Noise reduction method, electronic device, and storage device

Abstract

The application discloses a noise reduction method, an electronic device and a storage medium. The method comprises the following steps: obtaining a wake-up instruction; based on the wake-up instruction, waking up a voice module; and sending wake-up state information of the voice module to at least one target device, wherein the wake-up state information is used to instruct the at least one target device to adjust a first working mode to a second working mode, and noise generated by the target device in the first working mode is greater than noise generated by the target device in the second working mode. In the foregoing manner, the application can reduce the noise generated by the target device.

Description

Technical Field

[0001] This application relates to the field of speech processing technology, and in particular to a noise reduction method, electronic device, and storage medium. Background Technology

[0002] As artificial intelligence (AI) technology matures, more and more AI technologies are moving from the laboratory to the market, especially speech recognition technology, which is being applied to a wide range of products. Speech recognition technology is increasingly used in home appliances, but various types of noise exist in the home environment. The main noise comes from the appliances themselves and surrounding appliances, with the signal-to-noise ratio (SNR) at the appliance microphones approaching 0dB, or even being negative. This noise significantly affects speech recognition performance, resulting in low recognition rates. Summary of the Invention

[0003] The main technical problem addressed by this application is to provide a noise reduction method, electronic device, and storage medium that can reduce the noise generated by a target device.

[0004] To address the aforementioned technical problems, the first aspect of this application provides a noise reduction method, which includes: acquiring a wake-up command; waking up a voice module based on the wake-up command; and sending the wake-up status information of the voice module to at least one target device, wherein the wake-up status information is used to instruct the at least one target device to adjust a first working mode to a second working mode, and the noise generated by the target device in the first working mode is greater than the noise generated in the second working mode.

[0005] Before obtaining the wake-up command, the method further includes: obtaining the target wake-up voice and device noise information generated by at least one target device; matching the corresponding noise model based on the device noise information; removing the noise generated by at least one target device during operation contained in the target wake-up voice using the noise model; and obtaining the voice command based on the noise-removed target wake-up voice.

[0006] The noise model includes at least one of a first noise model, a second noise model, a third noise model, and a silent model. The first noise model, the second noise model, the third noise model, and the silent model are used to remove noise of different intensities, and the noise intensities used to remove decrease in sequence.

[0007] Before obtaining the wake-up command, the method further includes: obtaining the target wake-up voice and device noise information generated by at least one target device; obtaining a noise signal value that matches the device noise information from a noise information database; subtracting the voice signal value and the noise signal value corresponding to the target wake-up voice to obtain the subtracted target wake-up voice; and obtaining a voice command based on the subtracted target wake-up voice.

[0008] Wherein, the target device is a home appliance; and / or, after sending the wake-up status information of the voice module to at least one target device, the method further includes: sending target control voice to at least one target device, causing at least one target device to execute the control command in the target control voice.

[0009] To address the aforementioned technical problems, a second aspect of this application provides a noise reduction method, comprising: receiving wake-up state information of a voice module; adjusting a first operating mode of at least one target device to a second operating mode based on the wake-up state information, wherein the noise generated by the target device in the first operating mode is greater than the noise generated in the second operating mode.

[0010] The method further includes, after adjusting the first working mode of at least one target device to the second working mode based on the wake-up status information, the method further includes: if no control command is received from the voice module within a preset time, restoring the second working mode of the target device to the first working mode; or, after receiving the wake-up status information from the voice module, restoring the second working mode of the target device to the first working mode.

[0011] Wherein, the target device is a home appliance; and / or, after adjusting the first working mode of the target device to the second working mode based on the wake-up state information, the method further includes: receiving target control voice sent by the voice module; and executing the control instructions contained in the target control voice.

[0012] To address the aforementioned technical problems, a third aspect of this application provides an electronic device comprising a memory and a processor coupled to each other, wherein the memory stores program instructions; and the processor executes the program instructions stored in the memory to implement the noise reduction method described in the first or second aspect.

[0013] To address the aforementioned technical problems, a fourth aspect of this application provides a computer-readable storage medium for storing program instructions that can be executed to implement the noise reduction method described in the first or second aspect.

[0014] The beneficial effects of this application are as follows: Unlike existing technologies, this application, after obtaining a wake-up command, wakes up the voice module based on the wake-up command; and sends the wake-up status information of the voice module to at least one target device, wherein the wake-up status information is used to instruct at least one target device to adjust a first working mode to a second working mode, and the noise generated by the target device in the first working mode is greater than the noise generated in the second working mode. In this method, after the voice module is woken up, the noise generated by the target device can be reduced by changing the working mode of the target device. Attached Figure Description

[0015] Figure 1This is a flowchart illustrating the first embodiment of the noise reduction method provided in this application;

[0016] Figure 2 This is a flowchart illustrating the second embodiment of the noise reduction method provided in this application;

[0017] Figure 3 This is a flowchart illustrating the third embodiment of the noise reduction method provided in this application;

[0018] Figure 4 This is a flowchart illustrating the fourth embodiment of the noise reduction method provided in this application;

[0019] Figure 5 This is a flowchart illustrating the fifth embodiment of the noise reduction method provided in this application;

[0020] Figure 6 This is a flowchart illustrating the sixth embodiment of the noise reduction method provided in this application;

[0021] Figure 7 This is a schematic diagram of the framework structure of one embodiment of the electronic device provided in this application;

[0022] Figure 8 This is a schematic diagram of a framework of one embodiment of the computer-readable storage medium provided in this application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0024] It should be noted that the embodiments of this application contain descriptions involving "first," "second," etc., which are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0025] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0026] Please see Figure 1 , Figure 1 is a schematic flowchart of the first implementation manner of the noise reduction method provided by this application. The method includes:

[0027] S11: Obtain a wake-up instruction.

[0028] In one implementation manner, the wake-up instruction can be issued by the user or by a wake-up device. The wake-up device can be a mobile phone, a computer, etc. The wake-up instruction can be set according to the user's needs. For example, the wake-up instruction is "Xiaoyin". After the user issues the wake-up instruction, the processor receives the wake-up instruction issued by the user and wakes up the voice module according to the wake-up instruction.

[0029] In another implementation manner, the wake-up instruction is obtained after noise reduction processing of the target wake-up voice. The target wake-up voice includes the wake-up instruction and at least one noise generated when the target device is running. Then, noise reduction can be performed on the wake-up instruction to remove at least one noise generated when the target device is running. In a specific implementation manner, a noise model can be used to remove at least one noise generated when the target device is running; in another specific implementation manner, the difference can be taken between the noise signal value matching the device noise information generated by at least one target device and the voice signal value corresponding to the target wake-up voice to remove at least one noise generated when the target device is running.

[0030] S12: Wake up the voice module based on the wake-up instruction.

[0031] In one implementation manner, the voice module is default in a waiting-to-wake state. At this time, the voice module can only recognize the wake-up instruction. When the voice module is woken up, it can receive control instructions. Further, the wake-up state of the voice module after being woken up can be maintained for a preset time (such as one minute). If no control instruction is received within the preset time, the voice module resumes the waiting-to-wake state.

[0032] S13: Send the wake-up state information of the voice module to at least one target device.

[0033] In one implementation manner, after the voice module is woken up, it can send the wake-up state information of the voice module to at least one target device. The wake-up state information of the voice module can be sent to at least one target device through the voice module. Among them, the wake-up state information is used to instruct at least one target device to adjust the first working mode to the second working mode, and the noise generated by the target device in the first working mode is greater than that in the second working mode. The target device and the voice module are connected through a certain communication protocol (such as IIC, SPI, UART). The target device can be a household electrical appliance, such as a fan, a microwave oven, an oil fume extractor, a wall breaker, etc.

[0034] When multiple target devices exist, in one embodiment, the voice module can be connected to each target device separately. The voice module and each target device correspond to different processors. The voice module sends wake-up status information to the target devices, and the target devices adjust their first operating mode to a second operating mode based on the wake-up status information. In another embodiment, the voice module is connected to one target device, and the target devices are connected via a local area network (LAN) or a wide area network (WAN). The voice module and each target device correspond to different processors. The voice module sends wake-up status information to the target devices connected to it, and the target devices connected to it then send the wake-up status information to other target devices. Each target device adjusts its first operating mode to a second operating mode based on the wake-up status information.

[0035] In the above embodiments, the executing entity can be a voice module. After receiving a wake-up command, the voice module is activated based on the command. The activated state information of the voice module is sent to at least one target device. This wake-up state information instructs the target device to adjust its operating mode from a first operating mode to a second operating mode. The noise generated by the target device in the first operating mode is greater than the noise generated in the second operating mode. After the voice module is activated, the noise generated by the target device can be reduced by changing its operating mode.

[0036] Please see Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the noise reduction method provided in this application, which includes:

[0037] S21: Acquire the target wake-up voice and device noise information generated by at least one target device during operation.

[0038] In one embodiment, the target wake-up voice is acquired in a scenario where at least one target device is operating. The target wake-up voice may include a wake-up command issued by the user and device noise information generated by the target device during operation. The device noise information can be sent from the target device to the voice module. When multiple target devices exist, if all target devices are connected to the voice module, the multiple target devices directly send their generated device noise information to the voice module; if only one target device is connected to the voice module, the device noise information generated by the other target devices is sent to the target device connected to the voice module, which then sends its own generated device noise information and the device noise information generated by the other target devices to the voice module. The device noise information may include the name of the target device, the model of the target device, information about the noise-generating part (such as the fan speed of the target device), and the operating mode of the target device. The noise level generated by the target device varies depending on its operating mode; for example, the noise generated by a range hood at level one is lower than the noise generated by a range hood at level two.

[0039] S22: Match the corresponding noise model based on the equipment noise information.

[0040] In one embodiment, after receiving device noise information, the voice module can select a corresponding noise model based on the device noise information. The noise model includes at least one of a first noise model, a second noise model, a third noise model, and a silence model. The first noise model, second noise model, third noise model, and silence model are used to remove noise of different intensities, and the noise intensity used for removal decreases sequentially. In a specific embodiment, the noise model can be selected based on the target device's operating mode contained in the device noise information. For example, if the target device's operating mode is level three, the first noise model can be selected; if the target device's operating mode is level two, the second noise model can be selected; if the target device's operating mode is level one, the third noise model can be selected; furthermore, if no selection is made, the silence model is selected by default. The first noise model, second noise model, third noise model, and silence model are used to remove noise of different intensities, and the noise intensity used for removal decreases sequentially. The first noise model, second noise model, third noise model, and silence model have been pre-trained under different noise levels generated by the target device and are capable of receiving wake-up commands in the presence of noise.

[0041] S23: Use a noise model to remove at least one type of noise generated during the operation of the target device contained in the target wake-up speech.

[0042] In one embodiment, after selecting a matching noise model based on the device noise information, the noise model can be used to remove at least one type of noise generated during the operation of the target device contained in the target wake-up speech.

[0043] S24: Obtain the wake-up command based on the target wake-up speech after noise removal.

[0044] S25: Obtain wake-up command.

[0045] After removing at least one type of noise generated by the target device during operation from the target wake-up speech, the wake-up command can be obtained by recognizing the noise-removed target wake-up speech.

[0046] S26: Wake up the voice module based on the wake-up command.

[0047] S27: Send the wake-up status information of the voice module to at least one target device.

[0048] The specific implementation of steps S25-S27 can be referred to steps S11-S13 of the first implementation of the noise reduction method, and will not be repeated here.

[0049] This implementation method can accurately wake up the voice module by reducing noise in the target wake-up voice.

[0050] Please see Figure 3 , Figure 3 This is a flowchart illustrating the third embodiment of the noise reduction method provided in this application. The method includes:

[0051] S31: Acquire the target wake-up voice and device noise information generated by at least one target device during operation.

[0052] In one embodiment, the target wake-up voice is acquired in a scenario where at least one target device is operating. The target wake-up voice may include a wake-up command issued by the user and device noise information generated by the target device during operation. The device noise information can be sent from the target device to the voice module. When multiple target devices exist, if all target devices are connected to the voice module, the multiple target devices directly send their generated device noise information to the voice module; if only one target device is connected to the voice module, the device noise information generated by the other target devices is sent to the target device connected to the voice module, which then sends its own generated device noise information and the device noise information generated by the other target devices to the voice module. The device noise information may include the name of the target device, the model of the target device, information about the noise-generating part (such as the motor speed of the target device), and the operating mode of the target device. The noise level generated by the target device varies depending on its operating mode; for example, the noise generated by a blender at its lowest setting is lower than that generated by a range hood at its highest setting.

[0053] S32: Obtain the noise signal value that matches the equipment noise information from the noise information database.

[0054] In one embodiment, after receiving device noise information, the voice module can select a noise signal value that matches the device noise information from a noise information database. The noise information database can be pre-built by the user and may contain information such as the name of the target device, the model of the target device, relevant information about the noise-generating part (e.g., the speed of the target device's motor), the operating mode of the target device, and the noise signal value.

[0055] S33: Subtract the speech signal value and noise signal value corresponding to the target wake-up speech to obtain the subtracted target wake-up speech.

[0056] In one embodiment, after obtaining the voice signal value corresponding to the target wake-up voice and the noise signal value matching the device noise information, the difference between the voice signal value corresponding to the target wake-up voice and the noise signal value is calculated to obtain the subtracted target wake-up voice. In a specific embodiment, the obtained voice signal corresponding to the target wake-up voice is a time-domain signal, which can be converted into a frequency-domain signal, and the frequency value of the frequency-domain signal corresponding to the target wake-up voice is subtracted from the frequency value of the noise signal.

[0057] S34: Obtain the wake-up command based on the target wake-up speech after difference.

[0058] The wake-up command can be obtained by recognizing the target wake-up voice after subtraction.

[0059] S35: Obtain wake-up command.

[0060] After removing at least one type of noise generated by the target device during operation from the target wake-up speech, the wake-up command can be obtained by recognizing the noise-removed target wake-up speech.

[0061] S36: Wake up the voice module based on the wake-up command.

[0062] S37: Send the wake-up status information of the voice module to at least one target device.

[0063] The specific implementation of steps S35-S37 can be referred to steps S11-S13 of the first implementation of the noise reduction method, and will not be repeated here.

[0064] Please see Figure 4 , Figure 4 This is a flowchart illustrating the fourth embodiment of the noise reduction method provided in this application, which includes:

[0065] S41: Receive the wake-up status information of the voice module.

[0066] S42: Based on the wake-up status information, adjust the first working mode of at least one target device to the second working mode.

[0067] In one embodiment, the wake-up status information of the voice module can be sent by the voice module to the target device. In other embodiments, an intermediate device can first obtain the wake-up status information of the voice module and then send it to at least one target device. After receiving the wake-up status information, the target device adjusts its first operating mode to a second operating mode. The noise generated by the target device in the first operating mode is greater than the noise generated in the second operating mode. For example, the first operating mode of a range hood can be three levels, and the second operating mode can be two levels or one level. In some embodiments, the second operating mode of the target device is defaulted to the lowest level, i.e., generating the least noise.

[0068] When multiple target devices exist, in one specific embodiment, all target devices can be connected to the voice module. The voice module can then directly send wake-up status information to all target devices, causing them to adjust their first operating mode to the second operating mode. In another specific embodiment, only one target device is connected to the voice module, and the multiple target devices can be connected via a local area network (LAN) or a wide area network (WAN). The voice module sends wake-up status information to this target device, which then sends the wake-up status information to the other target devices, thereby causing all target devices to adjust their first operating mode to the second operating mode.

[0069] In this embodiment, the executing entity can be the target device. By changing the first working mode of the target device, which generates high noise, to the second working mode, which generates low noise, the noise of the target device can be reduced.

[0070] Please see Figure 5 , Figure 5 This is a flowchart illustrating the fifth embodiment of the noise reduction method provided in this application, which includes:

[0071] S51: Receive the wake-up status information of the voice module.

[0072] S52: Based on the wake-up status information, adjust the first working mode of at least one target device to the second working mode.

[0073] S53: If no control command is received from the voice module within a preset time, the second working mode of the target device is restored to the first working mode; or, after receiving the wake-up status information sent by the voice module, the second working mode of the target device is restored to the first working mode.

[0074] For steps S51-S52, please refer to steps S41-S42 of the fourth embodiment of the noise reduction method, which will not be repeated here.

[0075] In one embodiment, after the target device adjusts from the first operating mode to the second operating mode, it can continue to operate in the second operating mode if it does not receive any information from the voice module. If it receives an instruction from the voice module to adjust the operating mode, it can execute the instruction.

[0076] In another embodiment, after the target device switches from the first operating mode to the second operating mode, if it does not receive a control command from the voice module within a preset time, it will revert from the second operating mode to the first operating mode. The preset time can be set according to actual conditions, for example, 15 seconds, 30 seconds, etc.

[0077] In other embodiments, after the target device adjusts from the first working mode to the second working mode, if it receives a wake-up status information sent by the voice module, it restores the target device's second working mode to the first working mode. Specifically, after the voice module is woken up, if it does not receive a control command within a preset time, it will return to the wake-up state. At the same time, the voice module can send the wake-up status information to the target device, and the target device can then restore the second working mode to the first working mode.

[0078] It should be noted that in the above embodiments, the voice module and the target device can be connected through a certain communication protocol. When the state of either party changes, it can be sent to the other party through the communication protocol.

[0079] Please see Figure 6 , Figure 6 This is a flowchart illustrating the sixth embodiment of the noise reduction method provided in this application, which includes:

[0080] S61: Receive the wake-up status information of the voice module.

[0081] S62: Based on the wake-up status information, adjust the first working mode of at least one target device to the second working mode.

[0082] S63: Receive target control voice sent by the voice module.

[0083] S64: Execute the control commands contained in the target control voice.

[0084] For steps S61-S62, please refer to steps S41-S42 of the fourth embodiment of the noise reduction method, which will not be repeated here.

[0085] In one embodiment, after the target device adjusts from the first operating mode to the second operating mode, the noise generated by the target device is relatively small. Under these conditions, the signal-to-noise ratio of the target control voice acquired by the voice module is high, enabling it to recognize the target control voice, obtain control commands, and send the control commands to the target device, causing the target device to execute the control commands.

[0086] In another embodiment, the voice module can send target control voice to the target device, which recognizes the target control voice to obtain control commands and executes them. The control commands could be adjusting the target device's operating mode or turning off the target device, etc.

[0087] This implementation method enables accurate identification of user control commands during the operation of the target device, thereby achieving control of the target device even in noisy conditions.

[0088] Please see Figure 7 , Figure 7 This is a schematic diagram of the framework structure of one embodiment of the electronic device provided in this application.

[0089] The electronic device 70 includes a memory 71 and a processor 72 coupled to each other. The memory 71 stores program instructions, and the processor 72 executes the program instructions stored in the memory 71 to implement the steps of any of the above-described method embodiments. In one specific implementation scenario, the electronic device 70 may include, but is not limited to, a microcomputer or a server. Furthermore, the electronic device 70 may also include mobile devices such as laptops and tablets, without limitation. In this case, the electronic device 70 can acquire a wake-up command; wake up the voice module based on the wake-up command; and send the wake-up status information of the voice module to at least one target device, wherein the wake-up status information is used to instruct at least one target device to adjust the first operating mode to a second operating mode, and the noise generated by the target device in the first operating mode is greater than the noise generated in the second operating mode. In another specific implementation scenario, the electronic device 70 may also be a household appliance, such as a microwave oven or a blender. In this case, the electronic device 70 can receive the wake-up status information of the voice module; and adjust the first operating mode of at least one household appliance to a second operating mode based on the wake-up status information, wherein the noise generated by the household appliance in the first operating mode is greater than the noise generated in the second operating mode.

[0090] Specifically, processor 72 controls itself and memory 71 to implement the steps of any of the above-described organizational structure construction methods. Processor 72 can also be referred to as a CPU (Central Processing Unit). Processor 72 may be an integrated circuit chip with signal processing capabilities. Processor 72 can also be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor. Furthermore, processor 72 can be implemented using integrated circuit chips.

[0091] Please see Figure 8 , Figure 8 This is a schematic diagram of a framework of one embodiment of the computer-readable storage medium provided in this application.

[0092] The computer-readable storage medium 80 stores program instructions 81, which, when executed by a processor, are used to implement the steps in any of the above method embodiments.

[0093] The computer-readable storage medium 80 can specifically be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or a medium that can store computer programs. Alternatively, it can be a server that stores the computer program, which can send the stored computer program to other devices for execution or can also run the stored computer program itself.

[0094] If the technical solution of this application involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, with clear signs / information informing users of the personal information processing rules, authorization is obtained from the individual through pop-up information or by asking the individual to upload their personal information; wherein, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

[0095] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A noise reduction method, characterized in that, The method includes: Acquire the target wake-up voice and device noise information generated by multiple target devices during operation; Obtain a noise signal value that matches the noise information of the device from the noise information database; The difference between the speech signal value corresponding to the target wake-up speech and the noise signal value is calculated to obtain the target wake-up speech after the difference is calculated. A wake-up command is obtained based on the target wake-up voice after subtraction; The voice module is activated based on the wake-up command; and The voice module sends its wake-up status information to multiple target devices, wherein the wake-up status information is used to instruct the multiple target devices to adjust the first working mode to the second working mode, and the noise generated by the target devices in the first working mode is greater than the noise generated in the second working mode.

2. The method according to claim 1, characterized in that, After acquiring the target wake-up voice and device noise information generated during the operation of multiple target devices, the method includes: Match the corresponding noise model based on the device noise information; The noise model is used to remove noise generated by the multiple target devices during operation, which is included in the target wake-up speech; The wake-up command is obtained based on the target wake-up speech after removing the noise.

3. The method according to claim 2, characterized in that, The noise model includes at least one of a first noise model, a second noise model, a third noise model, and a silent model. The first noise model, the second noise model, the third noise model, and the silent model are used to remove noise of different intensities, and the noise intensities used to remove decrease in sequence.

4. The method according to claim 1, characterized in that, The target device is a household appliance; And / or, After sending the wake-up status information of the voice module to multiple target devices, the method further includes: Send target control voice to the plurality of target devices, causing the plurality of target devices to execute the control commands in the target control voice.

5. A noise reduction method, characterized in that, The method includes: The target device receives the wake-up status information of the voice module; wherein, the voice module is woken up based on a wake-up command, the wake-up command is obtained based on the target wake-up voice after subtraction, the target wake-up voice after subtraction is obtained by subtracting the voice signal value and the noise signal value corresponding to the target wake-up voice, and the noise signal value is obtained from the noise information database and matched with the device noise information; Based on the wake-up status information, the first working mode of multiple target devices is adjusted to the second working mode, wherein the noise generated by the target devices in the first working mode is greater than the noise generated in the second working mode.

6. The method according to claim 5, characterized in that, After adjusting the first operating mode of at least one target device to a second operating mode based on the wake-up state information, the method further includes: If no control command is received from the voice module within a preset time, the second working mode of the target device will be restored to the first working mode; Alternatively, upon receiving the wake-up status information sent by the voice module, the second working mode of the target device is restored to the first working mode.

7. The method according to claim 5, characterized in that, The target device is a household appliance; And / or, After adjusting the first operating mode of the target device to the second operating mode based on the wake-up state information, the method further includes: Receive the target control voice sent by the voice module; The control commands contained in the target control voice are executed.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor that are coupled to each other. The memory stores program instructions; The processor is configured to execute program instructions stored in the memory to implement the method according to any one of claims 1-4, or to implement the method according to any one of claims 5-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program instructions that can be executed to implement the method as claimed in any one of claims 1-4, or to implement the method as claimed in any one of claims 5-7.

Images