WO2024103893A1 - 唤醒应用程序的方法及电子设备 - Google Patents

唤醒应用程序的方法及电子设备 Download PDF

Info

Publication number
WO2024103893A1
WO2024103893A1 PCT/CN2023/114978 CN2023114978W WO2024103893A1 WO 2024103893 A1 WO2024103893 A1 WO 2024103893A1 CN 2023114978 W CN2023114978 W CN 2023114978W WO 2024103893 A1 WO2024103893 A1 WO 2024103893A1
Authority
WO
WIPO (PCT)
Prior art keywords
breath
awakening
application
software module
notification
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2023/114978
Other languages
English (en)
French (fr)
Inventor
戴璨
张冕
梁恒洲
程权
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Honor Device Co Ltd
Original Assignee
Honor Device Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Honor Device Co Ltd filed Critical Honor Device Co Ltd
Priority to US19/111,980 priority Critical patent/US20260024527A1/en
Priority to CN202380054837.1A priority patent/CN119604931A/zh
Priority to EP23890331.4A priority patent/EP4571734A4/en
Publication of WO2024103893A1 publication Critical patent/WO2024103893A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16—Sound input; Sound output
    • G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/54—Interprogram communication
    • G06F9/542—Event management; Broadcasting; Multicasting; Notifications
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • G10L15/063—Training
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • G10L15/063—Training
    • G10L2015/0631—Creating reference templates; Clustering
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L2015/088—Word spotting
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/225—Feedback of the input speech
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/226—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics

Definitions

  • the present application belongs to the field of terminal technology, and in particular relates to a method for waking up an application and an electronic device.
  • voice assistants such as YOYO, Xiaoyi, Siri, etc.
  • voice assistants have been added to many electronic devices to help users complete the human-computer interaction process with electronic devices.
  • the voice assistant is in a dormant state, and the user can wake up the voice assistant when he wants to use it.
  • button wake-up the voice assistant is woken up by the user's triggering operation on a button (such as the power button).
  • keyword wake-up the voice assistant is woken up by receiving a specific wake-up word (for example, "Hello, YOYO", "Xiaoyi, Xiaoyi", “Hi Siri") input by the user's voice.
  • waking up the voice assistant is rather cumbersome, resulting in a low user experience.
  • the present application provides a method for waking up an application and an electronic device, which not only realizes the waking up of the current application, but also prepares for the waking up of the next application, thereby improving the user experience.
  • the present application provides a method for waking up an application, which is applied to an electronic device, wherein the electronic device comprises: a first application, a breath waking up software module, and a breath waking up processing device;
  • the method includes:
  • the breath awakening processing device obtains first data
  • the breath awakening processing device sends the voice data in the first data to the breath awakening software module when detecting that the first data is used to indicate that the breath awakens the first application;
  • the breath awakening software module stores the voice data, starts the first application, and controls the breath awakening processing device to stop detecting the breath awakening of the first application and continue to obtain the voice data;
  • the breath awakening software module sends voice data to the first application in response to the first notification
  • the first application performs speech recognition on the speech data
  • the first application sends a second notification to the breath awakening software module when determining, based on the voice data, that the voice recognition is finished;
  • the breath awakening software module responds to the second notification and controls the breath awakening processing device to start detecting the first application program. The next breath of sequence awakens.
  • the breath awakening software module can start the first application, and use the breath awakening technology to wake up the first application, thereby ensuring the convenience and timeliness of starting the first application.
  • the breath awakening software module when the breath awakening software module starts the first application, it can control the breath awakening processing device to stop detecting the breath awakening of the first application, which can avoid interrupting the current voice recognition and ensure the quality of the current first application voice recognition.
  • the breath awakening software module can control the breath awakening processing device to start detecting the next breath awakening of the first application when the first application determines that the voice recognition is finished, so as to restore the breath awakening function of the first application and prepare for the next application awakening.
  • this application not only realizes the awakening of the current application, but also prepares for the awakening of the next application, thereby improving the user experience.
  • the method further includes:
  • the breath awakening processing device is controlled to start detecting the next breath awakening of the first application.
  • the breath awakening software module when the breath awakening software module does not receive the first notification or the second notification after a preset period of time, it can be determined that the current first application is not started, or the first application fails to call the breath awakening software module, so that the breath awakening software module cannot receive the first notification or the second notification.
  • the breath awakening software module can control the breath awakening processing device to start detecting the next breath awakening of the first application, so as to restore the breath awakening function of the voice assistant application.
  • the method further includes:
  • the first user interface is displayed
  • the first application displays the speech recognition result in the first user interface.
  • the breath awakening software module includes: a first software module, and a second software module, and the voice data is stored in the second software module;
  • a first notification is sent to the breath awakening software module, including:
  • the breath awakening software module sends voice data to the first application in response to the first notification, including:
  • the first software module calls the voice data from the second software module and sends the voice data to the first application.
  • the first software module can be an audio policy service module (audio policy service).
  • the second software module can be an audio driver (sound trigger-hal).
  • the first software module when the first application successfully calls the first software module, the first software module can call the voice data from the second software module and send the voice data to the first application, so that the first application can receive the voice data in time.
  • the method further includes:
  • the first software module sends a third notification to the second software module in response to the first notification
  • the second software module controls the breath awakening processing device to stop detecting the breath awakening of the first application and continue to obtain the voice data.
  • the second software module can respond to the third notification, control the breath awakening processing device to detect the breath awakening of the first application and continue to obtain voice data, and control the breath awakening processing device to stop detecting the breath awakening of the first application, so as to avoid interrupting the current voice recognition.
  • the quality of the current first application speech recognition is ensured again.
  • the breath awakening processing device stops detecting the breath awakening of the first application, which can also save power for the electronic device.
  • the breath awakening software module controls the breath awakening processing device to start detecting the next breath awakening of the first application in response to the second notification, including:
  • the first software module sends a fourth notification to the second software module in response to the second notification
  • the second software module controls the breath awakening processing device to start detecting the next breath awakening of the first application.
  • the breath awakening processing device when the breath awakening software module starts the first application, the breath awakening processing device can be controlled to stop detecting the breath awakening of the first application, and the second software module controls the breath awakening processing device to stop detecting the breath awakening of the first application in response to the third notification.
  • the second software module responds to the fourth notification and controls the breath wake-up processing device to start detecting the next breath wake-up of the first application, so as to facilitate the restoration of the breath wake-up function of the first application.
  • the breath awakening software module further includes a third software module and a fourth software module;
  • the breath awakening software module stores the voice data, starts the first application, controls the breath awakening processing device to stop detecting the breath awakening of the first application, and continues to obtain the voice data, including:
  • the second software module stores the voice data and sends a wake-up event to the third software module
  • the third software module sends the wake-up event to the fourth software module in response to the wake-up event, and sends a fifth notification to the second software module;
  • the fourth software module starts the first application in response to the wake-up event
  • the second software module controls the breath awakening processing device to stop detecting the breath awakening of the first application and continue to obtain the voice data.
  • the third software module can be a sound trigger module (sound trigger module).
  • the fourth software module may be an audio trigger module (sound trigger).
  • the fourth software module can start the first application in response to the wake-up event, thereby ensuring the timeliness of starting the first application.
  • controlling the breath wake-up processing device to stop detecting the breath wake-up of the first application can avoid interrupting the current voice recognition and ensure the quality of the current voice recognition of the first application.
  • the method further includes:
  • the third software module sets a timing time in response to the wake-up event and starts timing according to the timing time;
  • the sixth notification is sent to the second software module
  • the second software module controls the breath awakening processing device to start detecting the next breath awakening of the first application in response to the sixth notification;
  • the third software module turns off the timing of the timing time in response to the first notification.
  • the setting time of the timer can be used to determine whether the first notification or the second notification is received, so that when the first notification or the second notification is not received, the second software module controls the breath wake-up processing device to start detecting the next breath wake-up of the first application and restore the breath wake-up function.
  • the first application when the first application determines according to the voice data that the voice recognition ends, the first application sends a second notification to the breath awakening software module, including:
  • the first application determines, in response to an operation for instructing to end the speech recognition, that the speech recognition is ended;
  • the speech recognition is determined to be ended;
  • the first application When determining that the speech recognition is finished, the first application sends a second notification to the first software module.
  • the first application can determine whether the voice recognition is completed in two ways. One is to determine that the voice recognition is completed when the user's instruction to end the voice recognition is received. The other is to determine that the voice recognition is completed when the voice text corresponding to the voice data is determined to be a complete word or sentence.
  • the first application determines that the voice recognition is completed, it sends a second notification to the first software module to facilitate notifying the third software module.
  • the third software module can notify the second software module to control the breath awakening processing device to start detecting the next breath awakening of the first application.
  • the breath awakening processing device includes: an inertial detection sensor, a sound collection sensor, and an audio digital signal processor;
  • the first data includes: voice data and gesture data.
  • the breath awakening processing device obtains the first data, including:
  • the inertial detection sensor collects gesture data
  • the inertial detection sensor sends gesture data to the audio digital signal processor
  • the sound collection sensor collects voice data
  • the sound collection sensor sends voice data to the audio digital signal processor
  • the breath awakening processing device When the breath awakening processing device detects that the first data is used to indicate that the breath awakens the first application, the breath awakening processing device sends the voice data in the first data to the breath awakening software module, including:
  • the breath awakening processing device detects that the similarity between the gesture data and the preset awakening gesture data is greater than the first threshold, and the similarity between the voice data and the preset awakening breath data is greater than the second threshold, the voice data is sent to the breath awakening software module.
  • the inertial detection sensor can collect gesture data
  • the sound collection sensor can collect voice data
  • the breath awakening processing device can detect the gesture data collected by the inertial detection sensor and the voice data collected by the sound collection sensor.
  • the present application provides a device for waking up an application, and the device for triggering an electronic device to execute a function is used to execute the method for waking up an application in the first aspect and any possible design of the first aspect.
  • the present application provides an electronic device, comprising a processor; when the processor executes the computer code or instruction in the memory, the electronic device executes the first aspect and any possible design of the first aspect. Method to wake up the application.
  • the present application provides an electronic device comprising one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and when the computer programs are executed by the one or more processors, the electronic device executes the method for waking up an application in the first aspect and any possible design of the first aspect.
  • the present application provides a chip system comprising a processor for calling and running a computer program from a memory, so that an electronic device equipped with the chip system executes the method for waking up an application in the first aspect and any possible design of the first aspect.
  • the present application provides a computer-readable storage medium, including a computer program, which, when the computer program runs on an electronic device, enables the electronic device to execute the method for waking up an application in the first aspect and any possible design of the first aspect.
  • the present application provides a computer program product, which, when executed on a computer, enables the computer to execute the method for waking up an application in the first aspect and any possible design of the first aspect.
  • FIG1 is a schematic diagram of a scenario of a method for waking up an application program provided by an embodiment of the present application
  • FIG2 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application.
  • FIG3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application.
  • FIG4 is a schematic diagram of the structure of a breath awakening software module provided in one embodiment of the present application.
  • FIG5 is a flow chart of a method for waking up an application program provided by an embodiment of the present application
  • FIG6 is a flow chart of a method for waking up an application program provided by an embodiment of the present application.
  • FIGS. 7A-7E are schematic diagrams of a human-computer interaction interface provided in one embodiment of the present application.
  • first”, “second”, and “third” are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features.
  • a feature defined as “first”, “second”, and “third” may explicitly or implicitly include one or more of the features.
  • the electronic device After the electronic device collects voice data through a sound collection sensor (for example, a microphone), it sends it to a low-power audio digital signal processor (ADSP).
  • the ADSP detects the voice data through a voice wake-up model.
  • the ADSP When the ADSP detects that there is wake-up word data matching the preset wake-up word in the voice data, the ADSP sends the voice data to the wake-up software module. This process can be called first-level wake-up.
  • the wake-up software module performs text verification and voiceprint verification on the aforementioned voice data to determine whether the voice data matches the generated voiceprint model.
  • the wake-up software module can control the voice assistant application to start. This process can be called secondary wake-up.
  • the keyword wake-up voice assistant application has specific keywords. Each time it is woken up, the voice wake-up model can stop running once and start running once.
  • the electronic device After the electronic device collects voice data through the sound collection sensor and gesture data through the inertial detection sensor, it sends them to the low-power audio digital signal processor (ADSP).
  • the ADSP detects the voice data and gesture data through the breath awakening model.
  • the breath awakening model is used to detect the acquired voice data and gesture data, and to determine whether the similarity between the voice data and the preset awakening breath data is greater than a first threshold, and whether the similarity between the gesture data and the preset awakening gesture data is greater than a second threshold.
  • the original awakening model can be trained using sample awakening breath data and sample awakening gesture data to obtain a breath awakening model.
  • the ADSP When the ADSP detects that the similarity between the voice data and the preset wake-up breath data is greater than a first threshold, and the similarity between the gesture data and the preset wake-up gesture data is greater than a second threshold, the ADSP sends the voice data to the breath wake-up software module.
  • the breath wake-up software module controls the voice assistant application to start.
  • the present application may provide a method for waking up an application, an apparatus for waking up an application, an electronic device, a chip system, a computer-readable storage medium, and a computer program product.
  • the ADSP detects that the acquired voice data matches the preset wake-up breath data, and the gesture data matches the preset wake-up gesture data
  • the detected voice data is sent to the breath wake-up software module.
  • the breath wake-up software module stores the voice data, and controls the voice assistant application to start, and controls the ADSP to stop detecting the acquired data.
  • the breath wake-up software module may send voice data to the control voice assistant application, so that the control voice assistant application performs voice recognition on the voice data.
  • the voice assistant application determines that the voice recognition ends according to the voice data, it may notify the breath wake-up software module, and the breath wake-up software module may control the ADSP to restart and detect the next acquired data.
  • the current wake-up of the application is achieved, the user's interaction with the electronic device through the voice assistant is ensured, preparations are made for the next wake-up of the application, and the user experience is improved.
  • the method for waking up an application provided in the present application can be applied to an electronic device, which can be an electronic device with display hardware and corresponding software support.
  • the electronic device may be a mobile phone, a tablet computer, a wearable device, an in-vehicle device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant, a
  • UMPC ultra-mobile personal computer
  • a netbook a personal digital assistant
  • FIG. 1 shows a scenario diagram of a method for waking up an application provided in an embodiment of the present application.
  • the user can lift the electronic device, place the bottom of the electronic device close to the mouth, and speak into the microphone.
  • the electronic device After the electronic device collects the corresponding voice data when the user speaks through the microphone, and the corresponding gesture data when the user lifts the electronic device through the inertial detection sensor, it is sent to the low-power ADSP, and the ADSP detects the voice data and gesture data through the breath awakening model.
  • the ADSP detects that the similarity between the voice data and the preset awakening breath data is greater than the first threshold, and the similarity between the gesture data and the preset awakening gesture data is greater than the second threshold
  • the ADSP sends the voice data to the breath awakening software module.
  • the breath awakening software module controls the startup of the voice assistant.
  • the distance between the electronic device and the user's mouth can be maintained at 0-5cm, which makes it easier for the microphone of the electronic device to accurately collect the user's voice data.
  • gesture data may be gesture data of raising the wrist.
  • the user can lift the electronic device by raising the wrist gesture, and the inertial detection sensor can collect the gesture data of raising the wrist.
  • the user raises the electronic device through the wrist-raising gesture, he or she puts his or her mouth close to the microphone of the electronic device to speak, and can emit the breath indicated by part C.
  • the microphone can collect the breath and the voice data corresponding to the breath.
  • the electronic device 100 is taken as an example of a mobile phone.
  • the electronic device 100 may include a processor 101 and a communication module 102 .
  • the processor 101 may include one or more processing units, for example, the processor 101 may include an application processor (AP), a modem processor, a graphics processor, an image signal processor (ISP), a controller, a memory, a video stream codec, a digital signal processor (DSP), a baseband processor, and/or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated in one or more processors 101.
  • AP application processor
  • ISP image signal processor
  • DSP digital signal processor
  • NPU neural-network processing unit
  • the controller may be the nerve center and command center of the electronic device 100.
  • the controller may generate an operation control signal according to the instruction operation code and the timing signal to complete the control of fetching and executing instructions.
  • the processor 101 may also be provided with a memory for storing instructions and data.
  • the memory in the processor 101 is a high-speed cache memory.
  • the memory can store instructions or data that the processor 101 has just used or is cyclically used. If the processor 101 needs to use the instruction or data again, it can be directly called from the memory. This avoids repeated access and reduces the waiting time of the processor 101. And improve the efficiency of the system.
  • the processor 101 may include one or more interfaces.
  • the interface may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver/transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input/output (GPIO) interface, a subscriber identity module (SIM) interface, and/or a universal serial bus (USB) interface, etc.
  • I2C inter-integrated circuit
  • I2S inter-integrated circuit sound
  • PCM pulse code modulation
  • UART universal asynchronous receiver/transmitter
  • MIPI mobile industry processor interface
  • GPIO general-purpose input/output
  • SIM subscriber identity module
  • USB universal serial bus
  • the communication module 102 may include an antenna 1, an antenna 2, a mobile communication module, and/or a wireless communication module.
  • the electronic device 100 may further include an external memory interface 105 , an internal memory 104 , a USB interface 106 , a charging management module 107 , a power management module 108 , a battery 109 , and a sensor module 103 , etc.
  • NPU is a neural network (NN) computing processor.
  • NN neural network
  • applications such as intelligent cognition of electronic device 100 can be realized, such as image recognition, face recognition, voice recognition, text understanding, etc.
  • the charging management module 107 is used to receive charging input from a charger, where the charger can be a wireless charger or a wired charger.
  • the charging management module 107 may receive charging input from a wired charger through the USB interface 106 .
  • the charging management module 107 may receive wireless charging input via a wireless charging coil of the electronic device 100. While the charging management module 107 is charging the battery 109, it may also provide power to the electronic device 100 via the power management module 108.
  • the power management module 108 is used to connect the battery 109, the charging management module 107 and the processor 101.
  • the power management module 108 receives input from the battery 109 and/or the charging management module 107, and supplies power to the processor 101, the internal memory 104, the external memory, and the communication module 102.
  • the power management module 108 can also be used to monitor parameters such as battery capacity, battery cycle number, and battery health status (leakage, impedance).
  • the power management module 108 may also be disposed in the processor 101 .
  • the power management module 108 and the charging management module 107 may also be disposed in the same device.
  • the external memory interface 105 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100.
  • the external memory card communicates with the processor 101 through the external memory interface 105 to implement a data storage function. For example, files such as music and video streams are saved in the external memory card.
  • the internal memory 104 can be used to store computer executable program codes, and the executable program codes include instructions.
  • the processor 101 executes various functional applications and data processing of the electronic device 100 by running the instructions stored in the internal memory 104.
  • the internal memory 104 may include a program storage area and a data storage area.
  • the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.
  • the data storage area may store data created during the use of the electronic device 100 (such as audio data, a phone book, etc.), etc.
  • the internal memory 104 may include a high-speed random access memory, and may also include Non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.
  • the sensor module 103 in the electronic device 100 may include image sensors, touch sensors, pressure sensors, gyroscope sensors, air pressure sensors, magnetic sensors, acceleration sensors, distance sensors, proximity light sensors, ambient light sensors, fingerprint sensors, temperature sensors, bone conduction sensors and other components to realize sensing and/or acquisition functions for different signals.
  • the electronic device 100 may further include peripheral devices, such as a mouse, buttons, indicator lights, a keyboard, a speaker, a microphone, etc.
  • peripheral devices such as a mouse, buttons, indicator lights, a keyboard, a speaker, a microphone, etc.
  • the buttons include a power button, a volume button, etc.
  • the buttons may be mechanical buttons or touch buttons.
  • the electronic device 100 may receive button inputs and generate key signal inputs related to user settings and function controls of the electronic device 100.
  • the indicator may be a light indicator, which may be used to indicate the charging status and the change in the power level, and may also be used to indicate messages, missed calls, and notifications, etc.
  • the electronic device 100 may include more or fewer components than shown, or combine some components, or separate some components, or arrange the components differently.
  • the components shown may be implemented in hardware, software, or a combination of software and hardware.
  • Figure 3 is a schematic diagram of an electronic device provided in an embodiment of the present application.
  • the software in the electronic device 100 can be divided into an application layer 201, an application framework layer 202, and a driver layer 203 as shown in Figure 3.
  • multiple applications may be installed in the application layer 201, which may include a first application, etc.
  • the first application may be a voice assistant application (application, APP).
  • the application framework layer 202 may include an audio trigger module (sound trigger), a sound trigger module (sound trigger module), an audio policy service module (audio policy service), etc.
  • the application framework layer 202 may also include an audio service module (audio service), an audio trigger service module (sound trigger service), an audio indication module (audio flinger), etc.
  • the audio trigger module is used to control the startup of the voice assistant application of the application layer 201.
  • the sound trigger module is used to send a wake-up event to the audio trigger module, and to send a notification to the audio driver of the driver layer 203 to instruct the breath wake-up model to stop running or start running.
  • the audio strategy service module is used to establish a voice recognition channel with the voice assistant application of the application layer 201.
  • the audio service module is used to send a startup notification to the audio trigger module in response to the startup notification sent by the voice assistant application of the application layer 201.
  • the audio trigger module is also used to send a startup notification to the audio trigger service module in response to the startup notification sent by the audio service module.
  • the audio trigger service module is used to send a startup notification to the sound trigger module in response to the startup notification sent by the audio trigger module.
  • the sound trigger module is also used to send a notification to the audio policy service module to start running the breath awakening model in response to the startup notification sent by the audio trigger module.
  • the audio policy service module starts the notification to run the breath awakening model in response to the notification to start running the breath awakening model.
  • the audio indication module is used to send a notification to load the breath awakening model to the audio driver of the driver layer 203 in response to the notification of loading the breath awakening model sent by the audio policy service module.
  • the audio driver of the driver layer 203 is used to send a notification to the audio digital signal processor of the breath awakening processing device to indicate the start of running the breath awakening. Model notifications.
  • the driver layer 203 is a layer between hardware and software.
  • the driver layer 203 may include an audio driver (sound trigger-hal) and the like.
  • the driver layer 203 may be installed with a plurality of drivers for driving the hardware.
  • application layer 201 may also include other contents, which are not specifically limited here.
  • FIG. 3 also shows a breath awakening processing device connected to the driving layer 203 .
  • the breath awakening processing device may at least include an inertia detection sensor, a sound collection sensor, and an audio digital signal processor.
  • the inertial detection sensor is used to collect gesture data.
  • the sound collection sensor is used to collect voice data.
  • the audio signal processor is used to obtain the gesture data collected by the inertial detection sensor and the voice data collected by the sound collection sensor, and detect the gesture data and the voice data.
  • the application framework layer 202 may include a breath awakening software module.
  • the breath awakening software module can include an audio framework and an audio driver (sound trigger-hal).
  • the audio framework may include an audio trigger module (sound trigger), a sound trigger module (sound trigger module), and an audio policy service module (audio policy service).
  • sound trigger sound trigger
  • sound trigger module sound trigger module
  • audio policy service module audio policy service
  • the breath awakening processing device may include an audio digital signal processor (ADSP), a sound collection sensor, and an inertial detection sensor.
  • ADSP audio digital signal processor
  • the sound collection sensor and the inertial detection sensor are both connected to the audio digital signal processor.
  • FIG5 is a flowchart of a method for waking up an application provided in the present application.
  • the method can be divided into three different phases, namely, a preparation phase, a start-up phase, and an identification phase.
  • the preparation stage can be understood as the stage of starting the breath awakening function of the voice assistant application so that the breath awakening model in the audio digital signal processor is in a continuous running state.
  • the startup phase can be understood as the phase of controlling the startup of the voice assistant application when the voice data and gesture data used to wake up the voice assistant application are obtained.
  • the recognition stage can be understood as the stage in which the voice assistant application performs voice recognition on the voice data and determines whether to start or stop the breath awakening model based on the status of the voice recognition.
  • the method for waking up the application program of the present application may include:
  • the electronic device can display a method for waking up the voice assistant application in a setting interface.
  • This application does not limit the specific implementation method of the setting interface.
  • the above-mentioned setting interface may include a breath wake-up control, which is used to trigger the breath wake-up function of starting the voice assistant application.
  • this application does not limit the display position, display style, display size and other parameters of the breath wake-up control.
  • the electronic device can start the voice assistant application. Breath awakening function.
  • the voice assistant application sends a notification to the audio trigger module to instruct the audio trigger module to start.
  • the voice assistant application can send a startup notification to the audio trigger module, and the audio trigger module can be started in response to the startup notification.
  • the audio trigger module can receive and send data.
  • the audio trigger module is started in response to the notification for instructing to start the audio trigger module, and sends a notification for instructing to start the sound trigger module to the sound trigger module.
  • the audio trigger module can send a start notification to the sound trigger module, and the sound trigger module can be started in response to the start notification.
  • the sound trigger module can receive and send data.
  • the sound trigger module is started in response to the notification for instructing to start the sound trigger module, and sends a notification for instructing to start running the breath awakening model to the audio driver.
  • the audio driver controls the breath awakening model in the audio digital signal processor to start running in response to the notification for instructing to start running the breath awakening model.
  • the sound trigger module can send a notification to the audio driver to instruct the start of the breath awakening model.
  • the audio driver After receiving the notification for instructing to start running the breath awakening model, the audio driver can control the breath awakening model in the audio digital signal processor to start running.
  • S16 The audio digital signal processor runs the breath awakening model in response to the notification instructing to start running the breath awakening model.
  • the audio digital signal processor is a low-power digital signal processor.
  • the breath wake-up model can be in a continuously running state on the audio digital signal processor, which is convenient for real-time detection of the received voice data and gesture data.
  • the received data can be continuously detected to determine whether the received data is used to wake up the voice assistant application.
  • the data for waking up the voice assistant application is used to indicate that the similarity between the acquired voice data and the preset wake-up breath data is greater than a first threshold, and the similarity between the gesture data and the preset wake-up gesture data is greater than a second threshold.
  • the electronic device can start the breath wake-up function of the voice assistant application, so that the user can wake up the voice assistant by breath wake-up, ensuring the convenience of waking up the voice assistant application and improving the user experience.
  • the breath wake-up model can be in a continuously running state on the audio digital signal processor, detecting the received data in real time to determine whether the received data is used to wake up the voice assistant application, so as to facilitate waking up the voice assistant application in time when the received data is used to wake up the voice assistant application.
  • the sound collection sensor sends voice data to the audio digital signal processor
  • the sound collection sensor can collect voice data in real time, and after collecting the voice data, the voice data can be sent to Audio digital signal processor.
  • the sound collection sensor is a microphone (MIC).
  • the inertial detection sensor sends gesture data to the audio digital signal processor
  • the inertial detection sensor can collect gesture data in real time, and after collecting the gesture data, the gesture data can be sent to the audio digital signal processor.
  • the audio digital signal processor only receives the voice data sent by the sound collection sensor.
  • the breath awakening model in the audio digital signal processor receives the voice data sent by the sound collection sensor, it detects the voice data.
  • the audio digital signal processor only receives the gesture data sent by the hand inertia detection sensor.
  • the breath awakening model in the audio digital signal processor receives the gesture data sent by the inertia detection sensor, it detects the gesture data.
  • the audio digital signal processor simultaneously receives the gesture data sent by the inertial detection sensor and the voice data sent by the sound collection sensor.
  • the breath awakening model in the audio digital signal processor receives the voice data sent by the sound collection sensor and the gesture data sent by the inertial detection sensor, it can detect the received voice data and gesture data.
  • the audio digital signal processor may determine that the voice data and the gesture data are data for waking up the voice assistant application. Thus, the audio digital signal processor may trigger a wake-up event.
  • the gesture data is wrist-raising gesture data.
  • the gesture data is wrist-raising gesture data
  • the electronic device is a mobile phone
  • the sound collection sensor is a microphone.
  • the microphone when the user lifts up the mobile phone and puts the microphone of the mobile phone close to his mouth to speak, the microphone can collect voice data corresponding to the user's words and send the voice data to the audio digital signal processor.
  • the inertial detection sensor can collect gesture data corresponding to raising the wrist when the user lifts up the mobile phone, and send the gesture data to the audio digital signal processor.
  • the audio digital signal processor After receiving the above-mentioned voice data and gesture data, the audio digital signal processor detects the voice data and gesture data through the breath wake-up model. When it is determined that the similarity between the voice data and the preset wake-up breath data is greater than the first threshold, and the similarity between the gesture data and the preset wake-up gesture data is greater than the second threshold, the audio digital signal processor can trigger a wake-up event.
  • the audio digital signal processor sends voice data to the audio driver.
  • the audio digital signal processor can send the acquired voice data to the audio driver.
  • the audio driver can start storing voice data to prepare data for the voice assistant application to obtain the voice data.
  • the audio driver triggers the buffer to store voice data.
  • the audio driver After receiving the voice data, the audio driver can trigger the audio driver's buffer to store the voice. Data.
  • the voice assistant application can prepare the data for obtaining the voice data.
  • the audio driver can send a wake-up event to the sound trigger module, so that the sound trigger module can continue to send wake-up events to the audio trigger module.
  • S21 and S22 have no particular order in terms of timing, and can be executed sequentially or simultaneously.
  • the sound trigger module sends a notification to the audio driver to instruct the audio driver to stop running the breath awakening model.
  • the sound trigger module may send a notification to the audio driver to instruct it to stop running the breath wake-up model.
  • the awakening event Since the awakening event has been triggered, it can be regarded as consuming one awakening event, and the breath awakening model can stop running.
  • the audio digital signal processor can determine that the received data is data for waking up the voice assistant application and trigger a wake-up event.
  • the voice assistant application can be woken up based on the voice data, and there is no need for the breath wake-up model in the audio digital signal processor to detect again whether the acquired voice data is the data for waking up the voice assistant application.
  • the audio driver can control the breath wake-up model in the audio digital signal processor to stop running, that is, the breath wake-up model no longer detects whether the received data is the user's wake-up voice, and only needs to continue to receive voice data.
  • the sound trigger module starts a timer in response to the wake-up event.
  • the sound trigger module can also start a timer to facilitate the sound trigger module to determine whether a notification indicating the start of voice recognition or a notification indicating the end of voice recognition is received within the timing of the timer.
  • the sound trigger module can determine whether the audio strategy service module is successfully called through the setting time of the timer, so as to send a notification to the audio driver to instruct the start of the breath awakening model when the call is unsuccessful.
  • the timing period of the timer is 1-5s.
  • the timing period of the timer is 3s.
  • S23, S25, and S26 have no particular order in terms of timing and can be executed sequentially or simultaneously.
  • the sound trigger module sends the wake-up event to the audio trigger module.
  • the sound trigger module after receiving the wake-up event, can also send a wake-up event to the audio trigger module, so that the audio trigger module can control the startup of the voice assistant application after receiving the wake-up event.
  • the audio trigger module controls the voice assistant application to start in response to the wake-up event.
  • the audio trigger module After receiving the wake-up event, the audio trigger module can determine that the voice assistant application needs to be started. Thus, the audio trigger module can control the voice assistant application to start.
  • the electronic device can display a user interface.
  • This application does not limit the specific implementation method of the user interface.
  • the user interface can be displayed in a partial area of the current interface of the electronic device, or it can be displayed in a part of the current interface of the electronic device.
  • the current interface is a different interface.
  • the above-mentioned setting interface may include a voice assistant floating ball control, which is used to remind the user that the voice assistant application has been started and to trigger the voice assistant application to end voice recognition.
  • a voice assistant floating ball control which is used to remind the user that the voice assistant application has been started and to trigger the voice assistant application to end voice recognition.
  • this application does not limit the display position, display style, display size and other parameters of the voice assistant floating ball control.
  • the user can determine that the voice assistant application has been started.
  • the breath wake-up model in the audio digital signal processor can be in a continuous running state until it is determined that the similarity between the received voice data and the preset wake-up breath data is greater than the first threshold, and the similarity between the received gesture data and the preset wake-up gesture data is greater than the second threshold, the audio digital signal processor can trigger a wake-up event.
  • the audio digital signal processor can start to report the wake-up event step by step, and control the startup of the voice assistant application through the audio trigger module, ensuring the convenience and timeliness of the startup of the voice assistant application.
  • breath-awakening voice assistant technology does not require wake-up words and trigger buttons, simplifies the voice interaction steps, and starts the voice assistant application more quickly.
  • this breath-awakening voice assistant technology allows users to directly approach electronic devices to have conversations, which improves the accuracy of user interaction with electronic devices, reduces the risk of conversation content leakage in terms of privacy protection, and avoids interference with others.
  • the voice assistant application after the voice assistant application is started, it can start to call the sound policy server.
  • the call to the sound policy server is successful, the channel between the voice assistant application and the sound policy server can be opened.
  • the voice assistant application calls the sound policy server
  • success and failure there may be two situations: success and failure.
  • the voice assistant application may fail to call the sound policy server.
  • the recording function of the electronic device is turned on, the audio channel of the sound policy server is occupied, and the voice assistant application cannot successfully call the sound policy server.
  • the voice assistant application when it successfully calls the voice policy server, it can send a notification to the voice policy server to indicate the start of voice recognition.
  • the notification for indicating the start of voice recognition is used to indicate that the voice assistant application is able to receive voice data and recognize the voice data.
  • the sound policy server calls voice data from the audio driver in response to the notification indicating the start of voice recognition.
  • the sound policy server can receive a notification indicating the start of voice recognition.
  • the voice policy server can determine that the voice assistant should be used after the notification indicating the start of voice recognition.
  • the application can receive voice data and recognize the voice data.
  • the sound policy server calls the voice data from the audio driver to facilitate sending the voice data to the voice assistant application.
  • the sound policy server can carry voice data from the audio driver's buffer via a stream from an audio source 1999.
  • the voice policy server After the voice policy server receives the voice data from the audio driver, it sends the voice data to the voice assistant application.
  • the sound policy server After the sound policy server calls the audio data from the audio driver's buffer, it can send the voice data to the voice assistant application to facilitate the voice assistant application to recognize the voice data.
  • the voice assistant application After receiving the voice data, the voice assistant application recognizes the received voice data.
  • the voice assistant application recognizes the received voice data, not only recognizes the meaning of the voice data, but also converts the voice data into text.
  • the sound policy server In response to the notification for instructing the start of speech recognition, the sound policy server sends a notification for instructing the start of speech recognition to the sound trigger module.
  • the sound policy server may send the notification for indicating the start of speech recognition to the sound trigger module, so as to prepare for the sound trigger module to perform the next operation according to the notification for indicating the start of speech recognition.
  • S292 and S295 have no particular order in terms of timing and can be executed sequentially or simultaneously.
  • the sound trigger module turns off the timer in response to the notification indicating the start of voice recognition.
  • the sound trigger module receives a notification indicating the start of voice recognition, it can be determined that the voice assistant application has successfully called the sound policy server.
  • the sound trigger module has started the timer.
  • the sound trigger module can turn off the timer and start the timer to prepare for the next time the voice assistant application is woken up.
  • turning off the timer can also minimize the power consumption of electronic devices.
  • the sound trigger module sends a notification to the audio driver indicating the stop of the breath awakening model.
  • S297 is an optional step.
  • S297 is similar to that of S23 in the embodiment shown in FIG5 , and will not be further elaborated in this application.
  • the voice assistant application when the voice assistant application is performing voice recognition, if the breath awakening model is running, the awakening event may be triggered again, causing the current voice recognition to be interrupted.
  • the sound trigger module has sent a notification to the audio driver to instruct the stop running of the breath awakening model, and the breath awakening model can stop running.
  • the sound trigger module can send a notification to the audio driver again to instruct the stop running of the breath awakening model, so as to prevent the breath awakening model from starting and triggering the awakening event again.
  • S293 and S296 have no particular order in terms of timing and can be executed sequentially or simultaneously.
  • S298 is an optional step.
  • S298 is implemented in a similar manner to S24 in the embodiment shown in FIG5 , and will not be described in detail in this application.
  • the voice assistant application determines that the voice recognition has ended based on the voice data, the voice assistant application sends a notification indicating the end of the voice recognition to the sound policy server.
  • the voice assistant application can use multiple methods to determine the end of voice recognition based on voice data.
  • the voice assistant application when the voice assistant application receives the user's operation of triggering the voice assistant floating ball control in S28 according to the voice data, it can be determined that the user wants to end the voice recognition. Thus, the voice assistant application can end the voice recognition in response to the operation on the voice assistant floating ball control.
  • the voice assistant application determines that voice recognition ends when it determines that the voice text corresponding to the received voice data is a complete word or sentence.
  • the voice assistant application can determine that “Have you eaten today?” is a complete sentence, and the voice assistant application can determine that the voice recognition is finished.
  • the voice assistant application can determine that “eat today” is not a complete sentence, and the voice assistant application can determine that the voice recognition is not finished.
  • the voice assistant application can determine that the voice recognition is finished.
  • the voice assistant application determines that the voice recognition is finished according to the voice data, the voice assistant application displays the voice recognition result.
  • the speech recognition result may be text data corresponding to the speech data, or may be an interaction result corresponding to the user data.
  • the voice assistant application may convert the voice data into text during the process of recognizing the voice data and display it on the user interface in S28.
  • the voice assistant application when the voice data is “Today's weather”, after the voice assistant application recognizes “Today's weather”, it can display the text data corresponding to “Today's weather” on the user interface.
  • the voice assistant application may display the interaction results corresponding to the voice data on the user interface in S28 after the voice data recognition is completed.
  • the voice assistant application can determine that the user wants to know today's weather conditions, and can display the actual conditions such as the current temperature, maximum temperature, and minimum temperature corresponding to today's weather on the user interface.
  • the sound policy server In response to a notification indicating the end of speech recognition, the sound policy server sends a notification indicating the end of speech recognition to a sound trigger module.
  • the sound policy server may send the notification indicating the end of speech recognition to the sound trigger module, so as to prepare for the sound trigger module to perform the next operation according to the notification indicating the end of speech recognition.
  • the sound trigger module In response to the notification indicating the end of speech recognition, the sound trigger module sends a notification indicating the start of the breath awakening model to the audio driver.
  • the sound trigger module can send a notification to the audio driver to instruct the start of the breath wake-up model, so that the sound trigger module can control the audio digital signal
  • the breath awakening model in the processor starts running, so that the breath awakening model in the audio digital signal processor can detect the data received next time.
  • the audio driver can control the breath awakening model in the audio digital signal processor to start running, so as to restore the breath awakening function of the voice assistant application, so that the breath awakening model in the audio digital signal processor can detect the data received next time.
  • the sound trigger module does not receive a notification indicating the start of speech recognition or a notification indicating the end of speech recognition at the end of the timer, it sends a notification to the audio driver to instruct the start of the breath awakening model.
  • the “ ⁇ ” between the voice assistant application and the audio policy service module is used to indicate that the voice assistant application failed to call the audio policy service module.
  • the sound trigger module can receive a notification indicating the start of voice recognition.
  • the sound trigger module can receive a notification indicating the end of voice recognition.
  • the sound trigger module does not receive a notification indicating the start of voice recognition or a notification indicating the end of voice recognition at the end of the timer, it can be determined that the sound trigger module has failed to call the voice assistant application.
  • the sound trigger module can send a notification to the audio driver to instruct the start-up of the breath wake-up model, so that the audio driver can control the start-up of the breath wake-up model in the audio digital signal processor.
  • S312 In response to the notification for instructing to start running the breath awakening model, the audio driver controls the breath awakening model in the audio digital signal processor to start running.
  • S312 is implemented in a similar manner to S303 in the embodiment shown in FIG5 , and will not be described in detail in this application.
  • the sound trigger module can send a notification to the audio driver to stop running the breath wake-up module, so that the audio driver controls the breath wake-up model to stop running and avoid interrupting the current speech recognition.
  • the sound trigger module can send a notification to the audio driver to start running the breath wake-up module, so that the audio driver controls the breath wake-up model to start running, thereby facilitating the restoration of the breath wake-up function of the voice assistant application.
  • the sound trigger module when it does not receive a notification indicating the start of voice recognition or a notification indicating the end of voice recognition at the end of the timer's set time, it can send a notification to the audio driver to start running the breath wake-up module, so that the audio driver controls the breath wake-up model to start running, thereby facilitating the restoration of the breath wake-up function of the voice assistant application.
  • the sound trigger module can send a notification to the audio driver to start the breath wake-up module, so that the audio driver controls the breath wake-up model to start running, thereby facilitating the restoration of the breath wake-up function of the voice assistant application.
  • the sound trigger module can send a message to the audio driver at the right time to start the breath wake-up mode.
  • the notification of the block makes it easy for the audio driver to control the breath wake-up model to start running, which can not only avoid the interruption of the current voice recognition, but also ensure that the voice assistant application can be woken up normally next time.
  • the breath wake-up function when the electronic device receives an operation to start the breath wake-up function of the voice assistant application, the breath wake-up function is started, so that the user can wake up the voice assistant by breath wake-up, thereby improving the user experience.
  • the breath wake-up model can be in a continuously running state on the audio digital signal processor, so that when the received data is data for waking up the voice assistant application, the wake-up event is triggered in time, so that the voice assistant application can be woken up.
  • the breath wake-up module in the audio digital signal processor determines that the similarity between the received voice data and the preset breath wake-up data is greater than a first threshold, and the similarity between the received gesture data and the preset wake-up gesture data is greater than a second threshold, it can trigger a wake-up event and report the wake-up event step by step.
  • the voice assistant application is started by controlling the sound trigger module, thereby ensuring the convenience and timeliness of the startup of the voice assistant application.
  • the sound trigger module can send a notification to the audio driver to start the breath wake-up module, so that the audio driver controls the breath wake-up model to start running, thereby facilitating the restoration of the breath wake-up function of the voice assistant application.
  • the method of waking up the voice assistant application with breath in the present application is suitable for a variety of target customers, such as white-collar workers, civil servants and office workers who use voice assistant applications (accounting for more than 80% of users and covering a wider range of usage scenarios).
  • the method of awakening a voice assistant application by breath in the present application is applicable to multiple typical scenarios, for example, in relatively quiet public places such as coffee shops, western restaurants, or high-speed rail/airport lounges; when users are at subway stations, airports, train stations, etc., queuing to enter the station with luggage in their hands; when users are at supermarkets, shopping malls, etc., holding things in their hands to select and buy goods; when users are walking their dogs outdoors; when users drive into/out of parking lots, toll booths, communities/parks, and their hands are just freed from the steering wheel of the car.
  • the breath awakening voice assistant application method of the present application is applicable to a variety of needs, does not require wake-up words and trigger buttons, simplifies the voice interaction steps, and starts the voice assistant application more quickly.
  • users can directly approach the conversation, which improves the accuracy of the user's interaction with the electronic device, reduces the risk of conversation content leakage in terms of privacy protection, and avoids interference with others.
  • the present application provides a method for waking up an application.
  • the method for waking up an application in the present application may be executed by the electronic device in FIG. 2 .
  • FIG. 6 shows a flow chart of a method for waking up an application program provided in an embodiment of the present application.
  • the method for waking up an application provided in the present application is applied to an electronic device, and the electronic device includes: a first application, a breath-awakening software module, and a breath-awakening processing device.
  • the electronic device may be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a home appliance, or the like.
  • UMPC ultra-mobile personal computer
  • PDA personal digital assistant
  • the breath awakening software module may include a first software module, a third software module, a second software module, and a fourth software module.
  • the first software module may be an audio policy service module (audio policy service).
  • the third software module may be a sound trigger module.
  • the second software module can be an audio driver (sound trigger-hal).
  • the fourth software module may be an audio trigger module (sound trigger).
  • the breath awakening processing device may include an audio digital signal processor (ADSP), a sound collection sensor, and an inertial detection sensor.
  • ADSP audio digital signal processor
  • the breath awakening processing device may include an audio digital signal processor (ADSP), a sound collection sensor, and an inertial detection sensor.
  • ADSP audio digital signal processor
  • the sound collection sensor may be a microphone.
  • the method for waking up an application provided by the present application may include:
  • the breath awakening processing device obtains first data.
  • the first data may be data received by the audio digital signal sensor in S19 in FIG. 5 .
  • S101 can be found in the description of S17-S19 in FIG5 , which will not be elaborated here.
  • S102 can be found in the description of S19-S20 in FIG5 , which will not be elaborated here.
  • the breath awakening software module stores the voice data, starts the first application, and controls the breath awakening processing device to stop detecting the breath awakening of the first application and continue to obtain the voice data.
  • the first application can be a voice assistant application.
  • S103 can refer to the description of S21-S24 in FIG5 , which will not be described in detail here.
  • the first notification may refer to the description of the notification for indicating the start of speech recognition in S291 in FIG. 5 .
  • S104 can refer to the description of S21-S27 in FIG5 , which will not be described in detail here.
  • the breath awakening software module sends voice data to the first application in response to the first notification.
  • S106 The first application performs speech recognition on the speech data.
  • S106 can refer to the description of S296 in Figure 5, which will not be repeated here.
  • the first application determines according to the voice data that the voice recognition is finished, the first application sends a second notification to the breath awakening software module.
  • the second notification may refer to the description of the notification for indicating the end of speech recognition in S299 in FIG. 5 .
  • S107 can be found in the description of S299 in FIG. 5 , which will not be described in detail here.
  • the breath awakening software module controls the breath awakening processing device to start detecting the next breath awakening of the first application in response to the second notification.
  • S108 can refer to the description of S301-302 in FIG. 5 , which will not be described in detail here.
  • the breath awakening processing device detects the first data for indicating the breath awakening of the first application
  • the first application can be started through the breath awakening software module, thereby ensuring the convenience and timeliness of starting the first application.
  • the breath awakening processing device can be controlled to stop detecting the breath awakening of the first application, thereby avoiding interruption of the current voice recognition.
  • the breath awakening software module can control the breath awakening software module when the first application determines that the voice recognition ends.
  • the processing device starts detecting the next breath awakening of the first application program, so as to restore the breath awakening function of the first application program.
  • the method for waking up an application program of the present application may further include:
  • the breath awakening processing device is controlled to start detecting the next breath awakening of the first application.
  • the breath awakening software module when it does not receive the first notification or the second notification after a preset period of time, it controls the breath awakening processing device to start detecting the next breath awakening of the first application, so as to restore the breath awakening function of the voice assistant application.
  • the method for waking up an application program of the present application may further include:
  • a first user interface is displayed.
  • the first application displays the speech recognition result in the first user interface.
  • the first user interface may refer to interface 14 in FIG. 7D to FIG. 7E , and the description of the user interfaces in S28 and S300 in FIG. 5 .
  • the first user interface can display the voice recognition result, so that the user can understand the voice recognition result in time, thereby improving the user's usage experience.
  • the breath awakening software module includes: a first software module and a second software module, and the voice data is stored in the second software module.
  • the method of waking up an application program of the present application may include:
  • Step 201 After the first application is started, when the first software module is successfully called, a first notification is sent to the first software module.
  • step 201 can be found in the description of S291 in FIG. 5 , which will not be described in detail here.
  • Step 202 In response to the first notification, the first software module calls the voice data from the second software module and sends the voice data to the first application.
  • step 202 can be found in the description of S293-S295 in Figure 5, and will not be repeated here.
  • the first software module can call the voice data from the second software module and send the voice data to the first application, so that the first application can receive the voice data in time.
  • the method for waking up an application program of the present application may further include:
  • Step 301 In response to a first notification, a first software module sends a third notification to a second software module.
  • step 301 may include: the first software module sends the first notification to the third software module in response to the first notification; the third software module sends the third notification to the second software module in response to the first notification.
  • the third notification may refer to the description of the notification for instructing to stop running the breath awakening model in S297 in FIG. 5 .
  • step 301 can be found in the description of S295 and S297 in FIG. 5 , which will not be described in detail here.
  • Step 302 In response to the third notification, the second software module controls the breath awakening processing device to stop detecting the breath awakening of the first application and continue to obtain voice data.
  • step 302 The specific implementation method of step 302 can be found in the description of S297-S298 in Figure 5, and will not be repeated here.
  • controlling the breath awakening processing device to stop detecting the breath awakening of the first application can avoid interrupting the current voice recognition, and can again ensure the quality of the current first application voice recognition.
  • the method of waking up an application program of the present application may include:
  • Step 401 In response to the second notification, the first software module sends a fourth notification to the second software module.
  • Step 401 may include: the first software module sends the second notification to the third software module in response to the second notification, and the third software module sends a fourth notification to the second software module in response to the second notification.
  • the fourth notification may refer to the description of the notification for instructing to start running the breath awakening model in S302 in FIG. 5 .
  • step 401 can refer to the description of S301-S302 in FIG. 5 , which will not be described in detail here.
  • Step 402 In response to the fourth notification, the second software module controls the breath awakening processing device to start detecting the next breath awakening of the first application.
  • step 402 can be found in the description of S303 in FIG. 5 , and will not be described in detail here.
  • the second software module controls the breath awakening processing device in response to the fourth notification to start detecting the next breath awakening of the first application, so as to restore the breath awakening function of the first application.
  • the breath awakening software module further includes a third software module and a fourth software module.
  • the method of waking up an application program of the present application may include:
  • Step 501 The second software module stores voice data and sends a wake-up event to the third software module.
  • step 501 can be found in the description of S22 in FIG. 5 , and will not be described in detail here.
  • Step 502 In response to the wake-up event, the third software module sends a wake-up event to the fourth software module and sends a fifth notification to the second software module.
  • the fifth notification may refer to the description of the notification for instructing to stop running the breath awakening model in S23 in FIG. 5 .
  • step 502 can be found in the description of S23 and S26 in FIG. 5 , and will not be described in detail here.
  • Step 503 The fourth software module starts the first application in response to the wake-up event.
  • step 503 can be found in the description of S27 in FIG. 5 , which will not be described in detail here.
  • Step 504 In response to the fifth notification, the second software module controls the breath awakening processing device to stop detecting the breath awakening of the first application and continue to obtain voice data.
  • step 504 can be found in the description of S24 in FIG. 5 , which will not be described in detail here.
  • the fourth software module can start the first application in response to the wake-up event, thereby ensuring the timeliness and accuracy of starting the first application.
  • controlling the breath wake-up processing device to stop detecting the breath wake-up of the first application can avoid interrupting the current voice recognition and ensure the quality of the current voice recognition of the first application.
  • the method for waking up an application program of the present application may further include:
  • Step 601 The third software module sets a timing time in response to a wake-up event and starts timing according to the timing time.
  • step 601 can be found in the description of S25 in FIG. 5 , which will not be described in detail here.
  • Step 602 When the third software module determines that the timing time has expired and has not received the first notification or the second notification, the third software module sends a sixth notification to the second software module.
  • For the sixth notification please refer to the description of the notification for instructing to start running the breath awakening model in S311 in FIG. 5 .
  • step 602 can be found in the description of S311 in FIG. 5 , and will not be described in detail here.
  • Step 603 In response to the sixth notification, the second software module controls the breath awakening processing device to start detecting the next breath awakening of the first application.
  • step 603 can be found in the description of S312 in FIG. 5 , which will not be described in detail here.
  • Step 604 The third software module turns off the timing of the timing time in response to the first notification.
  • step 604 can be found in the description of S293 in FIG. 5 , which will not be described in detail here.
  • the setting time of the timer can be used to determine whether the first notification or the second notification is received, so that when the first notification or the second notification is not received, the second software module controls the breath wake-up processing device to start the next breath wake-up of the first application and restore the breath wake-up function.
  • the method of waking up an application program of the present application may include:
  • the first application determines that the voice recognition is ended in response to an operation for instructing to end the voice recognition.
  • the voice recognition is determined to be finished.
  • the first application When determining that the speech recognition is finished, the first application sends a second notification to the first software module.
  • the preset rule is that the voice text corresponding to the voice data is a complete word or sentence.
  • the first application can determine whether the voice recognition is completed through the above two methods.
  • the breath awakening processing device includes: an inertial detection sensor, a sound collection sensor, and an audio digital signal processor.
  • the first data includes: voice data and gesture data.
  • the method of waking up an application program of the present application may include:
  • Step 701 The inertial detection sensor collects gesture data
  • Step 702 The inertial detection sensor sends gesture data to the audio digital signal processor.
  • step 701 and step 702 can be found in the description of S18 in FIG. 5 , and will not be described in detail here.
  • Step 703 The sound collection sensor collects voice data
  • Step 704 The sound collection sensor sends voice data to the audio digital signal processor.
  • step 703 and step 704 can be found in the description of S17 in FIG. 5 , which will not be described in detail here.
  • Step 705 When the breath awakening processing device detects that the similarity between the gesture data and the preset awakening gesture data is greater than the first threshold, and the similarity between the voice data and the preset awakening breath data is greater than the second threshold, the voice data is sent to the breath awakening software module.
  • step 703 and step 704 can be found in the description of S19 in FIG. 5 , which will not be described in detail here.
  • the inertial detection sensor can collect gesture data
  • the sound collection sensor can collect voice data
  • the breath awakening processing device can detect the gesture data collected by the inertial detection sensor and the voice data collected by the sound collection sensor.
  • the electronic device is a mobile phone
  • the first application is a voice assistant
  • the mobile phone may display an interface 11 as shown in FIG. 7A , and the interface 11 is used to display icons of various application programs (applications, APPs) installed on the mobile phone.
  • the interface 11 may include: a control 101.
  • the control 101 is used to display an icon for setting an APP.
  • the mobile phone After receiving a user triggering operation (such as a click, double-click or long press operation, etc.) on the control 101 shown in FIG. 7A , the mobile phone may change from the interface 11 shown in FIG. 7A to the interface 12 shown in FIG. 7B .
  • a user triggering operation such as a click, double-click or long press operation, etc.
  • the interface 12 may include: a control 102.
  • the control 102 is used to trigger the setting interface of the voice assistant application.
  • the mobile phone may change from displaying the interface 12 shown in FIG. 7B to displaying the interface 13 shown in FIG. 7C .
  • the interface 13 may include: a control 103.
  • the control 103 is used to trigger the breath wake-up function of starting the voice assistant application.
  • the mobile phone After receiving the user's triggering operation on the control 103 shown in FIG. 7C , the mobile phone activates the breath wake-up function of the voice assistant application.
  • the voice assistant application can notify the breath awakening software module to start, and the breath awakening software module can notify the breath awakening processing device to detect the acquired data.
  • the breath awakening processing device detects that the acquired data is data for the breath awakening voice assistant application
  • the voice data in the data is sent to the breath awakening software module.
  • the breath awakening software module stores the voice data and controls the voice assistant application to start. After the voice assistant application is started, the mobile phone can display the interface 14 shown in FIG. 7D.
  • the breath awakening software module can also control the breath awakening processing device to stop detecting the received data and continue to receive the voice data in the above data.
  • the interface 14 may include a control 105.
  • the control 105 is used to remind the user that the voice assistant application has been started and to trigger the voice assistant application to end voice recognition.
  • the breath awakening software module can send voice data to the voice assistant application.
  • the voice assistant application can convert the voice data into text data.
  • the interface 14 can also include a control 104.
  • the control 104 is used to display the text data corresponding to the voice data.
  • the voice data is “Today's weather”
  • the text data displayed in the control 104 is “Today's weather”.
  • the mobile phone can display an interface 14 as shown in FIG. 7D .
  • the voice assistant application determines that the voice recognition is completed according to the voice data, it notifies the breath awakening software module, and the breath awakening software module can control the breath awakening processing device to restart and recognize the next received data. That is, the breath awakening function of the voice assistant application is restored.
  • the interface 14 may further include a control 106.
  • the control 106 is used to display the speech recognition result of the voice assistant application.
  • the voice recognition result displayed by the control 106 may be "City A, mostly cloudy, 10% chance of rainfall, current temperature 14°C, maximum temperature 17°C, minimum temperature 11°C".
  • the voice assistant application can be awakened by breath awakening, and after the voice assistant application determines that the voice recognition is completed, the breath awakening software module can control the breath awakening processing device to restart and recognize the next received data.
  • the present application provides a document processing device, which may include one or more modules for executing the method of waking up an application in the foregoing embodiment.
  • the present application provides an electronic device, including a processor; when the processor executes computer code or instructions in the memory, the electronic device executes the method of waking up the application in the above embodiment.
  • the present application provides an electronic device, comprising one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and when the computer programs are executed by the one or more processors, the electronic device executes the method for waking up the application in the foregoing embodiments.
  • the electronic device includes hardware and/or software modules corresponding to the execution of each function.
  • the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application in combination with the embodiments, but such implementation should not be considered to exceed the scope of the present application.
  • the electronic device can be divided into functional modules according to the above method example.
  • each functional module can be divided according to each function, or two or more functions can be integrated into one processing module.
  • the above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation.
  • the electronic device involved in the above embodiment may also include: a receiving module and a determining module.
  • the receiving module and the determining module cooperate with each other to support the electronic device to perform the above steps and/or other processes of the technology described in this article.
  • the electronic device provided in this embodiment is used to execute the above method of waking up the application program, and thus can achieve the same effect as the above implementation method.
  • the present application provides a chip system, which includes a processor for calling and running a computer program from a memory, so that an electronic device equipped with the chip system executes the method of waking up the application in the foregoing embodiment.
  • the present application provides a computer-readable storage medium, in which codes or instructions are stored.
  • the electronic device implements the method of waking up the application in the foregoing embodiment.
  • the present application provides a computer program product, which, when executed on a computer, enables an electronic device to implement the method for waking up an application in the foregoing embodiment.
  • the electronic device, computer-readable storage medium, computer program product or chip system provided in this embodiment is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above and will not be repeated here.
  • the disclosed devices and methods can be implemented in other ways.
  • the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.
  • Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
  • the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium.
  • the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the methods of each embodiment of the present application.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • General Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Acoustics & Sound (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Artificial Intelligence (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

本申请提供了一种唤醒应用程序的方法及电子设备，该方法包括：气息唤醒处理装置在检测出获取到的第一数据用于指示气息唤醒第一应用程序时，发送第一数据中的语音数据；气息唤醒软件模块存储语音数据，启动第一应用程序，控制气息唤醒处理装置停止检测第一应用程序的气息唤醒；第一应用程序在调用气息唤醒软件模块成功时，发送第一通知；气息唤醒软件模块向第一应用程序发送语音数据；第一应用程序对语音数据进行语音识别；第一应用程序在根据语音数据确定语音识别结束时发送第二通知；气息唤醒软件模块响应于第二通知控制气息唤醒处理装置启动下一次气息唤醒。从而，不仅实现了应用程序的唤醒，还为应用程序的唤醒做好了准备。

Description

唤醒应用程序的方法及电子设备
本申请要求于2022年11月16日提交国家知识产权局、申请号为202211438531.X、申请名称为“唤醒应用程序的方法及电子设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请属于终端技术领域，尤其涉及一种唤醒应用程序的方法及电子设备。
背景技术
随着语音识别技术的发展，许多电子设备中添加了语音助手(例如YOYO、小艺、Siri等)，帮助用户完成与电子设备的人机交互过程。一般而言，语音助手处于休眠状态，用户想要使用语音助手时，可以对语音助手进行唤醒。
目前，唤醒语音助手主要包括按键唤醒、和关键词唤醒这两种技术。按键唤醒的技术中，通过接收到的用户对按键(例如电源键)进行触发的操作，实现语音助手的唤醒。关键词唤醒的技术中，通过接收到的用户语音输入的特定唤醒词(例如，“你好，YOYO”、“小艺，小艺”、“Hi Siri”)，实现语音助手的唤醒。
然而，上述的实现过程中，唤醒语音助手的较为繁琐，使用户的体验不高。
发明内容
本申请提供了一种唤醒应用程序的方法及电子设备，不仅实现了当前次应用程序的唤醒，还为下一次应用程序的唤醒做好了准备，提高了用户的使用体验。
第一方面，本申请提供一种唤醒应用程序的方法，应用于电子设备，电子设备包括：第一应用程序、气息唤醒软件模块、和气息唤醒处理装置；
该方法包括：
气息唤醒处理装置获取第一数据；
气息唤醒处理装置在检测出第一数据用于指示气息唤醒第一应用程序时，向气息唤醒软件模块发送第一数据中的语音数据；
气息唤醒软件模块存储语音数据，启动第一应用程序，控制气息唤醒处理装置停止检测第一应用程序的气息唤醒且继续获取语音数据；
第一应用程序在启动后，调用气息唤醒软件模块成功时，向气息唤醒软件模块发送第一通知；
气息唤醒软件模块响应于第一通知，向第一应用程序发送语音数据；
第一应用程序对语音数据进行语音识别；
第一应用程序在根据语音数据确定语音识别结束时，向气息唤醒软件模块发送第二通知；
气息唤醒软件模块响应于第二通知，控制气息唤醒处理装置启动检测第一应用程 序的下一次气息唤醒。
上述方法，气息唤醒处理装置在检测出第一数据用于指示气息唤醒第一应用程序时，气息唤醒软件模块可启动第一应用程序，采用气息唤醒的技术唤醒第一应用程序，保证了第一应用程序启动的便捷性和及时性。
另外，气息唤醒软件模块启动第一应用程序时，可控制气息唤醒处理装置停止检测第一应用程序的气息唤醒，可以避免中断掉当前次的语音识别，保证了当前次第一应用程序语音识别的质量。
此外，气息唤醒软件模块可在第一应用程序确定语音识别结束时，控制气息唤醒处理装置启动检测第一应用程序的下一次气息唤醒，便于恢复第一应用程序的气息唤醒的功能，为下一次应用程序的唤醒做好准备。
可见，本申请不仅实现了当前次应用程序的唤醒，还为下一次应用程序的唤醒做好了准备，提高了用户的使用体验。
结合第一方面，在第一方面的某些实现方式中，该方法还包括：
气息唤醒软件模块在经过预设时长，未接收到第一通知，或者第二通知时，控制气息唤醒处理装置启动检测第一应用程序的下一次气息唤醒。
上述方法，气息唤醒软件模块在经过预设时长，未接收到第一通知，或者第二通知时，可确定当前第一应用程序未启动，或者第一应用程序调用气息唤醒软件模块未成功，使得气息唤醒软件模块收不到第一通知，或者第二通知。
从而，气息唤醒软件模块可控制气息唤醒处理装置启动检测第一应用程序的下一次气息唤醒，便于恢复语音助手应用程序的气息唤醒的功能。
结合第一方面，在第一方面的某些实现方式中，该方法还包括：
第一应用程序在启动后，显示第一用户界面；
第一应用程序在第一用户界面中显示语音识别结果。
其中，第一用户界面可以显示语音识别结果，便于用户能够及时了解语音识别结果，提高了用户的使用体验。
结合第一方面，在第一方面的某些实现方式中，气息唤醒软件模块包括：第一软件模块、和第二软件模块，语音数据存储在第二软件模块中；
第一应用程序在启动后，调用气息唤醒软件模块成功时，向气息唤醒软件模块发送第一通知，包括：
第一应用程序在启动后，调用第一软件模块成功时，向第一软件模块发送第一通知；
气息唤醒软件模块响应于第一通知，向第一应用程序发送语音数据，包括：
第一软件模块响应于第一通知，从第二软件模块中调用语音数据，向第一应用程序发送语音数据。
其中，第一软件模块可以为音频策略服务模块(audio policy service)。
第二软件模块可以为音频驱动(sound trigger-hal)。
上述方法中，第一应用程序在调用第一软件模块成功时，第一软件模块可从第二软件模块中调用语音数据，向第一应用程序发送语音数据，便于第一应用程序能够及时的接收到语音数据。
结合第一方面，在第一方面的某些实现方式中，该方法还包括：
第一软件模块响应于第一通知，向第二软件模块发送第三通知；
第二软件模块响应于第三通知，控制气息唤醒处理装置停止检测第一应用程序的气息唤醒且继续获取语音数据。
上述方法中，第二软件模块能够响应于第三通知，控制气息唤醒处理装置检测第一应用程序的气息唤醒且继续获取语音数据，控制气息唤醒处理装置停止检测第一应用程序的气息唤醒，可以避免中断掉当前次的语音识别。
再次保证了当前次第一应用程序语音识别的质量，气息唤醒处理装置停止检测第一应用程序的气息唤醒，还可以起到为电子设备省电的效果。
结合第一方面，在第一方面的某些实现方式中，气息唤醒软件模块响应于第二通知，控制气息唤醒处理装置启动检测第一应用程序的下一次气息唤醒，包括：
第一软件模块响应于第二通知，向第二软件模块发送第四通知；
第二软件模块响应于第四通知，控制气息唤醒处理装置启动检测第一应用程序的下一次气息唤醒。
上述方法中，由于气息唤醒软件模块启动第一应用程序时，可控制气息唤醒处理装置停止检测第一应用程序的气息唤醒，以及，第二软件模块响应于第三通知，控制气息唤醒处理装置停止检测第一应用程序的气息唤醒。
可见，当前控制气息唤醒处理装置已停止检测第一应用程序的气息唤醒，由此，第二软件模块响应于第四通知，控制气息唤醒处理装置启动检测第一应用程序的下一次气息唤醒，便于恢复第一应用程序的气息唤醒的功能。
结合第一方面，在第一方面的某些实现方式中，气息唤醒软件模块还包括第三软件模块和第四软件模块；
气息唤醒软件模块存储语音数据，启动第一应用程序，控制气息唤醒处理装置停止检测第一应用程序的气息唤醒，且继续获取语音数据，包括：
第二软件模块存储语音数据，向第三软件模块发送唤醒事件；
第三软件模块响应于唤醒事件，向第四软件模块发送唤醒事件，以及向第二软件模块发送第五通知；
第四软件模块响应于唤醒事件，启动第一应用程序；
第二软件模块响应于第五通知，控制气息唤醒处理装置停止检测第一应用程序的气息唤醒且继续获取语音数据。
其中，第三软件模块可以为声音触发模块(sound trigger module)。
第四软件模块可以为音频触发模块(sound trigger)。
上述方法中，第四软件模块响应于唤醒事件时，可启动第一应用程序，保证了第一应用程序启动的及时性。
另外，由于已触发唤醒事件，控制气息唤醒处理装置停止检测第一应用程序的气息唤醒，可以避免中断掉当前次的语音识别，保证了当前次第一应用程序语音识别的质量。
结合第一方面，在第一方面的某些实现方式中，方法还包括：
第三软件模块响应于唤醒事件，设定定时时间，并根据所述定时时间开始计时；
第三软件模块确定所述定时时间计时结束时，未接收到第一通知，或者第二通知时，向第二软件模块发送第六通知；
第二软件模块响应于第六通知，控制气息唤醒处理装置启动检测第一应用程序的下一次气息唤醒；
第三软件模块响应于第一通知，关闭定时时间的计时。
上述方法中，可通过定时器的设置时间，来确定是否收到第一通知或者第二通知，便于在未接收到第一通知，或者第二通知时，第二软件模块控制气息唤醒处理装置启动检测第一应用程序的下一次气息唤醒，恢复气息唤醒功能。
结合第一方面，在第一方面的某些实现方式中，第一应用程序在根据语音数据确定语音识别结束时，向气息唤醒软件模块发送第二通知，包括：
第一应用程序响应于用于指示结束语音识别的操作，确定语音识别结束；
或者，第一应用程序确定语音数据对应的语音文本满足预设规则时，确定语音识别结束；
第一应用程序在确定语音识别结束时，向第一软件模块发送第二通知。
其中，第一应用程序可通过两种方式，判断语音识别是否结束，一种为接收到用户指示的结束语音识别的操作时，确定语音识别结束，另一种为，确定语音数据对应的语音文本为一个完整的词语或者句子时，确定语音识别结束。
另外，第一应用程序在确定语音识别结束时，向第一软件模块发送第二通知，便于通知第三软件模块，第三软件模块能够通知第二软件模块，控制气息唤醒处理装置启动检测第一应用程序的下一次气息唤醒。
结合第一方面，在第一方面的某些实现方式中，气息唤醒处理装置包括：惯性检测传感器、声音采集传感器、和音频数字信号处理器；
第一数据中包括：语音数据和手势数据，气息唤醒处理装置获取第一数据，包括：
惯性检测传感器采集到手势数据；
所述惯性检测传感器向音频数字信号处理器发送手势数据；
声音采集传感器采集到语音数据；
所述声音采集传感器向音频数字信号处理器发送语音数据；
气息唤醒处理装置在检测出第一数据用于指示气息唤醒第一应用程序时，向气息唤醒软件模块发送第一数据中的语音数据，包括：
气息唤醒处理装置在检测出手势数据与预设唤醒手势数据之间的相似度大于第一阈值，且语音数据与预设唤醒气息数据之间的相似度大于第二阈值时，向气息唤醒软件模块发送语音数据。
上述方法中，惯性检测传感器可采集手势数据，声音采集传感器可采集语音数据。
气息唤醒处理装置可对惯性检测传感器采集到的手势数据，以及声音采集传感器采集到的语音数据进行检测。
第二方面，本申请提供一种唤醒应用程序的装置，该实现触发电子设备执行功能的装置用于执行第一方面及第一方面任一种可能的设计中的唤醒应用程序的方法。
第三方面，本申请提供一种电子设备，包括处理器；当处理器执行存储器中的计算机代码或指令时，使得电子设备执行第一方面及第一方面任一种可能的设计中的唤 醒应用程序的方法。
第四方面，本申请提供一种电子设备，包括一个或多个处理器；存储器；以及一个或多个计算机程序，其中一个或多个计算机程序存储在存储器上，当计算机程序被一个或多个处理器执行时，使得电子设备执行第一方面及第一方面任一种可能的设计中的唤醒应用程序的方法。
第五方面，本申请提供一种芯片系统，该芯片系统包括处理器，用于从存储器中调用并运行计算机程序，使得安装有芯片系统的电子设备执行第一方面及第一方面任一种可能的设计中的唤醒应用程序的方法。
第六方面，本申请提供一种计算机可读存储介质，包括计算机程序，当计算机程序在电子设备上运行时，使得电子设备执行第一方面及第一方面任一种可能的设计中的唤醒应用程序的方法。
第七方面，本申请提供一种计算机程序产品，当计算机程序产品在计算机上运行时，使得计算机执行第一方面及第一方面任一种可能的设计中的唤醒应用程序的方法。
可以理解的是，上述第二方面至第七方面的有益效果可以参见上述第一方面中的相关描述，在此不再赘述。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本申请一实施例提供的一种唤醒应用程序的方法的场景示意图；
图2为本申请一实施例提供的一种电子设备的结构示意图；
图3为本申请一实施例提供的一种电子设备的结构示意图；
图4为本申请一实施例提供的一种气息唤醒软件模块的结构示意图；
图5为本申请一实施例提供的一种唤醒应用程序的方法的流程示意图；
图6为本申请一实施例提供的一种唤醒应用程序的方法的流程示意图；
图7A-图7E为本申请一实施例提供的一种人机交互界面示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行描述。其中，在本申请实施例的描述中，除非另有说明，“/”表示或的意思，例如，A/B可以表示A或B；本文中的“和/或”仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，在本申请实施例的描述中，“多个”是指两个或多于两个。
以下，术语“第一”、“第二”、“第三”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”、“第三”的特征可以明示或者隐含地包括一个或者更多个该特征。
应理解，对于关键词唤醒语音助手应用程序(application，APP)而言：
电子设备通过声音采集传感器(例如，麦克风)采集到语音数据后，发送到低功耗的音频数字信号处理器(audio digital signal processing，ADSP)，ADSP通过语音唤醒模型检测该语音数据。
当ADSP检测到该语音数据中存在与预设的唤醒词匹配的唤醒词数据时，ADSP将语音数据发送给唤醒软件模块。其中，此过程可称为一级唤醒。
由唤醒软件模块对前述语音数据进行文本校验和声纹校验，以判断该语音数据是否与生成的声纹模型匹配。当语音数据与声纹模型匹配时，唤醒软件模块则可以控制语音助手应用程序启动。其中，此过程可称为二级唤醒。
其中，关键词唤醒语音助手应用程序，存在特定的关键词，每经过一次唤醒，语音唤醒模型可停止运行一次，并启动运行一次。
对于气息唤醒语音助手应用程序而言：
电子设备通过声音采集传感器采集到语音数据，以及通过惯性检测传感器采集到手势数据后，发送到低功耗的音频数字信号处理器(audio digital signal processing，ADSP)，ADSP通过气息唤醒模型检测该语音数据和手势数据。
其中，气息唤醒模型用于对获取到的语音数据和手势数据进行检测，并判断语音数据是否与预设唤醒气息数据之间的相似度大于第一阈值，以及手势数据是否与预设唤醒手势数据之间的相似度大于第二阈值。
另外，可通过样本唤醒气息数据和样本唤醒手势数据，对原始唤醒模型进行训练，得到气息唤醒模型。
当ADSP检测到该语音数据与预设唤醒气息数据之间的相似度大于第一阈值，且该手势数据与预设唤醒手势数据之间的相似度大于第二阈值时，ADSP将语音数据发送给气息唤醒软件模块。由气息唤醒软件模块控制语音助手应用程序启动。
可见，对于气息唤醒语音助手应用程序而言，仅存在一级唤醒的过程。
本申请可提供一种唤醒应用程序的方法、唤醒应用程序的装置、电子设备、芯片系统、计算机可读存储介质、以及计算机程序产品，ADSP可在检测到获取的语音数据与预设唤醒气息数据匹配，且手势数据与预设唤醒手势数据匹配时，将检测到的语音数据发送给气息唤醒软件模块。气息唤醒软件模块存储该语音数据，以及控制语音助手应用程序启动，控制ADSP停止对获取到的数据进行检测。语音助手应用程序启动后，且在调用气息唤醒软件模块成功时，气息唤醒软件模块可向控制语音助手应用程序发送语音数据，使得控制语音助手应用程序对语音数据进行语音识别。另外，语音助手应用程序在根据语音数据确定语音识别结束时，可通知气息唤醒软件模块，气息唤醒软件模块可控制ADSP重新启动对下一次获取到的数据进行检测。
从而，实现了应用程序当前次的唤醒，保证了用户通过语音助手与电子设备的交互，为应用程序的下一次唤醒做好了准备，提高了用户的使用体验。
其中，本申请提供的唤醒应用程序的方法，可以应用于电子设备。电子设备可以为具有显示屏硬件以及相应软件支持的电子设备。
例如，电子设备可以为手机、平板电脑、可穿戴设备、车载设备、笔记本电脑、超级移动个人计算机(ultra-mobile personal computer，UMPC)、上网本、个人数 字助理(personal digital assistant，PDA)、家居设备等设备，本申请对电子设备的具体类型不作任何限制。
请参阅图1，图1示出了本申请一实施例提供的一种唤醒应用程序的方法的场景示意图。
如图1所示，用户可抬起电子设备，将电子设备的底部靠近嘴边，对准麦克风说话。
电子设备通过麦克风采集到用户说话时对应的语音数据，以及通过惯性检测传感器采集到用户抬起电子设备对应的手势数据后，发送到低功耗的ADSP，ADSP通过气息唤醒模型检测该语音数据和手势数据。当ADSP检测到该语音数据与预设唤醒气息数据之间的相似度大于第一阈值，且该手势数据与预设唤醒手势数据之间的相似度大于第二阈值时，ADSP将语音数据发送给气息唤醒软件模块。气息唤醒软件模块控制语音助手启动。
其中，电子设备与用户的嘴部之间的距离可保持在0-5cm，便于电子设备的麦克风准确采集用户的语音数据。
另外，上述手势数据可以为抬腕的手势数据。
其中，图1中从左图的框A部分指示的手势状态，到右图的框B部分指示的手势状态可以看出，用户可通过抬腕的手势抬起电子设备，惯性检测传感器能够采集到该抬腕的手势数据。
图1中从右图可以看出，用户在通过抬腕的手势抬起电子设备后，嘴部靠近电子设备的麦克风说话，可发出C部分指示的气息，麦克风能够采集到该气息，以及气息对应的语音数据。
应理解，上述为对场景的举例说明，并不对本申请的场景作任何限定。
为了便于说明，图2中，以电子设备100为手机为例进行示意。
如图2所示，在一些实施例中，电子设备100可以包括处理器101和通信模块102等。
其中，处理器101可以包括一个或多个处理单元，例如：处理器101可以包括应用处理器(application processor，AP)，调制解调处理器，图形处理器，图像信号处理器(image signal processor，ISP)，控制器，存储器，视频流编解码器，数字信号处理器(digital signal processor，DSP)，基带处理器，和/或神经网络处理器(neural-network processing unit，NPU)等。其中，不同的处理单元可以是独立的器件，也可以集成在一个或多个处理器101中。
控制器可以是电子设备100的神经中枢和指挥中心。控制器可以根据指令操作码和时序信号，产生操作控制信号，完成取指令和执行指令的控制。
处理器101中还可以设置存储器，用于存储指令和数据。
在一些实施例中，处理器101中的存储器为高速缓冲存储器。该存储器可以保存处理器101刚用过或循环使用的指令或数据。如果处理器101需要再次使用该指令或数据，可从存储器中直接调用。避免了重复存取，减少了处理器101的等待时间，因 而提高了系统的效率。
在一些实施例中，处理器101可以包括一个或多个接口。接口可以包括集成电路(inter-integrated circuit，I2C)接口，集成电路内置音频(inter-integrated circuit sound，I2S)接口，脉冲编码调制(pulse code modulation，PCM)接口，通用异步收发传输器(universal asynchronous receiver/transmitter，UART)接口，移动产业处理器接口(mobile industry processor interface，MIPI)，通用输入输出(general-purpose input/output，GPIO)接口，用户标识模块(subscriber identity module，SIM)接口，和/或通用串行总线(universal serial bus，USB)接口等。
通信模块102可以包括天线1，天线2，移动通信模块，和/或无线通信模块。
如图2所示，在一些实施例中，电子设备100还可以包括外部存储器接口105、内部存储器104，USB接口106、充电管理模块107、电源管理模块108、电池109、和传感器模块103等。
NPU为神经网络(neural-network，NN)计算处理器，通过借鉴生物神经网络结构，例如借鉴人脑神经元之间传递模式，对输入信息快速处理，还可以不断的自学习。通过NPU可以实现电子设备100的智能认知等应用，例如：图像识别，人脸识别，语音识别，文本理解等。
充电管理模块107用于从充电器接收充电输入。其中，充电器可以是无线充电器，也可以是有线充电器。
在一些有线充电的实施例中，充电管理模块107可以通过USB接口106接收有线充电器的充电输入。
在一些无线充电的实施例中，充电管理模块107可以通过电子设备100的无线充电线圈接收无线充电输入。充电管理模块107为电池109充电的同时，还可以通过电源管理模块108为电子设备100供电。
电源管理模块108用于连接电池109，充电管理模块107与处理器101。电源管理模块108接收电池109和/或充电管理模块107的输入，为处理器101，内部存储器104，外部存储器，和通信模块102等供电。电源管理模块108还可以用于监测电池容量，电池循环次数，电池健康状态(漏电，阻抗)等参数。
在其他一些实施例中，电源管理模块108也可以设置于处理器101中。
在另一些实施例中，电源管理模块108和充电管理模块107也可以设置于同一个器件中。
外部存储器接口105可以用于连接外部存储卡，例如Micro SD卡，实现扩展电子设备100的存储能力。外部存储卡通过外部存储器接口105与处理器101通信，实现数据存储功能。例如将音乐，视频流等文件保存在外部存储卡中。
内部存储器104可以用于存储计算机可执行程序代码，可执行程序代码包括指令。处理器101通过运行存储在内部存储器104的指令，从而执行电子设备100的各种功能应用以及数据处理。内部存储器104可以包括存储程序区和存储数据区。其中，存储程序区可存储操作系统，至少一个功能所需的应用程序(比如声音播放功能，图像播放功能等)等。存储数据区可存储电子设备100使用过程中所创建的数据(比如音频数据，电话本等)等。此外，内部存储器104可以包括高速随机存取存储器，还可以包括 非易失性存储器，例如至少一个磁盘存储器件，闪存器件，通用闪存存储器(universal flash storage，UFS)等。
电子设备100中的传感器模块103可以包括图像传感器、触摸传感器、压力传感器、陀螺仪传感器、气压传感器、磁传感器、加速度传感器、距离传感器、接近光传感器、环境光传感器、指纹传感器、温度传感器、骨传导传感器等部件，以实现对于不同信号的感应和/或获取功能。
可选地，电子设备100还可以包括外设设备，例如鼠标、按键、指示灯、键盘、扬声器、麦克风等。
按键包括开机键，音量键等。按键可以是机械按键。也可以是触摸式按键。电子设备100可以接收按键输入，产生与电子设备100的用户设置以及功能控制有关的键信号输入。
指示器可以是指示灯，可以用于指示充电状态和电量变化，也可以用于指示消息、未接来电、和通知等。
可以理解的是，本实施例示意的结构并不构成对电子设备100的具体限定。
在另一些实施例中，电子设备100可以包括比图示更多或更少的部件，或者组合某些部件，或者拆分某些部件，或者不同的部件布置。图示的部件可以以硬件，软件或软件和硬件的组合实现。
请参考图3，为本申请实施例提供的一种电子设备的示意图。本申请实施例提供的唤醒应用程序的方法应用于图2所示的电子设备100时，电子设备100中的软件可以划分为如图3所示的应用程序层201、应用程序框架层202、和驱动层203。
如图3所示，应用程序层201中可以安装有多个应用程序，其中可以包括第一应用程序等。例如，第一应用程序可以为语音助手应用程序(application，APP)。
应用程序框架层202可以包括音频触发模块(sound trigger)、声音触发模块(sound trigger module)、音频策略服务模块(audio policy service)等。另外，应用程序框架层202还可以包括音频服务模块(audio service)、音频触发服务模块(sound trigger service)、音频指示模块(audio flinger)等。
其中，音频触发模块用于控制应用程序层201的语音助手应用程序启动。声音触发模块用于向音频触发模块发送唤醒事件，以及向驱动层203的音频驱动发送用于指示气息唤醒模型停止运行或者启动运行的通知。音频策略服务模块用于与应用程序层201的语音助手应用程序之间建立语音识别通道。
另外，音频服务模块器用于响应于应用程序层201的语音助手应用程序发送的启动通知，向音频触发模块发送启动通知。音频触发模块还用于响应于音频服务模块器发送的启动通知向音频触发服务模块器发送启动通知。音频触发服务模块用于响应于音频触发模块发送的启动通知，向声音触发模块发送启动通知。声音触发模块还用于响应于音频触发模块发送的启动通知，向音频策略服务模块发送启动运行气息唤醒模型的通知。音频策略服务模块响应于启动运行气息唤醒模型的通知，启动运行气息唤醒模型的通知。音频指示模块用于响应于音频策略服务模块发送的加载气息唤醒模型的通知，向驱动层203的音频驱动发送加载气息唤醒模型的通知。驱动层203的音频驱动用于向气息唤醒处理装置的音频数字信号处理器发送用于指示启动运行气息唤醒 模型的通知。
驱动层203是硬件和软件之间的层。驱动层203可以包括音频驱动(sound trigger-hal)等。
驱动层203中可以安装有多个用于驱动硬件工作的驱动(driver)。
需要说明的是，应用程序层201，应用程序框架层202以及驱动层203中也可以包括其他内容，在此不做具体限定。
此外，图3中还示出了与驱动层203连接的气息唤醒处理装置。
示例性的，如图3所示，该气息唤醒处理装置至少可以包括惯性检测传感器、声音采集传感器、和音频数字信号处理器等。
其中，惯性检测传感器用于采集手势数据。声音采集传感器用于采集语音数据。音频信号处理器用于获取惯性检测传感器采集的手势数据和声音采集传感器采集的语音数据，并对该手势数据和语音数据进行检测。
其中，应用程序框架层202可以包括气息唤醒软件模块。
气息唤醒软件模块可以包括音频框架和音频驱动(sound trigger-hal)。
如图4所示，音频框架可以包括音频触发模块(sound trigger)、声音触发模块(sound trigger module)、音频策略服务模块(audio policy service)。
如图5所示，气息唤醒处理装置可以包括音频数字信号处理器(audio digital signal processing，ADSP)、声音采集传感器、和惯性检测传感器。声音采集传感器、和惯性检测传感器皆与音频数字信号处理器连接。
下面，结合图5，详细介绍本申请的唤醒应用程序的方法的具体实现过程。
图5是本申请提供的一例唤醒应用程序的方法的流程示意图。
如图5所示，该方法可以划分为三个不同的阶段，分别为准备阶段、启动阶段、和识别阶段。
准备阶段可理解为启动语音助手应用程序的气息唤醒功能，使得音频数字信号处理器中的气息唤醒模型处于持续运行状态的阶段。
启动阶段可理解为在获取到用于唤醒语音助手应用程序的语音数据和手势数据时，控制启动语音助手应用程序的阶段。
识别阶段可理解为语音助手应用程序对语音数据进行语音识别，并根据语音识别的状态确定气息唤醒模型启动运行或者停止运行状态的阶段。
如图5所示，本申请的唤醒应用程序的方法可以包括：
【准备阶段】
S11、启动语音助手应用程序的气息唤醒功能。
电子设备可在一个设置界面显示唤醒语音助手应用程序的方式。本申请对设置界面的具体实现方式不做限定。
在一些实施例中，上述设置界面中可以包括气息唤醒控件，该气息唤醒控件用于触发启动语音助手应用程序的气息唤醒功能。
其中，本申请对气息唤醒控件的显示位置、显示样式、显示大小等参数不做限定。
从而，在接收到气息唤醒控件上的操作后，电子设备可启动语音助手应用程序的 气息唤醒功能。
S12、语音助手应用程序向音频触发模块发送用于指示启动音频触发模块的通知。
其中，语音助手应用程序在启动气息唤醒功能后，可向音频触发模块发送启动通知，音频触发模块可响应于启动通知启动。
从而，音频触发模块在启动后，能够接收数据和发送数据。
S13、音频触发模块响应于用于指示启动音频触发模块的通知启动，并向声音触发模块发送用于指示启动声音触发模块的通知。
其中，音频触发模块在启动后，能够向声音触发模块发送启动通知，声音触发模块可响应于启动通知启动。
从而，声音触发模块在启动后，能够接收数据和发送数据。
S14、声音触发模块响应于用于指示启动声音触发模块的通知启动，并向音频驱动发送用于指示启动运行气息唤醒模型的通知。
S15、音频驱动响应于用于指示启动运行气息唤醒模型的通知，控制音频数字信号处理器中的气息唤醒模型启动运行。
声音触发模块在启动后，可向音频驱动发送用于指示启动运行气息唤醒模型的通知。
音频驱动在接收到用于指示启动运行气息唤醒模型的通知后，可控制音频数字信号处理器中的气息唤醒模型启动运行。
由此，为音频数字信号处理器运行气息唤醒模块做好了数据准备。
S16、音频数字信号处理器响应于用于指示启动运行气息唤醒模型的通知，运行气息唤醒模型。
应理解，音频数字信号处理器为低功耗的数字信号处理器，在语音助手应用程序启动气息唤醒功能后，气息唤醒模型可在音频数字信号处理器上处于持续运行的状态，便于实时对接收到的语音数据和手势数据进行检测。
气息唤醒模型在运行过程中，可持续对接收到的数据进行检测，判断接收到的数据是否为用于唤醒语音助手应用程序的数据。
唤醒语音助手应用程序的数据用于表示获取到的语音数据与预设唤醒气息数据之间的相似度大于第一阈值，且手势数据与预设唤醒手势数据之间的相似度大于第二阈值。
综上，电子设备可在接收到用户指示的在气息唤醒控件上执行的操作后，启动语音助手应用程序的气息唤醒功能，便于用户能够通过气息唤醒的方式，唤醒语音助手，保证了唤醒语音助手应用程序的便捷性，提高了用户的使用体验。
另外，语音助手应用程序的气息唤醒功能启动后，气息唤醒模型可在音频数字信号处理器上处于持续运行的状态，实时对接收到的数据进行检测，判断接收到的数据是否为用于唤醒语音助手应用程序的数据，便于在接收到的数据为用于唤醒语音助手应用程序的数据时，及时唤醒语音助手应用程序。
【启动阶段】
S17、声音采集传感器向音频数字信号处理器发送语音数据；
声音采集传感器可实时采集语音数据，在采集到语音数据后可将语音数据发送到 音频数字信号处理器。
在一些实施例中，声音采集传感器为麦克风(microphone，MIC)。
S18、惯性检测传感器向音频数字信号处理器发送手势数据；
惯性检测传感器可实时采集手势数据，在采集到手势数据后可将手势数据发送到音频数字信号处理器。
S19、音频数字信号处理器检测出接收到的数据用于指示唤醒语音助手应用程序时，触发唤醒事件。
基于S16的描述，可以确定音频数字信号处理器中的气息唤醒模型处于持续运行的状态。也就是说，存在三种情况：
音频数字信号处理器仅接收到声音采集传感器发送的语音数据。音频数字信号处理器中的气息唤醒模型接收到声音采集传感器发送的语音数据时，对该语音数据进行检测。
音频数字信号处理器仅接收到手惯性检测传感器发送的势数据。音频数字信号处理器中的气息唤醒模型接收到惯性检测传感器发送的手势数据时，对该手势数据进行检测。
音频数字信号处理器同时接收到惯性检测传感器发送的手势数据、和声音采集传感器发送的语音数据。音频数字信号处理器中的气息唤醒模型接收到声音采集传感器发送的语音数据，以及接收到惯性检测传感器发送的手势数据时，可对接收到的语音数据和手势数据进行检测。
在确定语音数据与预设唤醒气息数据之间的相似度大于第一阈值，且手势数据与预设唤醒手势数据之间的相似度大于第二阈值时，音频数字信号处理器可确定该语音数据和手势数据为用于唤醒语音助手应用程序的数据。从而，音频数字信号处理器可触发唤醒事件。
在一些实施例中，手势数据为抬腕的手势数据。
假设手势数据为抬腕的手势数据，电子设备为手机，声音采集传感器为麦克风。
结合图1，在用户抬起手机，将手机的麦克风靠近嘴边说话时，麦克风可采集用户说的话对应的语音数据，并向音频数字信号处理器发送该语音数据，惯性检测传感器可采集用户抬起手机时抬腕对应的手势数据，并向音频数字信号处理器发送该手势数据。
音频数字信号处理器在接收到上述语音数据和手势数据后，通过气息唤醒模型对语音数据和手势数据进行检测，在确定语音数据与预设唤醒气息数据之间的相似度大于第一阈值，且手势数据与预设唤醒手势数据之间的相似度大于第二阈值时，音频数字信号处理器可触发唤醒事件。
S20、音频数字信号处理器向音频驱动发送语音数据。
音频数字信号处理器在触发唤醒事件后，可向音频驱动发送获取到的语音数据。
从而，音频驱动可开始存储语音数据，便于为语音助手应用程序获取该语音数据做好数据准备。
S21、音频驱动触发缓冲区存储语音数据。
音频驱动在接收到语音数据后，可触发音频驱动的缓冲区(buffer)存储该语音 数据。可为语音助手应用程序获取该语音数据做好数据准备。
S22、音频驱动向声音触发模块发送唤醒事件。
音频驱动在接收到语音数据后，可向声音触发模块发送唤醒事件，便于声音触发模块继续向音频触发模块发送唤醒事件。
其中，S21与S22在时序上不分先后，可顺序执行，也可同时执行。
S23、声音触发模块向音频驱动发送用于指示停止运行气息唤醒模型的通知。
声音触发模块在接收到唤醒事件后，可向音频驱动发送用于指示停止运行气息唤醒模型的通知。
由于，唤醒事件已触发，可看作消耗了一次唤醒事件，气息唤醒模型可停止运行。
S24、音频驱动响应于用于指示停止运行气息唤醒模型的通知，控制音频数字信号处理器中的气息唤醒模型停止运行。
基于S19，音频数字信号处理器可以确定接收到的数据为用于唤醒语音助手应用程序的数据，并触发唤醒事件。
也就是说，在当前次的唤醒事件中，基于该语音数据能够唤醒语音助手应用程序，不需要音频数字信号处理器中的气息唤醒模型再次检测获取到的语音数据是否为用于唤醒语音助手应用程序的数据。
那么，音频驱动在接收到用于指示停止运行气息唤醒模型的通知后，可控制音频数字信号处理器中的气息唤醒模型停止运行，即气息唤醒模型不再检测接收到的数据是否为用户唤醒语音，只需要继续接收语音数据即可。
S25、声音触发模块响应于唤醒事件，启动定时器。
声音触发模块在接收到唤醒事件后，还可启动定时器，便于声音触发模块对在定时器的定时时间内是否收到用于指示语音识别开始的通知或者用于指示语音识别结束的通知进行确定。
也就是说，声音触发模块可以通过定时器的设定时间，来确定音频策略服务模块是否调用成功，便于调用不成功时，向音频驱动发送用于指示启动运行气息唤醒模型的通知。
在一些实施例中，定时器的定时时间为1-5s。
例如，定时器的定时时间为3s。
其中，S23、S25、和S26在时序上不分先后，可顺序执行，也可同时执行。
S26、声音触发模块响应于唤醒事件，声音触发模块向音频触发模块发送唤醒事件。
其中，声音触发模块在接收到唤醒事件后，还可向音频触发模块发送唤醒事件，便于音频触发模块能够在接收到唤醒事件后控制语音助手应用程序启动。
S27、音频触发模块响应于唤醒事件，控制语音助手应用程序启动。
音频触发模块在接收到唤醒事件后，可确定需要启动语音助手应用程序。从而，音频触发模块可控制语音助手应用程序启动。
S28、语音助手应用程序启动后，显示用户界面。
语音助手应用程序在启动后，电子设备可显示一个用户界面，本申请对用户界面的具体实现方式不做限定。
其中，用户界面可以显示在电子设备当前界面中的部分区域，也可以与电子设备 当前界面为不同界面。
在一些实施例中，上述设置界面中可以包括语音助手悬浮球控件，该语音助手悬浮球控件用于提醒用户语音助手应用程序已启动，以及触发语音助手应用程序结束语音识别。
其中，本申请对语音助手悬浮球控件的显示位置、显示样式、显示大小等参数不做限定。
从而，在电子设备显示上述用户界面后，用户可以确定语音助手应用程序已启动。
综上，音频数字信号处理器中的气息唤醒模型可处于持续运行的状态，直至确定接收到的语音数据与预设唤醒气息数据之间的相似度大于第一阈值，且接收到的手势数据与预设唤醒手势数据之间的相似度大于第二阈值，音频数字信号处理器可触发唤醒事件。
由此，音频数字信号处理器可以开始逐级上报唤醒事件，通过音频触发模块控制语音助手应用程序启动，保证了语音助手应用程序启动的便捷性和及时性。
可见，上述气息唤醒语音助手的技术，不需要唤醒词和触发按键，简化了语音交互步骤，更加快速的启动语音助手应用程序。
另外，这种气息唤醒语音助手的技术，用户可直接凑近电子设备进行对话，提升了用户与电子设备交互的准确率，在隐私保护上也降低了对话内容泄露的风险，同时避免了对他人的干扰。
需要说明的是，调查发现，52％的受访者在使用语音助手时担心私密信息泄露，46％的受访者在公共场所听到他人使用语音助手应用程序，会感到烦扰。
【识别阶段】
S291、语音助手应用程序在启动后，调用声音策略服务器成功时，向声音策略服务器发送用于指示语音识别开始的通知。
其中，语音助手应用程序在启动后，可开始调用声音策略服务器，调用声音策略服务器成功时，语音助手应用程序和声音策略服务器之间的通道可打开。
需要说明的是，语音助手应用程序调用声音策略服务器，可存在成功和不成功两种情况，在声音策略服务器的音频通道被占用，或者语音助手在启动成功后又发生退出的情况时，语音助手应用程序可调用声音策略服务器不成功。
例如，语音助手应用程序在启动后，电子设备的录音功能正在开启，声音策略服务器的音频通道被占用，语音助手应用程序可调用声音策略服务器不成功。
从而，语音助手应用程序在调用声音策略服务器成功时，可向声音策略服务器发送用于指示语音识别开始的通知。
其中，用于指示语音识别开始的通知用于表示语音助手应用程序能够接收语音数据，并能够对语音数据进行识别。
S292、声音策略服务器响应于用于指示语音识别开始的通知，从音频驱动调用语音数据。
基于S21，可以确定语音数据存储在音频驱动的缓冲区，另外，基于S291,声音策略服务器可以接收到用于指示语音识别开始的通知。
那么，声音策略服务器在用于指示语音识别开始的通知后，可以确定语音助手应 用程序能够接收语音数据，并能够对语音数据进行识别，声音策略服务器从音频驱动调用语音数据，便于向语音助手应用程序发送语音数据。
在一些实施例中，声音策略服务器可通过音频源(audio source)1999的流来从音频驱动的缓冲区搬运语音数据。
S293、声音策略服务器在从音频驱动调用到语音数据后，向语音助手应用程序发送语音数据。
声音策略服务器在从音频驱动的缓冲区调用到音频数据后，可向语音助手应用程序发送语音数据，便于语音助手应用程序对该语音数据进行识别。
S294、语音助手应用程序在接收到语音数据后，对接收到的语音数据进行识别。
其中，语音助手应用程序对接收到的语音数据进行识别，不仅识别语音数据的意思，还可将语音数据转换成文本的形式。
S295、声音策略服务器响应于用于指示语音识别开始的通知，向声音触发模块发送用于指示语音识别开始的通知。
声音策略服务器在接收到用于指示语音识别开始的通知后，可向声音触发模块发送用于指示语音识别开始的通知，为声音触发模块根据用于指示语音识别开始的通知执行下一步操作做好准备。
其中，S292和S295在时序上不分先后，可顺序执行，也可同时执行。
S296、声音触发模块响应于用于指示语音识别开始的通知，关闭定时器。
可以理解的是，在声音触发模块接收到用于指示语音识别开始的通知时，可确定语音助手应用程序调用声音策略服务器成功。
基于S25，声音触发模块已启动定时器。
从而，声音触发模块在接收到用于指示语音识别开始的通知后，可关闭定时器，为下一次唤醒语音助手应用程序时，开启定时器做好准备。
另外，关闭定时器，还可尽量避免电子设备的电能消耗。
S297、声音触发模块响应于用于指示语音识别开始的通知，向音频驱动发送用于指示停止运行气息唤醒模型的通知。
其中，S297为可选步骤。
另外，S297与图5所示实施例中的S23实现方式类似，本申请此处不再赘述。
应理解，语音助手应用程序在进行语音识别的过程中，若气息唤醒模型运行，可再次触发唤醒事件，使得当前次的语音识别中断。
由此，基于S22，声音触发模块已向音频驱动发送用于指示停止运行气息唤醒模型的通知，气息唤醒模型可停止运行，为避免气息唤醒模型在停止运行后，再次因其他原因启动运行，声音触发模块可向音频驱动再次发送用于指示停止运行气息唤醒模型的通知，防止气息唤醒模型启动运行，再次触发唤醒事件。
其中，S293与S296在时序上不分先后，可顺序执行，也可同时执行。
S298、音频驱动响应于用于指示停止运行气息唤醒模型的通知，音频驱动控制音频数字信号处理器中的气息唤醒模型停止运行。
其中，S298为可选步骤。
其中，S298与图5所示实施例中的S24实现方式类似，本申请此处不再赘述。
S299、语音助手应用程序在根据语音数据确定语音识别结束时，向声音策略服务器发送用于指示语音识别结束的通知。
其中，语音助手应用程序在根据语音数据确定语音识别结束可采用多种方式。
在一些实施例中，语音助手应用程序接收到用户在根据语音数据在S28中语音助手悬浮球控件进行触发的操作时，可确定用户想要结束语音识别。从而，语音助手应用程序可响应于语音助手悬浮球控件上的操作，结束语音识别。
在另一些实施例中，语音助手应用程序在确定接收到的语音数据对应的语音文本为一个完整的词语或者句子时，确定语音识别结束。
假设语音数据为“今天吃饭了嘛”。
语音助手应用程序在接收到“今天吃饭了嘛”，可以确定“今天吃饭了嘛”是一个完整的句子，语音助手应用程序可以确定语音识别结束。
语音助手应用程序接收完“今天吃”，可以确定“今天吃”不是一个完整的句子，语音助手应用程序可以确定语音识别未结束。
直至语音助手应用程序接收到“饭了嘛”，使得“今天吃”与“饭了嘛”构成一个完整的句子，语音助手应用程序可以确定语音识别结束。
S300、语音助手应用程序在根据语音数据确定语音识别结束时，显示语音识别结果。
其中，语音识别结果可以为语音数据对应的文本数据，还可以为用户数据对应的交互结果。
在一些实施例中，语音助手应用程序可在对语音数据识别的过程中，将语音数据转换成文本的形式，显示在S28中的用户界面上。
例如，语音数据为“今天天气”时，语音助手应用程序在识别到“今天天气”后，可将“今天天气”对应的文本数据显示在用户界面上。
在另一些实施例中，语音助手应用程序可在语音数据识别结束后，将语音数据对应的交互结果，显示在S28中的用户界面上。
例如，语音数据为“今天天气”时，语音助手应用程序在识别到“今天天气”后，可以确定用户想要了解今天的天气情况，可将今天天气对应的当前温度、最高温度、和最低温度等实际情况显示在用户界面上。
S301、声音策略服务器响应于用于指示语音识别结束的通知，向声音触发模块发送用于指示语音识别结束的通知。
声音策略服务器在接收到用于指示语音识别结束的通知后，可向声音触发模块发送用于指示语音识别结束的通知，为声音触发模块根据用于指示语音识别结束的通知执行下一步操作做好准备。
S302、声音触发模块响应于用于指示语音识别结束的通知，向音频驱动发送用于指示启动运行气息唤醒模型的通知。
基于S24，或者S22和S298，可以确定音频驱动已控制音频数字信号处理器中的气息唤醒模型停止运行，语音助手应用程序停止气息唤醒的功能。
由此，为恢复语音助手应用程序的气息唤醒的功能，声音触发模块可以向音频驱动发送用于指示启动运行气息唤醒模型的通知，便于声音触发模块控制音频数字信号 处理器中的气息唤醒模型启动运行，使得音频数字信号处理器中的气息唤醒模型能够对下一次接收到的数据进行检测。
S303、音频驱动响应于用于指示启动运行气息唤醒模型的通知，控制音频数字信号处理器中的气息唤醒模型启动运行。
音频驱动在接收到用于指示启动运行气息唤醒模型的通知后，可控制音频数字信号处理器中的气息唤醒模型启动运行，使得恢复语音助手应用程序的气息唤醒的功能，便于音频数字信号处理器中的气息唤醒模型能够对下一次接收到的数据进行检测。
S311、声音触发模块在定时器的设定时间结束，未收到用于指示语音识别开始的通知或者用于指示语音识别结束的通知时，向音频驱动发送用于指示启动运行气息唤醒模型的通知。
其中，语音助手应用程序和音频策略服务模块之间的“×”用于表示语音助手应用程序调用音频策略服务模块未成功。
基于S295，声音触发模块在语音助手应用程序调用音频策略服务模块成功时，可接收到用于指示语音识别开始的通知。
基于S301，声音触发模块在语音助手应用程序调用音频策略服务模块成功后，且语音助手应用程序在语音识别结束时，可接收到用于指示语音识别结束的通知。
那么，声音触发模块在定时器的设定时间结束，未收到用于指示语音识别开始的通知或者用于指示语音识别结束的通知时，可确定声音触发模块调用语音助手应用程序不成功。
由此，为恢复语音助手应用程序的气息唤醒的功能，声音触发模块可向音频驱动发送用于指示启动运行气息唤醒模型的通知，便于音频驱动控制音频数字信号处理器中的气息唤醒模型启动运行。
S312、音频驱动响应于用于指示启动运行气息唤醒模型的通知，控制音频数字信号处理器中的控制气息唤醒模型启动运行。
其中，S312与图5所示实施例中的S303实现方式类似，本申请此处不再赘述。
综上，声音触发模块可在语音助手应用程序调用音频策略服务模块成功时，向音频驱动发送停止运行气息唤醒模块的通知，使得音频驱动控制气息唤醒模型停止运行，避免中断当前次的语音识别。
另外，声音触发模块可在语音助手应用程序确定语音识别结束时，向音频驱动发送启动运行气息唤醒模块的通知，使得音频驱动控制气息唤醒模型启动运行，便于恢复语音助手应用程序的气息唤醒的功能。
此外，声音触发模块可在定时器的设定时间结束，未收到用于指示语音识别开始的通知或者用于指示语音识别结束的通知时，向音频驱动发送启动运行气息唤醒模块的通知，使得音频驱动控制气息唤醒模型启动运行，便于恢复语音助手应用程序的气息唤醒的功能。
可见，语音助手应用程序调用音频策略服务模块无论是否成功，声音触发模块皆可向音频驱动发送启动运行气息唤醒模块的通知，使得音频驱动控制气息唤醒模型启动运行，便于恢复语音助手应用程序的气息唤醒的功能。
也就是说，声音触发模块能够在合适的时机向音频驱动发送启动运行气息唤醒模 块的通知，便于使得音频驱动控制气息唤醒模型启动运行，不仅可以避免当前次的语音识别中断，还可以保证下一次能够正常唤醒语音助手应用程序。
本申请中，电子设备在接收到启动语音助手应用程序的气息唤醒功能的操作，启动气息唤醒功能，便于用户能够通过气息唤醒的方式，唤醒语音助手，提高了用户的使用体验。语音助手应用程序的气息唤醒功能启动后，气息唤醒模型可在音频数字信号处理器上处于持续运行的状态，便于在接收到的数据为用于唤醒语音助手应用程序的数据时，及时触发唤醒事件，使得语音助手应用程序能够被唤醒。
另外，音频数字信号处理器中的气息唤醒模块在确定接收到的语音数据与预设气息唤醒数据之间的相似度大于第一阈值，且接收到的手势数据与预设唤醒手势数据之间的相似度大于第二阈值时，可触发唤醒事件，并逐级上报唤醒事件，通过声音触发模块控制语音助手应用程序启动，保证了语音助手应用程序启动的便捷性和及时性。
此外，无论语音助手应用程序调用音频策略服务模块是否成功，声音触发模块皆可向音频驱动发送启动运行气息唤醒模块的通知，使得音频驱动控制气息唤醒模型启动运行，便于恢复语音助手应用程序的气息唤醒的功能。
可见，本申请的气息唤醒语音助手应用程序的方法，适用于多种目标客户，例如使用语音助手应用程序的白领、公职人员和上班族(占80％以上用户，且覆盖使用场景更广)。
本申请的气息唤醒语音助手应用程序的方法，适用于多个典型场景，例如，咖啡店、西餐厅或高铁/机场休息室等相对比较安静的公共场合下；当用户在地铁站、机场、火车站等场所，手里拿着行李排队进站；当用户在超市、商场等场所，手里拿着东西进行商品选购；当用户在户外遛狗；用户开车进入/离开停车场、收费站、小区/园区时，双手刚从汽车的方向盘上解放出来。
本申请的气息唤醒语音助手应用程序的方法，适用于多种需求，不需要唤醒词和触发按键，简化了语音交互步骤，更加快速的启动语音助手应用程序。另外，用户可直接凑近对话，提升了用户与电子设备交互的准确率，在隐私保护上也降低了对话内容泄露的风险，同时避免了对他人的干扰。
基于前述的一些实施例，下面介绍本申请提供的唤醒应用程序的方法。
示例性地，本申请提供一种唤醒应用程序的方法。
为了便于说明，本申请的唤醒应用程序的方法可由图2中的电子设备来执行。
请参阅图6，图6示出了本申请一实施例提供的唤醒应用程序的方法的流程示意图。
如图6所示，本申请提供的唤醒应用程序的方法，应用于电子设备，电子设备包括：第一应用程序、气息唤醒软件模块、和气息唤醒处理装置。
其中，电子设备可以为手机、平板电脑、可穿戴设备、车载设备、笔记本电脑、超级移动个人计算机(ultra-mobile personal computer，UMPC)、上网本、个人数字助理(personal digital assistant，PDA)、家居设备等设备。
其中，气息唤醒软件模块可以包括第一软件模块、第三软件模块、第二软件模块、和第四软件模块。
如图4所示，第一软件模块可以为音频策略服务模块(audio policy service)。
第三软件模块可以为声音触发模块(sound trigger module)。
第二软件模块可以为音频驱动(sound trigger-hal)。
第四软件模块可以为音频触发模块(sound trigger)。
如图3所示，气息唤醒处理装置可以包括音频数字信号处理器(audio digital signal processing，ADSP)、声音采集传感器、和惯性检测传感器。
其中，声音采集传感器可以为麦克风。
具体而言，本申请提供的唤醒应用程序的方法可以包括：
S101、气息唤醒处理装置获取第一数据。
其中，第一数据可以为图5中的S19中的音频数字信号传感器接收到的数据。
S101的具体实现方式可参见图5中的S17-S19的描述，此处不做赘述。
S102、气息唤醒处理装置在检测出第一数据用于指示气息唤醒第一应用程序时，向气息唤醒软件模块发送第一数据中的语音数据。
S102的具体实现方式可参见图5中的S19-S20的描述，此处不做赘述。
S103、气息唤醒软件模块存储语音数据，启动第一应用程序，控制气息唤醒处理装置停止检测所述第一应用程序的气息唤醒且继续获取语音数据。
其中，第一应用程序可以为语音助手应用程序。
S103的具体实现方式可参见图5中的S21-S24的描述，此处不做赘述。
S104、第一应用程序在启动后，调用气息唤醒软件模块成功时，向气息唤醒软件模块发送第一通知。
其中，第一通知可参见图5中的S291中的用于指示语音识别开始的通知的描述。
S104的具体实现方式可参见图5中的S21-S27的描述，此处不做赘述。
S105、气息唤醒软件模块响应于第一通知，向第一应用程序发送语音数据。
S105的具体实现方式可参见图5中的S292-S295的描述，此处不做赘述。
S106、第一应用程序对语音数据进行语音识别。
S106的具体实现方式可参见图5中的S296的描述，此处不做赘述。
S107、第一应用程序在根据语音数据确定语音识别结束时，向气息唤醒软件模块发送第二通知。
其中，第二通知可参见图5中的S299中的用于指示语音识别结束的通知的描述。
S107的具体实现方式可参见图5中的S299的描述，此处不做赘述。
S108、气息唤醒软件模块响应于第二通知，控制气息唤醒处理装置启动检测第一应用程序的下一次气息唤醒。
S108的具体实现方式可参见图5中的S301-302的描述，此处不做赘述。
本申请的唤醒应用程序的方法，气息唤醒处理装置在检测出第一数据用于指示气息唤醒第一应用程序时，可通过气息唤醒软件模块启动第一应用程序，保证了第一应用程序启动的便捷性和及时性。
其中，气息唤醒软件模块启动第一应用程序时，可控制气息唤醒处理装置停止检测第一应用程序的气息唤醒，可以避免中断当前次的语音识别。
另外，气息唤醒软件模块可在第一应用程序确定语音识别结束时，控制气息唤醒 处理装置启动检测第一应用程序的下一次气息唤醒，便于恢复第一应用程序的气息唤醒的功能。
在一些实施例中，本申请的唤醒应用程序的方法还可以包括：
气息唤醒软件模块在经过预设时长，未接收到第一通知，或者第二通知时，控制气息唤醒处理装置启动检测第一应用程序的下一次气息唤醒。
此步骤的具体实现方式可参见图5中的S311-S312的描述，此处不做赘述。
其中，气息唤醒软件模块在经过预设时长，未接收到第一通知，或者第二通知时，控制气息唤醒处理装置启动检测第一应用程序的下一次气息唤醒，便于恢复语音助手应用程序的气息唤醒的功能。
在一些实施例中，本申请的唤醒应用程序的方法还可以包括：
第一应用程序在启动后，显示第一用户界面。
第一应用程序在第一用户界面中显示语音识别结果。
其中，第一用户界面可参见图7D-图7E中的界面14，以及图5中的S28和S300中的用户界面的描述。
此步骤的具体实现方式可参见图5中的S28和S300的描述，此处不做赘述。
其中，第一用户界面可以显示语音识别结果，便于用户能够及时了解语音识别结果，提高了用户的使用体验。
在一些实施例中，气息唤醒软件模块包括：第一软件模块和第二软件模块，语音数据存储在第二软件模块中。
在一些实施例中，本申请的唤醒应用程序的方法可以包括：
步骤201、第一应用程序在启动后，调用第一软件模块成功时，向第一软件模块发送第一通知。
步骤201的具体实现方式可参见图5中的S291的描述，此处不做赘述。
步骤202、第一软件模块响应于第一通知，从第二软件模块中调用语音数据，向第一应用程序发送语音数据。
步骤202的具体实现方式可参见图5中的S293-S295的描述，此处不做赘述。
其中，第一应用程序在调用第一软件模块成功时，第一软件模块可从第二软件模块中调用语音数据，向第一应用程序发送语音数据，便于第一应用程序能够及时的收到语音数据。
在一些实施例中，本申请的唤醒应用程序的方法还可以包括：
步骤301、第一软件模块响应于第一通知，向第二软件模块发送第三通知。
其中，步骤301可包括：第一软件模块响应于第一通知，向第三软件模块发送第一通知；第三软件模块响应于第一通知，向第二软件模块发送第三通知。
其中，第三通知可参见图5中的S297中的用于指示停止运行气息唤醒模型的通知的描述。
步骤301的具体实现方式可参见图5中的S295和S297的描述，此处不做赘述。
步骤302、第二软件模块响应于第三通知，控制气息唤醒处理装置停止检测第一应用程序的气息唤醒且继续获取语音数据。
步骤302的具体实现方式可参见图5中的S297-S298的描述，此处不做赘述。
其中，控制气息唤醒处理装置停止检测第一应用程序的气息唤醒，可以避免中断当前次的语音识别，可再次保证了当前次第一应用程序语音识别的质量。
在一些实施例中，本申请的唤醒应用程序的方法可以包括：
步骤401、第一软件模块响应于第二通知，向第二软件模块发送第四通知。
步骤401可包括：第一软件模块响应于第二通知，向第三软件模块发送第二通知，第三软件模块响应于第二通知，向第二软件模块发送第四通知。
其中，第四通知可参见图5中的S302中的用于指示启动运行气息唤醒模型的通知的描述。
步骤401的具体实现方式可参见图5中的S301-S302的描述，此处不做赘述。
步骤402、第二软件模块响应于第四通知，控制气息唤醒处理装置启动检测第一应用程序的下一次气息唤醒。
步骤402的具体实现方式可参见图5中的S303的描述，此处不做赘述。
其中，第二软件模块响应于第四通知，控制气息唤醒处理装置启动检测第一应用程序的下一次气息唤醒，便于恢复第一应用程序的气息唤醒的功能。
在一些实施例中，气息唤醒软件模块还包括第三软件模块和第四软件模块。
在一些实施例中，本申请的唤醒应用程序的方法可以包括：
步骤501、第二软件模块存储语音数据，向第三软件模块发送唤醒事件。
步骤501的具体实现方式可参见图5中的S22的描述，此处不做赘述。
步骤502、第三软件模块响应于唤醒事件，向第四软件模块发送唤醒事件，以及向第二软件模块发送第五通知。
其中，第五通知可参见图5中的S23中的用于指示停止运行气息唤醒模型的通知的描述。
步骤502的具体实现方式可参见图5中的S23和S26的描述，此处不做赘述。
步骤503、第四软件模块响应于唤醒事件，启动第一应用程序。
步骤503的具体实现方式可参见图5中的S27的描述，此处不做赘述。
步骤504、第二软件模块响应于第五通知，控制气息唤醒处理装置停止检测第一应用程序的气息唤醒且继续获取语音数据。
步骤504的具体实现方式可参见图5中的S24的描述，此处不做赘述。
可见，第四软件模块可响应于唤醒事件，启动第一应用程序，保证了第一应用程序启动的及时性和准确性。
另外，由于已触发唤醒事件，控制气息唤醒处理装置停止检测第一应用程序的气息唤醒，可以避免中断当前次的语音识别，保证了当前次第一应用程序语音识别的质量。
在一些实施例中，本申请的唤醒应用程序的方法还可以包括：
步骤601、第三软件模块响应于唤醒事件，设定定时时间，并根据定时时间开始计时。
步骤601的具体实现方式可参见图5中的S25的描述，此处不做赘述。
步骤602、第三软件模块确定定时时间计时结束时，未接收到第一通知，或者第二通知时，向第二软件模块发送第六通知。
其中，第六通知可参见图5中的S311中的用于指示启动运行气息唤醒模型的通知的描述。
步骤602的具体实现方式可参见图5中的S311的描述，此处不做赘述。
步骤603、第二软件模块响应于第六通知，控制气息唤醒处理装置启动检测第一应用程序的下一次气息唤醒。
步骤603的具体实现方式可参见图5中的S312的描述，此处不做赘述。
步骤604、第三软件模块响应于第一通知，关闭定时时间的计时。
步骤604的具体实现方式可参见图5中的S293的描述，此处不做赘述。
其中，可通过定时器的设置时间，来确定是否收到第一通知或者第二通知，便于在未接收到第一通知，或者第二通知时，第二软件模块控制气息唤醒处理装置启动对检测第一应用程序的下一次气息唤醒，恢复气息唤醒功能。
在一些实施例中，本申请的唤醒应用程序的方法可以包括：
第一应用程序响应于用于指示结束语音识别的操作，确定语音识别结束。
或者，第一应用程序确定语音数据对应的语音文本满足预设规则时，确定语音识别结束。
第一应用程序在确定语音识别结束时，向第一软件模块发送第二通知。
其中，预设规则为语音数据对应的语音文本为一个完整的词语或者句子。
上述步骤的具体实现方式可参见图5中的S299的描述，此处不做赘述。
可见，第一应用程序可通过上述两种方式，判断语音识别是否结束。
在一些实施例中，气息唤醒处理装置包括：惯性检测传感器、声音采集传感器、和音频数字信号处理器。
第一数据中包括：语音数据和手势数据。
在一些实施例中，本申请的唤醒应用程序的方法可以包括：
步骤701、惯性检测传感器采集到手势数据；
步骤702、惯性检测传感器向音频数字信号处理器发送手势数据。
步骤701和步骤702的具体实现方式可参见图5中的S18的描述，此处不做赘述。
步骤703、声音采集传感器采集到语音数据；
步骤704、声音采集传感器向音频数字信号处理器发送语音数据。
步骤703和步骤704的具体实现方式可参见图5中的S17的描述，此处不做赘述。
步骤705、气息唤醒处理装置在检测出手势数据与预设唤醒手势数据之间的相似度大于第一阈值，且语音数据与预设唤醒气息数据之间的相似度大于第二阈值时，向气息唤醒软件模块发送语音数据。
步骤703和步骤704的具体实现方式可参见图5中的S19的描述，此处不做赘述。
其中，惯性检测传感器可采集手势数据，声音采集传感器可采集语音数据。
气息唤醒处理装置可对惯性检测传感器采集到的手势数据，以及声音采集传感器采集到的语音数据进行检测。
基于前述描述，结合图7A-图7E，详细介绍电子设备实现本申请的唤醒应用程序的方法。为了便于说明，图7A-图7E中，以电子设备为手机、第一应用程序为语音助 手应用程序为例进行示意。
手机可显示如图7A所示的界面11，界面11用于显示手机上安装的各种应用程序(application，APP)的图标。例如，界面11中可以包括：控件101。其中，控件101用于显示设置APP的图标。
在接收到用户对图7A所示的控件101进行触发的操作(如点击、双击或长按操作等)后，手机可从如图7A所示的界面11变为显示如图7B所示的界面12。
其中，界面12中可以包括：控件102。控件102用于触发进入语音助手应用程序的设置界面。
在接收到用户对图7B所示的控件102进行触发的操作后，手机可从如图7B所示的界面12变为显示如图7C所示的界面13。
其中，界面13中可以包括：控件103。控件103用于触发启动语音助手应用程序的气息唤醒功能。
在接收到用户对图7C所示的控件103进行触发的操作后，手机启动语音助手应用程序的气息唤醒功能。
从而，语音助手应用程序可通知气息唤醒软件模块启动，气息唤醒软件模块可通知气息唤醒处理装置对获取到的数据进行检测。
在气息唤醒处理装置在检测出上述获取到的数据为用于气息唤醒语音助手应用程序的数据时，向气息唤醒软件模块发送数据中的语音数据。
气息唤醒软件模块存储语音数据，并控制语音助手应用程序启动。语音助手应用程序启动后，手机可显示如图7D所示的界面14。
另外，气息唤醒软件模块还可控制气息唤醒处理装置停止对接收到的数据进行检测，且继续接收上述数据中的语音数据。
其中，界面14中可以包括：控件105。控件105用于提醒用户语音助手应用程序已启动，以及触发语音助手应用程序结束语音识别。
语音助手应用程序在启动后，调用气息唤醒软件模块成功时，气息唤醒软件模块可向语音助手应用程序发送语音数据。
语音助手应用程序在接收到语音数据后可将语音数据转换为文本数据，此时，界面14中还可以包括控制104。控件104用于显示语音数据对应的文本数据。
例如，在语音数据为“今天天气”时，控件104中显示的文本数据为“今天天气”。
应理解，在语音数据为“今天天气”时，表示用户想要了解今天的天气情况。
语音助手应用程序在根据语音数据确定语音识别结束后，手机可显示如图7D所示的界面14。
另外，语音助手应用程序在根据语音数据确定语音识别结束后，通知气息唤醒软件模块，气息唤醒软件模块可控制气息唤醒处理装置重新启动对下一次接收到的数据进行识别。也就是恢复语音助手应用程序的气息唤醒功能。
其中，界面14中还可以包括控件106。控件106用于显示语音助手应用程序的语音识别结果。
例如，在语音数据为“今天天气”时，控件106显示的语音识别结果可以为“A市，大部多云，降雨概率10％，当前温度14℃，最高温度17℃，最低温度11℃”。
综上，可实现通过气息唤醒的方式唤醒语音助手应用程序，并且语音助手应用程序确定语音识别结束后，气息唤醒软件模块可控制气息唤醒处理装置重新启动对下一次接收到的数据进行识别。
示例性地，本申请提供一种文档处理装置，该装置可以包括用于执行前文实施例中的唤醒应用程序的方法的一个或者多个模块。
示例性地，本申请提供一种电子设备，包括处理器；当处理器执行存储器中的计算机代码或指令时，使得电子设备执行前文实施例中的唤醒应用程序的方法。
示例性地，本申请提供一种电子设备，包括一个或多个处理器；存储器；以及一个或多个计算机程序，其中一个或多个计算机程序存储在存储器上，当计算机程序被一个或多个处理器执行时，使得电子设备执行前文实施例中的唤醒应用程序的方法。
可以理解的是，电子设备为了实现上述功能，其包含了执行各个功能相应的硬件和/或软件模块。结合本文中所公开的实施例描述的各示例的算法步骤，本申请能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。本领域技术人员可以结合实施例对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
本实施例可以根据上述方法示例对电子设备进行功能模块的划分，例如，可以对应各个功能划分各个功能模块，也可以将两个或两个以上的功能集成在一个处理模块中。上述集成的模块可以采用硬件的形式实现。需要说明的是，本实施例中对模块的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。
在采用对应各个功能划分各个功能模块的情况下，上述实施例中涉及的电子设备还可以包括：接收模块、和确定模块。其中，接收模块、和确定模块相互配合，可以用于支持电子设备执行上述步骤，和/或用于本文所描述的技术的其他过程。
需要说明的是，上述方法实施例涉及的各步骤的所有相关内容均可以援引到对应功能模块的功能描述，在此不再赘述。
本实施例提供的电子设备，用于执行上述唤醒应用程序的方法，因此可以达到与上述实现方法相同的效果。
示例性地，本申请提供一种芯片系统，芯片系统包括处理器，用于从存储器中调用并运行计算机程序，使得安装有芯片系统的电子设备执行前文实施例中的唤醒应用程序的方法。
示例性地，本申请提供一种计算机可读存储介质，计算机可读存储介质中存储有代码或指令，当代码或指令在电子设备上运行时，使得电子设备执行时实现前文实施例中的唤醒应用程序的方法。
示例性地，本申请提供一种计算机程序产品，当计算机程序产品在计算机上运行时，使得电子设备实现前文实施例中的唤醒应用程序的方法。
其中，本实施例提供的电子设备、计算机可读存储介质、计算机程序产品或芯片系统均用于执行上文所提供的对应的方法，因此，其所能达到的有益效果可参考上文所提供的对应的方法中的有益效果，此处不再赘述。
通过以上实施方式的描述，所属领域的技术人员可以了解到，为描述的方便和简 洁，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将装置的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，模块或单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个装置，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是一个物理单元或多个物理单元，即可以位于一个地方，或者也可以分布到多个不同地方。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个可读取存储介质中。基于这样的理解，本申请实施例的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该软件产品存储在一个存储介质中，包括若干指令用以使得一个设备(可以是单片机，芯片等)或处理器(processor)执行本申请各个实施例方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(read only memory，ROM)、随机存取存储器(random access memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上内容，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以权利要求的保护范围为准。

Claims (13)

  1. 一种唤醒应用程序的方法，其特征在于，应用于电子设备，所述电子设备包括：第一应用程序、气息唤醒软件模块、和气息唤醒处理装置；
    所述方法包括：
    所述气息唤醒处理装置获取第一数据；
    所述气息唤醒处理装置在检测出所述第一数据用于指示气息唤醒所述第一应用程序时，向所述气息唤醒软件模块发送所述第一数据中的语音数据；
    所述气息唤醒软件模块存储所述语音数据，启动所述第一应用程序，控制所述气息唤醒处理装置停止检测所述第一应用程序的气息唤醒且继续获取语音数据；
    所述第一应用程序在启动后，调用所述气息唤醒软件模块成功时，向所述气息唤醒软件模块发送第一通知；
    所述气息唤醒软件模块响应于所述第一通知，向所述第一应用程序发送所述语音数据；
    所述第一应用程序对所述语音数据进行语音识别；
    所述第一应用程序在根据所述语音数据确定语音识别结束时，向所述气息唤醒软件模块发送第二通知；
    所述气息唤醒软件模块响应于所述第二通知，控制所述气息唤醒处理装置启动检测所述第一应用程序的下一次气息唤醒。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    所述气息唤醒软件模块在经过预设时长，未接收到所述第一通知，或者所述第二通知时，控制所述气息唤醒处理装置启动检测所述第一应用程序的下一次气息唤醒。
  3. 根据权利要求1或2所述的方法，其特征在于，所述方法还包括：
    所述第一应用程序在启动后，显示第一用户界面；
    所述第一应用程序在所述第一用户界面中显示语音识别结果。
  4. 根据权利要求1-3任一项所述的方法，其特征在于，所述气息唤醒软件模块包括：第一软件模块和第二软件模块，所述语音数据存储在所述第二软件模块中；
    所述第一应用程序在启动后，调用所述气息唤醒软件模块成功时，向所述气息唤醒软件模块发送第一通知，包括：
    所述第一应用程序在启动后，调用所述第一软件模块成功时，向所述第一软件模块发送所述第一通知；
    所述气息唤醒软件模块响应于所述第一通知，向所述第一应用程序发送所述语音数据，包括：
    所述第一软件模块响应于所述第一通知，从所述第二软件模块中调用所述语音数据，向所述第一应用程序发送所述语音数据。
  5. 根据权利要求4所述的方法，其特征在于，所述方法还包括：
    所述第一软件模块响应于所述第一通知，向所述第二软件模块发送第三通知；
    所述第二软件模块响应于所述第三通知，控制所述气息唤醒处理装置停止检测所述第一应用程序的气息唤醒且继续获取语音数据。
  6. 根据权利要求5所述的方法，其特征在于，所述气息唤醒软件模块响应于所述 第二通知，控制所述气息唤醒处理装置启动检测所述第一应用程序的下一次气息唤醒，包括：
    所述第一软件模块响应于所述第二通知，向所述第二软件模块发送第四通知；
    所述第二软件模块响应于所述第四通知，控制所述气息唤醒处理装置启动下一次检测所述第一应用程序的下一次气息唤醒。
  7. 根据权利要求5或6所述的方法，其特征在于，所述气息唤醒软件模块还包括第三软件模块和第四软件模块；
    所述气息唤醒软件模块存储所述语音数据，启动所述第一应用程序，控制所述气息唤醒处理装置停止气息唤醒处理装置停止检测所述第一应用程序的气息唤醒且继续获取语音数据，包括：
    所述第二软件模块存储所述语音数据，向所述第三软件模块发送唤醒事件；
    所述第三软件模块响应于所述唤醒事件，向所述第四软件模块发送所述唤醒事件，以及向所述第二软件模块发送第五通知；
    所述第四软件模块响应于所述唤醒事件，控制所述第一应用程序启动；
    所述第二软件模块响应于所述第五通知，控制所述气息唤醒处理装置停止检测所述第一应用程序的气息唤醒且继续获取语音数据。
  8. 根据权利要求7所述的方法，其特征在于，所述方法还包括：
    所述第三软件模块响应于所述唤醒事件，设定定时时间，并根据所述定时时间开始计时；
    所述第三软件模块确定所述定时时间计时结束时，未接收到所述第一通知，或者所述第二通知时，向所述第二软件模块发送第六通知；
    所述第二软件模块响应于所述第六通知，控制所述气息唤醒处理装置启动检测所述第一应用程序的下一次气息唤醒；
    所述第三软件模块响应于所述第一通知，关闭所述定时时间的计时。
  9. 根据权利要求4-8任一项所述的方法，其特征在于，所述第一应用程序在根据所述语音数据确定语音识别结束时，向所述气息唤醒软件模块发送第二通知，包括：
    所述第一应用程序响应于用于指示结束语音识别的操作，确定语音识别结束；
    或者，所述第一应用程序确定所述语音数据对应的语音文本满足预设规则时，确定语音识别结束；
    所述第一应用程序在确定语音识别结束时，向所述第一软件模块发送所述第二通知。
  10. 根据权利要求1-9任一项所述的方法，其特征在于，所述气息唤醒处理装置包括：惯性检测传感器、声音采集传感器、和音频数字信号处理器；
    所述第一数据中包括：所述语音数据和手势数据，所述气息唤醒处理装置获取第一数据，包括：
    所述惯性检测传感器采集手势数据；
    所述惯性检测传感器向所述音频数字信号处理器发送所述手势数据；
    所述声音采集传感器采集语音数据；
    所述声音采集传感器向所述音频数字信号处理器发送所述语音数据；
    所述气息唤醒处理装置在检测出所述第一数据用于指示气息唤醒所述第一应用程序时，向所述气息唤醒软件模块发送所述第一数据中的语音数据，包括：
    所述气息唤醒处理装置在检测出所述手势数据与预设唤醒手势数据之间的相似度大于第一阈值，且所述语音数据与预设唤醒气息数据之间的相似度大于第二阈值时，向所述气息唤醒软件模块发送所述语音数据。
  11. 一种电子设备，其特征在于，包括：
    一个或多个处理器；
    存储器；
    以及一个或多个计算机程序，其中所述一个或多个计算机程序存储在所述存储器上，当所述计算机程序被所述一个或多个处理器执行时，使得所述电子设备执行如权利要求1-10任一项所述的唤醒应用程序的方法。
  12. 一种芯片系统，其特征在于，所述芯片系统包括处理器，用于从存储器中调用并运行计算机程序，使得安装有所述芯片系统的电子设备执行如权利要求1-10任一项所述的唤醒应用程序的方法。
  13. 一种计算机可读存储介质，包括计算机程序，其特征在于，当所述计算机程序在电子设备上运行时，使得所述电子设备执行如权利要求1-10任一项所述的唤醒应用程序的方法。
PCT/CN2023/114978 2022-11-16 2023-08-25 唤醒应用程序的方法及电子设备 Ceased WO2024103893A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US19/111,980 US20260024527A1 (en) 2022-11-16 2023-08-25 Method for waking up application, and electronic device
CN202380054837.1A CN119604931A (zh) 2022-11-16 2023-08-25 唤醒应用程序的方法及电子设备
EP23890331.4A EP4571734A4 (en) 2022-11-16 2023-08-25 METHOD FOR WAKE-UP APPLICATION PROGRAM AND ELECTRONIC DEVICE

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211438531.X 2022-11-16
CN202211438531.XA CN118053423B (zh) 2022-11-16 2022-11-16 唤醒应用程序的方法及电子设备

Publications (1)

Publication Number Publication Date
WO2024103893A1 true WO2024103893A1 (zh) 2024-05-23

Family

ID=91049192

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/114978 Ceased WO2024103893A1 (zh) 2022-11-16 2023-08-25 唤醒应用程序的方法及电子设备

Country Status (4)

Country Link
US (1) US20260024527A1 (zh)
EP (1) EP4571734A4 (zh)
CN (3) CN118053423B (zh)
WO (1) WO2024103893A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117746849A (zh) * 2022-09-14 2024-03-22 荣耀终端有限公司 一种语音交互方法、装置及终端

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118057527A (zh) * 2022-11-18 2024-05-21 荣耀终端有限公司 一种语音交互方法、电子设备及计算机可读存储介质
US20250308520A1 (en) * 2024-03-29 2025-10-02 Sony Group Corporation Non-speech sound control with a hearable device
CN119922445B (zh) * 2025-03-19 2025-09-19 东莞市三奕电子科技股份有限公司 一种无线耳机、用于无线耳机的智能语音控制系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108492827A (zh) * 2018-04-02 2018-09-04 百度在线网络技术（北京）有限公司 应用程序的唤醒处理方法、装置及存储介质
CN111681655A (zh) * 2020-05-21 2020-09-18 北京声智科技有限公司 语音控制方法、装置、电子设备及存储介质
CN112583673A (zh) * 2020-12-04 2021-03-30 珠海格力电器股份有限公司 一种唤醒设备的控制方法以及装置
US20210225374A1 (en) * 2020-12-23 2021-07-22 Intel Corporation Method and system of environment-sensitive wake-on-voice initiation using ultrasound
CN113593541A (zh) * 2020-04-30 2021-11-02 阿里巴巴集团控股有限公司 数据处理方法、装置、电子设备和计算机存储介质
CN114999484A (zh) * 2022-05-31 2022-09-02 四川虹美智能科技有限公司 交互语音设备的选举方法及系统

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9288840B2 (en) * 2012-06-27 2016-03-15 Lg Electronics Inc. Mobile terminal and controlling method thereof using a blowing action
US9147398B2 (en) * 2013-01-23 2015-09-29 Nokia Technologies Oy Hybrid input device for touchless user interface
CN106653060B (zh) * 2017-01-11 2020-05-12 瑞声声学科技(深圳)有限公司 吹气声识别系统及采用该系统的吹气识别方法
US10649727B1 (en) * 2018-05-14 2020-05-12 Amazon Technologies, Inc. Wake word detection configuration
CN110858483A (zh) * 2018-08-23 2020-03-03 深圳市冠旭电子股份有限公司 智能设备、语音唤醒方法、语音唤醒装置及存储介质
KR20200063984A (ko) * 2018-11-28 2020-06-05 삼성전자주식회사 음성 인식 장치 및 방법
CN111223488B (zh) * 2019-12-30 2023-01-17 Oppo广东移动通信有限公司 语音唤醒方法、装置、设备及存储介质
CN112700782A (zh) * 2020-12-25 2021-04-23 维沃移动通信有限公司 语音处理方法和电子设备
CN115116438A (zh) * 2021-03-22 2022-09-27 华为技术有限公司 一种协同唤醒第一电子设备的方法及第一电子设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108492827A (zh) * 2018-04-02 2018-09-04 百度在线网络技术（北京）有限公司 应用程序的唤醒处理方法、装置及存储介质
CN113593541A (zh) * 2020-04-30 2021-11-02 阿里巴巴集团控股有限公司 数据处理方法、装置、电子设备和计算机存储介质
CN111681655A (zh) * 2020-05-21 2020-09-18 北京声智科技有限公司 语音控制方法、装置、电子设备及存储介质
CN112583673A (zh) * 2020-12-04 2021-03-30 珠海格力电器股份有限公司 一种唤醒设备的控制方法以及装置
US20210225374A1 (en) * 2020-12-23 2021-07-22 Intel Corporation Method and system of environment-sensitive wake-on-voice initiation using ultrasound
CN114999484A (zh) * 2022-05-31 2022-09-02 四川虹美智能科技有限公司 交互语音设备的选举方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4571734A4

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117746849A (zh) * 2022-09-14 2024-03-22 荣耀终端有限公司 一种语音交互方法、装置及终端
CN117746849B (zh) * 2022-09-14 2025-10-03 荣耀终端股份有限公司 一种语音交互方法、装置及终端

Also Published As

Publication number Publication date
CN119418695A (zh) 2025-02-11
CN119604931A (zh) 2025-03-11
CN118053423B (zh) 2024-11-08
EP4571734A1 (en) 2025-06-18
EP4571734A4 (en) 2025-12-10
CN118053423A (zh) 2024-05-17
US20260024527A1 (en) 2026-01-22

Similar Documents

Publication Publication Date Title
US12142274B2 (en) Voice wakeup method and device
EP4030422B1 (en) Voice interaction method and device
CN118053423B (zh) 唤醒应用程序的方法及电子设备
CN111722824B (zh) 语音控制方法、装置及计算机存储介质
CN110704004B (zh) 一种语音控制的分屏显示方法及电子设备
CN108320744B (zh) 语音处理方法和装置、电子设备、计算机可读存储介质
US20170140644A1 (en) Electronic device and method for performing operations according to proximity of external object
CN112739507B (zh) 一种交互沟通实现方法、设备和存储介质
KR20180083587A (ko) 전자 장치 및 그의 동작 방법
CN114333854B (zh) 语音唤醒方法、电子设备及芯片系统
CN112860169A (zh) 交互方法及装置、计算机可读介质和电子设备
CN110971763B (zh) 到站提醒方法、装置、存储介质及电子设备
KR102269387B1 (ko) 상황별 정보 공유 지원 방법 및 이를 지원하는 전자 장치
CN111681655A (zh) 语音控制方法、装置、电子设备及存储介质
CN110442391A (zh) 一种调用服务的方法及装置
CN114765026A (zh) 一种语音控制方法、装置及系统
US20140300535A1 (en) Method and electronic device for improving performance of non-contact type recognition function
CN119028333B (zh) 一种语音输入方法、装置、电子设备及存储介质
CN119028332B (zh) 一种语音数据处理方法、装置、电子设备及存储介质
CN112365899B (zh) 语音处理方法、装置、存储介质及终端设备
CN119229861B (zh) 一种通过语音控制终端设备的方法及终端设备
CN111488183A (zh) 基于终端设备的应用启动方法、装置、终端设备和介质
CN112489650A (zh) 唤醒控制方法、装置、存储介质及终端
CN115037832B (zh) 一种数据处理方法及电子设备
CN121214477A (zh) 一种基于用户照片识别人物的方法及电子设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23890331

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 202380054837.1

Country of ref document: CN

WWP Wipo information: published in national office

Ref document number: 202380054837.1

Country of ref document: CN

WWE Wipo information: entry into national phase

Ref document number: 2023890331

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2023890331

Country of ref document: EP

Effective date: 20250314

NENP Non-entry into the national phase

Ref country code: DE

WWP Wipo information: published in national office

Ref document number: 2023890331

Country of ref document: EP