Voice wake-up control method and device, computer equipment and storage medium

Abstract

The invention provides a voice wake-up control method and device, computer equipment and a storage medium. The method comprises the following steps: in response to equipment entering a preset mode, improving an awakening threshold value of a voice awakening module according to the grade of the preset mode, the preset mode having a plurality of grades, the grade of the preset mode being in positive correlation with the awakening threshold value, and the grade of the preset mode being in positive correlation with the awakening threshold value; the wake-up threshold is used for indicating the voice wake-up module to wake up the device based on the user audio when the matching degree of the collected user audio and the wake-up word is greater than or equal to the wake-up threshold. According to the embodiment provided by the invention, the power consumption of the voice wake-up module and the post-stage module thereof can be effectively reduced, more accurate power-saving control is realized, and the user experience is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of voice wake-up, and particularly to a voice wake-up control method, apparatus, computer device, and storage medium. Background Art

[0002] Currently, in the smartphone market, the voice wake-up function is a function that most types of mobile phones must be equipped with. In order to ensure that the user's wake-up word can be successfully read and converted into data and sent to the voice wake-up algorithm, the underlying hardware device of the mobile phone has to keep running and continuously consume power.

[0003] In the related art, the function adjustment made for power saving is to turn off the prompt sound, and the power saving effect is poor. Summary of the Invention

[0004] To overcome the problems existing in the related art, the present disclosure provides a voice wake-up control method, apparatus, computer device, and storage medium.

[0005] In a first aspect of the present disclosure, a voice wake-up control method is provided. The method includes:

[0006] In response to the device entering a preset mode, increase the wake-up threshold of the voice wake-up module according to the level of the preset mode. Among them, the preset mode has multiple levels, and the level of the preset mode is positively correlated with the wake-up threshold. Among them, the wake-up threshold is used to indicate that when the matching degree between the user audio collected by the voice wake-up module and the wake-up word is greater than or equal to the wake-up threshold, the device is woken up based on the user audio.

[0007] Optionally, the step of "In response to the device entering a preset mode, increase the wake-up threshold of the voice wake-up module according to the level of the preset mode" includes:

[0008] In response to the device entering a non-highest-level preset mode, determine a first threshold according to the level of the preset mode and increase the wake-up threshold of the voice wake-up module to the first threshold.

[0009] Optionally, the method further includes:

[0010] In response to the device entering the highest-level preset mode, turn off the voice wake-up module.

[0011] Optionally, the method further includes:

[0012] In response to the device exiting the preset mode, restore the wake-up threshold of the voice wake-up module to the default state.

[0013] Optionally, the method further includes:

[0014] In response to receiving a first instruction, set a wake-up threshold of the voice wake-up module according to the first instruction, where the first instruction indicates the wake-up threshold of the voice wake-up module;

[0015] In response to receiving a second instruction, restore the wake-up threshold of the voice wake-up module to the default state.

[0016] Optionally, the method further includes:

[0017] In response to the device exiting the preset mode, if the change flag is marked as unchanged, restore the wake-up threshold of the voice wake-up module to the default state; if the change flag is marked as changed, restore the wake-up threshold of the voice wake-up module to the wake-up threshold indicated by the first instruction, where the change flag is used to mark whether the change status is valid, and the change flag is marked as changed in response to receiving the first instruction and marked as unchanged in response to receiving the second instruction.

[0018] Optionally, raising the wake-up threshold of the voice wake-up module according to the level of the preset mode includes:

[0019] In response to the wake-up threshold corresponding to the level of the preset mode being higher than the current wake-up threshold of the device, raise the wake-up threshold of the voice wake-up module to the wake-up threshold corresponding to the level of the preset mode;

[0020] In response to the wake-up threshold corresponding to the level of the preset mode not being higher than the current wake-up threshold of the device, maintain the current wake-up threshold of the device.

[0021] Optionally, the method further includes:

[0022] In response to the device entering the preset mode, present a prompt message, receive a second threshold input by the user based on the prompt message, and set the wake-up threshold of the voice wake-up module to the second threshold.

[0023] Optionally, raising the wake-up threshold of the voice wake-up module according to the level of the preset mode includes:

[0024] Raise the wake-up threshold of the voice wake-up module within a reference range according to the level of the preset mode, where the reference range is a preset range or a range specified by the user.

[0025] Optionally, the method further includes:

[0026] In the case where the remaining power of the device is less than or equal to the power threshold, enter the preset mode and determine the level of the preset mode according to the remaining power.

[0027] Optionally, waking up the device based on the collected user audio includes:

[0028] Reporting the collected user audio to the application layer, so that when the matching degree between the user audio and the wake-up word is greater than or equal to the second threshold, the application layer responds based on the user audio.

[0029] A second aspect of the present disclosure provides a voice wake-up control device, the device includes:

[0030] A first threshold adjustment module, configured to, in response to the device entering a preset mode, increase the wake-up threshold of the voice wake-up module according to the level of the preset mode, where the preset mode has multiple levels, and the level of the preset mode is positively correlated with the wake-up threshold, where the wake-up threshold is used to indicate that when the matching degree between the collected user audio and the wake-up word is greater than or equal to the wake-up threshold, the device is woken up based on the user audio.

[0031] Optionally, when the first threshold adjustment module is configured to increase the wake-up threshold of the voice wake-up module according to the level of the preset mode in response to the device entering the preset mode, it is used for:

[0032] In response to the device entering a preset mode that is not the highest level, determining a first threshold according to the level of the preset mode and increasing the wake-up threshold of the voice wake-up module to the first threshold.

[0033] Optionally, when the first threshold adjustment module is configured to increase the wake-up threshold of the voice wake-up module according to the level of the preset mode in response to the device entering the preset mode, it is used for:

[0034] In response to the device entering the highest level of the preset mode, turning off the voice wake-up module.

[0035] Optionally, the device further includes:

[0036] A second threshold adjustment module, configured to, in response to the device exiting the preset mode, restore the wake-up threshold of the voice wake-up module to the default state.

[0037] Optionally, the device further includes:

[0038] A first instruction response module, configured to, in response to receiving a first instruction, set the wake-up threshold of the voice wake-up module according to the first instruction, where the first instruction indicates the wake-up threshold of the voice wake-up module;

[0039] A second instruction response module, configured to, in response to receiving a second instruction, restore the wake-up threshold of the voice wake-up module to the default state.

[0040] Optionally, the device further includes:

[0041] A third threshold adjustment module, configured to, in response to the device exiting the preset mode, restore the wake-up threshold of the voice wake-up module to the default state when the change flag is marked as unchanged, and restore the wake-up threshold of the voice wake-up module to the wake-up threshold indicated by the first instruction when the change flag is marked as changed, where the change flag is used to mark whether the change status is valid, and the change flag is marked as changed in response to receiving the first instruction and marked as unchanged in response to receiving the second instruction.

[0042] Optionally, when the first threshold adjustment module is used to increase the wake-up sensitivity of the voice wake-up module according to the level of the preset mode, it is used for:

[0043] In response to the wake-up threshold corresponding to the level of the preset mode being higher than the current wake-up threshold of the device, increasing the wake-up threshold of the voice wake-up module to the wake-up threshold corresponding to the level of the preset mode;

[0044] In response to the wake-up threshold corresponding to the level of the preset mode not being higher than the current wake-up threshold of the device, maintaining the current wake-up threshold of the device.

[0045] Optionally, the device further includes:

[0046] A fourth threshold adjustment module, configured to, in response to the device entering the preset mode, present a prompt message, receive a second threshold input by the user based on the prompt message, and set the wake-up threshold of the voice wake-up module to the second threshold.

[0047] Optionally, increasing the wake-up threshold of the voice wake-up module according to the level of the preset mode includes:

[0048] Increasing the wake-up threshold of the voice wake-up module within a reference range according to the level of the preset mode, where the reference range is a preset range or a range specified by the user.

[0049] Optionally, the device further includes:

[0050] A preset mode entry module, configured to enter the preset mode when the remaining power of the device is less than or equal to the power threshold, and determine the level of the preset mode according to the remaining power.

[0051] Optionally, when the first threshold adjustment module is used to wake up the device based on the collected user audio, it is used for:

[0052] Report the collected user audio to the application layer, so that when the matching degree between the user audio and the wake-up word is greater than or equal to the second-level threshold, the application layer makes a response based on the user audio.

[0053] The third aspect of the present disclosure provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the method described in the first aspect is implemented.

[0054] The fourth aspect of the present disclosure provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method described in the first aspect is implemented.

[0055] The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects:

[0056] In the embodiments of the present disclosure, multiple levels are configured for the preset mode of the device, and corresponding wake-up thresholds are configured for different levels of the preset mode according to the negative correlation relationship. When the device enters the preset mode, the wake-up threshold of the voice wake-up module is increased according to the level of the preset mode, so that according to the difference in the level of the preset mode, the voice wake-up module determines whether to wake up the device based on the collected user audio according to the corresponding wake-up threshold. Based on the above measures, the embodiments provided by the present disclosure can effectively reduce the power consumption of the voice wake-up module and its subsequent modules, achieve more accurate power-saving control, and improve the user experience.

[0057] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The drawings here are incorporated into the specification and form a part of the present disclosure, showing the embodiments that conform to the present disclosure, and are used together with the specification to explain the principles of the present disclosure.

[0059] Figure 1 It is an application scenario diagram of a voice wake-up control method shown in some exemplary embodiments.

[0060] Figure 2 It is a flowchart of a voice wake-up control method shown in some exemplary embodiments.

[0061] Figure 3 It is a flowchart of another voice wake-up control method shown in some exemplary embodiments.

[0062] Figure 4 It is a flowchart of yet another voice wake-up control method shown in some exemplary embodiments.

[0063] Figure 5It is a flowchart of yet another voice wake-up control method shown in some exemplary embodiments.

[0064] Figure 6 It is a block diagram of a voice wake-up control device shown in some exemplary embodiments.

[0065] Figure 7 It is a hardware structure diagram of a computer device shown in some exemplary embodiments. Detailed implementation manners

[0066] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0067] The terms used in the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure. The singular forms "a", "the", and "said" used in the present disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0068] It should be understood that although the terms first, second, third, etc. may be used in the present disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".

[0069] Currently in the smartphone market, the voice wake-up function is a function that most types of mobile phones must be configured with. In order to ensure that the wake-up word of the user can be successfully read and converted into data and sent to the voice wake-up algorithm, the underlying hardware device of the mobile phone has to keep running and continuously consume power.

[0070] In the related art, the function adjustment made for power saving is to turn off the prompt sound, and the power saving effect is poor.

[0071] In view of this, the present disclosure provides a voice wake-up control method, device, computer device, and storage medium. The concepts involved in the present disclosure will be explained below in combination with an exemplary application scenario.

[0072] Please refer to Figure 1 , which shows an exemplary voice wake-up architecture diagram applicable to the voice wake-up method provided by the present disclosure. Among them, the device (hereinafter referred to as "device" for short, which can be a mobile phone, a tablet computer, a smart assistant, an audio device, etc.) that executes the voice wake-up control method provided by the present disclosure is configured with a voice wake-up module 101 and an application layer 102; after the user speaks the user audio to the device, the audio input module (such as a microphone) configured on the device will record the audio data and send the audio data to the audio decoder. After the audio decoder performs encoding and decoding operations on the audio, the audio signal is transmitted to the voice wake-up module 101 for primary wake-up. Among them, the voice wake-up module 101 can be composed of various DSPs (Digital SingalProcessor, digital signal processing chips) or other low-power general-purpose or special-purpose processors, and a relatively simple wake-up word audio model is usually deployed thereon. The voice wake-up module 101 usually remains in an open state at all times, so that when the matching degree between the user audio and the wake-up word is greater than or equal to the wake-up threshold, the user audio is reported to the application layer 102 through an interface provided by a third-party vendor or the framework layer of the system, etc.; when the application layer 102 receives the user audio, it can re-judge the user audio based on a more accurate wake-up word audio model, and when the matching degree between the user audio and the wake-up word is greater than or equal to the secondary threshold, it responds based on the user audio. Among them, the wake-up word can be a preset word, or can be selected or recorded by the user himself / herself, and the present disclosure does not limit this.

[0073] In the present disclosure, for the convenience of description, the concept of wake-up sensitivity is introduced. Among them, the wake-up sensitivity refers to the tendency of the device to respond to the wake-up word contained in the user's voice. For example, when Figure 1In the application scenario shown, when the wake-up threshold of the voice wake-up module 101 is set to a relatively high value, the device's judgment on whether the user audio contains a wake-up word will be more stringent, and the wake-up sensitivity of the voice wake-up module will naturally decrease; on the contrary, if the wake-up threshold is set to a relatively low value, the device's judgment on whether the user audio contains a wake-up word will be more lenient, and the wake-up sensitivity of the voice wake-up module will increase; when the voice wake-up module 101 or the application layer 102 is in the off state, the device power consumption is the lowest, and at this time, the wake-up sensitivity of the voice wake-up module is also the lowest (i.e., the device is not woken up). In the present disclosure, increasing or decreasing the wake-up threshold can also be extended to increasing or decreasing the wake-up sensitivity, and the influencing factors of the wake-up sensitivity are included (such as the on / off state of the voice wake-up module). That is, the wake-up threshold can not only refer to a numerical value, but also refer to the wake-up sensitivity of the voice wake-up module (including the on / off state of the voice wake-up module and the threshold of the voice wake-up module). In other words, the present disclosure can solve the same technical problems by increasing or decreasing the wake-up sensitivity of the voice wake-up module.

[0074] Next, the embodiments of the present disclosure will be described in detail.

[0075] The first aspect of the present disclosure provides a voice wake-up control method. Please refer to Figure 2 , which includes the following steps:

[0076] Step S201, in response to the device entering a preset mode, increase the wake-up threshold of the voice wake-up module according to the level of the preset mode, where the preset mode has multiple levels, and the level of the preset mode is positively correlated with the wake-up threshold, where the wake-up threshold is used to indicate that when the matching degree between the user audio collected by the voice wake-up module and the wake-up word is greater than or equal to the wake-up threshold, the device is woken up based on the user audio.

[0077] Among them, the voice wake-up module is used to determine whether to wake up the device based on the collected user audio, and the preset mode can be the so-called "power-saving mode", "do not disturb mode", "flight mode", etc.; in practical applications, different levels of the preset mode can have different names. Taking the preset mode as the so-called power-saving mode with two levels as an example, its low level can be called "power-saving mode" (note that the power-saving mode here corresponds to the super power-saving mode below, which is a level name of the so-called power-saving mode, that is, the ordinary power-saving mode; hereinafter, the "power-saving mode" refers to a level of the preset mode, and the entire mode is still referred to as the "preset mode"), and its high level can be called "super power-saving mode". For the convenience of description, the present disclosure may use the above examples and the above naming method to describe the embodiments, but it should be understood that the number of preset modes is only for illustrative purposes. In practical applications, more levels can be set for the preset mode to achieve refined control of the wake-up threshold. The present disclosure does not limit it. In addition, different naming does not affect the present disclosure from achieving its original technical effects.

[0078] Exemplarily, the device can turn on the preset mode when receiving a user instruction indicating to turn on the preset mode, and determine the level indicated by the user instruction as the level of the preset mode; additionally, exemplarily, the device can enter the preset mode when the remaining battery power of the device is less than or equal to the power threshold, and determine the level of the preset mode according to the remaining power (for example, when the remaining power is less than or equal to 20% and not in the charging state, turn on the power-saving mode, and when the remaining power is less than or equal to 10% and not in the charging state, turn on the super power-saving mode); in addition, the above two methods can be applied simultaneously. For example, when the remaining battery power of the device is less than or equal to the power threshold, a prompt message can be presented to the user, and the user's indicated preset mode level based on the prompt message can be received. For another example, the user can be allowed to specify the power threshold of the device by himself / herself, and after the remaining battery power of the device is less than or equal to the power threshold, the preset mode level can be determined according to the remaining power. The above several ways of entering the preset mode customize the overall power-saving scheme of the device for the user, are convenient to operate, improve the user experience, and have high practical value.

[0079] Regarding the positive correlation, in other words, the higher the level of the preset mode, the higher the corresponding wake-up threshold, the lower the wake-up sensitivity of the voice wake-up module. As a result, the tendency of the wake-up device to respond to the wake-up word contained in the user's voice is lower, and the false wake-up rate of the voice wake-up module for subsequent modules such as the application layer is also lower, and the device is thus more power-saving. Among them, the wake-up sensitivity (or wake-up threshold) corresponding to the level of the preset mode can be preset by the device manufacturer, debugger or user, or can be obtained by summarizing the user's usage habits. For example, if the user has performed the operation of turning off the voice wake-up function every time after entering a certain level of the preset mode in the past five times (or other preset times), it can be considered that the user tends to directly turn off the voice wake-up module at this level of the preset mode to achieve the maximum power-saving effect, and the wake-up sensitivity corresponding to this level of the preset mode can be modified to turn off the voice wake-up module (that is, the sensitivity is zero). Among them, the wake-up sensitivity can be reflected by the quality of the audio signal received by the voice wake-up module (that is, the higher the audio signal quality, the higher the wake-up sensitivity), or can be reflected by the acquisition frequency or judgment frequency of the voice wake-up module (that is, the higher the frequency, the higher the wake-up sensitivity), or can be reflected by the wake-up threshold configured on the voice wake-up module (this method will be elaborated in detail later), and the present disclosure does not limit this.

[0080] Waking up the device based on the collected user audio, specifically, it can be directly waking up the device, or reporting the collected user audio to the application layer (such as application layer 102), so that when the matching degree between the user audio and the wake-up word is greater than or equal to the secondary threshold, the application layer responds based on the user audio. That is, through a multi-level wake-up strategy, taking into account both the power consumption of the device and the accuracy of the voice wake-up function of the device, the user experience is maximally improved. Among them, the response method of the device (or application layer) to the user audio can be to continue recording the user audio and perform corresponding operations according to the text content represented by the user audio, or to directly play a preset voice to respond to the user, or to directly perform corresponding operations according to the user audio.

[0081] In the embodiments of the present disclosure, multiple levels are configured for the preset mode of the device, and corresponding wake-up sensitivities (wake-up thresholds) are configured for different levels of the preset mode according to the negative correlation; when the device enters the preset mode, the wake-up sensitivity of the voice wake-up module is reduced according to the level of the preset mode, so that according to the different levels of the preset mode, the voice wake-up module determines whether to wake up the device based on the collected user audio based on the corresponding wake-up sensitivity. Based on the above measures, the embodiments provided by the present disclosure can effectively reduce the power consumption of the voice wake-up module and its subsequent modules, and achieve more accurate power-saving control, improving the user experience.

[0082] In some embodiments of the present disclosure, in response to the device entering a preset mode, reducing the wake-up sensitivity of the voice wake-up module according to the level of the preset mode includes:

[0083] In response to the device entering a preset mode that is not the highest level, determining a first threshold according to the level of the preset mode and raising the wake-up threshold of the voice wake-up module to the first threshold, where the wake-up threshold is used to indicate that when the matching degree between the user audio collected by the voice wake-up module and the wake-up word is greater than or equal to the wake-up threshold, the device is woken up based on the user audio;

[0084] In response to the device entering the highest level of the preset mode, turning off the voice wake-up module.

[0085] In the above embodiments, the wake-up sensitivity of the voice wake-up module is reflected by the wake-up threshold configured on the voice wake-up module. Based on the same principle as the foregoing embodiments, the wake-up threshold corresponding to each level of the preset mode can be preset by the device manufacturer, the regulator, or the user, or can be determined by summarizing the user's usage habits. However, the wake-up sensitivity corresponding to the highest level of the preset mode is always to turn off the voice wake-up module (the voice wake-up module can be put into a resting state at the hardware level or power supply to the voice wake-up module is stopped), so as to completely turn off the voice wake-up function of the device, thereby saving the power consumption of the device to the greatest extent. Based on the above measures, the embodiments provided by the present disclosure can further reduce the power consumption of the voice wake-up module and its subsequent modules, and achieve more accurate power-saving control, improving the user experience. It should be noted that the highest level and non-highest level of the preset mode refer to the highest level and non-highest level in the dimension of voice wake-up. As for the absolute number of levels of the preset mode and the level division of the preset mode in other dimensions, the present disclosure does not make any limitations. In addition, other modules used for voice wake-up can also be turned off when the voice wake-up module is turned off to achieve the best power-saving effect.

[0086] In some embodiments of the present disclosure, the method further includes:

[0087] In response to the device exiting the preset mode, restoring the wake-up threshold of the voice wake-up module to the default state.

[0088] Among them, the default state refers to the state before the wake-up sensitivity of the voice wake-up module is modified by the preset mode. At this time, the wake-up sensitivity of the voice wake-up module is controlled by the system default parameters, rather than the wake-up sensitivity indicated by the level of the preset mode. It should be noted that the default state does not necessarily refer to an exact value. It can also refer to a state controlled by the system default parameters, that is, the control right of the wake-up sensitivity of the voice wake-up module is returned to the system, and the voice wake-up module is configured according to the system default parameters (or the default regulation logic, where the default here means preset, which can also be applied to the principles in the foregoing embodiments and is determined by summarizing the user's usage habits). In addition, if the voice wake-up module is in the off state, it can respond to the device exiting the preset mode, turn on the voice wake-up module, and restore the wake-up threshold of the voice wake-up module to the default state.

[0089] In some embodiments of the present disclosure, the method further includes:

[0090] In response to receiving a first instruction, set the wake-up threshold of the voice wake-up module according to the first instruction, where the first instruction indicates the wake-up threshold of the voice wake-up module;

[0091] In response to receiving a second instruction, restore the wake-up threshold of the voice wake-up module to the default state.

[0092] Among them, the first instruction and the second instruction can be input by the user (for example, adjusting the sensitivity of the voice wake-up function through the control panel provided by the system), can also be sent by a certain module or process running on the device (sending to the system or to the module responsible for the voice wake-up function), or can be sent by other devices. In the above embodiments, the wake-up sensitivity of the voice wake-up module can be determined based on the received instructions. Among them, the first instruction can be used to specify the wake-up sensitivity of the voice wake-up module, and the second instruction can be used to indicate restoring the wake-up sensitivity of the voice wake-up module to the default state. For the definition of the default state, please refer to the relevant parts in the foregoing embodiments and will not be elaborated here. It should be noted that the first instruction and the second instruction can indicate the wake-up sensitivity of the voice wake-up module, not limited to the threshold. For example, the first instruction can indicate turning off the voice wake-up module, and the second instruction indicates turning on the voice wake-up module.

[0093] Combined with at least one of the above embodiments, it can be seen that in the method provided by the present disclosure, the wake-up sensitivity of the voice wake-up module can be determined by the wake-up sensitivity indicated by the preset mode or by the instructions received by the device. In order to better balance the priorities when the above multiple methods coexist, the present disclosure also provides the embodiments shown in Figure 3 That is, the method further includes:

[0094] Step S301, in response to the device exiting the preset mode, when the change flag is marked as unchanged, restore the wake-up threshold of the voice wake-up module to the default state; when the change flag is marked as changed, restore the wake-up threshold of the voice wake-up module to the wake-up threshold indicated by the first instruction, where the change flag is used to mark whether the change status is valid, and the change flag is marked as changed in response to receiving the first instruction and marked as unchanged in response to receiving the second instruction.

[0095] Similarly to the foregoing embodiments, the first instruction and the second instruction may indicate the wake-up sensitivity of the voice wake-up module, rather than being limited to the threshold. When the first instruction indicates to turn off the voice wake-up module and the second instruction indicates to turn on the voice wake-up module, in response to the device exiting the preset mode, when the change flag is marked as unchanged, turn on the voice wake-up module and restore the wake-up threshold of the voice wake-up module to the default state; when the change flag is marked as changed, keep the voice wake-up module turned off. Wherein, the change refers to the change made to the wake-up sensitivity of the voice wake-up module based on the instruction received by the device. When the device receives the first instruction and does not receive the second instruction, it can be considered that the device has made a change to the wake-up sensitivity of the voice wake-up module based on the received instruction.

[0096] In addition, the present disclosure also provides the following embodiments:

[0097] Increasing the wake-up threshold of the voice wake-up module according to the level of the preset mode includes:

[0098] In response to the wake-up threshold corresponding to the level of the preset mode being higher than the current wake-up threshold of the device, increase the wake-up threshold of the voice wake-up module to the wake-up threshold corresponding to the level of the preset mode;

[0099] In response to the wake-up threshold corresponding to the level of the preset mode not being higher than the current wake-up threshold of the device, keep the current wake-up threshold of the device.

[0100] In other words, in response to the wake-up sensitivity corresponding to the level of the preset mode being lower than the current wake-up sensitivity of the device, lower the wake-up sensitivity of the voice wake-up module to the wake-up sensitivity corresponding to the level of the preset mode; in response to the wake-up sensitivity corresponding to the level of the preset mode not being lower than the current wake-up sensitivity of the device, keep the current wake-up sensitivity of the device.

[0101] Specifically, in the method provided by the present disclosure, there may be the following two situations involving the aforementioned "balancing the priorities when the above-mentioned multiple methods coexist" (taking a device with three wake-up sensitivity levels of 0, 1, and 2 as an example, the default wake-up sensitivity level is 2, and the wake-up sensitivity level corresponding to the power-saving mode is 1. Herein, 0 represents turning off the voice wake-up module, 1 represents a low wake-up sensitivity level with the voice wake-up module turned on, and 2 represents a high wake-up sensitivity level with the voice wake-up module turned on):

[0102] Situation 1: The device enters the power-saving mode from the default state (i.e., the wake-up sensitivity level changes from 2 to 1 based on the level of the preset mode). At this time, if the device receives an instruction indicating level 0 (for example, the user manually turns off the voice wake-up module), then when the device exits the power-saving mode, it is based on the level indicated by the received instruction (i.e., keeps the voice wake-up module turned off), which can bring a better user experience.

[0103] Situation 2: The device receives an instruction indicating level 0 in the default state (for example, the user manually turns off the voice wake-up module). At this time, the wake-up sensitivity level changes from 2 to 0. Next, when the device enters the power-saving mode, the device does not change the voice wake-up module of the device at this time (i.e., keeps the wake-up sensitivity level at 0), which can bring a better user experience.

[0104] The above two situations respectively correspond to the two embodiments provided above. That is, when exiting the preset mode, only when the change flag is marked as unchanged, the wake-up sensitivity level is restored to the default state. If the change flag is marked as changed, the wake-up sensitivity level is set to the wake-up sensitivity level indicated by the first instruction (for example, the above Situation 1); when entering the preset mode, only when the wake-up sensitivity level corresponding to the level of the preset mode is lower than the current wake-up sensitivity level of the device, the wake-up sensitivity level is reduced to the wake-up sensitivity level corresponding to the level of the preset mode, otherwise the current wake-up sensitivity level of the device is maintained (for example, the above Situation 2).

[0105] In at least one of the above embodiments, the present disclosure provides a method for controlling the wake-up sensitivity level based on an instruction and based on the level of a preset mode. When the above two control methods are in effect at the same time, the wake-up sensitivity level based on the instruction has a higher priority, avoiding the confusion of the wake-up sensitivity level caused by the conflict between the two methods, thereby further improving the user experience and further reducing the power consumption of the device in daily use by the user.

[0106] In some embodiments of the present disclosure, the method further includes the following steps as Figure 4 shown:

[0107] Step S401, in response to the device entering the preset mode, presenting a prompt message, receiving a second threshold input by the user based on the prompt message, and setting the wake-up threshold of the voice wake-up module to the second threshold.

[0108] Among them, if the highest level of the preset mode always corresponds to turning off the voice wake-up module, then when the device enters a non-highest level of the preset mode, a prompt message can be presented, and a second threshold value input by the user based on the prompt message can be received, and the wake-up threshold of the voice wake-up module can be set to the second threshold value. When the device enters the highest level of the preset mode, a first confirmation message can be presented, and a first confirmation instruction input by the user based on the first confirmation message can be received. When the first confirmation instruction indicates to turn off the voice wake-up module, the voice wake-up module is turned off. In addition, in response to the device entering the preset mode, a second confirmation message can be presented, and a second confirmation instruction input by the user based on the second confirmation message can be received. When the second confirmation instruction indicates confirmation, the wake-up sensitivity of the voice wake-up module is reduced according to the level of the preset mode, and the second confirmation instruction carries the wake-up sensitivity corresponding to the level of the preset mode (for example, reflected by low / medium / high).

[0109] Regarding the way of presenting messages, specifically, for example, the device can present a notification of the device entering a preset mode to the user in the form of a visual pop-up window, and can also provide confirmation buttons, drop-down selection boxes, text boxes and other components that facilitate the user to issue user instructions. This method is more intuitive and has a good user experience; for another example, the device can present a notification of entering a preset mode to the user in the form of an audio broadcast, and at the same time turn on the voice recognition module to receive instructions issued by the user through voice. This method can receive user instructions through voice when it is inconvenient for the user to directly operate the device. It has a wider range of application scenarios and is more friendly to the visually impaired.

[0110] The above embodiments further provide a human-computer interaction method between the device and the user, so that the user can be more aware and purposeful when turning on the preset mode, thereby improving the user experience.

[0111] In some embodiments of the present disclosure, reducing the wake-up sensitivity of the voice wake-up module according to the level of the preset mode includes:

[0112] According to the level of the preset mode, the wake-up sensitivity of the voice wake-up module is reduced within a reference range, wherein the reference range is a preset range or a range specified by a user.

[0113] In other words, a specific wake-up sensitivity range can be specified by the user (for details on the input of user instructions and the like, please refer to the foregoing embodiments), or a default reference range can be preset by the device manufacturer or the debugger. Then, when the device adjusts the wake-up sensitivity of the voice wake-up module, it is ensured that the adjusted wake-up sensitivity does not exceed the reference range. The advantage of this is that it can achieve a customized wake-up sensitivity control range based on the user's own needs (for example, the user may not want to turn off the voice wake-up function under any circumstances) (the technical solution for user-defined control by setting the wake-up sensitivity corresponding to different levels of the preset mode has been described in the foregoing embodiments), improving the user experience; at the same time, in the actual application process, the method provided by the present disclosure may execute errors or repeat execution due to factors such as code negligence and special environments. At this time, the setting of the reference range can ensure that the wake-up sensitivity of the voice wake-up module is always within a reasonable range, improving the fault tolerance of the method.

[0114] Next, in combination with Figure 5 the flowchart shown, the foregoing at least one embodiment will be further described.

[0115] In Figure 5 the embodiment shown, the user can control the switch of the voice wake-up mode through the APP switch (that is, issue the first instruction and the second instruction based on the APP). In this embodiment, two enable values are set. Among them, the APP voice wake-up enable value is used to represent whether the user has performed a switch operation on the voice wake-up mode based on the APP (equivalent to the foregoing first flag). If the user turns off the voice wake-up mode based on the APP, the APP voice wake-up enable value is updated to 0, otherwise it is 1; the super power-saving voice wake-up enable value is used to indicate whether the voice wake-up module is turned on or off. When the voice wake-up enable value is 0, it indicates that the voice wake-up module is turned off, and when it is 1, it indicates that the voice wake-up module is turned on. When the user turns on the super power-saving mode, this method will judge whether the APP voice enable value is 1. If it is 1, it means that the user has not turned on or off the voice wake-up function through the APP. At this time, the voice wake-up function can be turned on or off based on the opening and closing of the super power-saving mode, and the super power-saving voice wake-up enable value is updated; if the APP voice wake-up enable value is 0, it means that the user has manually turned off the voice wake-up function through the APP, and at this time, no operation is performed on the voice wake-up function.

[0116] For the specific details and related advantages in the above steps, please refer to the foregoing embodiments and will not be elaborated here.

[0117] Corresponding to the foregoing method embodiments, the present disclosure also provides embodiments of a device and a terminal to which the device is applied.

[0118] A second aspect of the present disclosure provides a voice wake-up control device. Please refer toFigure 6 , the device includes:

[0119] A first threshold adjustment module 601, configured to, in response to the device entering a preset mode, increase the wake-up threshold of the voice wake-up module according to the level of the preset mode, where the preset mode has multiple levels, and the level of the preset mode is positively correlated with the wake-up threshold, and the wake-up threshold is used to indicate that when the matching degree between the user audio collected by the voice wake-up module and the wake-up word is greater than or equal to the wake-up threshold, the device is woken up based on the user audio.

[0120] Optionally, when the first threshold adjustment module 601 is configured to, in response to the device entering a preset mode, increase the wake-up threshold of the voice wake-up module according to the level of the preset mode, it is configured to:

[0121] In response to the device entering a preset mode that is not the highest level, determine a first threshold according to the level of the preset mode and increase the wake-up threshold of the voice wake-up module to the first threshold.

[0122] Optionally, when the first threshold adjustment module 601 is configured to, in response to the device entering a preset mode, increase the wake-up threshold of the voice wake-up module according to the level of the preset mode, it is configured to:

[0123] In response to the device entering the highest level of the preset mode, turn off the voice wake-up module.

[0124] Optionally, the device further includes:

[0125] A second threshold adjustment module, configured to, in response to the device exiting the preset mode, restore the wake-up threshold of the voice wake-up module to the default state.

[0126] Optionally, the device further includes:

[0127] A first instruction response module, configured to, in response to receiving a first instruction, set the wake-up threshold of the voice wake-up module according to the first instruction, where the first instruction indicates the wake-up threshold of the voice wake-up module;

[0128] A second instruction response module, configured to, in response to receiving a second instruction, restore the wake-up threshold of the voice wake-up module to the default state.

[0129] Optionally, the device further includes:

[0130] A third threshold adjustment module, configured to, in response to the device exiting the preset mode, restore the wake-up threshold of the voice wake-up module to the default state when the change flag is marked as unchanged, and restore the wake-up threshold of the voice wake-up module to the wake-up threshold indicated by the first instruction when the change flag is marked as changed, where the change flag is used to mark whether the change status is valid, and the change flag is marked as changed in response to receiving the first instruction and marked as unchanged in response to receiving the second instruction.

[0131] Optionally, when the first threshold adjustment module 601 is configured to increase the wake-up sensitivity of the voice wake-up module according to the level of the preset mode, it is configured to:

[0132] In response to the wake-up threshold corresponding to the level of the preset mode being higher than the current wake-up threshold of the device, increase the wake-up threshold of the voice wake-up module to the wake-up threshold corresponding to the level of the preset mode;

[0133] In response to the wake-up threshold corresponding to the level of the preset mode not being higher than the current wake-up threshold of the device, maintain the current wake-up threshold of the device.

[0134] Optionally, the device further includes:

[0135] A fourth threshold adjustment module, configured to, in response to the device entering the preset mode, present a prompt message, receive a second threshold input by the user based on the prompt message, and set the wake-up threshold of the voice wake-up module to the second threshold.

[0136] Optionally, increasing the wake-up threshold of the voice wake-up module according to the level of the preset mode includes:

[0137] Increasing the wake-up threshold of the voice wake-up module within a reference range according to the level of the preset mode, where the reference range is a preset range or a range specified by the user.

[0138] Optionally, the device further includes:

[0139] A preset mode entry module, configured to enter the preset mode when the remaining power of the device is less than or equal to the power threshold, and determine the level of the preset mode according to the remaining power.

[0140] Optionally, when the first threshold adjustment module 601 is configured to wake up the device based on the collected user audio, it is configured to:

[0141] Report the collected user audio to the application layer, so that the application layer responds based on the user audio when the matching degree between the user audio and the wake-up word is greater than or equal to the secondary threshold.

[0142] For the implementation process of the functions and roles of each module in the above device, please refer to the implementation process of the corresponding steps in the above method for details, which will not be elaborated here.

[0143] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can be referred to the partial description of the method embodiment. The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present disclosure solution. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0144] In a third aspect, the embodiments of the voice wake-up control device provided by the present disclosure can be applied to a computer device. Please refer to the attached Figure 7 , which exemplarily shows a hardware schematic diagram of a computer device. For example, the device 700 can be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0145] The device 700 may include one or more of the following components: a processing component 701, a memory 702, a power component 703, a multimedia component 704, an audio component 705, an input / output (I / O) interface 706, a sensor component 707, and a communication component 708.

[0146] The processing component 701 generally controls the overall operation of the device 700, such as operations associated with display, telephone calls, data communication, camera operations, and recording operations. The processing component 701 may include one or more processors 709 to execute instructions to complete all or part of the steps of the above method. In addition, the processing component 701 may include one or more modules to facilitate the interaction between the processing component 701 and other components. For example, the processing component 701 may include a multimedia module to facilitate the interaction between the multimedia component 704 and the processing component 701.

[0147] The memory 702 is configured to store various types of data to support the operation of the device 700. Examples of such data include instructions for any application or method operating on the device 700, contact data, phone book data, messages, pictures, videos, and the like. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0148] The power component 703 provides power to the various components of the device 700. The power component 703 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 700.

[0149] The multimedia component 704 includes a screen that provides an output interface between the device 700 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can not only sense the boundaries of the touch or swipe actions, but also detect the duration and pressure associated with the touch or swipe operation. In some embodiments, the multimedia component 704 includes a front camera and / or a rear camera. When the device 700 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each of the front camera and the rear camera can be a fixed optical lens system or have a focal length and optical zoom capabilities.

[0150] The audio component 705 is configured to output and / or input audio signals. For example, the audio component 705 includes a microphone (MIC) that is configured to receive external audio signals when the device 700 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals can be further stored in the memory 702 or transmitted via the communication component 708. In some embodiments, the audio component 705 further includes a speaker for outputting audio signals.

[0151] The I / O interface 706 provides an interface between the processing component 701 and a peripheral interface module, which can be a keyboard, click wheel, buttons, etc. These buttons can include, but are not limited to: a home button, volume buttons, a power-on button, and a lock button.

[0152] The sensor assembly 707 includes one or more sensors for providing a status assessment of various aspects of the device 700. For example, the sensor assembly 707 can detect the on / off state of the device 700, the relative positioning of components, such as the display and keypad of the device 700. The sensor assembly 707 can also detect a change in the position of the device 700 or a component of the device 700, the presence or absence of user contact with the device 700, the orientation or acceleration / deceleration of the device 700, and the temperature change of the device 700. The sensor assembly 707 can also include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 707 can also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 707 can also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0153] The communication component 708 is configured to facilitate communication between the device 700 and other devices in a wired or wireless manner. The device 700 can access a wireless network based on communication standards, such as WiFi, 2G or 3G, 4G or 5G, or a combination thereof. In an exemplary embodiment, the communication component 708 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 708 further includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0154] In an exemplary embodiment, the device 700 can be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the method for determining the holding manner of the above-mentioned electronic device.

[0155] In a fourth aspect, in an exemplary embodiment of the present disclosure, there is also provided a non-transitory computer-readable storage medium including instructions, such as a memory 702 including instructions, and the above instructions can be executed by a processor 709 of the device 700 to complete the method for determining the holding manner of the above-mentioned electronic device. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0156] The above describes specific embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the acts or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0157] Those skilled in the art will readily conceive of other implementations of the present disclosure after considering the specification and practicing the invention herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not claimed in the present disclosure. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of the present disclosure are pointed out by the following claims.

[0158] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the figures, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

[0159] The above are only the preferred embodiments of the present disclosure and are not intended to limit the present disclosure. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present disclosure shall be included within the scope of protection of the present disclosure.

Claims

1. A voice wake-up control method, characterized in that, the method includes: In response to the device entering a preset mode, increase the wake-up threshold of the voice wake-up module according to the level of the preset mode, where the preset mode has multiple levels, and the level of the preset mode is positively correlated with the wake-up threshold, where the wake-up threshold is used to indicate that when the matching degree between the user audio collected by the voice wake-up module and the wake-up word is greater than or equal to the wake-up threshold, the device is woken up based on the user audio.

2. The voice wake-up control method according to claim 1, characterized in that, the step of in response to the device entering a preset mode, increasing the wake-up threshold of the voice wake-up module according to the level of the preset mode includes: In response to the device entering a non-highest-level preset mode, determine a first threshold according to the level of the preset mode and increase the wake-up threshold of the voice wake-up module to the first threshold.

3. The voice wake-up control method according to claim 1, characterized in that, the method further includes: In response to the device entering the highest-level preset mode, turn off the voice wake-up module.

4. The voice wake-up control method according to claim 1, characterized in that, the method further includes: In response to the device exiting the preset mode, restore the wake-up threshold of the voice wake-up module to the default state.

5. The voice wake-up control method according to claim 1, characterized in that, the method further includes: In response to receiving a first instruction, set the wake-up threshold of the voice wake-up module according to the first instruction, where the first instruction indicates the wake-up threshold of the voice wake-up module; In response to receiving a second instruction, restore the wake-up threshold of the voice wake-up module to the default state.

6. The voice wake-up control method according to claim 5, characterized in that, the method further includes: In response to the device exiting the preset mode, if the change flag is marked as unchanged, restore the wake-up threshold of the voice wake-up module to the default state; if the change flag is marked as changed, restore the wake-up threshold of the voice wake-up module to the wake-up threshold indicated by the first instruction, where the change flag is used to mark whether the change state is valid, and the change flag is marked as changed in response to receiving the first instruction and marked as unchanged in response to receiving the second instruction.

7. The voice wake-up control method according to any one of claims 1 to 6, characterized in that, the step of increasing the wake-up threshold of the voice wake-up module according to the level of the preset mode includes: In response to the wake-up threshold corresponding to the level of the preset mode being higher than the current wake-up threshold of the device, increase the wake-up threshold of the voice wake-up module to the wake-up threshold corresponding to the level of the preset mode; In response to the wake-up threshold corresponding to the level of the preset mode not being higher than the current wake-up threshold of the device, maintain the current wake-up threshold of the device.

8. The voice wake-up control method according to claim 1, characterized in that, the method further includes: In response to the device entering the preset mode, a prompt message is presented, and a second threshold value input by the user based on the prompt message is received, and the wake-up threshold value of the voice wake-up module is set to the second threshold value.

9. The voice wake-up control method according to claim 1, wherein, raising the wake-up threshold value of the voice wake-up module according to the level of the preset mode includes: raising the wake-up threshold value of the voice wake-up module within a reference range according to the level of the preset mode, wherein the reference range is a preset range or a range specified by the user.

10. The voice wake-up control method according to claim 1, wherein, the method further includes: when the remaining power of the device is less than or equal to the power threshold value, entering the preset mode, and determining the level of the preset mode according to the remaining power.

11. The voice wake-up control method according to claim 1, wherein, waking up the device based on the collected user audio includes: reporting the collected user audio to the application layer, so that when the matching degree between the user audio and the wake-up word is greater than or equal to the secondary threshold value, the application layer responds based on the user audio.

12. A voice wake-up control device, wherein, the device includes: a first sensitivity adjustment module, configured to, in response to the device entering the preset mode, raise the wake-up threshold value of the voice wake-up module according to the level of the preset mode, wherein the preset mode has multiple levels, and the level of the preset mode is positively correlated with the wake-up threshold value, and the wake-up threshold value is used to indicate that when the matching degree between the collected user audio and the wake-up word is greater than or equal to the wake-up threshold value, the device is woken up based on the user audio.

13. A computer device, wherein, it includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, the method according to any one of claims 1 to 11 is implemented.

14. A computer-readable storage medium, on which a computer program is stored, wherein, when the program is executed by the processor, the method according to any one of claims 1 to 11 is implemented.

Images