on the cardiac impact signal within the current minute and the historical sleep staging model, and the sleep state information for the next minute is predicted based on the sleep state information for the current minute.

[0057] S12. Determine whether sleep state adjustment is needed based on the second sleep state information and the standard sleep cycle.

[0058] Specifically, the second sleep state information is predicted based on the first sleep state information. The user's second sleep state information is compared with the corresponding user standard sleep cycle to determine whether the user has reached the sleep state information corresponding to the standard sleep cycle. When the user has not reached the sleep state information corresponding to the standard sleep cycle, the user's sleep state needs to be adjusted so that the user can reach the standard sleep state.

[0059] S13. If so, output the corresponding adjustment scheme based on the first sleep state information, the second sleep state information, the user's physiological parameters, and the user's sleeping posture.

[0060] The adjustment scheme involves regulating the user's comfort during sleep. By altering the user's comfort level during sleep, it intervenes in the user's sleep state to achieve a standard sleep state. In this intervention, the first sleep state information is used as a baseline, while the second sleep state information and the user's physiological parameters are used as the basis for comfort adjustment. The user's sleep state is adjusted from the first sleep state information to the sleep state information corresponding to the standard sleep cycle.

[0061] The specific method is as shown in the example. A historical sleep staging model is obtained, and a standard sleep cycle is established for the user based on their physiological parameters and sleep status. The standard sleep cycle can be the user's standard sleep state per unit time from falling asleep to waking up. Simultaneously, the user's real-time sleep state is monitored. After the user falls asleep, the cardiac impact signal within the first minute is collected; this signal is the first cardiac impact signal. The current user's first sleep state information is determined based on the first cardiac impact signal and the historical sleep staging model, and this information is denoted as α. The cardiac impact signal within the second minute is predicted based on the cardiac impact signal within the first minute, and the second sleep state information β is determined based on the cardiac impact signal within the second minute. The need for sleep state adjustment is determined based on the second sleep state information β and the corresponding standard sleep cycle θ. When β ≠ θ, a corresponding adjustment plan is output based on the first sleep state information α, the second sleep state information β, and the user's physiological parameters.

[0062] The technical solution of this invention collects cardiac impact signals during the user's sleep process in real time, judges and predicts sleep state information based on the cardiac impact signals, and compares the predicted sleep state information with the standard sleep cycle. When the predicted sleep state information is inconsistent with the standard sleep cycle, the user's sleep state is adjusted and intervened to make the user's sleep state reach the standard sleep cycle, thereby improving the user's sleep quality and helping the user sleep healthily.

[0063] Optional, Figure 2 This is a flowchart of obtaining a historical sleep staging model according to an embodiment of the present invention, such as... Figure 2 As shown, the historical sleep staging model includes:

[0064] S20. Extract the historical time-domain and historical frequency-domain features of historical cardiac impact signals.

[0065] Among them, the historical cardiac impact signal can be based on historically collected cardiac impact signals, which can include cardiac impact signals from all sleep cycles of all users; extract the time domain features and frequency domain features from the historical cardiac impact signal, and establish the relationship between the historical cardiac impact signal and the sleep stage labeling model.

[0066] S21. Obtain the sleep stage label model, which includes the correspondence between time-domain features and frequency-domain features and sleep stage labels.

[0067] Sleep stage labels represent different sleep states within a user's sleep cycle. These labels can include dream state, first light sleep state, second light sleep state, and deep sleep state. Users exhibit different cardiac impact signals (heart rate, respiratory signals, and body movement signals) in these states. By acquiring a sleep stage label model, the correspondence between time-domain and frequency-domain features and dream state, first light sleep state, second light sleep state, and deep sleep state can be obtained.

[0068] S22. Based on historical time-domain characteristics, historical frequency-domain characteristics, and sleep stage labeling models, determine the historical sleep stage model corresponding to historical cardiac impact signals.

[0069] The historical sleep staging model is based on cardiac impulse signals from all sleep cycles of all users, corresponding to different sleep states. Establishing a historical sleep staging model allows each collected cardiac impulse signal to correspond to a different sleep stage label, i.e., the corresponding sleep state information.

[0070] Specifically, since historical cardiac impact signals contain corresponding historical time-domain and frequency-domain features, and the sleep staging label model also includes the correspondence between time-domain and frequency-domain features and sleep staging labels, the relationship between corresponding historical cardiac impact signals and sleep staging labels can be established based on time-domain and frequency-domain features as intermediate quantities, thus establishing a historical sleep staging model.

[0071] In this embodiment of the invention, a historical sleep stage model is established to obtain the correspondence between historical cardiac impact signals and sleep stage labels. This enables the acquisition of corresponding sleep state information through real-time cardiac impact signals after collecting the user's real-time cardiac impact signals, thereby achieving rapid identification of sleep state.

[0072] Optional, Figure 3 This is a flowchart of obtaining a user's standard sleep cycle according to an embodiment of the present invention, such as... Figure 3 As shown, obtaining a user's standard sleep cycle includes:

[0073] S30. Obtain the current user's physiological parameters and sleep parameters.

[0074] Among them, since the user's physiological parameters and sleep parameters directly affect the user's sleep quality and sleep state, the user's physiological parameters include the user's gender, age, height, weight, and physical condition information. The physical condition information includes whether the user has a certain disease, such as high blood pressure, diabetes, etc.; the sleep parameters include the user's sleep duration.

[0075] S31. Determine the current user's standard sleep cycle based on physiological parameter information, sleep parameter information, and standard sleep state parameter information.

[0076] This involves establishing a standard sleep cycle for each user based on their gender, age, height, weight, physical condition, and sleep duration. The standard sleep cycle can be defined as the period from falling asleep to waking up, and is broken down into segments to determine the user's standard sleep state for each segment.

[0077] In this embodiment of the invention, by obtaining the user's standard sleep cycle and using the standard sleep cycle as a reference, when the user's sleep state information is inconsistent with the standard sleep cycle, the user's sleep state is adjusted to improve the user's sleep quality and achieve the user's standard sleep cycle.

[0078] Based on the above embodiments, Figure 4 This is a flowchart of a second method for intelligently regulating sleep state provided by an embodiment of the present invention, combined with... Figure 4 As shown, the method for intelligently regulating sleep states includes:

[0079] S40. Obtain the historical sleep staging model, the user's standard sleep cycle, and the first cardiac impact signal. The first cardiac impact signal is the user's cardiac impact signal in the current time segment.

[0080] S41. Determine the first sleep state information corresponding to the first heart impact signal based on the first heart impact signal and the historical sleep stage model.

[0081] For example, the first cardiac impulse signal can be the cardiac impulse signal in the first time segment after the user falls asleep. The sleep state information in the first time segment is determined based on the cardiac impulse signal in the first time segment, which is the first sleep state information.

[0082] S42. Predict the second cardiac impact signal based on the first cardiac impact signal. The second cardiac impact signal is the cardiac impact signal in the next time segment.

[0083] For example, the cardiac impact signal in the second time segment is predicted based on the cardiac impact signal in the first time segment.

[0084] S43. Determine the second sleep state information based on the second cardiac impact signal and the historical sleep stage model.

[0085] For example, sleep state information within the second time segment is determined based on the predicted cardiac impact signal within the second time segment and the historical sleep staging model.

[0086] S44. Determine whether sleep state adjustment is needed based on the second sleep state information and the standard sleep cycle.

[0087] S45. If so, output the corresponding adjustment plan based on the first sleep state information, the second sleep state information, and the user's physiological parameters.

[0088] In this embodiment of the invention, a second cardiac impact signal is predicted based on a first cardiac impact signal, and a second sleep state information is determined based on the second cardiac impact signal. The second sleep state information is compared with a standard sleep cycle, and a judgment is made based on the comparison result as to whether sleep state adjustment is necessary.

[0089] Based on the above embodiments, Figure 5 This is a flowchart of a third method for intelligently regulating sleep state provided by an embodiment of the present invention, such as... Figure 5 As shown, the method for intelligently regulating sleep states includes:

[0090] S50. Obtain historical sleep staging model, user's standard sleep cycle and first cardiac impact signal. The first cardiac impact signal is the user's cardiac impact signal in the current time segment.

[0091] S51. Determine the first sleep state information corresponding to the first heart impact signal based on the first heart impact signal and the historical sleep stage model.

[0092] S52. Calculate the functional correspondence between the cardiac impact signal and the time segment using nonlinear interpolation based on the first cardiac impact signal.

[0093] For example, during a user's sleep, cardiac impulse signals are collected in real time. One minute after the user falls asleep, all cardiac impulse signals from the previous minute are collected and recorded as the first cardiac impulse signal. A functional correspondence between the cardiac impulse signals and time segments is established using nonlinear interpolation.

[0094] S53. Calculate the cardiac impact signal for the next time segment based on the function correspondence.

[0095] Specifically, the cardiac impact signal corresponding to the next time segment is obtained based on the obtained function correspondence and the next time segment. The cardiac impact signal in the next time segment is the second cardiac impact signal.

[0096] S54. Determine the second sleep state information based on the second cardiac impact signal and the historical sleep stage model.

[0097] S55. Determine whether sleep state adjustment is needed based on the second sleep state information and the standard sleep cycle.

[0098] S56. If so, output the corresponding adjustment plan based on the first sleep state information, the second sleep state information, and the user's physiological parameters.

[0099] The technical solution of this invention establishes a functional relationship between the cardiac impact signal and a time segment using the first cardiac impact signal, and predicts the cardiac impact signal of the next time segment through the functional relationship, thereby obtaining second sleep state information.

[0100] Based on the above embodiments, Figure 6 This is a flowchart of a fourth method for intelligently regulating sleep state provided by an embodiment of the present invention, as shown below. Figure 6 As shown, the method for intelligently regulating sleep states includes:

[0101] S60. Obtain the historical sleep stage model, the user's standard sleep cycle, and the first cardiac impact signal. The first cardiac impact signal is the user's cardiac impact signal in the current time segment.

[0102] S61. Determine the user's first sleep state information and predict the second sleep state information based on the first cardiac impact signal and the historical sleep stage model. The first sleep state information is the sleep state information under the current time segment, and the second sleep state information is the sleep state information under the next time segment.

[0103] S62. Obtain the sleep start time and determine the first moment information corresponding to the second sleep state information based on the second sleep state information.

[0104] The first moment information refers to the moment t when the user is in the corresponding second sleep state information.

[0105] S63. Determine the sleep duration information based on the first moment information and the sleep onset time.

[0106] Here, the sleep start time is set as t0, and the sleep duration information can be the time difference information from the sleep start time t0 to the time t corresponding to the second sleep state information.

[0107] S64. Determine the standard sleep state information corresponding to the sleep duration information within the standard sleep cycle based on the sleep duration information.

[0108] Specifically, determining the standard sleep state information corresponding to the duration of sleep within a standard sleep cycle based on the duration of sleep can be achieved by taking the sleep start time t0 as the starting point within the standard sleep cycle and acquiring the corresponding standard sleep state information at the time corresponding to the time difference.

[0109] S65. Determine whether sleep state adjustment is needed based on whether the second sleep state information and the standard sleep state information are the same.

[0110] Among them, it is determined whether the second sleep state information and the standard sleep state information are consistent under the same sleep duration. If they are consistent, no sleep state adjustment is required.

[0111] S66. If so, output the corresponding adjustment plan based on the first sleep state information, the second sleep state information, and the user's physiological parameters.

[0112] In this embodiment of the invention, by comparing the second sleep state information and the standard sleep state information when the user falls asleep for the same duration, it is determined whether the user's sleep state is consistent with the standard sleep state and whether to intervene in the user's sleep state.

[0113] Based on the above embodiments, Figure 7 This is a flowchart of a fifth method for intelligently regulating sleep state provided by an embodiment of the present invention, as shown below. Figure 7 As shown, the method for intelligently regulating sleep states includes:

[0114] S70. Obtain the historical sleep stage model, the user's standard sleep cycle, and the first cardiac impact signal. The first cardiac impact signal is the user's cardiac impact signal in the current time segment.

[0115] S71. Determine the user's first sleep state information and predict the second sleep state information based on the first cardiac impact signal and the historical sleep stage model. The first sleep state information is the sleep state information under the current time segment, and the second sleep state information is the sleep state information under the next time segment.

[0116] S72. Determine whether sleep state adjustment is needed based on the second sleep state information and the standard sleep cycle.

[0117] S73. If so, adjust the user's sleep comfort based on the first sleep state information, the user's physiological parameters, and the user's sleeping posture, so that the second sleep state information is adjusted to the standard sleep state information.

[0118] Taking the airbag pressure in a mattress as an example, during sleep, parameters such as the user's gender, age, height, weight, physical condition, and sleeping position can all affect the user's sleep state. Therefore, the user's physiological parameters include gender, age, height, weight, and physical condition, while sleeping positions can include supine and side-lying positions. In adjusting the user's sleep comfort, different airbag pressure parameters in the mattress can be adjusted according to the user's different genders, ages, heights, weights, and physical conditions to meet the user's comfort level during sleep. Simultaneously, under the same physiological parameters, the user's sleeping position can also be adjusted by changing different airbag pressure parameters, including changing from a supine to a side-lying position or vice versa, thereby changing the user's sleep state type by altering their comfort level. Sleep state types can be ranked from deep to lightest as: waking state, dreaming state, first light sleep state, second light sleep state, and deep sleep state. For example, in this embodiment of the invention, the correspondence between changes in sleep state type and user comfort adjustment can be established using pre-collection. When the user maintains a certain sleeping posture and enters a sleep state with corresponding physiological parameters, the pressure parameters of the airbags in the mattress are adjusted to change the user's comfort. During the adjustment of the airbag pressure parameters, the user's sleeping posture may or may not change. By collecting the airbag pressure parameters and sleeping postures corresponding to different sleep state types, the relationship between comfort and sleep state type is established. In this embodiment of the invention, the user's sleep state is intervened in by intervening in the user's sleep state type, thereby improving the user's sleep quality.

[0119] Based on the same inventive concept, embodiments of the present invention also provide a device for intelligently regulating sleep state, which is used to perform a method for intelligently regulating sleep state. Figure 8This is a schematic diagram of the structure of a device for intelligently regulating sleep state according to an embodiment of the present invention, as shown below. Figure 8 As shown, the device includes:

[0120] The sleep parameter acquisition module 100 is used to acquire historical sleep staging models, the user's standard sleep cycle, and the first cardiac impact signal, which is the user's cardiac impact signal in the current time segment.

[0121] The sleep state determination module 200 is used to determine the user's first sleep state information and predict the second sleep state information based on the first cardiac impact signal and the historical sleep staging model. The first sleep state information is the sleep state information under the current time segment, and the second sleep state information is the sleep state information under the next time segment.

[0122] The sleep regulation judgment module 300 is used to determine whether sleep regulation is needed based on the second sleep state information and the standard sleep cycle.

[0123] The sleep regulation module 400 is used to output a corresponding regulation scheme based on the first sleep state information, the second sleep state information, the user's physiological parameters, and the user's sleeping posture when sleep state regulation is required.

[0124] Since the device for intelligently regulating sleep state is used to execute the method for intelligently regulating sleep state, the device for intelligently regulating sleep state also has the beneficial effects of the method for intelligently regulating sleep state in the above embodiments, and will not be described again in this embodiment.

[0125] Based on the same inventive concept, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for intelligently adjusting a sleep state.

[0126] Of course, the computer-readable storage medium provided in the embodiments of the present invention has computer-executable instructions that are not limited to the method operations described above, but can also perform related operations in the method for intelligently adjusting sleep state provided in any embodiment of the present invention.

[0127] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0128] It is worth noting that in the embodiments of the search device described above, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0129] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0130] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method of intelligently adjusting sleep states, the method comprising: The method for intelligently adjusting a sleep state comprises: obtaining a historical sleep staging model, a standard sleep cycle of a user, and a first ballistocardiogram of the user, the first ballistocardiogram being a ballistocardiogram of the user in a current time segment; determining first sleep state information of the user and predicting second sleep state information according to the first ballistocardiogram and the historical sleep staging model, the first sleep state information being sleep state information in the current time segment, and the second sleep state information being sleep state information in a next time segment; judging whether sleep state adjustment is needed according to the second sleep state information and the standard sleep cycle; if so, outputting a corresponding adjustment scheme according to the first sleep state information, the second sleep state information, physiological parameters of the user, and a sleep posture of the user; the determining of the first sleep state information of the user and the predicting of the second sleep state information according to the first ballistocardiogram and the historical sleep staging model comprises: determining the first sleep state information corresponding to the first ballistocardiogram according to the first ballistocardiogram and the historical sleep staging model; predicting a second ballistocardiogram according to the first ballistocardiogram, the second ballistocardiogram being a ballistocardiogram in the next time segment; determining the second sleep state information according to the second ballistocardiogram and the historical sleep staging model; the predicting of the second ballistocardiogram according to the first ballistocardiogram comprises: calculating a function corresponding relationship between a ballistocardiogram and a time segment according to the first ballistocardiogram by using a nonlinear interpolation method; calculating the ballistocardiogram in the next time segment according to the function corresponding relationship.

2. The method of claim 1, wherein, The obtaining of the historical sleep staging model comprises: extracting historical time domain features and historical frequency domain features of historical ballistocardiograms; obtaining a sleep staging label model, the sleep staging label model comprising a corresponding relationship between time domain features and frequency domain features and sleep staging labels; determining a historical sleep staging model corresponding to the historical ballistocardiograms according to the historical time domain features, the historical frequency domain features, and the sleep staging label model.

3. The method of claim 1, wherein the method further comprises: The obtaining of the standard sleep cycle of the user comprises: obtaining physiological parameter information and sleep parameter information of a current user; determining the standard sleep cycle of the current user according to the physiological parameter information, the sleep parameter information, and standard sleep state parameter information.

4. The method of claim 3, wherein the sleep state is adjusted based on the determined sleep state of the user. The physiological parameter information comprises gender, age, height, weight, and whether the user has a certain disease; the sleep parameter information comprises sleep duration.

5. The method for intelligently adjusting a sleep state according to claim 1, wherein the judging of whether sleep state adjustment is needed according to the second sleep state information and the standard sleep cycle comprises: obtaining a sleep start time and determining first time information corresponding to the second sleep state information according to the second sleep state information; determining sleep duration information according to the first time information and the sleep start time; determining standard sleep state information corresponding to the sleep duration information in the standard sleep cycle according to the sleep duration information. ​ determining whether sleep state adjustment is needed according to whether the second sleep state information and the standard sleep state information are identical.

6. The method of claim 5, wherein the sleep state is adjusted based on the determined sleep state of the user. outputting a corresponding adjustment scheme according to the first sleep state information, the second sleep state information, a physiological parameter of the user, and a sleep posture of the user, including: adjusting sleep comfort of the user according to the first sleep state information, the physiological parameter of the user, and the sleep posture of the user, so that the second sleep state information is adjusted to the standard sleep state information.

7. A device for intelligently regulating sleep state, characterized in that, The device for intelligently adjusting a sleep state includes: a sleep parameter acquisition module, configured to acquire a historical sleep staging model, a standard sleep cycle of a user, and a first ballistocardiogram of the user, the first ballistocardiogram being a ballistocardiogram of the user in a current time segment; a sleep state determination module, configured to determine first sleep state information of the user and predict second sleep state information according to the first ballistocardiogram and the historical sleep staging model, the first sleep state information being sleep state information in the current time segment, and the second sleep state information being sleep state information in a next time segment; a sleep adjustment determination module, configured to determine whether sleep state adjustment is needed according to the second sleep state information and the standard sleep cycle; a sleep adjustment module, configured to output a corresponding adjustment scheme according to the first sleep state information, the second sleep state information, a physiological parameter of the user, and a sleep posture of the user when sleep state adjustment is needed; the determining first sleep state information of the user and predicting second sleep state information according to the first ballistocardiogram and the historical sleep staging model, including: determining the first sleep state information corresponding to the first ballistocardiogram according to the first ballistocardiogram and the historical sleep staging model; predicting a second ballistocardiogram according to the first ballistocardiogram, the second ballistocardiogram being a ballistocardiogram in the next time segment; determining the second sleep state information according to the second ballistocardiogram and the historical sleep staging model; the predicting a second ballistocardiogram according to the first ballistocardiogram, including: calculating a function corresponding relationship between a ballistocardiogram and a time segment according to the first ballistocardiogram by using a nonlinear interpolation method; calculating the ballistocardiogram in the next time segment according to the function corresponding relationship.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method of any one of claims 1-6. The program is executed by the processor to implement the method of any one of claims 1-6.

Images