Based on the sound control method under screen lock state and device thereof
Technical field
The present invention relates to the fields such as voice/semantics recognition technology, natural language processing technique and mobile terminal applicating developing technology, particularly relate to a kind of based on the sound control method under screen lock state and device thereof.
Background technology
Along with the fast development of intelligent mobile terminal (such as, Android phone) and day by day universal, the function of intelligent mobile terminal is more and more abundanter.At present, intelligent mobile terminal has abundant unlocking manner, such as, manually to input the unlock password that numeral or letter carry out unlocking, slide unblock, figure unblock etc.Wherein especially manually input numeral or letter carry out unlocking as a kind of traditional unlocking manner, namely unlock by comparing after key feeding cipher.Because the password of numeral or alphabetic character string composition is easier to be decrypted, is also easily peeped by other people and known when using in public places, thus easily causing the leakage of the private data in mobile terminal.For the people that those are inconvenient to use manual manipulation keyboard or screen, above-mentioned non-voice unlocking manner is used to bring some inconvenience.
In addition, when mobile terminal is in screen lock state, if desired execution is called, sends note, is called certain application program, first needs to remove screen locking, then just can call relevant application program, perform and operate accordingly.Like this, operating efficiency can be caused relatively low.
Therefore, need one can carry out sound control method and phonetic controller based under screen lock state.
Summary of the invention
The object of the present invention is to provide a kind of based on the sound control method under screen lock state and device thereof, the problem that could perform associative operation after password unlocks manually is inputted to solve in prior art, even if realize mobile terminal to be in screen lock state, still can call some application programs, to perform relevant operation, namely without the need to manual unlocking, just can perform associative operation by phonetic entry and unlock, so improve whole operating efficiency.
For solving the problems of the technologies described above, the invention provides a kind of based on the sound control method under screen lock state, said method comprising the steps of: (1), in locking screen interface, shows an indicative operational order; (2) touch action is obtained; (3) feedback action is provided, to start to receive speech input information; (4) received speech input information is identified, and change into character string information; (5) process according to changed character string information, and Graphics Processing result in the unlocked state.
Further, in step (5), comprise further: by the semantic parser pre-seted, changed into character string information is resolved to standard commands and parameter; The standard commands resolved to is sent to together with parameter the application program module of a Semantic; Described application program module calls corresponding application program, to perform associative operation, and shows the operation interface of described application program in the unlocked state.
Further, in step (2), comprise further: the first duration detecting touch action, and judge whether the first duration was more than or equal to a first presetting reference time; If described first duration is more than or equal to described first reference time, then perform feedback action.
Further, in step (3), comprise further: the second duration detecting speech input information, and judge whether the second duration was more than or equal to a second presetting reference time; If described second duration is more than or equal to described second reference time, then stops receiving speech input information, and start the identification performing speech input information.
Further, in step (3), comprising further: when starting to receive speech input information, playing an animation, the time that animation is play was the second duration.
For solving the problems of the technologies described above, present invention also offers a kind of based on the phonetic controller under screen lock state, describedly to comprise based on the phonetic controller under screen lock state: an indicative operational order display unit, in locking screen interface, display one indicative operational order; One touch action acquiring unit, for obtaining a touch action; One feedback action providing unit, for providing a feedback action, to start to receive speech input information; One speech input information recognition unit, for identifying received speech input information, and changes into character string information; One processing unit, for processing according to changed character string information, and Graphics Processing result in the unlocked state.
Further, describedly also comprise a character string information resolution unit, a standard commands parameter delivery unit and an application execution unit based on the phonetic controller under screen lock state, described character string information resolution unit is used for the semantic parser by pre-seting, and changed into character string information is resolved to standard commands and parameter; Described standard commands parameter delivery unit is used for the application program module standard commands resolved to being sent to together with parameter a Semantic; Described application execution unit is used for described application program module and calls corresponding application program, to perform associative operation, and shows the operation interface of described application program in the unlocked state.
Further, describedly also comprise one first detecting unit and one first judging unit based on the phonetic controller under screen lock state, described first detecting unit is for detecting the first duration of touch action, described first judging unit is for judging whether the first duration was more than or equal to a first presetting reference time, if whether the first duration was more than or equal to a first presetting reference time, then provide a feedback action by feedback action providing unit.
Further, describedly also comprise one second detecting unit and one second judging unit based on the phonetic controller under screen lock state, described second detecting unit is for detecting the second duration of speech input information, second judging unit is for judging whether the second duration was more than or equal to a second presetting reference time, if described second duration is more than or equal to described second reference time, then stop receiving speech input information, and start by described speech input information recognition unit the identification performing speech input information.
Further, describedly also comprising an animation broadcast unit based on the phonetic controller under screen lock state, for when starting to receive speech input information, playing an animation; The time that wherein animation is play was the second duration.
Compared with prior art, the invention has the advantages that by described sound control method and device thereof, even if realize mobile terminal to be in screen lock state, still can call some application programs, to perform relevant operation, namely without the need to manual unlocking, just can perform associative operation by phonetic entry and unlock.First unlock compared with the mode that operates again with traditional, invention increases whole operating efficiency, also can avoid presumable misoperation in releasing process simultaneously.In addition, after having called related application, mobile terminal has switched to released state from screen lock state automatically, and operation is more easy like this.
Accompanying drawing explanation
Fig. 1 is the flow chart of steps of the embodiment based on the sound control method under screen lock state of the present invention;
Fig. 2 A is the Organization Chart based on the phonetic controller under screen lock state described in the preferred embodiment for the present invention;
Fig. 2 B is the Organization Chart of the described touch action acquiring unit based on the phonetic controller under screen lock state;
Fig. 2 C is the Organization Chart of the described feedback action providing unit based on the phonetic controller under screen lock state;
Fig. 2 D is the Organization Chart of the described processing unit based on the phonetic controller under screen lock state;
Fig. 3 A ~ Fig. 3 D is the schematic diagram of the specific embodiment of the invention one;
Fig. 4 A ~ Fig. 4 D is the schematic diagram of the specific embodiment of the invention two.
Embodiment
Elaborate below in conjunction with the embodiment of accompanying drawing to the sound control method that the present invention is based under screen lock state and device thereof.
The object of the present invention is to provide a kind of based on the sound control method under screen lock state and device thereof, the problem that could perform associative operation after password unlocks manually is inputted to solve in prior art, even if realize mobile terminal to be in screen lock state, still can call some application programs, to perform relevant operation, namely without the need to manual unlocking, just can perform associative operation by phonetic entry and unlock, so improve whole operating efficiency.
Fig. 1 is the flow chart of steps of the embodiment based on the sound control method under screen lock state of the present invention.Shown in Figure 1, a kind of based on the sound control method under screen lock state, comprise the following steps: S110, in locking screen interface, display one indicative operational order; S120, obtain a touch action; S130, provide a feedback action, to start to receive speech input information; S140, received speech input information to be identified, and change into character string information; S150, to process according to changed character string information, and Graphics Processing result in the unlocked state.
Below will illustrate each step.
Step S110: in locking screen interface, display one indicative operational order.
Under mobile terminal is in screen lock state (namely with locking screen interface display), in locking screen interface, show a speech recognition button.An indicative operational order is had, such as: " click me to say, phone certain contact person " in the below of described speech recognition button, " click me to say, phone assigned number ", " clicking me to say; certain contact person and assigned number ", " click me to say, send a note ", " click me to say; send note to certain contact person ", " click me to say, send note to assigned number ", " click me to say, open certain application program ".In addition, indicative operational order also can be " today, weather how ", " some time tomorrow makes me get up ".Above-mentioned indicative operational order with animation form display, and according to inside arrange can randomness or specific aim display.Be generally random display, but can show pointedly after meeting certain condition, such as: user goes out if detect, can point out " weather of today how "; If detect, user goes on business in other places, can point out inquiry " hotel that neighbouring cost performance is higher ".
Step S120: obtain a touch action.
When user clicks speech recognition button according to indicative operational order.Now, speech recognition button obtains a touch action.
Step S130: provide a feedback action, to start to receive speech input information.
After receiving touch action, provide a feedback action, such as, embody in vibrational feedback mode, also other feedback systems (such as playing a sound) reminding user can be carried out, to start phonetic entry at other execution modes of the present invention.
Step S140: received speech input information is identified, and changes into character string information.
By received speech input information by built-in speech analysis device, change into corresponding character string information.Transform generate character string information comprise Chinese character string information and/or English character string information.
Step S150: process according to changed character string information, and Graphics Processing result in the unlocked state.
This step S150 is further comprising the steps:
(1): by the semantic parser pre-seted, changed into character string information is resolved to standard commands and parameter.
By the semantic parser pre-seted, changed into character string information is resolved to standard commands and parameter, also export the label ID mapping to an application program module simultaneously.
(2): the application program module standard commands resolved to being sent to together with parameter a Semantic.
According to the label ID of application program module, the standard commands resolved to is sent to corresponding application program module together with parameter.This application program module is Semantic SDK.
(3): described application program module calls corresponding application program, to perform associative operation, and the operation interface of described application program is shown in the unlocked state.
Described application program module calls corresponding application program, and according to described standard commands and parameter, performs relevant operation (such as phone certain contact person, send a note to assigned number, open a certain Application Program Interface etc.).Now, mobile terminal shows the operation interface of this application program, and is in solution screen state.Certainly, the specific embodiment of the invention mainly for the situation of screen lock state, without the need to security verification.If have encryption under screen lock state, such as digital phase-locking or figure lock, now opens certain application program or SMS is (for the security consideration) that can not directly call, and some other basic function can normal call.Such as, under screen lock state, click speech recognition button and say that " opening certain chat application " now needs manually to untie password, password is untied and just can automatically be opened this chat application afterwards.
In addition, may further include the present invention is based in the sound control method under screen lock state:
Comprise further in step (S120): (A) detects the first duration of touch action, and judge whether the first duration was more than or equal to a first presetting reference time; (B) if described first duration is more than or equal to described first reference time, then feedback action is performed.
Being embodied as of above-mentioned steps (A) and step (B) is avoided some user misoperation and is clicked speech recognition button but do not have the situation of speech input information.Wherein, the first reference time can be set to two seconds.
May further include the present invention is based in the sound control method under screen lock state:
In step (S130), comprise further: (C) detects the second duration of speech input information, and judge whether the second duration was more than or equal to a second presetting reference time; (D) if described second duration is more than or equal to described second reference time, then stop receiving speech input information, and start the identification performing speech input information.
The enforcement of above-mentioned steps (C) and step (D) is in order to more effectively processed voice inputs information, avoids the content great majority of received speech input information for situation that is empty or meaningless information.Wherein, the second reference time can be set to 60 seconds.
In the process that step (S130) performs, can comprising further: when starting to receive speech input information, playing an animation.Wherein, the time that animation is play was the second duration.Described animation can be shown as an annulus and at the uniform velocity rotate in a clockwise direction or counterclockwise around speech recognition button.Like this, point out user the current stage having entered phonetic entry by playing timing animation, thus be supplied to user one better operating experience.
Next the preferred implementation based on the phonetic controller under screen lock state of the present invention is provided by reference to the accompanying drawings.
It is the Organization Chart based on the phonetic controller under screen lock state described in the preferred embodiment for the present invention shown in Fig. 2 A.Fig. 2 B is the Organization Chart of the described touch action acquiring unit based on the phonetic controller under screen lock state.Fig. 2 C is the Organization Chart of the described feedback action providing unit based on the phonetic controller under screen lock state.Fig. 2 D is the Organization Chart of the described processing unit based on the phonetic controller under screen lock state.
Describedly to comprise based on the phonetic controller under screen lock state: indicative operational order display unit 21, touch action acquiring unit 22, feedback action providing unit 23, speech input information recognition unit 24, processing unit 25.
Wherein, indicative operational order display unit 21, in locking screen interface, shows an indicative operational order.A speech recognition button is shown in locking screen interface, an indicative operational order is had in the below of described speech recognition button, such as: " clicking me to say; phone certain contact person ", " click me to say; phone assigned number ", " clicking me to say, certain contact person and assigned number ", " click me to say; send a note ", " click me to say, send note to certain contact person ", " click me to say; send note to assigned number ", " click me to say, open certain application program ".In addition, indicative operational order also can be " today, weather how ", " some time tomorrow makes me get up ".Above-mentioned indicative operational order with the display of animation form, and arranges can randomness show or specific aim display according to inside.
Touch action acquiring unit 22 is for obtaining a touch action.
Feedback action providing unit 23 for providing a feedback action, to start to receive speech input information.After receiving touch action, provide a feedback action, such as, embody in vibrational feedback mode, also other feedback systems (such as playing a sound) reminding user can be carried out, to start phonetic entry at other execution modes of the present invention.
Speech input information recognition unit 24 for identifying received speech input information, and changes into character string information.Wherein, by received speech input information by built-in speech analysis device, corresponding character string information is changed into.Transform generate character string information comprise Chinese character string information and/or English character string information.
Processing unit 25 is for processing according to changed character string information, and Graphics Processing result in the unlocked state.Wherein, described processing unit 25 comprises character string information resolution unit 251, standard commands parameter delivery unit 252 and an application execution unit 253 further, shown in Fig. 2 D.
Changed into character string information, for the semantic parser by pre-seting, is resolved to standard commands and parameter by described character string information resolution unit 251.Wherein, the semantic parser of character string information resolution unit 251 by pre-seting, resolves to standard commands and parameter by changed into character string information, also exports the label ID mapping to an application program module simultaneously.
The standard commands resolved to, for according to above-mentioned label ID, is sent to the application program module of a Semantic by described standard commands parameter delivery unit 252 together with parameter.
Described application execution unit 253 calls corresponding application program for described application program module, to perform associative operation, and shows the operation interface of described application program.Described application program module calls corresponding application program, and according to described standard commands and parameter, performs relevant operation (such as phone certain contact person, send a note to assigned number, open a certain Application Program Interface etc.).
Describedly also comprise one first detecting unit 221 and one first judging unit 222, shown in Fig. 2 B based on the phonetic controller under screen lock state.Described first detecting unit 221 is for detecting the first duration of touch action, described first judging unit 222 is for judging whether the first duration was more than or equal to a first presetting reference time, if whether the first duration was more than or equal to a first presetting reference time, then provide a feedback action by feedback action providing unit 23.By arranging the first detecting unit 221 and the first judging unit 222 and can avoid some user misoperation and clicking speech recognition button but do not have the situation of speech input information.
Describedly also comprise one second detecting unit 231 and one second judging unit 232, shown in Fig. 2 C based on the phonetic controller under screen lock state.Described second detecting unit 231 is for detecting the second duration of speech input information, second judging unit 232 is for judging whether the second duration was more than or equal to a second presetting reference time, if described second duration is more than or equal to described second reference time, then stop receiving speech input information, and start by described speech input information recognition unit 24 identification performing speech input information.Can more effectively processed voice input information by arranging the second detecting unit 231 and the second judging unit 232, avoid the content great majority of received speech input information for situation that is empty or meaningless information.
Further, describedly an animation broadcast unit 233 is also comprised, shown in Fig. 2 C based on the phonetic controller under screen lock state.Described animation broadcast unit 233, for when starting to receive speech input information, plays an animation; The time that wherein animation is play was the second duration.Described animation can be shown as an annulus and at the uniform velocity rotate in a clockwise direction or counterclockwise around speech recognition button.Like this, point out user the current stage having entered phonetic entry by playing timing animation, thus be supplied to user one better operating experience.
Below provide several specific embodiment, for illustration of of the present invention based on the sound control method under screen lock state.
Embodiment one:
User needs to carry out to the mobile terminal be under screen lock state the operation that Voice command completes voice dial phone.Described mobile terminal is a smart mobile phone, and unencryption.Described mobile terminal comprises described based on the phonetic controller under screen lock state.Shown in Fig. 3 A ~ 3D, wherein, Fig. 3 A ~ 3C be depicted as mobile terminal be in screen lock state under locking screen interface.Fig. 3 D is that mobile terminal is unlocked, and is in " calling " application A interface.
Refer step (a1): in locking screen interface, display one indicative operational order.
Under smart mobile phone is in screen lock state, smart mobile phone shows with locking screen interface.A speech recognition button is shown in locking screen interface.An indicative operational order is had in the below of described speech recognition button.Such as: click me and say, phone certain contact person, shown in Fig. 3 A.This indicative operational order shows with animation form.
Refer step (a2): describedly obtain a touch action based on the phonetic controller under screen lock state.
When user clicks speech recognition button according to indicative operational order.Now, speech recognition button obtains a touch action, shown in Fig. 3 B.
Refer step (a3): describedly provide a feedback action based on the phonetic controller under screen lock state, to start the speech input information receiving user.
After receiving touch action, describedly provide a feedback action based on the phonetic controller under screen lock state, carry out reminding user in vibrational feedback mode, to start phonetic entry, shown in Fig. 3 C.Now, user says speech recognition button, " phoning father ".
Refer step (a4): received speech input information is identified, and changes into character string information.
By received speech input information by built-in speech analysis device, change into corresponding character string information.
Refer step (a5): by the semantic parser pre-seted, resolves to standard commands and parameter by changed into character string information.
Utilize described semantic parser, parsing character string information is need call application A built-in in smart mobile phone " to call ", and parameter is " father ", and the label ID(mapping to one " calling " module is such as 100).
Refer step (a6): the application program module standard commands resolved to being sent to together with parameter a Semantic.
According to the label ID of " calling " module, label ID is 100 herein, the standard commands resolved to " is called " and parameter " father " is sent to together and " calls " module accordingly.Should " calling " module Semantic SDK.
Refer step (a7): described application program module calls corresponding application program, to perform associative operation, and shows the operation interface of described application program.
" call " module to call and call application program, and match corresponding contact number according to parameter " father ", and perform and dial operation.Now, smart mobile phone has automatically switched to the main interface of " calling " from locking screen interface, can see shown in Fig. 3 D.
Embodiment two:
User needs to carry out to the mobile terminal be under screen lock state the operation that Voice command completes weather lookup.Described mobile terminal is a smart mobile phone, and unencryption.Described mobile terminal comprises described based on the phonetic controller under screen lock state.Shown in Fig. 4 A ~ 4D, wherein, Fig. 4 A ~ 4C be depicted as mobile terminal be in screen lock state under locking screen interface.Fig. 4 D is that mobile terminal is unlocked, and is in " weather lookup " application program B interface.
Refer step (b1): in locking screen interface, display one indicative operational order.
Under smart mobile phone is in screen lock state, smart mobile phone shows with locking screen interface.A speech recognition button is shown in locking screen interface.An indicative operational order is had in the below of described speech recognition button.If detect, user goes out, then point out " weather of today how ", shown in Fig. 4 A.
Refer step (b2): describedly obtain a touch action based on the phonetic controller under screen lock state.
When user clicks speech recognition button according to indicative operational order.Now, speech recognition button obtains a touch action, shown in Fig. 4 B.
Refer step (b3): describedly provide a feedback action based on the phonetic controller under screen lock state, to start the speech input information receiving user.
After receiving touch action, describedly provide a feedback action based on the phonetic controller under screen lock state, carry out reminding user in sound feedback mode, to start phonetic entry.Now, user says speech recognition button, and " weather of today how ", shown in Fig. 4 C.
Refer step (b4): received speech input information is identified, and changes into character string information.
By received speech input information by built-in speech analysis device, change into corresponding character string information.
Refer step (b5): by the semantic parser pre-seted, resolves to standard commands and parameter by changed into character string information.
Utilize described semantic parser, parsing character string information is to call application program B " weather lookup " built-in in smart mobile phone, parameter is " today " and default parameters " this locality ", and the label ID(mapping to one " weather lookup " module is such as 600).
Refer step (b6): the application program module standard commands resolved to being sent to together with parameter a Semantic.
According to the label ID of " weather lookup " module, label ID is 600 herein, and the standard commands resolved to " weather lookup " and parameter are sent to " weather lookup " module accordingly together for " today " and default parameters " this locality ".Should " weather lookup " module Semantic SDK.
Refer step (b7): described application program module calls corresponding application program, to perform associative operation, and shows the operation interface of described application program.
" weather lookup " module calls weather lookup application program, and match corresponding information according to parameter for " today " and default parameters " this locality ", and show " today, the weather in somewhere was fine, and day temperature is 15 ~ 20 degree, and nocturnal temperature is 10 ~ 15 degree ".Now, smart mobile phone has automatically switched to the main interface of " weather lookup " from locking screen interface, can see shown in Fig. 4 D.
Embodiment three:
User needs to carry out Voice command to the mobile terminal be under screen lock state and completes the operation arranging alarm clock and wake.Described mobile terminal is a smart mobile phone, and unencryption.Described mobile terminal comprises described based on the phonetic controller under screen lock state.
Refer step (c1): in locking screen interface, display one indicative operational order.
Under smart mobile phone is in screen lock state, smart mobile phone shows with locking screen interface.A speech recognition button is shown in locking screen interface.An indicative operational order is had in the below of described speech recognition button.
Refer step (c2): describedly obtain a touch action based on the phonetic controller under screen lock state.
When user clicks speech recognition button according to indicative operational order.Now, speech recognition button obtains a touch action.
Refer step (c3): describedly provide a feedback action based on the phonetic controller under screen lock state, to start the speech input information receiving user.
After receiving touch action, describedly provide a feedback action based on the phonetic controller under screen lock state, carry out reminding user in sound feedback mode, to start phonetic entry.Now, user says speech recognition button, " 8:00 tomorrow morning makes me get up ".
Refer step (c4): received speech input information is identified, and changes into character string information.
By received speech input information by built-in speech analysis device, change into corresponding character string information.
Refer step (c5): by the semantic parser pre-seted, resolves to standard commands and parameter by changed into character string information.
Utilize described semantic parser, parsing character string information is need call application program C built-in in smart mobile phone " to arrange alarm clock to wake ", parameter is " tomorrow " " morning " " 8 point ", and the label ID(mapping to one " arranging alarm clock to wake " module is such as 800).
Refer step (c6): the application program module standard commands resolved to being sent to together with parameter a Semantic.
According to the label ID of " arranging alarm clock to wake " module, label ID is 800 herein, the standard commands resolved to " is arranged alarm clock to wake " and parameter for being sent to corresponding " arranging alarm clock to wake " module " tomorrow " " morning " " 8 point " together.Should " arranging alarm clock to wake " module Semantic SDK.
Refer step (c7): described application program module calls corresponding application program, to perform associative operation, and shows the operation interface of described application program.
" arrange alarm clock to wake " module to call and arrange alarm clock and wake application program, and according to parameter " tomorrow " " morning " " 8 point " alarm clock waken that setting completed, and show the icon of one " alarm clock is arranged " on the main interface of smart mobile phone.Now, smart mobile phone has automatically switched to the main interface of smart mobile phone from locking screen interface.
The above is only the preferred embodiment of the present invention; it should be pointed out that for those skilled in the art, under the premise without departing from the principles of the invention; can also make some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.