Terminal wake-up setting method, wake-up method and corresponding system
Technical Field
The embodiment of the invention relates to a data processing technology, in particular to a method for setting terminal awakening, an awakening method and a corresponding system.
Background
With the continuous development of intelligent terminals, new intelligent terminals such as VR provide more comprehensive virtual experience for users, and although the intelligent terminals have various characteristics, the intelligent terminals basically keep the energy-saving mode in the mobile phone.
In the energy-saving mode, peripheral hardware units such as a sensor of the intelligent terminal are powered off, so that electric energy is saved. When waking up, a user is required to press a button to send a wake-up instruction to instruct each hardware to be powered on and run. However, in some cases, for example, a user wearing a VR headset does not have the convenience of touching a button to wake up. For another example, when it is inconvenient to hold the intelligent terminal, it is also inconvenient to wake up the device by pressing the button. Therefore, there is a need for improvements to existing wake-up approaches.
Disclosure of Invention
The invention provides a method for setting terminal awakening, an awakening method and a corresponding system, which aim to solve the problem that the existing intelligent terminal only can awaken the terminal by means of mechanical touch.
In a first aspect, an embodiment of the present invention provides a method for setting a terminal to wake up, including: receiving a wake-up voice signal within a preset verification duration, and presetting a voice recognition threshold, wherein the voice recognition threshold is used for determining whether to start recognizing a boundary value of the received voice signal during wake-up; and storing the received awakening voice signal in an awakening processing module of the terminal.
In a second aspect, an embodiment of the present invention further provides a method for waking up a terminal, including: when the terminal is switched into a dormant state, starting a wake-up processing module in the terminal; conveying the received voice signal to the wake-up processing module during sleep; and when the awakening processing module monitors that the voice signal meets a preset voice recognition threshold, verifying whether the received voice signal can awaken the terminal.
In a third aspect, an embodiment of the present invention further provides a system for setting a terminal to wake up, where the system includes: the device comprises a setting module, a verification module and a voice recognition module, wherein the setting module is used for receiving a wake-up voice signal within a preset verification duration and presetting a voice recognition threshold, and the voice recognition threshold is used for determining whether to start recognizing a boundary value of the received voice signal during wake-up; and the awakening voice signal storage module is used for storing the received awakening voice signal in the awakening processing module of the terminal.
In a fourth aspect, an embodiment of the present invention further provides a wake-up system for a terminal, including: a wake-up processing module; the starting module is used for starting the loss awakening processing module in the terminal when the terminal is switched into a dormant state; the voice receiving module is used for transmitting the received voice signal to the awakening processing module during dormancy; and the awakening processing module is used for verifying whether the received voice signal can awaken the terminal or not when the awakening processing module monitors that the voice signal meets a preset voice recognition threshold.
According to the invention, through setting the awakening voice signal with the limited time length and the voice recognition threshold, on one hand, a more flexible unlocking mode can be provided, and the flexibility of setting the voice signal can be improved.
Drawings
Fig. 1 is a flowchart of a method for setting a terminal wake-up according to a first embodiment of the present invention;
fig. 2 is a schematic structural diagram of a system for setting terminal wake-up according to a second embodiment of the present invention;
fig. 3 is a flowchart of a wake-up method for a terminal according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a wake-up system for a terminal according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a method for setting a terminal wake-up according to an embodiment of the present invention, where the embodiment is applicable to a case where a terminal is set for waking up in order to wake up the terminal in a voice manner, and the method may be executed by a setting system, where the setting system is installed in the terminal. The terminal includes but is not limited to: cell-phone, VR device, wear the device etc. wherein, to the VR device as the excellent. The setting method specifically comprises the following steps:
step S110, receiving a wake-up voice signal within a preset verification duration, and presetting a voice recognition threshold, where the voice recognition threshold is used to determine whether to start recognizing a boundary value of the received voice signal during wake-up.
Specifically, a user clicks a button for inputting a wake-up voice signal on a setting interface of the terminal and speaks a sentence for verifying wake-up, and the setting system receives the voice signal within a preset verification duration through a voice receiving module (i.e., a circuit including a microphone) of the terminal. In order to reduce the data volume of the voice signal processed by the wake-up processing module, the preset verification time duration of the setting system does not exceed 3 s.
Meanwhile, the voice recognition threshold is also preset before the awakening voice signal is received or after the awakening voice signal is received.
Specifically, in one case, the voice recognition threshold may be at least one of a minimum energy threshold (e.g., 30 db), a maximum energy threshold, a minimum frequency threshold, and a maximum frequency threshold that are pre-fixed before the wake-up voice signal is received, and the voice recognition threshold is stored in a non-volatile storage medium. And storing the stored voice recognition threshold in a wake-up processing module when the setting system determines to set the wake-up voice signal based on the operation of the user.
In another case, when receiving the wake-up voice signal, the setting system displays a frequency law interval and/or an energy interval (e.g., a decibel interval) where the wake-up voice signal is located in real time. The user can select to set the voice recognition threshold according to each displayed interval, and the set voice recognition threshold is respectively stored in the nonvolatile storage medium of the terminal and the awakening processing module by the setting system.
In another case, the setting system is set according to the frequency range and/or the energy range of the wake-up voice signal when receiving the wake-up voice signal or after receiving the wake-up voice signal.
For example, the setting system uses at least one of the minimum value and the maximum value in the frequency range and/or the energy range of the received wake-up voice signal as a voice recognition threshold, and stores the set voice recognition threshold in the non-volatile storage medium of the terminal and the wake-up processing module, respectively.
For another example, the setting system sets a speech recognition threshold on the basis of at least one of the minimum value and the maximum value in the frequency range and/or the energy range of the received wake-up speech signal according to the preset expansion ratio of the lower limit and the upper limit, and respectively stores the set speech recognition threshold in the nonvolatile storage medium of the terminal and the wake-up processing module.
Here, the wake-up processing module may be configured by a main processor, a memory, and the like of the terminal. In order to reduce the power consumption caused by hardware operation as much as possible, the wake-up processing module is composed of a circuit containing a Micro Control Unit (MCU). And the MCU is internally provided with a storage medium for storing the voice recognition threshold. In addition, during the terminal wake-up state, the main processor occupies resources of the voice receiving module (e.g., microphone, etc.). The main processor in the setup system may instruct the MCU to store the wake-up speech signal and the speech recognition threshold, etc.
And step S120, storing the received awakening voice signal in an awakening processing module of the terminal.
Here, the setup system may store the received original wake-up voice signal in the wake-up processing module. Alternatively, the setting system extracts feature information in the wake-up voice signal, and stores the feature information in a wake-up processing module, where the feature information includes: a characteristic waveform in the wake-up speech signal, and/or textual information translated from the wake-up speech signal.
For example, the setting system extracts the frequency waveform, the characteristic waveform with the fastest frequency change and the like of the wake-up voice signal, and stores the extracted characteristic waveform in the wake-up processing module.
For another example, the setting system converts the received wake-up speech signal into corresponding text information according to a preset speech-to-text translator, and stores the text information as feature information in the wake-up processing module.
It should be noted that the setting system may store the extracted feature information in the wake-up processing module in both examples.
In this embodiment, by setting the time-limited wake-up voice signal and the voice recognition threshold, on one hand, the complexity of the terminal in verifying the voice signal during the sleep state can be effectively reduced, and on the other hand, the power consumption in verifying the voice signal can be reduced.
Example two
As shown in fig. 2, a schematic structural diagram of a system for setting terminal wake-up according to a second embodiment of the present invention is applicable to a situation where a terminal is set to wake up in order to wake up the terminal in a voice manner. Wherein the setting system is installed in a terminal. The terminal includes but is not limited to: cell-phone, VR device, wear the device etc. wherein, to the VR device as the excellent. The setting system 1 specifically includes: a setting module 11 and a wake-up voice signal storage module 12.
The setting module 11 is configured to receive a wake-up voice signal within a preset verification duration, and preset a voice recognition threshold, where the voice recognition threshold is used to determine whether to start recognizing a boundary value of the received voice signal during wake-up.
Specifically, a user clicks a button for inputting a wake-up voice signal on a setting interface of the terminal and speaks a sentence for verifying wake-up, and the setting module 11 receives the voice signal within a preset verification duration through a voice receiving module (i.e., a circuit including a microphone) of the terminal. In order to reduce the data amount of the voice signal processed by the wake-up processing module, the verification duration preset by the setting module 11 does not exceed 3s, for example.
Meanwhile, the voice recognition threshold is also preset before the awakening voice signal is received or after the awakening voice signal is received.
Specifically, in one case, the voice recognition threshold may be at least one of a minimum energy threshold (e.g., 30 db), a maximum energy threshold, a minimum frequency threshold, and a maximum frequency threshold that are pre-fixed before the wake-up voice signal is received, and the voice recognition threshold is stored in a non-volatile storage medium. When the setting module 11 determines to set the wake-up voice signal based on the user operation, the stored voice recognition threshold is stored in the wake-up processing module.
In another case, when receiving the wake-up voice signal, the setting module 11 displays a frequency law interval and/or an energy interval (e.g., a decibel interval) where the wake-up voice signal is located in real time. The user can select to set the speech recognition threshold according to each displayed interval, and the setting module 11 stores the set speech recognition threshold in the non-volatile storage medium of the terminal and the wake-up processing module respectively.
In another case, the setting module 11 is set according to the frequency range and/or the energy range of the wake-up voice signal when receiving the wake-up voice signal or after receiving the wake-up voice signal.
For example, the setting module 11 uses at least one of the minimum value and the maximum value in the frequency range and/or the energy range of the received wake-up voice signal as a voice recognition threshold, and stores the set voice recognition threshold in the non-volatile storage medium of the terminal and the wake-up processing module, respectively.
For another example, the setting module 11 sets a speech recognition threshold on the basis of at least one of the minimum value and the maximum value in the frequency range and/or the energy range of the received wake-up speech signal according to the preset expansion ratio of the lower limit and the upper limit, and respectively stores the set speech recognition threshold in the nonvolatile storage medium of the terminal and the wake-up processing module.
Here, the wake-up processing module may be configured by a main processor, a memory, and the like of the terminal. In order to reduce the power consumption caused by hardware operation as much as possible, the wake-up processing module is composed of a circuit containing a Micro Control Unit (MCU). And the MCU is internally provided with a storage medium for storing the voice recognition threshold. In addition, during the terminal wake-up state, the main processor occupies resources of the voice receiving module (e.g., microphone, etc.). The main processor in the setting module 11 may instruct the MCU to store the wake-up speech signal and the speech recognition threshold.
The awakening voice signal storage module 12 is configured to store the received awakening voice signal in an awakening processing module of the terminal.
Here, the wake-up voice signal storage module 12 may store the received original wake-up voice signal in the wake-up processing module. Alternatively, the wake-up voice signal storage module 12 extracts feature information from the wake-up voice signal, and stores the feature information in a wake-up processing module, where the feature information includes: a characteristic waveform in the wake-up speech signal, and/or textual information translated from the wake-up speech signal.
For example, the wake-up voice signal storage module 12 extracts a frequency waveform, a characteristic waveform with the fastest frequency change, and the like of the wake-up voice signal, and stores the extracted characteristic waveform in the wake-up processing module.
For another example, the wake-up voice signal storage module 12 converts the received wake-up voice signal into corresponding text information according to a preset voice-to-word translator, and stores the text information as feature information in the wake-up processing module.
It should be noted that the wake-up voice signal storage module 12 may store the extracted feature information in the wake-up processing module in both examples.
EXAMPLE III
As shown in fig. 3, the present embodiment provides a wake-up method for a terminal. The wake-up method wakes up a situation of the terminal by monitoring and recognizing a voice signal during a sleep state of the terminal. The wake-up method is performed by a wake-up system installed in the terminal. The terminal includes but is not limited to: cell-phone, VR device, wear the device etc. wherein, to the VR device as the excellent. The awakening method comprises the following steps:
step S210, when the terminal is switched into a dormant state, a wake-up processing module in the terminal is started.
Specifically, when the terminal is not operated for a long time or is switched to a sleep state under a sleep instruction, the wake-up system starts the wake-up processing module.
Here, the wake-up system may perform the verification wake-up process of the wake-up processing module by a main processing unit (a hardware unit including a main processor and a memory) of the terminal.
In one alternative, the wake-up processing module comprises an MCU and its peripheral circuits. And the MCU is connected with a main processing unit in the terminal.
And when the awakening system monitors that the terminal is switched into a dormant state, switching a voice receiving module in the terminal from a main processing unit in the terminal to an awakening processing module.
Specifically, when the wake-up system monitors that the terminal is switched to the sleep state, the main processor is controlled to output a start instruction to the MCU, so that the wake-up processing module executes a preset monitoring and wake-up verification process.
Step S220, transmitting the received voice signal to the wake-up processing module during the sleep period.
Here, the wake-up system instructs the main processor to transfer the control of the voice receiving module to the wake-up processing module. During sleep, the wake-up system outputs a voice signal received by a voice receiving module (e.g., a microphone) to a wake-up processing module. And the awakening processing module receives the voice signal in real time and executes an awakening verification process. The wake-up verification process is not necessarily a software program, and may be a wake-up verification process combining a hardware circuit and software.
In the process of awakening verification, the awakening processing module determines whether to start awakening verification according to a preset voice recognition threshold.
For example, when the frequency of the real-time received voice signal does not reach the minimum value of the voice recognition threshold or exceeds the maximum value of the voice recognition threshold, the wake-up processing module does not perform step S230, otherwise, performs step S230.
For another example, when the decibel number of the real-time received voice signal does not reach the minimum value of the voice recognition threshold or exceeds the maximum value of the voice recognition threshold, the wake-up processing module does not execute step S230, otherwise, executes step S230.
Step S230, when the wake-up processing module monitors that the voice signal meets a preset voice recognition threshold, verifying whether the received voice signal can wake up the terminal.
Here, the wake-up processing module verifies that the received voice signal matches a pre-stored voice signal in waveform when monitoring that the voice signal meets a preset voice recognition threshold.
Alternatively, before verifying whether the received voice signal can wake up the terminal, the step S230 further includes: and judging whether the duration of the voice signal meeting the preset voice recognition threshold exceeds the preset verification duration, if so, not verifying whether the voice signal can awaken the terminal, and otherwise, verifying whether the voice signal can awaken the terminal.
For example, if the duration of the voice signal satisfying the voice recognition threshold exceeds the preset verification duration, it indicates that the voice signal is not an instruction signal for waking up the terminal, and on this basis, it is not verified whether the voice signal can wake up the terminal. Otherwise, whether the voice signal can wake up the terminal is verified.
On the basis of the foregoing optional embodiments, the wake-up processing module extracts feature information in the voice signal, matches the extracted feature information with stored feature information, and determines whether to wake up the terminal based on a matching result, where the stored feature information includes: a characteristic waveform in the wake-up speech signal, and/or textual information translated from the wake-up speech signal.
Here, the wake-up processing module extracts feature information of the voice information received in the sleep state according to a feature information extraction manner when the wake-up voice signal is set in the first embodiment, matches the extracted feature information with the stored feature information, and determines whether to wake up the terminal according to a matching result.
For example, if the signature in the received speech signal is scaled up/down to match the stored signature, the verification is determined to be successful.
In an alternative, the step S230 includes: steps S231 and S232. (none are shown in the drawings)
And S231, receiving a voice signal with preset verification duration when the preset voice recognition threshold is met.
Specifically, when the wake-up system determines that the received voice signal meets the voice recognition threshold, the wake-up system takes the determined time as the starting time and receives the voice signal with the preset verification duration.
S232, extracting the characteristic information in the voice signal, matching the extracted characteristic information with the stored characteristic information, and determining whether to awaken the terminal based on the matching result.
In this embodiment, the wake-up system extracts feature information from the received voice signal with verification duration in the manner described above.
It should be noted that, if the wake-up processing module is executed by the MCU to perform the wake-up verification process, when the wake-up interrupt is determined and the wake-up system wakes up the terminal, the voice receiving module is switched from the wake-up processing module to the main processing unit.
The wake-up system starts the main processing unit and other hardware units based on the information of successful verification provided by the wake-up processing module, and instructs the main processing unit to switch the control right of the voice receiving module from the MCU to the main processing unit.
In the embodiment, when the voice signal meets the preset voice recognition threshold, whether the received voice signal can wake up the terminal is verified, so that the problem of overlarge power consumption of the terminal during the sleep period can be effectively prevented. In addition, the MCU is utilized to reduce the power consumption of monitoring the voice signal. In addition, when the duration of the voice signal meeting the preset voice recognition threshold is judged to exceed the preset verification duration, whether the voice signal is matched with the preset characteristic information is verified, so that the verification times can be effectively reduced, and the energy consumption loss in the dormancy period can be reduced as far as possible. In addition, only the voice signal with the verification duration is received for awakening verification, and the verification efficiency can be effectively improved.
Example four
As shown in fig. 4, the present embodiment provides a wake-up system for a terminal. The wake-up system wakes up the situation of the terminal by monitoring and recognizing a voice signal during the terminal is in a sleep state. The wake-up system is installed in the terminal. The terminal includes but is not limited to: cell-phone, VR device, wear the device etc. wherein, to the VR device as the excellent. The wake-up system 2 comprises: the device comprises a starting module 21, a voice receiving module 22 and a wake-up processing module 23.
The starting module 21 is configured to start the wake-up processing module 23 in the terminal when the terminal is turned into a sleep state.
Specifically, when the terminal is not operated for a long time or is turned into a sleep state under a sleep instruction, the starting module 21 starts the wake-up processing module 23.
Here, the start module 21 may execute the verification wake-up process of the wake-up processing module 23 by a main processing unit (a hardware unit including a main processor and a memory) of the terminal.
In one alternative, the wake-up processing module 23 includes an MCU and its peripheral circuits. And the MCU is connected with a main processing unit in the terminal.
When the starting module 21 monitors that the terminal is switched into the dormant state, the voice receiving module 22 in the terminal is switched from the main processing unit in the terminal to the awakening processing module 23.
Specifically, when the start module 21 monitors that the terminal is in the sleep state, the main processor is controlled to output a start instruction to the MCU, so that the wake-up processing module 23 executes a preset monitoring and wake-up verification process.
The voice receiving module 22 is used for delivering the received voice signal to the wake-up processing module 23 during the sleep period.
Here, the voice receiving module 22 instructs the main processor to transfer the control of the voice receiving module 22 to the wake-up processing module 23. During the sleep period, the voice receiving module 22 outputs the voice signal received by the voice receiving module 22 (such as a microphone) to the wake-up processing module 23. The wake-up processing module 23 receives the voice signal in real time and performs a wake-up verification process. The wake-up verification process is not necessarily a software program, and may be a wake-up verification process combining a hardware circuit and software.
In the process of the wake-up verification, the wake-up processing module 23 determines whether to start the wake-up verification according to a preset voice recognition threshold.
For example, when the frequency of the real-time received voice signal does not reach the minimum value of the voice recognition threshold or exceeds the maximum value of the voice recognition threshold, the wake-up processing module 23 does not perform the wake-up verification process, otherwise, performs the wake-up verification process.
For another example, when the decibel number of the real-time received voice signal does not reach the minimum value of the voice recognition threshold or exceeds the maximum value of the voice recognition threshold, the wake-up processing module 23 does not perform the wake-up verification process, otherwise, performs the wake-up verification process.
When the wake-up processing module 23 monitors that the voice signal meets a preset voice recognition threshold, it is verified whether the received voice signal can wake up the terminal.
Here, when it is monitored that the voice signal meets a preset voice recognition threshold, the wake-up processing module 23 verifies that the received voice signal matches a pre-stored voice signal in a waveform.
One alternative is that before verifying whether the received voice signal can wake up the terminal, the wake-up processing module 23 is further configured to determine whether a duration of the voice signal meeting a preset voice recognition threshold exceeds a preset verification duration, if so, not verifying whether the voice signal can wake up the terminal, and if not, verifying whether the voice signal can wake up the terminal.
For example, if the duration of the voice signal satisfying the voice recognition threshold exceeds the preset verification duration, it indicates that the voice signal is not an instruction signal for waking up the terminal, and on this basis, it is not verified whether the voice signal can wake up the terminal. Otherwise, whether the voice signal can wake up the terminal is verified.
On the basis of the foregoing optional embodiments, the wake-up processing module 23 extracts feature information in the voice signal, matches the extracted feature information with stored feature information, and determines whether to wake up the terminal based on a matching result, where the stored feature information includes: a characteristic waveform in the wake-up speech signal, and/or textual information translated from the wake-up speech signal.
Here, the wake-up processing module 23 extracts the feature information of the voice information received in the sleep state according to the feature information extraction method when the wake-up voice signal is set in the first embodiment, matches the extracted feature information with the stored feature information, and determines whether to wake up the terminal according to the matching result.
For example, if the signature in the received speech signal is scaled up/down to match the stored signature, the verification is determined to be successful.
In an alternative, the wake-up processing module 23 is further configured to receive a voice signal with a preset verification duration when it is determined that a preset voice recognition threshold is met; and the voice terminal is used for extracting the characteristic information in the voice signal, matching the extracted characteristic information with the stored characteristic information and determining whether to wake up the terminal or not based on the matching result.
Specifically, when determining that the received voice signal meets the voice recognition threshold, the wake-up processing module 23 takes the determined time as the start time, and receives the voice signal with the preset verification time duration.
In this embodiment, the wake-up processing module 23 extracts feature information from the received voice signal with verification duration according to the above-described manner.
It should be noted that, if the wake-up processing module 23 is executed by the MCU to perform the wake-up verification process, when determining the wake-up interrupt, and the wake-up processing module 23 wakes up the terminal, the voice receiving module 22 is switched from the wake-up processing module 23 to the main processing unit.
Here, the information of successful verification provided by the wake-up processing module 23 starts the main processing unit and other hardware units, and instructs the main processing unit to switch the control right of the voice receiving module 22 from the MCU to the main processing unit.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.