Equipment shutdown control method and device, equipment and storage medium

Abstract

The invention provides an equipment shutdown control method and device, equipment and a storage medium, and the method comprises the steps: obtaining sleep data of a user when learning equipment is in a working state, the sleep data comprising a sleep image and a sleep audio; performing sleep state detection based on the sleep data to obtain a sleep state detection result; when the sleep state detection result indicates that the user is in the sleep state, the learning device is controlled to interrupt the working state and is shut down, the learning device can be intelligently controlled according to the state of the user, and when the user is in the sleep state, the learning device can be automatically shut down, so that the user experience is improved. Therefore, interference to sleep of the user and waste of electric quantity are avoided, the flexibility of equipment control is improved, the intelligent degree of the learning equipment is enhanced, the service time of the equipment is prolonged, the use requirements of the user in different scenes can be met, the learning effect of the user can be improved, and the equipment use experience of the user can be optimized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent terminal technology, and in particular to a device shutdown control method, device, equipment and storage medium. Background Art

[0002] In the process of learning English, listening practice is the key to improving language communication skills. With the development of technology, many devices that assist listening learning have emerged on the market. These devices provide students with convenient and efficient listening training methods, which help them improve their listening skills.

[0003] At present, when users use devices for listening practice, if it is during the day, users can flexibly adjust the practice time according to their personal study or work needs, and manually turn on and off the device to ensure that other matters are not affected. However, at night, users who are used to doing listening practice at night often fall asleep during practice, resulting in the inability to manually turn off the device in time. This may not only wake the user up due to the continued playback of the device, affecting the quality of sleep, but also cause the device to run out of power at night, affecting normal use the next day. Summary of the invention

[0004] The present invention provides a device shutdown control method, apparatus, equipment and storage medium, which are used to solve the problem in the prior art that the device power on and off completely relies on manual operation of the user, which is inconvenient to use and easily brings a bad experience to the user. The present invention realizes automated device shutdown control, which can automatically shut down the device when the user is in a sleeping state, thereby saving power while avoiding interference with the user's sleep and affecting their sleep quality.

[0005] The present invention provides a device shutdown control method, comprising: When the learning device is in working state, obtaining sleep data of the user, wherein the sleep data includes sleep images and sleep audio; Performing sleep state detection based on the sleep data to obtain a sleep state detection result; When the sleep state detection result indicates that the user is in a sleep state, the learning device is controlled to interrupt the working state and shut down.

[0006] According to a device shutdown control method provided by the present invention, when the sleep state detection result indicates that the user is in a sleep state, controlling the learning device to interrupt the working state and shut down, comprising: When the sleep state detection result obtained by the sleep state detection indicates for the first time that the user is in a sleep state, controlling the learning device to lower the working parameter; When the sleep state detection result obtained by performing the sleep state detection again after the preset time still indicates that the user is in the sleep state, controlling the learning device to interrupt the working state and shut down; Wherein, lowering the working parameter includes lowering the working volume and / or dimming the working brightness.

[0007] According to a device shutdown control method provided by the present invention, when the sleep state detection result obtained by performing the sleep state detection again after the preset time still indicates that the user is in the sleep state, the learning device is controlled to interrupt the working state and shut down, including: Performing speaker detection based on the sleep data of the user within the preset time to obtain a speaker detection result; When the speaker detection result indicates that the user is not detected speaking, and no device control operation of the user is received within the preset time, performing sleep state detection again based on the sleep data within the preset time; When the sleep state detection result obtained by performing the sleep state detection again still indicates that the user is in the sleep state, the learning device is controlled to interrupt the working state and shut down.

[0008] According to a device shutdown control method provided by the present invention, the speaker detection is performed based on the sleep data of the user within the preset time to obtain the speaker detection result, and then the method further includes: When the speaker detection result indicates that the user is detected speaking, and / or when a device control operation of the user is received within the preset time, the learning device is controlled to adjust working parameters, and / or respond to the device control operation.

[0009] According to a device shutdown control method provided by the present invention, when the learning device is in a working state, obtaining the user's sleep data includes: Acquire, from the learning device, the device usage data of the user in the historical time, and / or the device operation data set by the user at the current time; Determining a target time based on the device usage data and / or the device operation data; When the learning device is in working state, human voice detection is performed based on a period of sleep data of the user after the target moment to obtain a human voice detection result, and when the human voice detection result indicates that no human voice is detected, the sleep data of the user is obtained.

[0010] According to a device shutdown control method provided by the present invention, the sleep data also includes sleep actions; the sleep state detection based on the sleep data to obtain the sleep state detection result includes: Extracting image sleep features of the sleep image, wherein the image sleep features include at least one of a sleep posture feature, a sleep expression feature, and a sleep eye feature; Extracting audio sleep features of the sleep audio, where the audio sleep features include at least one of a sleep slow wave feature, a breathing rhythm feature, and a heart rate feature; Extracting motion sleep features of the sleep motion, wherein the motion sleep features include at least one of motion frequency features, motion displacement features, and motion change features; Sleep state detection is performed based on the image sleep feature, the audio sleep feature, and the action sleep feature to obtain the sleep state detection result.

[0011] The present invention also provides a device shutdown control device, comprising: an acquisition unit, configured to acquire sleep data of a user when the learning device is in a working state, wherein the sleep data includes sleep images and sleep audio; a detection unit, configured to perform sleep state detection based on the sleep data to obtain a sleep state detection result; A control unit is used to control the learning device to interrupt the working state and shut down when the sleep state detection result indicates that the user is in a sleep state.

[0012] The present invention also provides a learning device, comprising a camera, a sound pickup and a processor; The processor is used to control the camera and the microphone to respectively collect the user's sleep images and sleep audio as the user's sleep data when the learning device is in working state, and perform sleep state detection based on the sleep data to obtain a sleep state detection result; when the sleep state detection result indicates that the user is in a sleep state, control the learning device to interrupt the working state and shut down.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the device shutdown control method as described in any one of the above is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the device shutdown control method as described in any one of the above is implemented.

[0015] The device shutdown control method, apparatus, device and storage medium provided by the present invention obtain the user's sleep image and sleep audio when the learning device is in a working state; perform sleep state detection based on the sleep image and sleep audio to obtain a sleep state detection result; when the sleep state detection result indicates that the user is in a sleep state, control the learning device to interrupt the working state and shut down, and can intelligently control the learning device according to the user's state, and can automatically shut down when the user is in a sleep state, thereby avoiding interference with the user's sleep and wasting power, increasing the flexibility of device control, enhancing the intelligence of the learning device, extending the use time of the device, being able to meet the user's usage needs in different scenarios, and helping to improve the user's learning effect and optimize the user's device usage experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 It is a flow chart of the device shutdown control method provided by the present invention; Figure 2 It is a structural schematic diagram of the equipment shutdown control device provided by the present invention; Figure 3 It is a structural schematic diagram of the learning device provided by the present invention; Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Currently, when users use the device at night, they tend to fall asleep during practice, resulting in an inability to manually turn off the device in time. This may not only wake them up and affect their sleep quality, but also cause the device to run out of power at night, affecting normal use the next day.

[0020] In addition, the current listening practice equipment on the market is relatively simple in structure design, and generally only uses the power button to realize the manual power on and off function. This single control method lacks intelligence and automation, and cannot meet the user's demand for automatic shutdown of the device in specific scenarios (such as practicing before bed), which brings many inconveniences to the user's actual use.

[0021] In this regard, the present invention provides a device shutdown control method, which aims to achieve more flexible and intelligent device management, and can automatically control the shutdown of the device according to the user's status, thereby avoiding interference to the user and waste of power in the sleep state, increasing the intelligence of the device, extending the use time of the device, and meeting the user's usage needs in different scenarios, which helps to optimize the user's learning effect and device usage experience.

[0022] Figure 1 FIG. 1 is a flow chart of a device shutdown control method provided by the present invention, such as Figure 1 As shown, the method can be applied to a learning device, and the specific execution subject can be a processor in the learning device; it can also be applied to a server that directly controls the learning device, and the embodiment of the present invention does not specifically limit this. The learning device here can be an electronic device with multiple auxiliary learning functions, such as a learning machine, a listening device, etc. The method includes: Step 110, when the learning device is in working state, obtaining the user's sleep data, the sleep data including sleep images and sleep audio; Step 120, performing sleep state detection based on the sleep data to obtain a sleep state detection result; Step 130: When the sleep state detection result indicates that the user is in the sleep state, control the learning device to interrupt the working state and shut down.

[0023] Specifically, considering that current learning devices, especially listening practice devices, are usually simple in structure and only rely on the power button to achieve manual power on and off, in this case, when users use learning devices for auxiliary learning at night, once the user falls asleep, the learning device will continue to work without anyone controlling it, which may not only affect the user's sleep, but also cause ineffective consumption of device power, affecting normal use the next day.

[0024] Based on this, in an embodiment of the present invention, it is proposed that the usage data of the device can be obtained during the user's use process to determine the user's state, so that the device can be intelligently controlled according to the user's state. When the user falls into a sleep state, the device can be controlled to shut down. When the user is studying / working normally, the device can be controlled to work normally and the volume can be lowered to avoid interference, etc., so as to meet the user's usage needs in different scenarios, achieve more flexible, efficient and intelligent control, and then optimize the user's device usage experience.

[0025] It is understandable that in actual application, if intelligent control of learning equipment is to be achieved, it is first necessary to obtain relevant data of the user during the use of the equipment. The data may be images, audio, or other data such as actions, which are not specifically limited in the embodiments of the present invention. Preferably, in order to ensure the diversity of data so as to accurately identify the user's state in the subsequent state detection link, the data here may include images and audio.

[0026] That is, when the user uses the learning device to learn, which can also be understood as when the learning device is in working state, the image and audio of the user can be collected by the image acquisition device and the audio acquisition device respectively, so as to obtain the sleep image and the sleep audio. The image acquisition device here can be a camera, etc., which can be installed on the learning device or can be set separately from the learning device, and the communication connection with the learning device can be maintained. The audio acquisition device can be a pickup, such as a microphone, which can be installed on the learning device or on headphones connected to the learning device, and the embodiment of the present invention does not make specific limitations.

[0027] After obtaining the user's sleep image and sleep audio, in an embodiment of the present invention, the user's sleep state detection can be performed based on the sleep image and sleep audio to detect whether the user is currently in a sleep state, thereby obtaining the user's sleep state detection result, so as to implement intelligent device control based on this, thereby helping to optimize the user experience.

[0028] Specifically, the sleep state of the user can be detected based on the sleep image and sleep audio to determine whether the user is currently asleep. Specifically, a comprehensive analysis can be performed based on the user's eye condition, body posture, facial expression, etc. presented in the sleep image, and the user's breathing rhythm, frequency, severity, etc. reflected in the sleep audio, to accurately determine whether the user is asleep from multiple levels and dimensions, thereby obtaining the user's sleep state detection result.

[0029] After that, the learning device can be intelligently controlled according to the user's sleep status detection results. Specifically, when the sleep status detection indicates that the user is currently asleep, that is, the user is in a sleeping state, in order to avoid ineffective consumption of power and affecting the user's sleep, the learning device can be controlled to stop working, that is, interrupt the current working state, such as jumping out of the working application / program / process, etc., and control the learning device to shut down to avoid affecting subsequent use.

[0030] Correspondingly, when the sleep state detection result indicates that the user is not currently asleep, that is, the user is not in a sleep state, no additional control can be performed on the device, so that it maintains the current working state and works normally; specific control can also be performed according to specific circumstances. For example, when the user is not asleep but is about to fall asleep, or when the user is busy with other work, the learning device can be controlled to lower the volume, reduce the screen brightness, etc., to avoid disturbing the user; for another example, when the user is not asleep and is studying seriously, the learning device can be controlled to appropriately increase the brightness.

[0031] The device shutdown control method provided by the present invention obtains the user's sleep image and sleep audio when the learning device is in a working state; performs sleep state detection based on the sleep image and sleep audio to obtain a sleep state detection result; and controls the learning device to interrupt the working state and shut down when the sleep state detection result indicates that the user is in a sleep state. The learning device can be intelligently controlled according to the user's state, and can be automatically shut down when the user is in a sleep state, thereby avoiding interference with the user's sleep and wasting power, increasing the flexibility of device control, enhancing the intelligence of the learning device, extending the use time of the device, being able to meet the user's use needs in different scenarios, and helping to improve the user's learning effect and optimize the user's device usage experience.

[0032] Based on the above embodiment, step 130 includes: When the sleep state detection result obtained by the sleep state detection indicates for the first time that the user is in a sleep state, controlling the learning device to lower the working parameter; When the sleep state detection result obtained by performing the sleep state detection again after the preset time still indicates that the user is in the sleep state, controlling the learning device to interrupt the working state and shut down; Wherein, lowering the working parameters includes lowering the working volume and / or dimming the working brightness.

[0033] Specifically, in step 130, when the sleep state detection result indicates that the user is in a sleep state, the process of controlling the learning device to interrupt the working state and shut down may specifically include: Considering that falling asleep is a continuous process, and sleep is divided into stages, some shallow and some deep, in order to avoid misjudgment and ensure the accuracy of sleep state detection, in the embodiment of the present invention, the sleep state detection process is set to be continuous. That is, after obtaining the user's sleep data, the first sleep state detection can be performed. If the sleep state detection result at this time shows that the user is in a sleep state, it is determined that the user has been detected in a sleep state for the first time; conversely, if the sleep state detection result at this time shows that the user is not in a sleep state, continuous monitoring can be performed to obtain the user's next sleep data, and sleep state detection can be performed until the user is detected in a sleep state, at which time the user is detected in a sleep state for the first time.

[0034] When it is detected for the first time that the user is asleep, that is, when the sleep state detection result obtained by the sleep state detection indicates for the first time that the user is asleep, the learning device can be controlled to lower the working parameters, specifically, the working volume and / or the working brightness can be lowered, and continuous monitoring can be performed to obtain the user's next sleep data, so that further control can be performed based on the user's next sleep data, thereby avoiding the problem of directly controlling the device to shut down, resulting in interruption of the working state, and causing a bad experience for the user when the user falls asleep lightly or the state is misjudged. More precise, flexible and intelligent device control can be achieved in a step-by-step manner, which can better guarantee the user's device usage experience.

[0035] Furthermore, after the learning device is controlled to adjust the working parameters, in an embodiment of the present invention, a preset time may be waited, such as 5 minutes, 10 minutes, etc., and a sleep state detection may be performed again after the preset time to determine whether the user has truly entered a sleep state, rather than a misjudgment, shallow sleep, etc. That is, after the learning device is controlled to adjust the working parameters, a preset time may be waited first, and then a sleep state detection may be performed to obtain a sleep state detection result. The sleep state detection here may be based on the user's sleep data within the preset time, or on the user's sleep data collected after the preset time, which is not specifically limited in the embodiment of the present invention.

[0036] After that, if the sleep status detection result obtained by performing the sleep status detection again after the preset time still indicates that the user is in the sleep state, it can be determined that the sleep status detection result indicating that the user is in the sleep state for the first time is not a misjudgment. Therefore, when it is confirmed again that the user is in the sleep state, the learning device can be directly controlled to interrupt the working state and shut down.

[0037] Based on the above embodiment, when the sleep state detection result obtained by performing the sleep state detection again after the preset time still indicates that the user is in the sleep state, controlling the learning device to interrupt the working state and shut down includes: Perform speaker detection based on the user's sleep data within a preset time to obtain a speaker detection result; When the speaker detection result indicates that no user speech is detected and no device control operation of the user is received within a preset time, sleep state detection is performed again based on sleep data within the preset time; When the sleep state detection result obtained by performing the sleep state detection again still indicates that the user is in the sleep state, the learning device is controlled to interrupt the working state and shut down.

[0038] Specifically, when the sleep state detection result obtained by performing the sleep state detection again after the preset time still indicates that the user is in the sleep state, the process of controlling the learning device to interrupt the working state and shut down may specifically include the following steps: To achieve more precise and intelligent device control, in an embodiment of the present invention, after the learning device is controlled to lower the working parameters, the user can be continuously monitored to obtain the user's sleep data within a preset time. Specifically, after the learning device lowers the working parameters, the image acquisition device and the audio acquisition device are controlled to respectively collect the user's sleep images and sleep audio within the preset time, and the sleep data collected by the image acquisition device and the audio acquisition device are obtained.

[0039] After that, speaker detection can be performed based on the sleep data within the preset time to confirm whether someone is speaking during this period and whether the speaker is the user, thereby obtaining a speaker detection result. The speaker detection here can be implemented by currently mature speaker detection algorithms, programs, etc.

[0040] Furthermore, when the speaker detection result indicates that the user is not detected speaking, if the learning device does not receive the user's device control operation within the preset time, it can be determined that the user has not responded to the learning device to lower the working parameters. At this time, the sleep state detection can be performed again based on the sleep data obtained within the preset time to detect whether the user has truly entered the sleep state, rather than a misjudgment, shallow sleep, etc. If the sleep state detection result obtained by performing the sleep state detection again still indicates that the user is in the sleep state, it can be determined that the first detection of the user in the sleep state is not a misjudgment. At this time, the learning device can be directly controlled to interrupt the working state and shut down. In this way, it can avoid the problem of directly controlling the device to shut down when the user is in a shallow sleep or the state is misjudged, which brings a bad experience to the user, and realizes more flexible and intelligent device control, and better guarantees the user experience.

[0041] Based on the above embodiment, speaker detection is performed based on the sleep data of the user within a preset time to obtain a speaker detection result, and then the following steps are further included: When the speaker detection result indicates that the user is speaking, and / or a device control operation of the user is received within a preset time, the learning device is controlled to adjust the working parameters, and / or respond to the device control operation.

[0042] Specifically, after performing speaker detection based on the user's sleep data within a preset time, if the speaker detection result indicates that the user is detected speaking, or the learning device receives the user's device control operation within the preset time (such as turning up the volume, turning on the screen, turning up the screen brightness, etc.), or not only receives the user's device control operation but also detects the user speaking, it can be determined that the user has not fallen asleep, and has responded to the learning device's lowering of the working parameters. Therefore, the original working state can be restored, that is, the learning device can be controlled to increase the working parameters, and / or the learning device can be controlled to respond to the user's device control operation, so as to meet the user's needs and thereby ensure the user's usage experience.

[0043] Based on the above embodiment, step 110 includes: Obtaining, from the learning device, the user's device usage data in the historical period, and / or the device operation data set by the user at the current time; Determine the target time based on the device usage data and / or the device work data; When the learning device is in working state, human voice detection is performed based on a period of sleep data of the user after the target moment to obtain a human voice detection result, and when the human voice detection result indicates that no human voice is detected, the user's sleep data is obtained.

[0044] Specifically, in step 110, when the learning device is in working state, the process of obtaining the user's sleep data may specifically include: In order to avoid unnecessary power consumption and equipment loss caused by long-term uninterrupted monitoring of image acquisition devices and audio acquisition devices, in an embodiment of the present invention, it is proposed to "fix" the data collection process so as to start monitoring after a certain located time point / moment to obtain the user's sleep data. In this way, the required data can be efficiently obtained while reducing the load of long-term operation and monitoring of the equipment and reducing power loss.

[0045] Specifically, here, the positioning can be first performed based on the user's usage habits, the user's currently set working hours, etc., that is, the target time can be determined based on the user's device usage data and / or the device working data currently set by the user. This process is actually based on the user's habit of using the learning device for learning, for example, the habit of studying from 8 to 10 pm every day, the habit of studying for an hour and a half every day, etc., and / or the user's own set learning time, for example, studying for an hour and a half from the current time, studying from now until 10 pm, etc., to analyze and locate the time point of the user's state change, thereby determining the target time.

[0046] For example, if the user's device usage data and / or the device work data set by the user both indicate that the user is likely to rest at 10 o'clock in the evening, the target time can be determined based on 10 o'clock. The target time here can be 10 o'clock, 5 minutes after 10 o'clock, 9:55, 10 minutes after 10 o'clock, or other time points close to 10 o'clock.

[0047] After determining the target time, in an embodiment of the present invention, data collection can be performed based on this so as to obtain the required sleep data of the user. Specifically, when the learning device is in working state, when the current time reaches the target time, a period of sleep data of the user after the target time can be obtained first. For example, when the target time is ten o'clock, the sleep data of the user during the period from ten o'clock to five minutes after ten can be obtained as a period of sleep data of the user after the target time. Then, human voice detection can be performed based on this period of sleep data to detect whether anyone is speaking during this period, so as to obtain the human voice detection result during this period. The human voice detection here can be achieved by the current mature human voice detection algorithm.

[0048] After that, data can be captured according to the voice detection result to obtain the required sleep data of the user. Specifically, when the voice detection result shows that no one is detected talking during this period, the image acquisition device and the audio acquisition device are controlled to collect data to obtain the user's sleep data. If the voice detection result shows that someone is detected talking during this period, because the user is unlikely to fall into a deep sleep when someone is obviously talking, you can continue to wait, collect data again and perform voice detection after a period of time, until no one is detected talking, and then the image acquisition device and the audio acquisition device collect data to obtain the user's sleep data.

[0049] Based on the above embodiment, the sleep data also includes sleep movements; Step 120 includes: Extracting image sleep features of the sleep image, where the image sleep features include at least one of a sleep posture feature, a sleep expression feature, and a sleep eye feature; Extracting audio sleep features of sleep audio, where the audio sleep features include at least one of sleep slow wave features, breathing rhythm features, and heart rate features; Extracting motion sleep features of sleep movements, where the motion sleep features include at least one of motion frequency features, motion displacement features, and motion change features; The sleep state detection is performed based on the image sleep features, the audio sleep features, and the motion sleep features to obtain the sleep state detection result.

[0050] Specifically, in step 120, the process of performing sleep state detection according to the sleep data to obtain the sleep state detection result may specifically include: First, feature extraction can be performed on the sleep data to obtain the user's sleep features. That is, feature extraction can be performed on the user's sleep images, sleep audio, and sleep movements, respectively, to extract features of the user at multiple levels, thereby obtaining the user's sleep features.

[0051] Here, it can be specifically performed feature extraction on the sleep image to extract information representing the user's sleeping posture, facial expression, eye condition, etc., and encode to obtain the user's image sleep features. The image sleep features may include any one or more of sleep posture features, sleep expression features, and sleep eye features. Feature extraction is performed on the sleep audio to extract information reflecting the user's breathing rhythm, heart rate, severity, etc., and encode to obtain the user's audio sleep features. The audio sleep features here include at least one of sleep slow wave features, breathing rhythm features, and heart rate features. Feature extraction is performed on the sleep action to extract information reflecting the degree of change of the user's action, the amount of change of the action, the frequency, etc., and encode to obtain the action sleep features. The action sleep features include at least one of action frequency features, action displacement features, and action change features.

[0052] Subsequently, the sleep state detection can be performed together based on the features of multiple levels extracted in the previous step, namely, the image sleep features, the audio sleep features, and the motion sleep features, so as to obtain accurate and reliable sleep state detection results. That is, the features of multiple levels can be integrated to perform sleep state detection, so as to ensure the comprehensive and accurate detection and the accuracy and reliability of the detection results.

[0053] The device shutdown control apparatus provided by the present invention is described below. The device shutdown control apparatus described below and the device shutdown control method described above can be referred to each other.

[0054] Figure 2 Schematic diagram of the structure of the device shutdown control device provided by the present invention, such as Figure 2 As shown, the device comprises: An acquisition unit 210, configured to acquire sleep data of a user when the learning device is in working state, wherein the sleep data includes sleep images and sleep audio; A detection unit 220, configured to perform sleep state detection based on the sleep data to obtain a sleep state detection result; The control unit 230 is used to control the learning device to interrupt the working state and shut down when the sleep state detection result indicates that the user is in the sleep state.

[0055] The device shutdown control device provided by the present invention obtains the user's sleep image and sleep audio when the learning device is in a working state; performs sleep state detection based on the sleep image and sleep audio to obtain a sleep state detection result; and controls the learning device to interrupt the working state and shut down when the sleep state detection result indicates that the user is in a sleep state. The learning device can be intelligently controlled according to the user's state, and can automatically shut down when the user is in a sleep state, thereby avoiding interference with the user's sleep and wasting electricity, increasing the flexibility of device control, enhancing the intelligence of the learning device, extending the use time of the device, being able to meet the user's use needs in different scenarios, and helping to improve the user's learning effect and optimize the user's device usage experience.

[0056] Based on the above embodiment, the control unit 230 is used for: When the sleep state detection result obtained by the sleep state detection indicates for the first time that the user is in a sleep state, controlling the learning device to lower the working parameter; When the sleep state detection result obtained by performing the sleep state detection again after the preset time still indicates that the user is in the sleep state, controlling the learning device to interrupt the working state and shut down; Wherein, lowering the working parameter includes lowering the working volume and / or dimming the working brightness.

[0057] Based on the above embodiment, the control unit 230 is used for: Performing speaker detection based on the sleep data of the user within the preset time to obtain a speaker detection result; When the speaker detection result indicates that the user is not detected speaking, and no device control operation of the user is received within the preset time, performing sleep state detection again based on the sleep data within the preset time; When the sleep state detection result obtained by performing the sleep state detection again still indicates that the user is in the sleep state, the learning device is controlled to interrupt the working state and shut down.

[0058] Based on the above embodiment, the control unit 230 is further configured to: When the speaker detection result indicates that the user is detected speaking, and / or when a device control operation of the user is received within the preset time, the learning device is controlled to adjust working parameters, and / or respond to the device control operation.

[0059] Based on the above embodiment, the acquisition unit 210 is used for: Acquire, from the learning device, the device usage data of the user in the historical time, and / or the device operation data set by the user at the current time; Determining a target time based on the device usage data and / or the device operation data; When the learning device is in working state, human voice detection is performed based on a period of sleep data of the user after the target moment to obtain a human voice detection result, and when the human voice detection result indicates that no human voice is detected, the sleep data of the user is obtained.

[0060] Based on the above embodiment, the sleep data also includes sleep movements; The detection unit 220 is used for: Extracting image sleep features of the sleep image, wherein the image sleep features include at least one of a sleep posture feature, a sleep expression feature, and a sleep eye feature; Extracting audio sleep features of the sleep audio, where the audio sleep features include at least one of a sleep slow wave feature, a breathing rhythm feature, and a heart rate feature; Extracting motion sleep features of the sleep motion, wherein the motion sleep features include at least one of motion frequency features, motion displacement features, and motion change features; Sleep state detection is performed based on the image sleep feature, the audio sleep feature, and the action sleep feature to obtain the sleep state detection result.

[0061] Figure 3 It is a structural schematic diagram of the learning device provided by the present invention, such as Figure 3 As shown, the device includes a camera 310, a sound pickup 320 and a processor 330; The processor 330 is used to control the camera 310 and the microphone 320 to respectively collect the user's sleep images and sleep audio as the user's sleep data when the learning device is in working state, and perform sleep state detection based on the sleep data to obtain a sleep state detection result; when the sleep state detection result indicates that the user is in a sleep state, control the learning device to interrupt the working state and shut down.

[0062] The learning device provided by the present invention includes a camera, a microphone and a processor; the processor is used to control the camera and the microphone to respectively collect the user's sleep image and sleep audio as the user's sleep data when the learning device is in a working state, and perform sleep state detection based on the sleep data to obtain a sleep state detection result; when the sleep state detection result indicates that the user is in a sleep state, the learning device is controlled to interrupt the working state and shut down, and can intelligently control the learning device according to the user's state, and can automatically shut down when the user is in a sleep state, thereby avoiding interference with the user's sleep and wasting electricity, increasing the flexibility of device control, enhancing the intelligence of the learning device, extending the use time of the device, being able to meet the user's use needs in different scenarios, and helping to improve the user's learning effect and optimize the user's device usage experience.

[0063] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the device shutdown control method, which includes: when the learning device is in a working state, obtaining the user's sleep data, the sleep data including sleep images and sleep audio; performing sleep state detection based on the sleep data to obtain a sleep state detection result; when the sleep state detection result indicates that the user is in a sleep state, controlling the learning device to interrupt the working state and shut down.

[0064] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0065] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the device shutdown control method provided by the above methods, and the method includes: when the learning device is in a working state, obtaining the user's sleep data, the sleep data including sleep images and sleep audio; performing sleep state detection based on the sleep data to obtain a sleep state detection result; when the sleep state detection result indicates that the user is in a sleep state, controlling the learning device to interrupt the working state and shut down.

[0066] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the device shutdown control method provided by the above-mentioned methods. The method includes: when the learning device is in a working state, obtaining the user's sleep data, the sleep data including sleep images and sleep audio; performing sleep state detection based on the sleep data to obtain a sleep state detection result; when the sleep state detection result indicates that the user is in a sleep state, controlling the learning device to interrupt the working state and shut down.

[0067] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0068] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0069] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A device shutdown control method, characterized in that: include: When the learning device is in working state, obtaining sleep data of the user, wherein the sleep data includes sleep images and sleep audio; Performing sleep state detection based on the sleep data to obtain a sleep state detection result; When the sleep state detection result indicates that the user is in a sleep state, the learning device is controlled to interrupt the working state and shut down.

2. The device shutdown control method according to claim 1, characterized in that: When the sleep state detection result indicates that the user is in a sleep state, controlling the learning device to interrupt the working state and shut down includes: When the sleep state detection result obtained by the sleep state detection indicates for the first time that the user is in a sleep state, controlling the learning device to lower the working parameter; When the sleep state detection result obtained by performing the sleep state detection again after the preset time still indicates that the user is in the sleep state, controlling the learning device to interrupt the working state and shut down; Wherein, lowering the working parameter includes lowering the working volume and / or dimming the working brightness.

3. The device shutdown control method according to claim 2, characterized in that: When the sleep state detection result obtained by performing the sleep state detection again after the preset time still indicates that the user is in the sleep state, controlling the learning device to interrupt the working state and shut down, including: Performing speaker detection based on the sleep data of the user within the preset time to obtain a speaker detection result; When the speaker detection result indicates that the user is not detected speaking, and no device control operation of the user is received within the preset time, performing sleep state detection again based on the sleep data within the preset time; When the sleep state detection result obtained by performing the sleep state detection again still indicates that the user is in the sleep state, the learning device is controlled to interrupt the working state and shut down.

4. The device shutdown control method according to claim 3, characterized in that: The method further comprises: performing speaker detection based on the sleep data of the user within the preset time to obtain a speaker detection result; and then: When the speaker detection result indicates that the user is detected speaking, and / or when a device control operation of the user is received within the preset time, the learning device is controlled to adjust working parameters, and / or respond to the device control operation.

5. The device shutdown control method according to any one of claims 1 to 4, characterized in that: The step of obtaining the sleep data of the user when the learning device is in working state includes: Acquire, from the learning device, the device usage data of the user in the historical time, and / or the device operation data set by the user at the current time; Determining a target time based on the device usage data and / or the device operation data; When the learning device is in working state, human voice detection is performed based on a period of sleep data of the user after the target moment to obtain a human voice detection result, and when the human voice detection result indicates that no human voice is detected, the sleep data of the user is obtained.

6. The device shutdown control method according to any one of claims 1 to 4, characterized in that: The sleep data also includes sleep movements; The performing sleep state detection based on the sleep data to obtain a sleep state detection result includes: Extracting image sleep features of the sleep image, wherein the image sleep features include at least one of a sleep posture feature, a sleep expression feature, and a sleep eye feature; Extracting audio sleep features of the sleep audio, where the audio sleep features include at least one of a sleep slow wave feature, a breathing rhythm feature, and a heart rate feature; Extracting motion sleep features of the sleep motion, wherein the motion sleep features include at least one of motion frequency features, motion displacement features, and motion change features; Sleep state detection is performed based on the image sleep feature, the audio sleep feature, and the action sleep feature to obtain the sleep state detection result.

7. A device shutdown control device, characterized in that: include: an acquisition unit, configured to acquire sleep data of a user when the learning device is in a working state, wherein the sleep data includes sleep images and sleep audio; a detection unit, configured to perform sleep state detection based on the sleep data to obtain a sleep state detection result; A control unit is used to control the learning device to interrupt the working state and shut down when the sleep state detection result indicates that the user is in a sleep state.

8. A learning device, characterized in that: Includes camera, sound pickup and processor; The processor is used to control the camera and the microphone to respectively collect the user's sleep image and sleep audio as the user's sleep data when the learning device is in working state, and perform sleep state detection based on the sleep data to obtain a sleep state detection result; when the sleep state detection result indicates that the user is in a sleep state, control the learning device to interrupt the working state and shut down.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the device shutdown control method according to any one of claims 1 to 6 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the device shutdown control method according to any one of claims 1 to 6 is implemented.

Images