Sleep assisting method based on artificial intelligence and related device

Abstract

The invention is suitable for the technical field of sound box playing, provides a sleep assisting method based on artificial intelligence and a related device, and aims to establish an audio environment suitable for sleep for a user. The sleep assisting method based on artificial intelligence and applied to the intelligent loudspeaker box mainly comprises the steps that the sleep state of a target user is acquired; and according to the sleep state, adjusting sleep-aiding audio played by the intelligent sound box, wherein the sleep-aiding audio is used for creating an audio environment suitable for sleep.

Description

Technical Field

[0001] This application belongs to the technical field of speaker playback, and particularly relates to a sleep assistance method based on artificial intelligence and related devices. Background Art

[0002] As a high-quality audio output device, speakers have entered thousands of households. They are usually used in conjunction with video playback devices to provide audio-visual services, or to achieve ordinary audio playback functions such as playing songs, music, and radio broadcasts.

[0003] However, with the rapid development and maturity of artificial intelligence (AI), AI technology can be introduced into the audio playback of speakers to achieve some more intelligent and brand-new audio playback functions. Summary of the Invention

[0004] The purpose of this application is to provide a sleep assistance method based on artificial intelligence and related devices, so as to create an audio environment suitable for sleep for users.

[0005] In a first aspect, this application provides a sleep assistance method based on artificial intelligence, which is applied to a smart speaker and includes:

[0006] Obtain the sleep state of the target user;

[0007] Adjust the sleep assistance audio played by the smart speaker according to the sleep state, and the sleep assistance audio is used to create an audio environment suitable for sleep.

[0008] Optionally, the sleep state includes: the first sleep stage before falling asleep, the second sleep stage just entering sleep, and the third sleep stage in deep sleep;

[0009] The adjusting the sleep assistance audio played by the smart speaker according to the sleep state includes:

[0010] When it is determined that the target user is in the first sleep stage, play personalized soothing and relaxing music based on the historical preference data of the target user, and gradually reduce the volume played by the smart speaker to a preset volume value within a first preset duration;

[0011] When it is determined that the target user is in the second sleep stage, switch to playing a preset non-periodic natural background simulation sound;

[0012] When it is determined that the target user is in the third sleep stage, switch to playing a preset sound wave that can extend the deep sleep duration.

[0013] Optionally, the preset sound wave is a subsonic pulse of 0.5 to 2 Hz.

[0014] Optionally, the method further includes:

[0015] When it is determined that the target user is in the REM sleep state, the played sleep aid audio is ended, and the current environmental background noise is played.

[0016] Optionally, obtaining the sleep state of the target user includes:

[0017] Obtaining the sleep state by communicating and connecting with a wearable intelligent device worn by the target user; or,

[0018] Obtaining the sleep state by communicating and connecting with a smart home device in the environment where the target user is located.

[0019] Optionally, the smart speaker has also established a communication connection with other smart home devices, and the method further includes:

[0020] Generating control instructions for other smart home devices according to the sleep state;

[0021] Sending the control instructions and / or the sleep state to the other smart home devices, so that the other smart home devices cooperate to create a sleep-friendly environmental atmosphere according to the control instructions and / or the sleep state.

[0022] In a second aspect, the present application provides a sleep assistance device based on artificial intelligence, which is applied to a smart speaker and includes:

[0023] An obtaining unit, configured to obtain the sleep state of a target user;

[0024] A playing unit, configured to adjust the sleep aid audio played by the smart speaker according to the sleep state, and the sleep aid audio is used to create an audio environment suitable for sleep.

[0025] Optionally, the sleep state includes: a first sleep stage before falling asleep, a second sleep stage just entering sleep, and a third sleep stage in deep sleep;

[0026] When the playing unit adjusts the sleep aid audio played by the smart speaker according to the sleep state, it is specifically configured to:

[0027] When it is determined that the target user is in the first sleep stage, play personalized soothing and relaxing music based on the historical preference data of the target user, and make the volume played by the smart speaker gradually decrease to a preset volume value within a first preset duration;

[0028] When it is determined that the target user is in the second sleep stage, switch to playing a preset non-periodic natural background simulation sound;

[0029] When it is determined that the target user is in the third stage of sleep, switch to playing a preset sound wave that can extend the duration of deep sleep.

[0030] Optionally, the preset sound wave is a infrasonic pulse of 0.5 to 2 Hz.

[0031] Optionally, the device further includes:

[0032] An end unit, configured to end the played sleep aid audio and play the current ambient background noise when it is determined that the target user is in the rapid eye movement sleep state.

[0033] Optionally, when the acquisition unit acquires the sleep state of the target user, it specifically is used for:

[0034] Acquiring the sleep state by communicating with a wearable intelligent device worn by the target user; or,

[0035] Acquiring the sleep state by communicating with a smart home device in the environment where the target user is located.

[0036] Optionally, the smart speaker has also established a communication connection with other smart home devices, and the device further includes:

[0037] A generation unit, configured to generate control instructions for other smart home devices according to the sleep state;

[0038] A sending unit, configured to send the control instructions and / or the sleep state to the other smart home devices, so that the other smart home devices cooperate to create a sleep-friendly environmental atmosphere according to the control instructions and / or the sleep state.

[0039] In a third aspect, the present application provides a computer device, including:

[0040] A processor, a memory, a bus, an input / output interface, and a network interface;

[0041] The processor is connected to the memory, the input / output interface, and the network interface through the bus;

[0042] A program is stored in the memory;

[0043] When the processor executes the program stored in the memory, it implements the artificial intelligence-based sleep assistance method described in any one of the first aspects above.

[0044] Fourthly, the present application provides a computer storage medium storing instructions, which when executed on a computer, cause the computer to execute the sleep assistance method based on artificial intelligence according to any one of the above first aspects.

[0045] Fifthly, the present application provides a computer program product, which when executed on a computer, causes the computer to execute the sleep assistance method based on artificial intelligence according to any one of the above first aspects.

[0046] As can be seen from the above technical solutions, the embodiments of the present application have the following advantages:

[0047] The sleep assistance method based on artificial intelligence applied to the smart speaker in the present application obtains the sleep state of the target user to know the sleep stage of the target user; adjusts the sleep assistance audio played by the smart speaker according to the sleep state, and the sleep assistance audio is used to create an audio environment suitable for sleep, thereby realizing building an audio environment suitable for sleep for the user and realizing the sleep assistance function through the smart speaker. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic flowchart of an embodiment of the sleep assistance method based on artificial intelligence of the present application;

[0049] Figure 2 It is a schematic flowchart of another embodiment of the sleep assistance method based on artificial intelligence of the present application;

[0050] Figure 3 It is a schematic flowchart of another embodiment of the sleep assistance method based on artificial intelligence of the present application;

[0051] Figure 4 It is a schematic structural diagram of an embodiment of the sleep assistance device based on artificial intelligence of the present application;

[0052] Figure 5 It is a schematic structural diagram of an embodiment of the sleep assistance device based on artificial intelligence of the present application;

[0053] Figure 6 It is a schematic structural diagram of an embodiment of the computer device of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0055] It should be noted that the sleep environment has a crucial impact on a person's sleep quality. A good sleep environment can prompt people to fall asleep quickly and extend the deep sleep time, while a poor sleep environment is likely to cause people to have insomnia and wake up easily. To create a good sleep environment, considering that people usually close their eyes and find a relatively safe environment when sleeping, one of the major reasons affecting sleep quality is the sound in the sleep environment. In view of this, this embodiment proposes a sleep assistance method based on artificial intelligence (AI) applied to a smart speaker. The smart speaker mainly includes: a central processing unit, a memory module, an artificial intelligence chip module, a communication module, a speaker power amplifier module, an ambient light module, a power supply module, etc. After connecting the above-mentioned modules through a printed circuit board (PCB) and fitting them into a suitable speaker, the smart speaker is obtained. Among them, the central processing unit is mainly used to comprehensively schedule each connected component module to implement the sleep assistance method mentioned in this embodiment; the power supply module is mainly used to provide appropriate working voltages for the central processing unit module, the memory module, the artificial intelligence chip module, the communication module, the speaker power amplifier module, the ambient light module, etc. The power supply module can be in a mode of self-powered battery or mains supply mode, and the power source of the power supply module is not limited here; the memory module mainly stores programs for implementing the relevant steps of this embodiment. At the same time, the memory also stores a pre-trained artificial intelligence model, preset music data, natural background simulation sound data, preset sound wave data that can extend the deep sleep duration, control instruction data for controlling other smart home devices, etc.; the artificial intelligence chip module is used to quickly load and run the artificial intelligence model stored in the memory module and adjust the sleep state of the target user to play sleep assistance audio on the smart speaker; the communication module is mainly used for communication with the outside world (electronic devices such as mobile phones, tablets, computers, and smart home devices such as smart air conditioners, smart indoor lights, and smart fans); the speaker power amplifier module is mainly used to control the playback of different audio sounds according to the central processing unit module to achieve the playback function of the speaker; the ambient light module can be turned off or on. When the ambient light module is turned on, it can achieve the pulsating display of the light according to the strength of the audio sound or display the light according to a preset program to form an ambient light atmosphere. In another embodiment, the smart speaker of this embodiment can further be integrated with a sensor module, which includes but is not limited to a microphone array, an infrared camera, etc. The ambient audio data is obtained through the microphone array, and the personnel data such as the position, posture, and body temperature of the personnel in the environment is obtained through the infrared camera.

[0056] Based on the above understanding, please refer to Figure 1 , an embodiment of the sleep assistance method based on artificial intelligence applied to a smart speaker in this application, includes:

[0057] 101. Obtain the sleep state of the target user.

[0058] It should be noted that the smart speaker in this embodiment should be in the same space as the target user, and the speaker of the smart speaker should be oriented towards the resting position of the target user, and the smart speaker should be activated with the sleep assistance function. This sleep assistance function can be entered through voice wake-up or user setting operations. The resting position of the target user is within the sound effect coverage range of the smart speaker. Different smart speakers have different sound effect coverage ranges. For example, within a diameter range of 5 meters or 10 meters centered on the smart speaker or in the direction the smart speaker is facing. In view of this, the sleep state of the target user in this step can be obtained through the sensor module of the smart speaker. For example, data such as the position, posture, and body temperature of the person can be obtained through the infrared camera of the smart speaker, and the sleep state of the target user can be obtained through recognition by a trained artificial intelligence model. The training of the artificial intelligence model in this embodiment can collect infrared camera image data in various sleep states from hospital volunteers, maternity hospital volunteers, etc. as training samples. When necessary, combined with manual classification of the sleep states (before sleep, falling asleep, deep sleep, rapid eye movement sleep, etc.) of the volunteer personnel in different training samples for facial expressions, so that the artificial intelligence model can be trained to obtain a trained artificial intelligence model that can identify the sleep state of the target user in the infrared image. It can be understood that the smart speaker can also be installed with other functional modules capable of obtaining the physiological data of the target user, and then combined with the corresponding trained artificial intelligence model to identify and analyze the physiological data of the target user to obtain the corresponding sleep state of the target user. The method for the smart speaker to obtain the sleep state of the target user is not limited here. The artificial intelligence model in this embodiment includes a deep learning model, which can continuously optimize the sleep assistance audio playback strategy according to the historical sleep data, sleep assistance audio feedback, physiological data, environmental data, etc. of the target user.

[0059] 102. Adjust the sleep assistance audio played by the smart speaker according to the sleep state. The sleep assistance audio is used to create an audio environment suitable for sleep.

[0060] After knowing the target user's sleeping state in step 101, in this step, the smart speaker adjusts the sleep-aiding audio played by the smart speaker according to the sleeping state, so as to create an audio environment suitable for sleep in various situations of the target user's sleeping state. For example, assuming that the sleep state includes the first stage of sleep before falling asleep, the second stage of sleep just entering sleep, and the third stage of sleep in deep sleep, then this step can, when it is determined that the target user is in the first stage of sleep, play personalized soothing and relaxing music (such as pure music, lullabies, etc.) based on the historical preference data of the target user using the smart speaker, and gradually reduce the volume of the smart speaker to a preset volume value (between 20-40dB) within a first preset time period (such as 10 minutes, 30 minutes, etc.) to not excessively disturb the target user's sleep; when it is determined that the target user is in the second stage of sleep, switch to playing a preset non-periodic nature background simulation sound while maintaining the preset volume value setting; when it is determined that the target user is in the third stage of sleep, switch to playing a preset sound wave that can prolong the deep sleep time, such as a preset sound wave of 0.5 to 2 Hz infrasound pulse, so as to better guide the target user to gradually enter a longer period of deep sleep, in exchange for a better mental state after waking up. It can be seen that this embodiment builds an audio environment suitable for sleep for the target user, enriching the sleep-aiding function of the smart speaker.

[0061] See also Figure 2 Another embodiment of the artificial intelligence-based sleep assistance method applied to a smart speaker of the present application includes:

[0062] 201. Obtain the sleep status of the target user.

[0063] The execution of this step is the same as the above Figure 1 The operations performed in step 101 of the embodiment are similar and will not be repeated here.

[0064] In another embodiment, this step can also be that the smart speaker obtains the sleep status of the target user through the communication module and the wearable device worn by the target user. The wearable device is worn close to the target user and communicates with the smart speaker at all times to share the monitored sleep status or physiological data of the target user. If the wearable device shares the sleep status of the target user to the smart speaker, this step can reduce computing power expenditure and quickly respond to the sleep status of the target user to execute step 202; if the wearable device shares the physiological data of the target user to the smart speaker, the smart speaker needs to combine the corresponding trained artificial intelligence model to identify and analyze the physiological data of the target user to obtain the corresponding sleep status of the target user; there is no limitation on the method and means of obtaining the sleep status of the target user.

[0065] 202. Adjust the sleep-aiding audio played by the smart speaker according to the sleep state. The sleep-aiding audio is used to create an audio environment suitable for sleep.

[0066] The execution of this step is similar to the operations performed in Figure 1 Step 201 of the foregoing embodiment and will not be elaborated here.

[0067] In another possible specific embodiment, when the target user is in various stages of the sleep state, according to the changes in some physiological data indicators of the target user, this embodiment can also enable the smart speaker to adopt some audio playback strategies to guide the target user to relax for better sleep. The following strategies can be selected and executed singly or in combination. The association strategy between the physiological data of the target user and the playback of the sleep-aiding audio is, for example: when it is detected that the target user's heart rate is too high (heart rate greater than 90 beats per minute), the preset low-frequency alpha wave music (8-12 Hz) can be switched for playback and combined with the sound of forest streams to guide the target user's heart rate to gradually decrease; when it is detected that the target user's breathing rate is rapid (respiratory rate greater than 20 times per minute), the preset slow-paced piano music (below 60 BPM) can be switched for playback, and the breathing rhythm can be adjusted synchronously through the progressive breathing guidance audio; when it is detected that the target user frequently makes turning-over movements (mainly for the first stage of sleep before falling asleep), the preset deep white noise (such as pink noise) can be switched for playback and the volume can be reduced (less than 40 dB) to generalize and reduce external interference; when the galvanic skin response (GSR) of the target user is detected through a wearable device, if the corresponding emotional physiological index reflects that the target user has a high stress index and the sympathetic nerve is relatively active, the preset binaural beat audio (Delta wave, 0.5-4 Hz) can be switched for playback, and combined with the meditation guidance voice to guide the target user into a meditation state and reduce the target user's sense of anxiety; when the electroencephalogram (EEG) of the target user is detected through a wearable device and it is found that the Beta wave of the target user is active in the waking state, the preset progressive ASMR sound effects (such as the sound of raindrops + maracas) can be switched for playback and gradually transition to the Theta wave frequency music (4-8 Hz).

[0068] The association strategy between the environmental data of the target user and the playback of sleep-aiding audio. For example, when the high-frequency noise in the environment is greater than 60 dB, an active noise cancellation algorithm can be superimposed, and masking white noise (such as the sound of a fan) can be played and the noise frequency band can be dynamically matched to cancel the high-frequency noise; when the smart speaker is equipped with an ambient light sensor and detects that the strong light at night is greater than 300 lux, the dark environment sound effect (such as the sound of a campfire) can be played, and the brightness of the ambient light can be reduced to form an audiovisual collaborative relaxation effect; when the smart speaker is equipped with a temperature and humidity sensor and detects high temperature and high humidity (ambient temperature is greater than 28 °C, ambient humidity is greater than 70%), the preset cool sound effect (glacier melt water sound + metal wind chime sound) can be played, and when necessary, the smart air conditioner can be controlled to automatically cool down to 26 °C; when the smart speaker is equipped with a carbon dioxide concentration sensor and detects that the carbon dioxide concentration is too high (greater than 1000 ppm), the preset simulated air flow sense sound wave can be played, and the fresh air system can be started for indoor ventilation.

[0069] 203. When it is determined that the target user is in the rapid eye movement sleep state, stop playing the sleep-aiding audio and play the current environmental background noise.

[0070] It should be noted that many physiological functions inside the human body will change significantly after sleep, such as a slower heart rate, a drop in blood pressure, a slow metabolism, and a decrease in the number of breaths. After the target user enters deep sleep, they will also enter the rapid eye movement sleep state. Rapid eye movement sleep is a biological need. Prolonged blocking of a person's rapid eye movement sleep will cause serious cognitive impairments similar to those of psychotic patients. To prevent the target user in the rapid eye movement sleep state from being frightened, this step will stop playing the sleep-aiding audio at this stage, obtain the current environmental background noise through the microphone, play the current environmental background noise, and make the playback of the current environmental background noise less than 15 dB to prevent waking up the target user.

[0071] In another possible embodiment, please refer to Figure 3 , another embodiment of the sleep assistance method based on artificial intelligence applied to a smart speaker, includes:

[0072] 301. Generate control instructions for other smart home devices according to the sleep state.

[0073] It can be understood that the smart speaker in this embodiment can also serve as a control platform for controlling other smart home devices, support linkage settings with smart home devices, and create a comfortable sleep environment. Then, in this step, control instructions for other smart home devices can be generated according to the sleep state. The so-called other smart home devices include but are not limited to: smart lights, smart air conditioners, smart electric curtains, smart air humidifiers, etc. Support the target user to preset the mode states that need to be cooperated by such smart home devices in different sleep states (such as various states and corresponding strategies mentioned above in this embodiment), so as to correspondingly generate control instructions in this step.

[0074] 302. Send the control instruction and / or sleep state to other smart home devices so that other smart home devices create an environment atmosphere suitable for sleep according to the control instruction and / or sleep state.

[0075] Send the control instruction in step 301 to other smart home devices. Of course, the sleep state of the target user can also be sent to the smart home devices. Some smart home devices can be adjusted to an adapted working mode according to the sleep state of the target user to create an environment atmosphere suitable for sleep. For example, 30 minutes before the target user sets the bedtime, the smart speaker in this embodiment specifically links the smart lights to automatically adjust to warm yellow light (color temperature 2700K). When it is monitored that the heart rate of the target user enters the resting heart rate state (less than 75 beats per minute), it is considered that the target user enters the first stage before sleep.

[0076] Of course, the smart speaker in this embodiment can support multiple sleep aid modes, such as relaxation mode, deep sleep mode, wake-up mode, etc. Users can choose a suitable mode according to their own needs. The smart speaker also supports voice interaction functions. Users can control operations such as playing, pausing, switching songs, and adjusting the volume of the speaker through voice commands. The smart speaker in this embodiment can provide personalized sleep aid solutions according to the user's sleep state, emotional state, environmental data, etc., and adopts a non-drug sleep aid method, which is safe and has no side effects, and improves the sleep aid effect.

[0077] The above embodiments have described the embodiments of the application of the present application to the sleep assistance method based on artificial intelligence for smart speakers. Next, the application of the present application to the sleep assistance device based on artificial intelligence for smart speakers will be described. Please refer to Figure 4 , including:

[0078] An acquisition unit 401, configured to acquire the sleep state of a target user;

[0079] A playback unit 402, configured to adjust the sleep aid audio played by the smart speaker according to the sleep state, where the sleep aid audio is used to create an audio environment suitable for sleep.

[0080] The operations performed by the sleep assistance device based on artificial intelligence of the smart speaker in this application are similar to those described in the foregoing Figure 1 embodiment and will not be elaborated herein.

[0081] Please refer to Figure 5 , another embodiment of the sleep assistance device based on artificial intelligence of the smart speaker in this application, includes:

[0082] An acquisition unit 501, configured to acquire the sleep state of a target user;

[0083] A playback unit 502, configured to adjust the sleep assistance audio played by the smart speaker according to the sleep state, where the sleep assistance audio is used to create an audio environment suitable for sleep.

[0084] Optionally, the sleep state includes: a first sleep stage before falling asleep, a second sleep stage just entering sleep, and a third sleep stage in deep sleep;

[0085] When the playback unit 502 adjusts the sleep assistance audio played by the smart speaker according to the sleep state, it is specifically configured to:

[0086] When it is determined that the target user is in the first sleep stage, play personalized soothing and relaxing music based on the historical preference data of the target user, and gradually reduce the volume played by the smart speaker to a preset volume value within a first preset duration;

[0087] When it is determined that the target user is in the second sleep stage, switch to playing a preset non-periodic natural background simulation sound;

[0088] When it is determined that the target user is in the third sleep stage, switch to playing a preset sound wave that can extend the deep sleep duration.

[0089] Optionally, the preset sound wave is a subsonic pulse of 0.5 to 2 Hz.

[0090] Optionally, the device further includes:

[0091] An end unit 503, configured to end the played sleep assistance audio and play the current ambient background noise when it is determined that the target user is in the rapid eye movement sleep state.

[0092] Optionally, when the acquisition unit 501 acquires the sleep state of the target user, it is specifically configured to:

[0093] Acquire the sleep state by communicating with a wearable smart device worn by the target user; or,

[0094] By communicating and connecting with the smart home devices in the environment where the target user is located, the sleep state is obtained.

[0095] Optionally, the smart speaker has also established a communication connection with other smart home devices, and the device further includes:

[0096] A generating unit 504, configured to generate control instructions for other smart home devices according to the sleep state;

[0097] A sending unit 505, configured to send the control instructions and / or the sleep state to the other smart home devices, so that the other smart home devices cooperate to create an environment atmosphere suitable for sleeping according to the control instructions and / or the sleep state.

[0098] This application is applied to the operations performed by the sleep assistance device of the smart speaker based on artificial intelligence, which are similar to the operations described in any of the foregoing Figure 1 , Figure 2 and Figure 3 any one of the embodiments, and will not be described in detail herein.

[0099] Next, the computer device in the embodiments of the present application will be described. Please refer to Figure 6 , an embodiment of the computer device in the embodiments of the present application includes:

[0100] The computer device 600 may include one or more processors (central processing units, CPUs) 601 and a memory 602, and one or more application programs or data are stored in the memory 602. Among them, the memory 602 is volatile storage or persistent storage. The program stored in the memory 602 may include one or more modules, and each module may include a series of instruction operations on the computer device. Further, the processor 601 may be configured to communicate with the memory 602 and execute a series of instruction operations in the memory 602 on the computer device 600. The computer device 600 may further include: one or more network interfaces 603, one or more input / output interfaces 604, and / or, one or more operating systems, such as HarmonyOS, Windows Server, Mac OS, Unix, Linux, FreeBSD, etc. The processor 601 may execute the operations performed in any of the foregoing Figures 1 to 3 any one of the illustrated embodiments, and will not be described in detail here.

[0101] In several embodiments provided by the embodiments of the present application, those skilled in the art should understand that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the unit is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be in an electrical, mechanical, or other form.

[0102] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that can store program codes.

[0103] The foregoing is only a preferred embodiment of the present application and is not intended to limit the present application. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A sleep assistance method based on artificial intelligence, characterized in that Applied to a smart speaker, including: Obtain the sleep state of the target user; Adjust the sleep-aiding audio played by the smart speaker according to the sleep state, where the sleep-aiding audio is used to create an audio environment suitable for sleep.

2. The sleep assistance method according to claim 1, wherein The sleep state includes: the first stage of sleep before falling asleep, the second stage of sleep just entering sleep, and the third stage of sleep in deep sleep; The adjusting the sleep-aiding audio played by the smart speaker according to the sleep state includes: When it is determined that the target user is in the first stage of sleep, play personalized soothing and relaxing music based on the historical preference data of the target user, and gradually reduce the volume played by the smart speaker to a preset volume value within a first preset duration; When it is determined that the target user is in the second stage of sleep, switch to playing a preset non-periodic natural background simulation sound; When it is determined that the target user is in the third stage of sleep, switch to playing a preset sound wave that can extend the deep sleep duration.

3. The sleep assistance method according to claim 2, wherein The preset sound wave is a subsonic pulse of 0.5 to 2 Hz.

4. The sleep assistance method according to claim 2, wherein The method further includes: When it is determined that the target user is in the rapid eye movement sleep state, end the played sleep-aiding audio and play the current ambient background noise.

5. The sleep assistance method according to claim 1, characterized in that, Obtaining the sleep state of the target user includes: Obtain the sleep state by communicating and connecting with a wearable intelligent device worn by the target user; or, Obtain the sleep state by communicating and connecting with a smart home device in the environment where the target user is located.

6. The sleep assistance method according to claim 1, wherein The smart speaker is also communicatively connected to other smart home devices, and the method further includes: Generate control instructions for other smart home devices according to the sleep state; Send the control instructions and / or the sleep state to the other smart home devices so that the other smart home devices cooperate to create an environment atmosphere suitable for sleep according to the control instructions and / or the sleep state.

7. A sleep assistance device based on artificial intelligence, characterized in that, Applied to a smart speaker, including: An obtaining unit for obtaining the sleep state of the target user; A playing unit for adjusting the sleep-aiding audio played by the smart speaker according to the sleep state, where the sleep-aiding audio is used to create an audio environment suitable for sleep.

8. A computer device, characterized in that, Including: A processor, a memory, a bus, an input / output interface, and a network interface; The processor is connected to the memory, the input / output interface, and the network interface through the bus; A program is stored in the memory; When the processor executes the program stored in the memory, it implements the artificial intelligence-based sleep assistance method according to any one of claims 1 to 6.

9. A computer storage medium, characterized in that, Instructions are stored in the computer storage medium, and when the instructions are executed on a computer, the computer is caused to execute the artificial intelligence-based sleep assistance method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, When the computer program product is executed on a computer, the computer is caused to execute the artificial intelligence-based sleep assistance method according to any one of claims 1 to 6.

Images