Voice wake-up control method and device, voice intelligent device, and storage medium

Abstract

The application discloses a voice wake-up control method and device, a voice intelligent device and a storage medium, and relates to the technical field of voice wake-up control. The method comprises the following steps: after receiving a voice wake-up instruction, it is detected whether a preset first audio signal is collected; if the preset first audio signal is not collected, a preset second audio signal is output based on a current device, so that other devices remain in a mute state; and a voice intelligent function of the current device is started according to the voice wake-up instruction. Through the detection of the first audio signal and the output of the second audio signal, the application controls single-device response in a multi-device scene, avoids repeated execution of voice instructions of a user by multiple devices, and realizes the technical effect of improving device response efficiency.

Description

Technical Field

[0001] This invention relates to the field of voice intelligence technology, and in particular to a voice wake-up control method, device, voice intelligence device, and storage medium. Background Technology

[0002] With the development of artificial intelligence (AI), more and more voice-enabled smart devices are equipped with voice control capabilities. In smart home scenarios, users can control home appliances such as TVs, refrigerators, and air conditioners via voice commands. The application of voice interaction in home environments brings users a very convenient operating experience.

[0003] In the same living space, there may be smart devices of the same brand that share the same wake word. When a user speaks the wake word, each device responds to the user's command, resulting in multiple devices responding and repeatedly executing voice commands, leading to low response efficiency. Summary of the Invention

[0004] The main objective of this invention is to provide a voice wake-up control method, device, voice intelligent device, and storage medium, aiming to solve the problem of low device response efficiency in environments with multiple voice intelligent devices.

[0005] To achieve the above objectives, the present invention provides a voice wake-up control method, the method comprising:

[0006] Upon receiving a voice wake-up command, it checks whether a preset first audio signal has been acquired.

[0007] If the preset first audio signal is not captured, the preset second audio signal is output based on the current device to keep other devices silent.

[0008] The voice-activated smart function of the current device is activated according to the voice wake-up command.

[0009] Optionally, the step of detecting whether a preset first audio signal has been acquired includes:

[0010] Within the current audio receiving range of the device, the original audio signal is acquired at a preset sampling frequency;

[0011] After acquiring the original audio signal, obtain the frequency information of the original audio signal, and determine whether the frequency of the original audio signal matches the frequency of the first audio signal based on the frequency information;

[0012] If the frequency of the original audio signal does not match the frequency of the first audio signal, then it is determined that the first audio signal was not collected.

[0013] Optionally, the step of outputting a preset second audio signal based on the current device includes:

[0014] Obtain audio signal output information regarding the wake-up notification;

[0015] The audio signal output information is used to control the audio transmission module in the current device to output the second audio signal.

[0016] Optionally, the step of activating the voice intelligence function of the current device according to the voice wake-up command includes:

[0017] Extract the text feature information from the voice wake-up command and compare the text feature information with preset wake-up feature information;

[0018] If the text feature information matches the wake-up feature information, a wake-up confirmation signal is sent to the preset voice intelligence module so that the voice intelligence module changes from sleep state to working state.

[0019] Optionally, after the step of activating the voice intelligence function of the current device according to the voice wake-up command, the method further includes:

[0020] Based on the aforementioned voice intelligence function, receive voice operation commands and detect whether the voice operation commands have been executed successfully.

[0021] If the voice operation command fails to execute, a third audio signal is generated based on the voice wake-up command and the voice operation command.

[0022] The third audio signal is output to wake up the device to be responded to in accordance with the voice operation command.

[0023] Optionally, the step of detecting whether the voice operation command was executed successfully includes:

[0024] The voice operation command is converted into operation command information, and the operation command information is matched with the initial command information in the preset command database;

[0025] If the operation instruction information does not match the initial instruction information, then the voice operation instruction is determined to have failed to execute.

[0026] Optionally, the step of generating a third audio signal based on the voice wake-up command and the voice operation command includes:

[0027] The voice wake-up command and the voice operation command are combined into an audio control signal;

[0028] The audio control signal is applied to the original signal to be modulated with a preset frequency to form the third audio signal.

[0029] Furthermore, to achieve the above objectives, the present invention also provides a voice wake-up control device, the voice wake-up control device comprising:

[0030] The detection module is used to detect whether a preset first audio signal has been collected after receiving a voice wake-up command;

[0031] The output module is used to output a preset second audio signal based on the current device if the preset first audio signal is not collected, so as to keep other devices silent.

[0032] The activation module is used to activate the voice intelligence function of the current device according to the voice wake-up command.

[0033] In addition, to achieve the above objectives, the present invention also provides a voice-enabled intelligent device, the voice-enabled intelligent device comprising: a memory, a processor, and a voice wake-up control program stored in the memory and executable on the processor, the voice wake-up control program being configured to implement the steps of the voice wake-up control method as described above.

[0034] In addition, to achieve the above objectives, the present invention also provides a computer-readable storage medium storing a voice wake-up control program, which, when executed by a processor, implements the steps of the voice wake-up control method described above.

[0035] The voice wake-up control method provided by this invention, upon receiving a voice wake-up command, detects whether a preset first audio signal has been acquired. If the preset first audio signal has not been acquired, a preset second audio signal is output based on the current device to keep other devices silent. The voice intelligence function of the current device is activated according to the voice wake-up command. After the current device receives the voice wake-up command and prepares to respond, it determines that the current device is the responding device by detecting the acquisition status of the first audio signal and sends the second audio signal to other devices, controlling other devices not to respond to the voice wake-up command. This ensures that only one device responds when multiple devices use the same wake-up word, avoids multiple devices repeatedly executing the user's voice command, improves device response efficiency, and the current device can achieve the effect of single-device response without networking with other devices, reducing networking costs. Attached Figure Description

[0036] Figure 1 This is a schematic diagram of a multi-device response scenario provided by an embodiment of the present invention;

[0037] Figure 2This is a flowchart illustrating the first embodiment of the voice wake-up control method of the present invention;

[0038] Figure 3 This is a schematic diagram of another multi-device response scenario provided by an embodiment of the present invention;

[0039] Figure 4 This is a flowchart illustrating the second embodiment of the voice wake-up control method of the present invention;

[0040] Figure 5 This is a schematic diagram of the voice wake-up control device of the present invention;

[0041] Figure 6 This is a schematic diagram of the structure of a voice-enabled intelligent device in the hardware operating environment of an embodiment of the present invention.

[0042] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0043] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0044] The increasing number of voice-activated smart devices has facilitated the intelligentization of daily life, but it has also brought some problems, such as multiple devices responding to the same wake word. Generally, solving the problem of multiple devices responding requires networking all voice-activated smart devices and processing the response judgment logic in the cloud, or having the devices and servers negotiate together. When the judgment process involves the cloud or server, response delays are likely to occur.

[0045] Figure 1 This is a schematic diagram of a multi-device response scenario provided by an embodiment of the present invention, such as... Figure 1 As shown, in the same space, there are three voice-activated smart devices—TV 100, refrigerator 200, and smart speaker 300—that share the same wake word. When the user says the wake word (e.g., "Xiao A Xiao A"), TV 100, refrigerator 200, and smart speaker 300 may all respond, replying "I'm here." With multiple devices responding, the user's voice command is repeatedly executed by multiple voice-activated smart devices, resulting in low response efficiency.

[0046] based on Figure 1 In the multi-device response scenario shown, this embodiment of the invention provides a voice wake-up control method, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of a voice wake-up control method according to the present invention.

[0047] In this embodiment, the voice wake-up control method includes:

[0048] Step S10: After receiving the voice wake-up command, detect whether the preset first audio signal has been collected;

[0049] The executing entity in this embodiment can be a voice-activated smart device; in this embodiment, the current device refers to the same entity as the executing entity. The voice-activated smart device can include an audio receiving module and an audio transmitting module. The audio receiving module can receive voice commands input by the user, and the audio transmitting module can output audio signals to the outside world. The audio receiving module can be a microphone or a microphone array. The audio transmitting module can be a speaker or a speaker array.

[0050] Voice wake-up commands can include a voice wake-up word input by the user into the voice-activated smart device. Generally, when the voice-activated smart device recognizes the correct wake-up word, it can activate its voice intelligence function and execute corresponding operations by recognizing subsequent voice commands input by the user. When multiple voice-activated smart devices exist in the same space, after the current device receives the voice wake-up command, it adds a process of detecting whether a preset first audio signal has been acquired. The presence or absence of this first audio signal determines whether the current device is the first to respond. Figure 3 This is a schematic diagram of another multi-device response scenario provided by an embodiment of the present invention, such as... Figure 3 As shown, since the smart speaker 300 is closest to the user, if the smart speaker 300 does not detect the first audio signal after receiving the voice wake-up command, it will continue to execute subsequent steps, such as replying to the user "I am here".

[0051] As an example, the step of detecting whether a preset first audio signal has been acquired may include:

[0052] Step A1: Acquire the original audio signal at a preset sampling frequency within the audio receiving range of the current device;

[0053] Step A2: After acquiring the original audio signal, obtain the frequency information of the original audio signal, and determine whether the frequency of the original audio signal matches the frequency of the first audio signal based on the frequency information;

[0054] Step A3: If the frequency of the original audio signal does not match the frequency of the first audio signal, then it is determined that the first audio signal has not been collected.

[0055] When in standby mode, voice-activated smart devices can monitor ambient audio signals. The audio receiving module in a voice-activated smart device has a certain audio reception range under normal operating conditions. The size of the audio reception range is related to the performance of the audio receiving module. Within this range, the audio receiving module can acquire the raw audio signal. The audio receiving module acquires the raw audio signal at a preset sampling frequency, which can be set according to the actual application. Analyzing the acquired raw audio signal allows us to determine the frequency of the audio signals by obtaining their frequency information. The frequency range of sound waves emitted by humans during normal conversation is mainly 500Hz-2000Hz, while the frequency range of human speech is mainly 200Hz-4000Hz. The frequency range of sound that the human ear can perceive is 20Hz-20000Hz. The first audio signal can be an ultrasonic signal with a frequency exceeding 20000Hz. The frequency range of the first audio signal is changed by the generating device. If the frequency of the raw audio signal is not within the frequency range of the first audio signal, it indicates that the device has not acquired the first audio signal. By using the first audio signal, the current device can determine whether it is a device that needs to respond to the voice wake-up command. The first audio signal is an ultrasonic signal that cannot be perceived by the human ear. Therefore, the "negotiation" process between voice-enabled smart devices is carried out imperceptibly to the user, which can prevent noise interference to the user.

[0056] Step S20: If the preset first audio signal is not collected, the preset second audio signal is output based on the current device to keep other devices silent.

[0057] If a voice wake-up command is received but the first audio signal is not collected, the current device can determine that it is the device responding to the voice wake-up command, while other voice-enabled smart devices in the same space are not responding. The device can output a preset second audio signal to notify other devices not to respond to the voice wake-up command.

[0058] As an example, the step of outputting a preset second audio signal based on the current device may include:

[0059] Step B1: Obtain audio signal output information regarding the wake-up notification;

[0060] Step B2: Control the audio transmission module in the current device to output the second audio signal according to the audio signal output information.

[0061] The audio signal output information includes audio feature information of the second audio signal, the main features of which are frequency and time characteristics. The sound wave frequency and duration of the second audio signal can be determined through the audio signal output information. In some embodiments, the sound wave frequency of the second audio signal can be above 20000Hz, and the duration can be 2 seconds. The second audio signal can have the same frequency characteristics as the first audio signal. The audio transmission module outputs a second audio signal with a set sound wave frequency and duration. After receiving the second audio signal, other devices can know that a device has already received the voice wake-up command, and other devices should not respond to the voice wake-up command, maintaining a silent state. The second audio signal is also an audio signal imperceptible to the human ear. Without interfering with the user, the output of the second audio signal can be performed using the existing hardware configuration of the voice-enabled smart device, without increasing hardware costs.

[0062] Step S30: Activate the voice intelligence function of the current device according to the voice wake-up command.

[0063] After notifying other devices to remain silent, the current device can begin responding to the voice wake-up command, activating the voice intelligence function, and continuing to respond to subsequent voice commands from the user. In voice intelligence scenarios, the voice intelligence function can replace manual operation by the user to achieve the same execution effect. For example, when a user wants to turn up the TV volume, they can say "turn up the TV volume" to the TV. After receiving the user's voice, the TV will automatically perform the operation to turn up the volume, replacing the traditional action of the user controlling the TV volume with a remote control.

[0064] As an example, the steps to activate the voice intelligence function of the current device based on a voice wake-up command may include:

[0065] Step C1: Extract the text feature information from the voice wake-up command and compare the text feature information with the preset wake-up feature information;

[0066] Step C2: If the text feature information matches the wake-up feature information, a wake-up confirmation signal is sent to the preset voice intelligence module so that the voice intelligence module changes from sleep state to working state.

[0067] For voice-enabled smart devices, a specific wake-up word can be set to trigger voice-enabled smart functions. The voice information in the wake-up command can be converted into text feature information, which is then compared with preset wake-up feature information. The wake-up feature information may include the wake-up word. When the extracted text feature information matches the wake-up feature information, the voice wake-up command is confirmed to be correct, and a wake-up confirmation signal can be sent to the voice-enabled smart module. The preset voice-enabled smart module may include a voice-enabled smart chip. After receiving the wake-up confirmation signal, the voice-enabled smart chip transitions from sleep mode to active mode, analyzes the audio signal received by the device, interprets the user's intent, and controls the hardware or software in the device to perform corresponding operations.

[0068] In this embodiment, upon receiving a voice wake-up command, it checks whether a preset first audio signal has been acquired. If the preset first audio signal has not been acquired, a preset second audio signal is output based on the current device to keep other devices silent. The voice intelligence function of the current device is activated according to the voice wake-up command. After the current device receives the voice wake-up command and prepares to respond, it determines that the current device is the responding device by detecting the acquisition status of the first audio signal and sends the second audio signal to other devices to control other devices not to respond to the voice wake-up command. This ensures that only one device responds when multiple devices use the same wake-up word, avoids multiple devices repeatedly executing the user's voice command, improves device response efficiency, and the current device can achieve the effect of single-device response without networking with other devices, reducing networking costs.

[0069] Furthermore, in the second embodiment of the voice wake-up control method of the present invention, referring to Figure 4 The method includes:

[0070] Step S11: Receive voice operation instructions based on the voice intelligence function, and detect whether the voice operation instructions have been successfully executed;

[0071] In this embodiment, the executing entity can be a voice-activated smart device, and the current device referred to in this embodiment is the same as the executing entity. After the voice-activated smart function of the current device is enabled, it can continue to receive the user's voice operation commands and execute the actions corresponding to the voice operation commands. In a multi-device scenario, the currently activated device may not be the device that the user actually wants to activate, which may result in the current device failing to execute the voice operation commands.

[0072] As an example, the steps to detect whether a voice command was executed successfully may include:

[0073] Step a1: Convert the voice operation command into operation command information, and match the operation command information with the initial command information in the preset command database;

[0074] Step a2: If the operation instruction information does not match the initial instruction information, then it is determined that the voice operation instruction has failed to execute.

[0075] Voice-enabled smart devices can contain a pre-set command database to store initial command information. This initial command information corresponds to the operational commands that the voice-enabled smart device can perform. The audio-based voice operation commands are converted into operation command information and matched against the initial command information. If the operation command information does not match the initial command information, it means the current device cannot perform the corresponding operation based on the initial command information, and the voice operation command execution fails. If the operation command information matches the initial command information, it means the current device can perform the corresponding operation based on the initial command information, and the voice operation command execution is successful. Detecting the execution status of voice operation commands allows the current device to know whether it has been correctly woken up.

[0076] Step S12: If the voice operation command fails to execute, a third audio signal is generated based on the voice wake-up command and the voice operation command.

[0077] If a voice command fails to execute, the current device can "negotiate" with other devices via a third audio signal to wake up the other devices and execute the voice command.

[0078] As an example, the step of generating a third audio signal based on a voice wake-up command and a voice operation command may include:

[0079] Step b1: Combine the voice wake-up command and the voice operation command into an audio control signal;

[0080] Step b2: The audio control signal is loaded onto the original signal to be modulated with a preset frequency to form the third audio signal.

[0081] The current device can communicate with other devices via a third audio signal. The received voice wake-up command and voice operation command are combined into an audio control signal, which contains first characteristic information of the voice wake-up command and second characteristic information of the voice operation command. The preset frequency of the original signal to be modulated can be above 20000Hz. The original signal to be modulated does not have characteristic information, while the modulated third audio signal carries the first and second characteristic information. The third audio signal is an audio signal imperceptible to the human ear, avoiding interference to the user during the "negotiation" process between devices.

[0082] Step S13: Output the third audio signal to wake up the device to be responded to in accordance with the voice operation command.

[0083] The current device can still output a third audio signal through the audio transmission module. After receiving the third audio signal, other devices will activate the voice intelligence function based on the first feature information and execute voice operation commands based on the second feature information. Other devices that successfully execute the voice operation commands will become the corresponding response devices. The third audio signal may also include silent wake-up feature information. When other devices receive the silent wake-up feature information, even if they recognize the correct wake-up word, they will not respond to the user through audio. They will only notify the user of success when the voice intelligence function is activated and the voice operation command is successfully executed, thus improving the accuracy of voice wake-up.

[0084] In this embodiment, after the voice operation command fails to execute, the correct device to be responded to is woken up by a third audio signal and the voice operation command is successfully executed. In the case that the previously woken-up device is not the correct device, the correct device is found in a way that is imperceptible to the human body, thus improving the accuracy of voice wake-up.

[0085] This invention also provides a voice wake-up control device, such as... Figure 5 As shown, the voice wake-up control device includes:

[0086] The detection module 101 is used to detect whether a preset first audio signal has been collected after receiving a voice wake-up command;

[0087] The output module 102 is used to output a preset second audio signal based on the current device if a preset first audio signal is not collected, so as to keep other devices silent.

[0088] The activation module 103 is used to activate the voice intelligence function of the current device according to the voice wake-up command.

[0089] Optionally, the detection module 101 is also used for:

[0090] Within the current audio receiving range of the device, the original audio signal is acquired at a preset sampling frequency;

[0091] After acquiring the original audio signal, obtain the frequency information of the original audio signal, and determine whether the frequency of the original audio signal matches the frequency of the first audio signal based on the frequency information;

[0092] If the frequency of the original audio signal does not match the frequency of the first audio signal, then it is determined that the first audio signal was not collected.

[0093] Optionally, the output module 102 is also used for:

[0094] Obtain audio signal output information regarding the wake-up notification;

[0095] The audio signal output information is used to control the audio transmission module in the current device to output the second audio signal.

[0096] Optionally, the enabling module 103 is also used for:

[0097] Extract the text feature information from the voice wake-up command and compare the text feature information with preset wake-up feature information;

[0098] If the text feature information matches the wake-up feature information, a wake-up confirmation signal is sent to the preset voice intelligence module so that the voice intelligence module changes from sleep state to working state.

[0099] Optionally, the voice wake-up control device further includes an execution module for:

[0100] Based on the aforementioned voice intelligence function, receive voice operation commands and detect whether the voice operation commands have been executed successfully.

[0101] If the voice operation command fails to execute, a third audio signal is generated based on the voice wake-up command and the voice operation command.

[0102] The third audio signal is output to wake up the device to be responded to in accordance with the voice operation command.

[0103] Optionally, the voice wake-up control device further includes a determining module for:

[0104] The voice operation command is converted into operation command information, and the operation command information is matched with the initial command information in the preset command database;

[0105] If the operation instruction information does not match the initial instruction information, then the voice operation instruction is determined to have failed to execute.

[0106] Optionally, the voice wake-up control device further includes a generation module for:

[0107] The voice wake-up command and the voice operation command are combined into an audio control signal;

[0108] The audio control signal is applied to the original signal to be modulated with a preset frequency to form the third audio signal.

[0109] Reference Figure 6 , Figure 6 This is a schematic diagram of the hardware operating environment of the voice-enabled intelligent device involved in the embodiments of the present invention.

[0110] like Figure 6As shown, the voice-enabled intelligent device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0111] Those skilled in the art will understand that Figure 6 The structure shown does not constitute a limitation on voice-enabled smart devices and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0112] like Figure 6 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a voice wake-up control program.

[0113] exist Figure 6 In the voice-enabled smart device shown, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and memory 1005 in the voice-enabled smart device of the present invention can be set in the voice-enabled smart device, and the voice-enabled smart device calls the voice wake-up control program stored in the memory 1005 through the processor 1001 and executes the following steps:

[0114] Upon receiving a voice wake-up command, it checks whether a preset first audio signal has been acquired.

[0115] If the preset first audio signal is not captured, the preset second audio signal is output based on the current device to keep other devices silent.

[0116] The voice-activated smart function of the current device is activated according to the voice wake-up command.

[0117] Optionally, the processor 1001 may call the voice wake-up control program stored in the memory 1005 and may also perform the following steps:

[0118] Within the current audio receiving range of the device, the original audio signal is acquired at a preset sampling frequency;

[0119] After acquiring the original audio signal, obtain the frequency information of the original audio signal, and determine whether the frequency of the original audio signal matches the frequency of the first audio signal based on the frequency information;

[0120] If the frequency of the original audio signal does not match the frequency of the first audio signal, then it is determined that the first audio signal was not collected.

[0121] Optionally, the processor 1001 may call the voice wake-up control program stored in the memory 1005 and may also perform the following steps:

[0122] Obtain audio signal output information regarding the wake-up notification;

[0123] The audio signal output information is used to control the audio transmission module in the current device to output the second audio signal.

[0124] Optionally, the processor 1001 may call the voice wake-up control program stored in the memory 1005 and may also perform the following steps:

[0125] Extract the text feature information from the voice wake-up command and compare the text feature information with preset wake-up feature information;

[0126] If the text feature information matches the wake-up feature information, a wake-up confirmation signal is sent to the preset voice intelligence module so that the voice intelligence module changes from sleep state to working state.

[0127] Optionally, the processor 1001 may call the voice wake-up control program stored in the memory 1005 and may also perform the following steps:

[0128] Based on the aforementioned voice intelligence function, receive voice operation commands and detect whether the voice operation commands have been executed successfully.

[0129] If the voice operation command fails to execute, a third audio signal is generated based on the voice wake-up command and the voice operation command.

[0130] The third audio signal is output to wake up the device to be responded to in accordance with the voice operation command.

[0131] Optionally, the processor 1001 may call the voice wake-up control program stored in the memory 1005 and may also perform the following steps:

[0132] The voice operation command is converted into operation command information, and the operation command information is matched with the initial command information in the preset command database;

[0133] If the operation instruction information does not match the initial instruction information, then the voice operation instruction is determined to have failed to execute.

[0134] Optionally, the processor 1001 may call the voice wake-up control program stored in the memory 1005 and may also perform the following steps:

[0135] The voice wake-up command and the voice operation command are combined into an audio control signal;

[0136] The audio control signal is applied to the original signal to be modulated with a preset frequency to form the third audio signal.

[0137] This invention also provides a computer-readable storage medium storing a voice wake-up control program. When executed by a processor, the voice wake-up control program implements the steps of the voice wake-up control method described above. Specific embodiments of the computer-readable storage medium of this invention are described in the various embodiments of the voice wake-up control method described above, and will not be repeated here.

[0138] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0139] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0140] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0141] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A voice wake-up control method, characterized in that, The voice wake-up control method includes the following steps: Upon receiving a voice wake-up command, it checks whether a preset first audio signal has been acquired. If the preset first audio signal is not captured, the preset second audio signal is output based on the current device to keep other devices silent. The voice-activated smart function of the current device is activated according to the voice wake-up command; Based on the aforementioned voice intelligence function, receive voice operation commands and detect whether the voice operation commands have been executed successfully. If the voice operation command fails to execute, a third audio signal is generated based on the voice wake-up command and the voice operation command, wherein the third audio signal contains the first feature information of the voice wake-up command and the second feature information of the voice operation command; The third audio signal is output to wake up the device to be responded to in accordance with the voice operation command; The sound wave frequencies of the first audio signal, the second audio signal, and the third audio signal are all greater than 20,000 Hz.

2. The voice wake-up control method as described in claim 1, characterized in that, The step of detecting whether a preset first audio signal has been acquired includes: Within the current audio receiving range of the device, the original audio signal is acquired at a preset sampling frequency; After acquiring the original audio signal, obtain the frequency information of the original audio signal, and determine whether the frequency of the original audio signal matches the frequency of the first audio signal based on the frequency information; If the frequency of the original audio signal does not match the frequency of the first audio signal, then it is determined that the first audio signal was not collected.

3. The voice wake-up control method as described in claim 1, characterized in that, The step of outputting a preset second audio signal based on the current device includes: Obtain audio signal output information regarding the wake-up notification; The audio signal output information is used to control the audio transmission module in the current device to output the second audio signal.

4. The voice wake-up control method as described in claim 1, characterized in that, The step of activating the voice intelligence function of the current device according to the voice wake-up command includes: Extract the text feature information from the voice wake-up command and compare the text feature information with preset wake-up feature information; If the text feature information matches the wake-up feature information, a wake-up confirmation signal is sent to the preset voice intelligence module so that the voice intelligence module changes from sleep state to working state.

5. The voice wake-up control method as described in claim 1, characterized in that, The step of detecting whether the voice operation command was executed successfully includes: The voice operation command is converted into operation command information, and the operation command information is matched with the initial command information in the preset command database; If the operation instruction information does not match the initial instruction information, then the voice operation instruction is determined to have failed to execute.

6. The voice wake-up control method as described in claim 1, characterized in that, The step of generating a third audio signal based on the voice wake-up command and the voice operation command includes: The voice wake-up command and the voice operation command are combined into an audio control signal; The audio control signal is applied to the original signal to be modulated with a preset frequency to form the third audio signal.

7. A voice wake-up control device, characterized in that, The voice wake-up control device includes: The detection module is used to detect whether a preset first audio signal has been collected after receiving a voice wake-up command; The output module is used to output a preset second audio signal based on the current device if the preset first audio signal is not collected, so as to keep other devices silent. An activation module is used to activate the voice intelligence function of the current device according to the voice wake-up command. The activation module is also used to receive voice operation instructions based on the voice intelligence function, and detect whether the voice operation instructions are executed successfully; if the voice operation instructions fail to be executed, a third audio signal is generated according to the voice wake-up instruction and the voice operation instructions, wherein the third audio signal contains the first feature information of the voice wake-up instruction and the second feature information of the voice operation instructions; the third audio signal is output to wake up the waiting device corresponding to the voice operation instructions. The sound wave frequencies of the first audio signal, the second audio signal, and the third audio signal are all greater than 20,000 Hz.

8. A voice-activated intelligent device, characterized in that, The voice-activated smart device includes: a memory, a processor, and a voice wake-up control program stored in the memory and executable on the processor, the voice wake-up control program being configured to implement the steps of the voice wake-up control method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a voice wake-up control program, which, when executed by a processor, implements the steps of the voice wake-up control method as described in any one of claims 1 to 6.

Images