CN107277904A - A kind of terminal and voice awakening method - Google Patents
A kind of terminal and voice awakening method Download PDFInfo
- Publication number
- CN107277904A CN107277904A CN201710534424.XA CN201710534424A CN107277904A CN 107277904 A CN107277904 A CN 107277904A CN 201710534424 A CN201710534424 A CN 201710534424A CN 107277904 A CN107277904 A CN 107277904A
- Authority
- CN
- China
- Prior art keywords
- phonetic order
- main processor
- module
- processor modules
- feature information
- 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.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
- H04W52/02—Power saving arrangements
- H04W52/0209—Power saving arrangements in terminal devices
- H04W52/0251—Power saving arrangements in terminal devices using monitoring of local events, e.g. events related to user activity
- H04W52/0254—Power saving arrangements in terminal devices using monitoring of local events, e.g. events related to user activity detecting a user operation or a tactile contact or a motion of the device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/32—Means for saving power
- G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
- G06F1/3234—Power saving characterised by the action undertaken
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/32—Means for saving power
- G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
- G06F1/3234—Power saving characterised by the action undertaken
- G06F1/3293—Power saving characterised by the action undertaken by switching to a less power-consuming processor, e.g. sub-CPU
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
- H04W52/02—Power saving arrangements
- H04W52/0209—Power saving arrangements in terminal devices
- H04W52/0261—Power saving arrangements in terminal devices managing power supply demand, e.g. depending on battery level
- H04W52/0274—Power saving arrangements in terminal devices managing power supply demand, e.g. depending on battery level by switching on or off the equipment or parts thereof
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2250/00—Details of telephonic subscriber devices
- H04M2250/74—Details of telephonic subscriber devices with voice recognition means
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The present invention discloses a kind of terminal, including microphone and main processor modules, also include a co-processor module, wherein, the microphone, is connected with the co-processor module, for when the main processor modules in a dormant state when, the first phonetic order is gathered, and first phonetic order is input in the co-processor module, first phonetic order includes fisrt feature information；The co-processor module, it is connected with the main processor modules, for pre-setting the second phonetic order, second phonetic order includes second feature information, and be compared the fisrt feature information of first phonetic order of acquisition and the second feature information, if relative error is less than a pre-set threshold value, output one wakes up instruction to the main processor modules；The main processor modules, instruct laggard line activating receiving described wake up, reduce the power consumption of terminal.
Description
Technical field
The invention belongs to field of terminal technology, more particularly to terminal and voice awakening method.
Background technology
Speech recognition technology, its target is that the vocabulary Content Transformation in the voice by the mankind is computer-readable input,
Such as button, binary coding or character string.
Under apple Siri drive, voice assistant has started one and has applied upsurge.There is voice assistant, user only needs
Go out demand or the instruction of oneself, equipment utilization speech recognition and machine learning are that can perform, and greatly improve Consumer's Experience.
But current most scheme is all that speech identifying function could be used under bright screen state, functional limitation compared with
Greatly.Due to recognize the phonetic entry of user when standby at any time, the microphone of mobile phone will be constantly in working condition, and now
As mobile phone main control unit also can not deep-sleep, the standby current of mobile phone will be substantially improved, and add the power consumption of mobile phone.
Therefore, how the power consumption of terminal is reduced in speech recognition, as urgent problem to be solved.
The content of the invention
The technical scheme that the present invention is provided is as follows：
The present invention provides a kind of terminal, including microphone and main processor modules, in addition to a co-processor module, its
In,
The microphone, is connected with the co-processor module, for when the main processor modules in a dormant state
When, the first phonetic order is gathered, and first phonetic order is input in the co-processor module, first voice
Instruction includes fisrt feature information；
The co-processor module, is connected with the main processor modules, described for pre-setting the second phonetic order
Second phonetic order include second feature information, and by the fisrt feature information in first phonetic order of acquisition with it is described
Second feature information is compared, if relative error is less than a pre-set threshold value, and output one wakes up instruction to the main process task
Device module；
The main processor modules, laggard line activating is instructed receiving described wake up.
Preferably, the terminal also includes touch screen module,
The touch screen module is connected with the co-processor module, for exporting a screen command to the coprocessor
Module, the screen command includes third feature information；
The co-processor module, is additionally operable to the third feature information of the screen command of acquisition is special with described second
Reference breath is compared, if relative error is less than a pre-set threshold value, output one wakes up instruction to the main processor modules.
Preferably, the terminal also includes power module,
The power module, connects with the microphone, main processor modules, touch screen module and co-processor module respectively
Connect, and the co-processor module exports a control signal to the power module, the control signal is used to control the electricity
Source module is exported to the power supply of the microphone, touch screen module and main processor modules.
Preferably, the co-processor module, is additionally operable to be pre-configured with second phonetic order and corresponding application journey
Sequence title, stores the corresponding relation of second phonetic order and application name.
Preferably, the microphone, is additionally operable to recognize the second phonetic order of user's input, and sends second voice
Instruct to the co-processor module；
The co-processor module, is additionally operable to obtain second phonetic order, second language set according to user
Sound instructs corresponding application name, stores the corresponding relation of second phonetic order and the Apply Names.
Preferably, the co-processor module, is additionally operable to after the resting state activation of the main processor modules, send
Second phonetic order and application name are to the main processor modules；
The main processor modules, are additionally operable to according to second phonetic order of acquisition and the application name
Corresponding relation, runs the corresponding application program of the application name.
Preferably,
The main processor modules, are additionally operable to be pre-configured with and store the 3rd phonetic order and corresponding application name
Claim, the 3rd phonetic order includes fourth feature information；
The co-processor module, be additionally operable to fisrt feature information in first phonetic order by acquisition with it is described
Second feature information is matched, if matching is unsuccessful, and output one wakes up instruction to the main processor modules, and sends institute
The first phonetic order is stated to the main processor modules；
The main processor modules, receive it is described wake up the laggard line activating of instruction, and by first language of acquisition
Fisrt feature information in sound instruction is compared with the fourth feature information, if relative error is less than a pre-set threshold value,
Then according to the corresponding application name of the 3rd phonetic order, application journey corresponding with the application name is run
Sequence.
Present invention also offers a kind of voice awakening method, methods described includes：
S1, when main processor modules in a dormant state when, microphone gathers the first phonetic order, and by first language
Sound instruction is sent into co-processor module, and first phonetic order includes fisrt feature information；
S2, the co-processor module pre-sets the second phonetic order, and second phonetic order includes second feature
Information, and the fisrt feature information in first phonetic order of acquisition and the second feature information are compared, if
When relative error is less than a pre-set threshold value, then exports one and wake up instruction to the main processor modules；
S3, the main processor modules enter line activating after the wake-up instruction is received.
Preferably,
The step S2 also includes：
Second phonetic order of microphone identification user's input, and send at second phonetic order to the association
Manage device module；
The co-processor module obtains second phonetic order, second phonetic order pair set according to user
The application name answered, stores the corresponding relation of second phonetic order and the Apply Names.
Preferably, the step S2 also includes,
After the resting state activation of the main processor modules, second phonetic order and application name are sent
To the main processor modules；
The step S3 also includes：
The main processor modules are closed according to second phonetic order of acquisition and the correspondence of the application name
System, runs application program corresponding with the application name.
Compared with prior art, the present invention is provided terminal and voice awakening method, have the advantages that：Voice refers to
The processing work of order is undertaken by the co-processor module of low-power consumption, is made terminal handler in a dormant state, is reduced terminal
Power consumption, saves the electricity consumption of terminal, is brought convenience to user；User sets the voice of activation primary processor to refer to according to their needs
Order, and the corresponding application name of the phonetic order is set, after primary processor is activated, run corresponding application name
Claim, both reduced the power consumption of terminal, the experience of user is improved again；Characteristic information in phonetic order is compared, and is kept away
The identification error for also thering is user to be brought because pronouncing difference is exempted from, has improved the identification of command information, brought preferably to user
Experience；The phonetic order is stored in the co-processor module, when terminal is in without network condition or network condition ratio
In the case of poor, the resting state of primary processor can also be activated, the power consumption of primary processor is reduced, brings very big to user
Convenience.
Brief description of the drawings
Below by clearly understandable mode, preferred embodiment is described with reference to the drawings, a kind of terminal and voice are waken up
Above-mentioned characteristic, technical characteristic, advantage and its implementation of method are further described.
Fig. 1 is a kind of composition structural representation of terminal of the invention；
Fig. 2 is a kind of structural representation of the specific embodiment of terminal of the invention；
Fig. 3 is a kind of schematic flow sheet of voice awakening method of the invention.
Embodiment
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, control is illustrated below
The embodiment of the present invention.It should be evident that drawings in the following description are only some embodiments of the present invention, for
For those of ordinary skill in the art, on the premise of not paying creative work, other can also be obtained according to these accompanying drawings
Accompanying drawing, and obtain other embodiments.
To make only to schematically show part related to the present invention in simplified form, each figure, they are not represented
Its as product practical structures.In addition, so that simplified form is readily appreciated, there is identical structure or function in some figures
Part, only symbolically depicts one of those, or has only marked one of those.Herein, " one " is not only represented
" only this ", can also represent the situation of " more than one ".
As shown in figure 1, according to one embodiment of present invention, a kind of terminal, including microphone and main processor modules, its
It is characterised by, in addition to a co-processor module, wherein,
The microphone 10, is connected with the co-processor module, for being in dormancy shape when the main processor modules
During state, the first phonetic order is gathered, and first phonetic order is input in the co-processor module, first language
Sound instruction includes fisrt feature information；
The co-processor module 11, is connected with the main processor modules, for pre-setting the second phonetic order, institute
The second phonetic order is stated including second feature information, and by the fisrt feature information of first phonetic order of acquisition with it is described
Second feature information is compared, if relative error is less than a pre-set threshold value, and output one wakes up instruction to the main process task
Device module；
The main processor modules 12, for being instructed according to the wake-up of acquisition, activate the primary processor.
In specific implementation process, microphone 10 is connected with the co-processor module, when terminal in a dormant state when,
Main processor modules namely in terminal in a dormant state when, user inputs the first voice by the microphone 10 of terminal and referred to
Order, first phonetic order is used for the instruction for waking up the main processor modules of the terminal, can be set by user or system
Set, first phonetic order includes fisrt feature information, such as, the first phonetic order of input is " opening wechat ", " micro-
Letter " is just fisrt feature information.The microphone 10 is collected after the first phonetic order, and first phonetic order is inputted
Into the co-processor module.
The co-processor module 11, is connected with the main processor modules.In the co-processor module 11 in advance
Second phonetic order is set, and second phonetic order includes second feature information, such as, sets the second phonetic order " to beat
It is just second feature information to open wechat " wechat ".After the co-processor module receives first phonetic order, obtain
The fisrt feature information of first phonetic order, the fisrt feature information is compared with the second feature information,
If relative error is less than a pre-set threshold value, output one wakes up instruction to the main processor modules, default second language
Sound instructs the instruction of the main processor modules for waking up the terminal, can be set by user's setting or system.It is described
Main processor modules 12 are received after the wake-up instruction, are instructed according to described wake up, are entered line activating.
According to the technical scheme, the microphone is connected with the co-processor module, handles association of the work by low-power consumption
Processor module undertakes, and makes terminal handler in a dormant state, reduces the power consumption of terminal, saves the electricity consumption of terminal, gives
User brings convenience, such as, user terminal in a dormant state under, pass through this phonetic order of microphone input wechat, association
Processor module receives wechat phonetic order, is carried out with being stored in advance in the second phonetic order of wechat of co-processor module
Compare, if unanimously, co-processor module sends a signal to processor module, active processor module, processor module
And then according to the first phonetic order of the wechat, open wechat application program；Characteristic information in phonetic order is compared
Compared with, it is to avoid also have user because pronounce it is different the identification error brought, improve the identification of command information, brought more to user
Good experience.
Preferably, the touch screen module is connected with the co-processor module, for exporting a screen command to described
Co-processor module, the screen command includes third feature information；
The co-processor module, is additionally operable to the third feature information of the screen command of acquisition is special with described second
Reference breath is compared, if relative error is less than a pre-set threshold value, output one wakes up instruction to the main processor modules.
The specific embodiment of the present invention, the terminal also includes a touch screen module, the touch screen module and the association
Processor module is connected.After user inputs a screen command by touch-screen, the touch screen module is received after the screen command,
And export the screen command to the co-processor module, the screen command is used for the main processor modules for waking up the terminal
Instruction, can have user set or system set, the screen command include third feature information.The coprocessor mould
Block is received after the screen command, and the screen command and the second feature information of default second phonetic order are compared
Compared with.Specifically, second phonetic order is identified the co-processor module, and second phonetic order is converted into
Alphabetic character, then the screen command is identified with second phonetic order, obtains in second phonetic order
Second feature information.If relative error is less than a pre-set threshold value, output one wakes up instruction to the main processor modules, institute
State main processor modules and receive the wake-up instruction, instructed according to described wake up, activate the main processor modules, institute
State after main processor modules are activated, carry out corresponding application program launching.According to the technical scheme, user can be by end
Entr screen instructs to wake up the main processor modules on the touch-screen at end.
Preferably, the power module, is handled with the microphone, main processor modules, touch screen module and association respectively
Device module is connected, and the co-processor module exports a control signal to the power module, and the control signal is used to control
The power module is made to export to the power supply of the microphone, touch screen module and main processor modules.
As shown in Fig. 2 the specific embodiment of the present invention, terminal includes microphone 20, co-processor module 21, main process task
Device module 22, power module 23 and touch screen module 24.Power module 23, respectively with the microphone 20, main processor modules
22nd, touch screen module 24 and co-processor module 21 are connected, microphone 20, main processor modules described in the power module 23
22nd, touch screen module 24 and co-processor module 21 are powered, and the co-processor module 21 exports a control signal to institute
Power module 23 is stated, the control signal is used to control the power module 23 to export to the microphone 20, touch screen module
24 and the power supply of main processor modules 22, the control of co-processor module 21 supply of power module 23 microphone 20, touch-screen
The power supply output of module 24 and main processor modules 22.Microphone 20 is carried out by digital serial interface with co-processor module 21
Communication connection, the first phonetic order that microphone 20 is gathered is sent to co-processor module 21 by stating in serial line interface.Touch
Panel module 24 passes through standard I2C interfaces (Inter-Integrated Circuit, twin wire universal serial bus) and coprocessor mould
Block 21 is connected, and the touch screen module 24 obtains screen command, and the screen command is sent to association by I2C interfaces and handled
Device module 21.Co-processor module 21 can pass through SPI interface (SerialPeripheral with main processor modules 22
Interface, Serial Peripheral Interface (SPI)) serial line interface carries out data communication, or data communication is carried out by parallel interface.Work as association
First phonetic order or the screen command are obtained the first spy in first phonetic order by processor module 21
Reference ceases, or the third feature information in the screen command, and the second feature with default second phonetic order is believed respectively
Breath is compared.Such as, it is 10% to set a pre-set threshold value, if relative error is less than 10%, co-processor module 21 is defeated
Go out a hardware interrupt to a GPIO pins of main processor modules 22.Main processor modules 22 receive the interrupt signal
Afterwards, the main processor modules are activated, after the main processor modules are activated, corresponding application program launching are carried out.
Preferably, the co-processor module, is additionally operable to be pre-configured with second phonetic order and corresponding application journey
Sequence title, stores the corresponding relation of second phonetic order and application name.
Specifically, the co-processor module is pre-configured with second phonetic order in systems, and described in configuration
The corresponding application name of second phonetic order, stores the corresponding relation of second phonetic order and application name,
And second phonetic order and application name are sent to the main processor modules.Default second phonetic order
For the instruction for the main processor modules for waking up the terminal.
According to the technical scheme, the second phonetic order is pre-configured with system, second phonetic order can be according to user
General key feature word is configured, such as key feature word is wechat, and the second phonetic order is configured to wechat, corresponding
Application program be wechat application program.
Preferably,
The microphone, is additionally operable to recognize the second phonetic order of user's input, and sends second phonetic order extremely
The co-processor module；
The co-processor module, is additionally operable to obtain second phonetic order, second language set according to user
Sound instructs corresponding application name, stores the corresponding relation of second phonetic order and the Apply Names.
Specifically, user can set the second phonetic order according to their needs.The microphone input that user passes through terminal
Second phonetic order, the microphone recognizes second phonetic order, and second phonetic order is sent to the association
Manage device module.The corresponding application name of second phonetic order can be set in user.The co-processor module receives institute
The second phonetic order is stated, second phonetic order is obtained and is stored, second phonetic order set according to user
Corresponding application name, stores the corresponding relation of second phonetic order and the Apply Names.
The specific embodiment of the present invention, user can set the second phonetic order in the interface of terminal, or pass through end
One APP management softwares are installed to set the second phonetic order in end.It is specifically described with installing APP management softwares.In the APP
On the setting interface of management software, there is a prompting input frame, remind user to pass through the phonetic order of terminal microphone input second.
Before this, the microphone function that user opens a terminal.User says the second phonetic order, such as Taobao by microphone, when with
Family is said after this second phonetic order of Taobao, is set interface display alarm input frame again, is asked user to input identical again
This second phonetic order of Taobao, after inputting correct twice, user's selection preserves second phonetic order.When user has preserved
Cheng Hou, shows a prompting frame, and user selects the corresponding application name of the second phonetic order, such as Xuan Zu Taobaos apply journey
Sequence title, then selection is preserved.The phonetic order of set Taobao second correspondence that the co-processor module is set according to user
Taobao's application name, store the corresponding relation of the phonetic order of Taobao second and Taobao's application name.
According to the technical scheme, the voice that user can activate primary processor resting state according to setting the need for itself refers to
Order, it is possible to set the corresponding application name of the phonetic order, after the primary processor is activated, operation is described should
With program, the phonetic order is stored in the co-processor module, when terminal is in without network condition or network condition
In the case of poor, the resting state of primary processor can also be activated, the power consumption of primary processor is reduced, user is brought very
Big convenience.
Preferably, the co-processor module, is additionally operable to after the resting state activation of the main processor modules, send
Second phonetic order and application name are to the main processor modules；
The main processor modules, are additionally operable to according to second phonetic order of acquisition and the application name
Corresponding relation, runs application program corresponding with the application name.
The specific embodiment of the present invention, instruction is waken up to the main processor modules when the co-processor module is sent
Afterwards, the main processor modules receive the dormancy for waking up after instruction, the primary processor being activated according to the wake-up instruction
State.After the main processor modules are activated, the co-processor module sends second phonetic order and application program
Title to the main processor modules, the main processor modules receive second phonetic order and application name, root
According to second phonetic order and the corresponding relation of the application name of acquisition, the application name correspondence is run
Application program.The specific embodiment of the present invention, user sets this second phonetic order of wechat and corresponding wechat application
Program name.When user terminal in a dormant state under, pass through the phonetic order of microphone input wechat first, coprocessor mould
Block receives the phonetic order of wechat first, is compared with being stored in advance in the second phonetic order of wechat of co-processor module
Compared with if unanimously, co-processor module sends a signal to main processor modules, the dormancy shape of activation main processor modules
State.After primary processor is activated, co-processor module sends the second phonetic order and wechat application name of wechat extremely
Main processor modules, main processor modules are opened according to the wechat phonetic order and corresponding wechat application name of reception
Wechat application program.
According to the technical scheme, user sets the phonetic order of activation primary processor according to their needs, and sets the language
Sound instructs corresponding application name, after primary processor is activated, and runs corresponding application name, both reduces end
The power consumption at end, improves the experience of user again.
Preferably,
The main processor modules, are additionally operable to be pre-configured with and store the 3rd phonetic order and corresponding application name
Claim, the 3rd phonetic order includes fourth feature information；
The co-processor module, is additionally operable to the fisrt feature information of first phonetic order of acquisition and described the
Two characteristic informations are matched, if matching is unsuccessful, and output one wakes up instruction to the main processor modules, and send described
First phonetic order is to the main processor modules；
The main processor modules, receive it is described wake up the laggard line activating of instruction, and by first language of acquisition
Fisrt feature information in sound instruction is compared with the fourth feature information, if relative error is less than a pre-set threshold value,
Then according to the corresponding application name of the 3rd phonetic order, the corresponding application program of the application name is run.
Specifically, this specific embodiment be applied to the co-processor module amount of storage it is smaller when, it is impossible to store more
Phonetic order, by wake up instruction be stored in main processor modules.The main processor modules are pre-configured with and store described
Three phonetic orders and corresponding application name, can be set or system configuration, the 3rd phonetic order by user
Including fourth feature information.So that user is set as an example, user can set the 3rd phonetic order and corresponding application by terminal
Program name.User also can be in work shape by the phonetic order of microphone input the 3rd, the main processor modules of the terminal
State, is not on resting state.The co-processor module passes through the 3rd phonetic order and the application name
Data communication channel is pass-through to the main processor modules.The main processor modules receive the 3rd phonetic order and described
Application name, and store the corresponding relation of second phonetic order and the application name.When primary processor mould
Block in a dormant state when, user is by the phonetic order of microphone input first, and microphone sends first phonetic order extremely
The co-processor module, first phonetic order includes fisrt feature information.The co-processor module is by the institute of acquisition
State fisrt feature information in the first phonetic order to be matched with the second feature information in second phonetic order, if matching
It is unsuccessful, then export one and wake up instruction to the main processor modules, and send first phonetic order to the main process task
Device module.The main processor modules are instructed according to the wake-up of acquisition, activate the primary processor, obtain first language
The fisrt feature information of sound instruction, and by first phonetic order and the fourth feature information in the 3rd phonetic order
It is compared, if relative error is less than a pre-set threshold value, according to the corresponding application name of the 3rd phonetic order,
Run the corresponding application program of the application name.
As shown in figure 3, according to one embodiment of present invention, a kind of voice awakening method, methods described includes：
S301, when main processor modules in a dormant state when, microphone gathers the first phonetic order, and by described first
Phonetic order is sent into co-processor module, and first phonetic order includes fisrt feature information；
S302, the co-processor module pre-sets the second phonetic order, and it is special that second phonetic order includes second
Reference is ceased, and the fisrt feature information in first phonetic order of acquisition and the second feature information are compared,
If relative error is less than a pre-set threshold value, output one wakes up instruction to the main processor modules；
S303, the main processor modules enter line activating after the wake-up instruction is received.
Specifically, when terminal in a dormant state when, that is, main processor modules in terminal in a dormant state when,
User passes through the phonetic order of microphone input first of terminal, primary processor of first phonetic order for waking up the terminal
The instruction of module, can be set by user or system is set.The microphone is collected after the first phonetic order, and will be described
First phonetic order is input in the co-processor module, and first phonetic order includes fisrt feature information.The association
Processor module pre-sets the second phonetic order, and second phonetic order includes second feature information.When association processing
Device module is received after first phonetic order, the fisrt feature information of first phonetic order is obtained, by described first
Characteristic information is compared with second feature information, if relative error is less than a pre-set threshold value, output one wakes up instruction to institute
Main processor modules are stated, default second phonetic order is used for the instruction for waking up the main processor modules of the terminal, can
With what is set by user's setting or system.The main processor modules receive described wake up and instructed, and are referred to according to the wake-up
Order, activates the main processor modules.
By the technical scheme, the processing work of phonetic order is undertaken by the co-processor module of low-power consumption, makes end
Manage device in a dormant state, reduce the power consumption of terminal, save the electricity consumption of terminal, brought convenience to user.
Preferably：
The step S302 also includes：
Second phonetic order of microphone identification user's input, and send at second phonetic order to the association
Manage device module
The co-processor module obtains second phonetic order, second phonetic order pair set according to user
The application name answered, stores the corresponding relation of second phonetic order and the Apply Names.
Preferably,
The step S302 also includes,
After the resting state activation of the main processor modules, second phonetic order and application name are sent
To the main processor modules；
The step S303 also includes：
The main processor modules are closed according to second phonetic order of acquisition and the correspondence of the application name
System, runs application program corresponding with the application name
The specific embodiment of the present invention, user can set the second phonetic order according to their needs.User passes through end
The phonetic order of microphone input second at end, the microphone recognizes second phonetic order, and by second phonetic order
Send to the co-processor module.The corresponding application name of second phonetic order can be set in user.At the association
Manage device module and receive second phonetic order, obtain second phonetic order and stored, the institute set according to user
The corresponding application name of the second phonetic order is stated, the correspondence pass of second phonetic order and the Apply Names is stored
System.
The still another embodiment of the present invention, instruction is waken up to the primary processor mould when the co-processor module is sent
After block, the main processor modules reception is described to be waken up after instruction, and stopping for the instruction activation primary processor is waken up according to described
Dormancy state.After the main processor modules are activated, the co-processor module sends second phonetic order and applies journey
Sequence title to the main processor modules, the main processor modules receive second phonetic order and application name,
According to second phonetic order and the corresponding relation of the application name of acquisition, the application name pair is run
The application program answered.The specific embodiment of the present invention, user sets this second phonetic order of wechat and corresponding wechat should
Use program name.When user terminal in a dormant state under, pass through the phonetic order of microphone input wechat first, coprocessor
Module receives the phonetic order of wechat first, is compared with being stored in advance in the second phonetic order of wechat of co-processor module
Compared with if unanimously, co-processor module sends a signal to main processor modules, the dormancy shape of activation main processor modules
State.After primary processor is activated, co-processor module sends the second phonetic order and wechat application name of wechat extremely
Main processor modules, main processor modules are opened according to the wechat phonetic order and corresponding wechat application name of reception
Wechat application program.
The present invention by the way that microphone is connected with co-processor module, when main processor modules in a dormant state when, assist
The wake-up instruction of processing module processing microphone input, main processor modules reduce the power consumption of terminal, carried without real-time working
The high experience of user.
It should be noted that above-described embodiment can independent assortment as needed.Described above is only the preferred of the present invention
Embodiment, it is noted that for those skilled in the art, is not departing from the premise of the principle of the invention
Under, some improvements and modifications can also be made, these improvements and modifications also should be regarded as protection scope of the present invention.
Claims (10)
1. a kind of terminal, including microphone and main processor modules, it is characterised in that also including a co-processor module, wherein,
The microphone, is connected with the co-processor module, for when the main processor modules in a dormant state when, adopt
Collect the first phonetic order, and first phonetic order is input in the co-processor module, first phonetic order
Including fisrt feature information；
The co-processor module, is connected with the main processor modules, for pre-setting the second phonetic order, described second
Phonetic order includes second feature information, and by the fisrt feature information and described second in first phonetic order of acquisition
Characteristic information is compared, if relative error is less than a pre-set threshold value, and output one wakes up instruction to the primary processor mould
Block；
The main processor modules, laggard line activating is instructed receiving described wake up.
2. terminal as claimed in claim 1, it is characterised in that the terminal also includes touch screen module,
The touch screen module is connected with the co-processor module, for exporting a screen command to the coprocessor mould
Block, the screen command includes third feature information；
The co-processor module, is additionally operable to believe the third feature information of the screen command of acquisition and the second feature
Breath is compared, if relative error is less than a pre-set threshold value, output one wakes up instruction to the main processor modules.
3. terminal as claimed in claim 2, it is characterised in that the terminal also includes power module,
The power module, is connected with the microphone, main processor modules, touch screen module and co-processor module respectively,
And the co-processor module exports a control signal to the power module, the control signal is used to control the power supply mould
Block is exported to the power supply of the microphone, touch screen module and main processor modules.
4. terminal as claimed in claim 3, it is characterised in that the co-processor module, is additionally operable to be pre-configured with described
Two phonetic orders and corresponding application name, store the corresponding relation of second phonetic order and application name.
5. terminal as claimed in claim 3, it is characterised in that
The microphone, is additionally operable to recognize the second phonetic order of user's input, and sends second phonetic order to described
Co-processor module；
The co-processor module, is additionally operable to obtain second phonetic order, second voice set according to user refers to
Corresponding application name is made, the corresponding relation of second phonetic order and the Apply Names is stored.
6. the terminal as described in claim 4 or 5, it is characterised in that
The co-processor module, is additionally operable to after the resting state activation of the main processor modules, send second language
Sound is instructed and application name to the main processor modules；
The main processor modules, are additionally operable to second phonetic order and the correspondence of the application name according to acquisition
Relation, runs the corresponding application program of the application name.
7. terminal as claimed in claim 1, it is characterised in that
The main processor modules, are additionally operable to be pre-configured with and store the 3rd phonetic order and corresponding application name, institute
Stating the 3rd phonetic order includes fourth feature information；
The co-processor module, is additionally operable to the fisrt feature information and described second in first phonetic order by acquisition
Characteristic information is matched, if matching is unsuccessful, and output one wakes up instruction to the main processor modules, and sends described the
One phonetic order is to the main processor modules；
The main processor modules, instruct laggard line activating, and first voice of acquisition is referred to receiving described wake up
Fisrt feature information in order is compared with the fourth feature information, if relative error is less than a pre-set threshold value, root
According to the corresponding application name of the 3rd phonetic order, application program corresponding with the application name is run.
8. a kind of voice awakening method, it is characterised in that methods described includes：
S1, when main processor modules in a dormant state when, microphone gathers the first phonetic order, and first voice is referred to
Order is sent into co-processor module, and first phonetic order includes fisrt feature information；
S2, the co-processor module pre-sets the second phonetic order, and second phonetic order includes second feature information,
And be compared the fisrt feature information in first phonetic order of acquisition and the second feature information, if comparing mistake
When difference is less than a pre-set threshold value, then exports one and wake up instruction to the main processor modules；
S3, the main processor modules enter line activating after the wake-up instruction is received.
9. voice awakening method as claimed in claim 8, it is characterised in that
The step S2 also includes：
Second phonetic order of microphone identification user's input, and second phonetic order is sent to the coprocessor
Module；
The co-processor module obtains second phonetic order, corresponding according to second phonetic order that user is set
Application name, stores the corresponding relation of second phonetic order and the Apply Names.
10. voice awakening method as claimed in claim 9, it is characterised in that
The step S2 also includes,
After the resting state activation of the main processor modules, second phonetic order and application name are sent to institute
State main processor modules；
The step S3 also includes：
The main processor modules are according to second phonetic order and the corresponding relation of the application name of acquisition, fortune
Row application program corresponding with the application name.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710534424.XA CN107277904A (en) | 2017-07-03 | 2017-07-03 | A kind of terminal and voice awakening method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710534424.XA CN107277904A (en) | 2017-07-03 | 2017-07-03 | A kind of terminal and voice awakening method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107277904A true CN107277904A (en) | 2017-10-20 |
Family
ID=60070872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710534424.XA Pending CN107277904A (en) | 2017-07-03 | 2017-07-03 | A kind of terminal and voice awakening method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107277904A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107680595A (en) * | 2017-11-15 | 2018-02-09 | 安徽声讯信息技术有限公司 | A kind of intelligent sound mobile phone or intelligent sound flat board |
| CN108108007A (en) * | 2017-12-21 | 2018-06-01 | 维沃移动通信有限公司 | A kind of processing method and mobile terminal for reducing power consumption |
| CN108469894A (en) * | 2018-03-13 | 2018-08-31 | 深圳阿凡达智控有限公司 | Voice recognition chip control method, device and system |
| CN108520745A (en) * | 2018-03-16 | 2018-09-11 | 北京云知声信息技术有限公司 | The operating method and device of equipment portrait information |
| CN109195073A (en) * | 2018-08-03 | 2019-01-11 | 努比亚技术有限公司 | A kind of microphone, audio-frequency processing method, terminal and computer readable storage medium |
| CN109979438A (en) * | 2019-04-04 | 2019-07-05 | Oppo广东移动通信有限公司 | Voice awakening method and electronic equipment |
| CN110703895A (en) * | 2019-09-30 | 2020-01-17 | 联想(北京)有限公司 | Control method and device |
| WO2020038010A1 (en) * | 2018-08-23 | 2020-02-27 | 深圳市冠旭电子股份有限公司 | Intelligent device, voice wake-up method, voice wake-up apparatus, and storage medium |
| CN110968353A (en) * | 2019-12-06 | 2020-04-07 | 惠州Tcl移动通信有限公司 | Central processing unit awakening method and device, voice processor and user equipment |
| WO2020077540A1 (en) * | 2018-10-16 | 2020-04-23 | 华为技术有限公司 | Information processing method and electronic device |
| CN111742539A (en) * | 2018-08-07 | 2020-10-02 | 华为技术有限公司 | Voice control command generation method and terminal |
| CN111819533A (en) * | 2018-10-11 | 2020-10-23 | 华为技术有限公司 | Method for triggering electronic equipment to execute function and electronic equipment |
| CN113031749A (en) * | 2019-12-09 | 2021-06-25 | Oppo广东移动通信有限公司 | Electronic device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106200853A (en) * | 2016-07-02 | 2016-12-07 | 上海与德通讯技术有限公司 | A kind of wake-up circuit and awakening method |
-
2017
- 2017-07-03 CN CN201710534424.XA patent/CN107277904A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106200853A (en) * | 2016-07-02 | 2016-12-07 | 上海与德通讯技术有限公司 | A kind of wake-up circuit and awakening method |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107680595A (en) * | 2017-11-15 | 2018-02-09 | 安徽声讯信息技术有限公司 | A kind of intelligent sound mobile phone or intelligent sound flat board |
| CN108108007A (en) * | 2017-12-21 | 2018-06-01 | 维沃移动通信有限公司 | A kind of processing method and mobile terminal for reducing power consumption |
| WO2019120087A1 (en) * | 2017-12-21 | 2019-06-27 | 维沃移动通信有限公司 | Processing method for reducing power consumption and mobile terminal |
| US11366510B2 (en) | 2017-12-21 | 2022-06-21 | Vivo Mobile Communication Co., Ltd. | Processing method for reducing power consumption and mobile terminal |
| CN108469894A (en) * | 2018-03-13 | 2018-08-31 | 深圳阿凡达智控有限公司 | Voice recognition chip control method, device and system |
| CN108520745B (en) * | 2018-03-16 | 2020-10-02 | 北京云知声信息技术有限公司 | Method and device for operating equipment portrait information |
| CN108520745A (en) * | 2018-03-16 | 2018-09-11 | 北京云知声信息技术有限公司 | The operating method and device of equipment portrait information |
| CN109195073A (en) * | 2018-08-03 | 2019-01-11 | 努比亚技术有限公司 | A kind of microphone, audio-frequency processing method, terminal and computer readable storage medium |
| CN111742539A (en) * | 2018-08-07 | 2020-10-02 | 华为技术有限公司 | Voice control command generation method and terminal |
| US11848016B2 (en) | 2018-08-07 | 2023-12-19 | Huawei Technologies Co., Ltd. | Voice control command generation method and terminal |
| WO2020038010A1 (en) * | 2018-08-23 | 2020-02-27 | 深圳市冠旭电子股份有限公司 | Intelligent device, voice wake-up method, voice wake-up apparatus, and storage medium |
| CN111819533A (en) * | 2018-10-11 | 2020-10-23 | 华为技术有限公司 | Method for triggering electronic equipment to execute function and electronic equipment |
| CN111819533B (en) * | 2018-10-11 | 2022-06-14 | 华为技术有限公司 | Method for triggering electronic equipment to execute function and electronic equipment |
| WO2020077540A1 (en) * | 2018-10-16 | 2020-04-23 | 华为技术有限公司 | Information processing method and electronic device |
| CN109979438A (en) * | 2019-04-04 | 2019-07-05 | Oppo广东移动通信有限公司 | Voice awakening method and electronic equipment |
| CN110703895A (en) * | 2019-09-30 | 2020-01-17 | 联想(北京)有限公司 | Control method and device |
| CN110968353A (en) * | 2019-12-06 | 2020-04-07 | 惠州Tcl移动通信有限公司 | Central processing unit awakening method and device, voice processor and user equipment |
| CN113031749A (en) * | 2019-12-09 | 2021-06-25 | Oppo广东移动通信有限公司 | Electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107277904A (en) | A kind of terminal and voice awakening method | |
| CN104795068B (en) | The wake-up control method and its control system of robot | |
| CN107147792B (en) | Method and device for automatically configuring sound effect, mobile terminal and storage device | |
| CN105976814B (en) | Control method and device of head-mounted equipment | |
| CN106814639A (en) | Speech control system and method | |
| CN107358954A (en) | It is a kind of to change the device and method for waking up word in real time | |
| CN102546953A (en) | System and method for full voice control of mobile terminal | |
| CN103021411A (en) | Speech control device and speech control method | |
| CN109192208B (en) | Control method, system, device, equipment and medium for electrical equipment | |
| CN108877805A (en) | Speech processes mould group and terminal with phonetic function | |
| CN110060678B (en) | Virtual role control method based on intelligent device and intelligent device | |
| CN105957526A (en) | Voice awakening system and awakening method | |
| CN110322880A (en) | Vehicle-mounted terminal equipment and the method for waking up its multiple interactive voice program | |
| CN106095492A (en) | The method for closing of a kind of application program and device | |
| CN110968353A (en) | Central processing unit awakening method and device, voice processor and user equipment | |
| CN112363851A (en) | Voice awakening method and system of intelligent terminal, intelligent watch and storage medium | |
| CN108093350B (en) | Microphone control method and microphone | |
| CN112085463A (en) | Vehicle-mounted voice schedule management device and method and vehicle-mounted terminal | |
| CN202424833U (en) | System of full-voice control mobile terminal | |
| CN111292716A (en) | Voice chip and electronic equipment | |
| CN106228047B (en) | A kind of application icon processing method and terminal device | |
| CN110956968A (en) | Voice wake-up and voice wake-up function triggering method and device, and terminal equipment | |
| US20210201894A1 (en) | N/a | |
| CN213392751U (en) | Voice interaction intelligent electric fan based on neural network chip and electric fan system | |
| CN105430155A (en) | Wearable equipment and control method thereof based on speech signals |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171020 |
|
| WD01 | Invention patent application deemed withdrawn after publication |