CN104866274A

CN104866274A - Information processing method and electronic equipment

Info

Publication number: CN104866274A
Application number: CN201410718193.4A
Authority: CN
Inventors: 朱少峰
Original assignee: Lenovo Beijing Ltd
Current assignee: Lenovo Beijing Ltd
Priority date: 2014-12-01
Filing date: 2014-12-01
Publication date: 2015-08-26
Anticipated expiration: 2034-12-01
Also published as: CN104866274B

Abstract

The invention discloses an information processing method and electronic equipment. The method comprises steps as follows: when the electronic equipment is in a first working state, a voice wake-up unit detects a first voice input by a user; the first voice is stored and analyzed, and an analysis result is generated; when the analysis result indicates that the first voice comprises an instruction voice part, the voice wake-up unit executes voice wake-up operation according to the instruction voice part, so that the electronic equipment is switched from the first working state to the second working state; the instruction voice part is used for indicating first electronic equipment to execute the first operation; when the analysis result indicates that the first voice further comprises a content voice part, the first voice is recognized after the electronic equipment is switched to the second working state, and a recognition result is formed; the content voice part is used for indicating the first electronic equipment to determine execution of operation parameters related to the first operation; the recognition result comprises the operation parameters; according to the recognition result, the electronic equipment is controlled to execute the first operation on the basis of the first operation parameters.

Description

Information processing method and electronic equipment

Technical field

The present invention relates to the information processing of electronic device field, particularly relate to a kind of information processing method and electronic equipment.

Background technology

At present along with the development of electronic technology, the application that speech recognition and speech recognition are correlated with is more and more extensive in the electronic device, specifically as voice wake up.The electronic equipment that described voice wake up as being under low dormant state by detecting speech trigger is switched to state of activation.Usually electronic equipment can not carry out the functions such as voice call, short message sending or web page browsing in this condition, if user needs electronic equipment to perform above-mentioned functions, first must wake electronic equipment up; Voice wake up, and be the instruction voice part that electronic equipment receives user's input, electronic equipment wakes described electronic equipment up under the effect of instruction voice part.

But, when usual user needs to carry out appointed function operation, just can wake electronic equipment up by specified speech, as user's needs and contact person A make a phone call; Described instruction voice if " make a phone call ", when then user says " making a phone call " this specified speech to electronic equipment, electronic equipment is waken up, find in actual use, also need user manually to operate or voice operating to electronic equipment again input operation instruction, electronic equipment performs the operation made a call to contact person A just now, obvious electronic equipment not intelligent, and then result in the loaded down with trivial details and user of user operation and use susceptibility poor.

Summary of the invention

In view of this, the embodiment of the present invention is expected to provide a kind of information processing method and electronic equipment, to improve the intelligent of electronic equipment and user's user satisfaction.

For achieving the above object, technical scheme of the present invention is achieved in that the embodiment of the present invention provides a kind of information processing method, is applied in the electronic equipment comprising or be connected with voice wakeup unit; The duty of described electronic equipment comprises the first duty and the second duty; When described electronic equipment is in described first duty, described voice wakeup unit is in running order; Power consumption when described electronic equipment is in the first duty is lower than power consumption when being in described second duty;

Described method comprises:

When described electronic equipment is in the first duty, described voice wakeup unit detects the first voice of user's input;

Store and resolve described first voice, generating analysis result

When analysis result shows that described first voice comprise instruction voice part, described voice wakeup unit performs wake operation according to described instruction voice part, makes described electronic equipment be switched to described second duty from the first duty; Described instruction voice part is used to indicate described first electronic equipment and performs the first operation;

When described analysis result shows also to comprise content phonological component in the first voice, after described electronic equipment is switched to described second duty, identify that described first voice form recognition result; Described content phonological component is used to indicate described first electronic equipment and determines to perform the operating parameter with described first operative association; Described recognition result comprises described operating parameter;

Control described electronic equipment according to described recognition result and perform the first operation based on described operating parameter.

Preferably,

Described electronic equipment also comprises voice recognition unit; Described voice recognition unit is in off working state when described electronic equipment is in described first state, in running order when described electronic equipment is in described second duty;

Described first voice of described storage are: described voice wakeup unit stores described first voice;

Described method also comprises:

When described first voice comprise described instruction voice part, generate and wake mark up;

Described identify after described electronic equipment is switched to described second duty described first voice formed recognition result, comprising:

Described voice recognition unit receives described voice wakeup unit and sends described content phonological component;

Identify described content phonological component, form described recognition result;

Describedly control described electronic equipment according to described recognition result and perform the first operation based on described operating parameter, comprising:

Wake mark and described recognition result up described in foundation, control described electronic equipment and perform the first operation.

Preferably,

Described first voice of described identification form recognition result, comprising:

Described voice recognition unit receives described first voice that described voice wakeup unit sends;

Identify that described instruction voice part and described content phonological component form described recognition result.

Preferably,

Described first voice of described storage, comprising:

Receive the first voice of user's input, form the first voice signal;

Data processing is carried out to described first voice signal, forms the second voice signal; Wherein, the data volume of described second voice signal is less than the data volume of described first voice;

Described method also comprises:

After described electronic equipment is switched to described second state from described first state, give described recognition unit by described second transmitting voice signal.

Preferably,

Described first voice signal is analog voice signal; Described second voice signal is audio digital signals;

Described data processing is carried out to described first voice signal, forms the second voice signal, comprising:

Described analog voice signal is changed into audio digital signals.

Preferably,

Described data processing is carried out to described first voice signal, forms the second voice signal, also comprise:

Compress described audio digital signals, form described second voice.

Preferably,

The duty of described electronic equipment also comprises handover preparation state;

Described handover preparation state is the intermediateness that described first duty is switched to described second duty, or performs handover preparation operation to accelerate to be switched to the state of described second duty;

Described instruction voice part divides Part I and Part II by parsing order;

Described method also comprises:

When being resolved to described first voice and comprising described Part I, described voice wakeup unit controls described electronic equipment and is in described handover preparation state;

When described first voice also comprise described Part II, described voice wakeup unit controls described electronic equipment and is switched to described second duty from described handover preparation state, when described first voice do not comprise described Part II, described voice wakeup unit controls described electronic equipment and returns described first duty.

Embodiment of the present invention second aspect provides a kind of electronic equipment, and described electronic equipment comprises or is connected with in the electronic equipment of voice wakeup unit; The duty of described electronic equipment comprises the first duty and the second duty; When described electronic equipment is in described first duty, described voice wakeup unit is in running order; Power consumption when described electronic equipment is in the first duty is lower than power consumption when being in described second duty;

Described electronic equipment also comprises storing and resolving unit, voice recognition unit and performance element;

Described voice wakeup unit, specifically for when described electronic equipment is in the first duty, detects the first voice of user's input;

Described storing and resolving unit, for storing and resolving described first voice, generates analysis result

Described voice wakeup unit, time also for showing that when analysis result described first voice comprise instruction voice part, performing wake operation according to described instruction voice part, making described electronic equipment be switched to described second duty from the first duty; Described instruction voice part is used to indicate described first electronic equipment and performs the first operation;

Described voice recognition unit, during for showing when described analysis result also to comprise content phonological component in the first voice, identifies that after described electronic equipment is switched to described second duty described first voice form recognition result; Described content phonological component is used to indicate described first electronic equipment and determines to perform the operating parameter with described first operative association; Described recognition result comprises described operating parameter;

Performance element, performs the first operation for controlling described electronic equipment according to described recognition result based on described operating parameter.

Preferably,

Described voice recognition unit is in off working state when described electronic equipment is in described first state, in running order when described electronic equipment is in described second duty;

Described storing and resolving unit is a part for described voice wakeup unit, for storing described first voice;

Described voice wakeup unit, also for

Described recognition unit, sends described content phonological component for receiving described voice wakeup unit, and identifies described content phonological component;

Described voice recognition unit, for receiving described content phonological component; And identify described content phonological component, form described recognition result;

Described performance element, for waking mark and described recognition result described in foundation up, controlling described electronic equipment and performing the first operation.

Preferably,

Described voice recognition unit, for receiving described first voice that described voice wakeup unit sends; And identify that described instruction voice part and described content phonological component form described recognition result.

Preferably,

Described voice wakeup unit, specifically for receiving the first voice of user's input, forms the first voice signal; Data processing is carried out to described first voice signal, forms the second voice signal; Wherein, the data volume of described second voice signal is less than the data volume of described first voice;

Described voice wakeup unit, also for after described electronic equipment is switched to described second state from described first state, gives described recognition unit by described second transmitting voice signal.

Preferably,

Described voice wakeup unit, specifically for changing into audio digital signals by described analog voice signal.

Preferably,

Described voice wakeup unit, also for compressing described audio digital signals, forms described second voice signal.

Preferably,

Described instruction voice part divides Part I and Part II by parsing order;

Described voice wakeup unit, also for when being resolved to described first voice and comprising described Part I, controls described electronic equipment and is in described handover preparation state;

Described voice wakeup unit, also for when described first voice also comprise described Part II, control described electronic equipment and be switched to described second duty from described handover preparation state, when described first voice do not comprise described Part II, control described electronic equipment and return described first duty.

Information processing method described in the embodiment of the present invention and electronic equipment, after receiving the first voice, when described first voice comprise instruction voice part, wake described electronic equipment up, and after electronic equipment is waken up, the at least content phonological component of the first voice stored is given to voice recognition unit, determines the operating parameter performing the first operation according to instruction voice part, and then perform the first operation.Obvious user to call so-and-so by inputting an instruction electronic equipment to electronic equipment or to refresh the first similar voice of unrestrained microblogging, electronic equipment is by the execution phonetic storage of intelligence, resolve, waking up of electronic equipment, speech recognition, and the final electronic equipment that controls performs the operating parameter determined according to content phonological component, perform the first operation, like this relative to prior art, first user need not wake electronic equipment up by waking voice up, specify application to operations such as electronic equipment input operation voice by opening again, just can control electronic equipment and perform the first operation, embodiment of the present invention method is applied to existing electronic equipment, better make use of electronic equipment, improve the intelligent of electronic equipment and user's user satisfaction.

Accompanying drawing explanation

One of schematic flow sheet that Fig. 1 is the information processing method described in the embodiment of the present invention;

The schematic flow sheet two that Fig. 2 is the information processing method described in the embodiment of the present invention;

The schematic flow sheet three that Fig. 3 is the information processing method described in the embodiment of the present invention;

The schematic flow sheet four that Fig. 4 is the information processing method described in the embodiment of the present invention;

One of structural representation that Fig. 5 is the electronic equipment described in the embodiment of the present invention;

The structural representation two that Fig. 6 is the electronic equipment described in the embodiment of the present invention.

Embodiment

Below in conjunction with Figure of description and specific embodiment technical scheme of the present invention done and further elaborate.

Embodiment of the method one:

As shown in Figure 1, the present embodiment provides a kind of information processing method, is applied in the electronic equipment comprising or be connected with voice wakeup unit; The duty of described electronic equipment comprises the first duty and the second duty; When described electronic equipment is in described first duty, described voice wakeup unit is in running order; Power consumption when described electronic equipment is in the first duty is lower than power consumption when being in described second duty;

Described method comprises:

Step S110: when described electronic equipment is in the first duty, described voice wakeup unit detects the first voice of user's input;

Step S120: store and resolve described first voice, generates analysis result

Step S130: when analysis result shows that described first voice comprise instruction voice part, described voice wakeup unit performs wake operation according to described instruction voice part, makes described electronic equipment be switched to described second duty from the first duty; Wherein, described instruction voice part is used to indicate described first electronic equipment and performs the first operation;

Step S140: when described analysis result shows also to comprise content phonological component in the first voice, identifies that after described electronic equipment is switched to described second duty described first voice form recognition result; Described content phonological component is used to indicate described first electronic equipment and determines to perform the operating parameter with described first operative association; Described recognition result comprises described operating parameter;

Step S150: control described electronic equipment according to described recognition result and perform the first operation based on described operating parameter.

Described first electronic equipment can be the electronic equipments such as mobile phone, panel computer or e-book, is preferably mobile electronic device.

Described first duty can be the low power consumpting states such as dormant state, and the now application such as the voice recognition unit of described electronic equipment and performance element or process structure are all in off working state, to save power consumption.Described second duty can be the duty that the electronic equipment such as state of activation or ready state normally can perform various operation, and to be comparatively in described first duty high for the power consumption of described electronic equipment in this condition.

In the present embodiment, when described first electronic equipment is in the first duty, can normally work when described wakeup unit is in running order; Concrete as, can receive and wake voice up and wake electronic equipment up.Usually after described first electronic equipment is in described second duty, described wakeup unit can in running order or off working state, is preferably off working state to reduce the power consumption of electronic equipment under described second duty.

Described first voice are the voice operating instruction that user wants to be sent to described electronic equipment by voice, and concrete as " making a phone call to Zhang San ", this is an operational order.Wherein, described " making a phone call " is instruction voice part, and instruction electronic equipment performs the operation of making a phone call; Described " to Zhang San " is the content phonological component with described this operative association of making a phone call, and can determine make a phone call to whom according to content phonological component.Wherein, described to Zhang San be contact person; Described instruction voice part be for control electronic equipment carry out voice or short message communication time, described content phonological component can comprise the contact person that carries out communicating and wait operating parameter.

For another example, described first voice can also be as " browsing Sina's microblogging ".Now, described " browsing " and " microblogging " are instruction electronic equipment and perform the operation of opening microblogging application, if current electronic device can run Sina's microblogging application, Tengxun's microblogging application, specifically open which microblogging, content phonological component " Sina " then in described " browsing Sina's microblogging " defines the operating parameter opening microblogging application, is specially and opens Sina's microblogging application.

Obvious described instruction voice part can be the phonological component of continuous distribution in the first voice, also can be the phonological component of discrete distribution in the first voice; The instruction voice part of continuous distribution comprises " making a phone call " or " sending short messages " etc.The instruction voice part of discrete distribution comprises " browsing " and " microblogging " and forms.

Usually, described instruction voice part at least may comprise a verb, described verb is the action that instruction electronic equipment performs the first operation, concrete as " the beating " in " making a phone call ", " browsing " in " sending out " in " sending short messages " for another example and " browsing xx microblogging ", these verb lists understand it is that instruction electronic equipment performs an action.And described content phonological component possibility correspondence is that noun or a pronoun etc. have tell-tale noun or pronoun phrase, the object that in a described instruction voice part pointed to, action is pointed to may be pointed to; Concrete as make a phone call to Zhang San but not Li Si or other people, be Sina's microblogging as what browse, but not Tengxun's microblogging; What " consult the short breath finally received " for another example and consult is the note finally received, but not the second from the bottom note received recently.When specific implementation, described electronic equipment can receive, limit stores and resolves the first voice.When described first voice are described " making a phone call to Zhang San ".When resolving, find the instruction voice part that these voice comprise " making a phone call ", this part of speech can be used for triggering described wakeup unit simultaneously and wakes described first electronic equipment up, controls described first electronic equipment and is switched to described second duty by described first duty.

This one receives simultaneously and resolves simultaneous operation, after receiving whole first voice, then resolves, be advanced by the initial time of parsing, can acquisition analysis result more early, wake electronic equipment up faster, from the response speed that can promote electronic equipment and respond the first voice.

When the voice wakeup unit described in the present embodiment receives described first voice, storage medium in running order in the first operative state in electronic equipment stores the voice of lower described " making a phone call to Zhang San ", and resolves described voice.Storage medium under in running order under described first duty can be the storage medium in described voice wakeup unit or the less storer of the power consumption being separated setting with described voice wakeup unit.

After described second electronic device works to the second duty, described electronic equipment is waken up, and system or the voice recognition unit of electronic equipment are also waken up, concrete as, the structures such as the application processor AP of described electronic equipment or microprocessor are waken up.

After described electronic equipment is waken up, system or recognition unit receive described first voice from described wakeup unit, resolve described voice, obtain at least about the recognition result of described content phonological component.The recognition result of described content phonological component at least may be used for determining that described electronic equipment performs at least one operating parameter of the first operation, as made a phone call to whom.

If in the prior art, if user is when electronic equipment is in dormant state, input described first voice, electronic equipment None-identified goes out will to making a phone call, user has to first allow electronic equipment be waken up with waking voice up, repeat again once to indicate electronic equipment to perform the first voice of the first operation, make electronic equipment determine specifically how to perform described operation.

Comprehensively above-mentioned, no matter be the operation voice that " browsing Sina's microblogging " or " making a phone call to Zhang San " are user's input, but after electronic equipment detects these voice, first voice not only resolved, store, to facilitate follow-up identification simultaneously; At this, will wake operation be performed according to the instruction voice part in voice, after electronic equipment is waken up, to by described voice, and will directly perform corresponding operation according to described recognition result; Voice of obvious user input, electronic equipment will perform a series of operation, finally can rapidly for user improves its service wanted, and obvious electronic equipment has intelligent height and the high advantage of user's user satisfaction.

Specifically how to resolve described first voice, to determine whether to comprise in described first voice described specified speech part and described content phonological component mode is a lot, below provide a kind of method: specifically comprise:

Extract the fisrt feature of described first voice;

The second feature of described fisrt feature with the specified speech part prestored is mated, forms matching result;

According to described matching result, control the switching of the duty of described electronic equipment.

Described fisrt feature and second feature may comprise word, word or phoneme feature.As comprised the voice of " making a phone call ".Determine whether comprise instruction voice part in the first voice by voice match.Wherein, described second feature can be stored in speech database, can include multiple second feature in described speech database.The instruction voice part that described speech database can pre-enter from user is in advance set up, also can be before electronic equipment dispatches from the factory or electronic equipment dispatch from the factory after the speech database downloaded from other electronic equipments (as network) of electronic equipment determine.

But at the coupling exact matching of fisrt feature and second feature; Now, described database comprises the feature of a lot of operational orders; As " making a phone call ", " sending short messages ", " making a phone call " and " refreshing unrestrained microblogging "; But only there is the feature of specifying, as " making a phone call ", " sending short messages " and " making a phone call " character pair are just identified as second feature; This be only described first voice comprise above-mentioned three at least one of them time, just perform confirm described first voice comprise described instruction voice part.If now, the first voice only comprise " refreshing unrestrained microblogging ", electronic equipment is thought in step s 130, which and is not comprised instruction voice part in described first voice.

In coupling or the fuzzy matching of fisrt feature and second feature; Fuzzy assorted mode comprises again two kinds:

The first: store the feature of specifying in database, as " making a phone call " but when parsing first voice " calling Zhang San ", find the synonym of " making a phone call ", now also determine that described fisrt feature is the second feature that correspondence is specified.The second: every described database can identifying operation instruction, all can think and comprise described instruction voice part.In this fashion, the first voice only comprise " refreshing unrestrained microblogging " electronic equipment and think that described first voice comprise instruction voice part in step s 130, which.In this fashion, when described first voice only comprise " to Zhang San ", owing to there is no operational order, then can think and not comprise instruction voice part, when other comprise instruction voice part, as long as this instruction voice part is identified correctly, can wake up.

Adopt before the requirement of a kind of mode to the database of the wakeup unit of electronic equipment lower, user can according to oneself need carry out individual character setting, the second way is obviously more intelligent.When determining whether to comprise content phonological component in described first voice, following at least two kinds of methods can be comprised:

Method one: can simply by whether the voice comprised beyond instruction voice part are determined, if comprise the voice beyond instruction voice part, can think that these first voice comprise content phonological component, need to be waken up rear System on Chip/SoC by electronic equipment or the more powerful speech chip of function identifies.

Method two: usual described voice wakeup unit can also be split voice according to naturally semantic, the relation between and instruction phonological component can be determined, can determine whether the voice in the first voice beyond instruction phonological component are the content phonological component that can be used in determining the operating parameter that execution first operates.

When described first voice are: please make a phone call to Zhang San.If described " making a phone call " is instruction voice part; According to first method, directly " please to Zhang San " can be considered as content phonological component; According to second method, then can using described " to Zhang San " as content phonological component.

When Chinese identification, described content phonological component at least comprises the adverbial modifier's part that correspond to instruction voice part verb usually, and described adverbial modifier's part is for determining the object etc. that described action executing points to.

When specific implementation, described first voice can be as " making a phone call to Zhang San " as described in content phonological component in the first voice clear and definite give " to Zhang San " object that this is made a phone call.

Sometimes, described first voice are fuzzyyer when indicating the operating parameter for performing the first operation, now may need to carry out fuzzy parsing to content phonological component, to determine described operating parameter in step S140.Concrete as, when described first voice are " checking the note just received ", the instruction voice part that these voice comprise " checking xx note "; Possible electronic equipment receives many notes before this, specifically after electronic equipment is waken up, show which bar note on an electronic device, then may need to check current time in step S140, to not sorted by the priority that the note of checking carries out time of reception, determine that the note finally received before current time is described note A, then in step S150S150, directly on the display unit of electronic equipment, show described note A.

In addition, described first operation is used for making a general reference the sequence of operations determined according to described instruction voice part in the present embodiment; Concrete as " making a phone call ", then described electronic equipment is when operation is made a phone call in execution, first, comprise the application of opening and making a phone call, according to described content phonological component query communication record, thus obtain the communication identifier A (as cell-phone number) of communication the other side, according to operations such as described communication identifier A externally dial.

For another example, " checking Sohu's webpage ", step S150S150 performs described first operation and may comprise, and open any browser enters searched page, " Sohu " searched for as key word; Find the chained address of Sohu's webpage, obtain described chained address and enter Sohu's webpage, the homepage of electronic equipment display Sohu webpage.

Obvious electronic equipment is final externally to dial according to communication identifier A and the homepage of electronic equipment display Sohu webpage, is last operation in described first operation.Therefore the described electronic equipment of described first operation general reference is according to the sequence of operations performed after being waken up in described first voice.

When specific implementation, electronic equipment only can perform last operation of described first operation on the foreground of electronic equipment, other operations in described first operation perform by the backstage of described first electronic equipment; Also can be that described electronic equipment performs each operation in described first operation on foreground, can see current operation progress to make user.

What operate in foreground execution first is operating as by the mode such as display screen or voice-output unit, by the output of process that current operation performs, so that user operation.Specifically as query communication record, when performing on foreground, then the display unit display communication record etc. of electronic equipment.

According to two kinds of operation executive modes, can corresponding two kinds of operator schemes; Electronic equipment is determined according to different operator schemes.Certainly, when described electronic equipment response is enough fast, be preferably first kind of way, if the implementation of display electronic equipment, too fast owing to operating, the effect that user checks is not good.

When specific implementation, in order to the use safety of described electronic equipment, the information processing method described in the present embodiment can also comprise:

Extract the voice characteristics information of described first voice;

Safety verification is carried out according to described voice characteristics information; Wherein, safety verification can be: voice print verification; Described voice characteristics information is vocal print feature, compare with the vocal print feature of the validated user be stored in advance in voice wakeup unit, when the comparison goodness of fit reaches designated value, as the comparison goodness of fit has exceeded 80%, then determine by described safety verification, otherwise safety verification failure;

After described safety verification passes through, just perform described step S150, with the information security of the use safety and described electronic equipment inner storag information that improve electronic equipment.

Embodiment of the method two:

Described method comprises:

Step S120: store and resolve described first voice, generates analysis result

Step S130: when analysis result shows that described first voice comprise instruction voice part, described voice wakeup unit performs wake operation according to described instruction voice part, makes described electronic equipment be switched to described second duty from the first duty; Described instruction voice part is used to indicate described first electronic equipment and performs the first operation;

Described first voice of storage in described step S120 specifically can be: described voice wakeup unit stores described first voice; When specific implementation, described first voice can store in the storage medium or storer keeping duty in the first operative state.

Be specifically how to identify described first voice in step S140 and step S150, how to perform the first method operated according to recognition result has multiple, below provides a kind of optional manner:

As shown in Figure 2, described method also comprises:

Step S131: when described first voice comprise described instruction voice part, generates and wakes mark up;

Described step S140 can comprise:

Step S141: described voice recognition unit receives described voice wakeup unit and sends described content phonological component;

Step S142: identify described content phonological component, form described recognition result.

Described step S150 comprises:

In this fashion, described voice wakeup unit based on any one instruction voice part in N number of instruction voice part, may carry out wake operation; In the present embodiment when voice wakeup unit detect be a certain instruction voice part time, also formed wake mark up, with reduce be waken up rear voice recognition unit need identify voice length, to improve the speed of response.

Concrete as, " make a phone call ", " browsing xx webpage ", " sending short messages " can as instruction voice part, while controlling the operation of described electronic equipment execution response, also described electronic equipment is made to be switched to the second duty from the first duty as waking voice up.If electronic equipment finds by resolving, first voice " are made a phone call " to comprise described instruction voice part and " are made a phone call " to be formed and wake mark " 1 " up to Zhang Shan, now, voice wake-up module is also by according to the instruction voice part in described first voice " to be made a phone call " and other parts are separated, specifically according to natural sentence logic, first voice are split, obtains described content phonological component; Described content phonological component is sent to voice recognition unit; Then now voice recognition unit only identifies the content phonological component of " to Zhang San ", the voice contraction in length obviously identified.

When Subsequent electronic equipment performs described first operation, wake mark described in knowing up and determine to need to perform the operation of making a phone call, at the recognition result according to content phonological component, can know and to make a phone call to Zhang San; Information processing method described in obvious the present embodiment, electronic equipment can not only be made when user inputs operation voice, complete waking up and respective operations of electronic equipment, simultaneously also by the fractionation to input voice, complete speech recognition fast, and decrease the response delay that described electronic equipment performs described first operation.

As shown in Figure 3, in the T1 moment, described first electronic equipment is in running order, now voice wakeup unit is in running order, voice recognition unit be in non-off working state, voice wakeup unit and be between the electronic structures such as off working state by the internal communications interface of the electronic equipments such as bus be connected.

In the T1 moment, voice wakeup unit receives the first voice, sends wake-up signal, make described second electronic equipment be switched to the second duty to the structure such as voice recognition unit being in off working state.

In the T2 moment, electronic equipment is waken up and is switched to the second duty, and described voice recognition unit the structure such as to fall and is switched to duty, and now, voice wakeup unit is by described content phonological component and wake mark up and send to voice recognition unit.Wherein, the described T2 moment is the moment being later than the described T1 moment.

Embodiment of the method three:

Described method comprises:

Step S120: store and resolve described first voice, generates analysis result

Described step S150 comprises:

Whole voice are all sent to described voice recognition unit by described voice wakeup unit in the present embodiment, voice recognition unit carries out entirety to described first voice and identifies, as " making a phone call to Zhang San " in the present embodiment can to as described in make a phone call to carry out entirety to Zhang San and identify, the recognition result of such formation comprises the recognition result part to the identification of instruction voice part and the recognition result to the identification of content phonological component.Electronic equipment only can perform described first operation according to described recognition result.

Specifically as shown in Figure 4, in the T1 moment, described first electronic equipment is in running order, now voice wakeup unit is in running order, voice recognition unit be in non-off working state, voice wakeup unit and be between the electronic structures such as off working state by the internal communications interface of the electronic equipments such as bus be connected.

In the T3 moment, electronic equipment is waken up and is switched to the second duty, and described voice recognition unit the structure such as to fall and is switched to duty, and now, described the first complete voice are sent to voice recognition unit by voice wakeup unit.Wherein, the described T3 moment is the moment being later than the described T1 moment.

Compare the present embodiment and embodiment of the method two or Fig. 3 or Fig. 4 difference to be: in the present embodiment, electronic equipment upon awakening, is the entirety identification to the first voice; And can not be formed and wake mark up; Adopt and and need not pinch in this way and can split and wake the generation of mark up by voice, have and realize easy and low to the hardware and software performance requirement of voice wakeup unit advantage.

Embodiment of the method four:

Described method comprises:

Step S120: store and resolve described first voice, generates analysis result

Mode one:

As shown in Figure 2, described method also comprises:

Described step S140 can comprise: described voice recognition unit receives described voice wakeup unit and sends described content phonological component; And identify described content phonological component, form described recognition result;

Described step S150 comprises:

Mode two:

Described step S150 comprises:

Described step S120 stores described first voice, comprising:

Step S121: the first voice receiving user's input, form the first voice signal;

Step S122: data processing is carried out to described first voice signal, forms the second voice signal; Wherein, the data volume of described second voice signal is less than the data volume of described first voice;

Described method also comprises:

Method described in the present embodiment, also carry out data processing by the first voice signal corresponding to the first voice, form the second voice signal that data volume is less relative to the data volume of described first voice signal, to reduce the data volume stored, and finally with reduce the data volume that sends to voice recognition unit number, obvious this can reduce voice recognition unit and obtain the first complete voice or the time span of content phonological component, thus reduces the response delay that described electronic equipment performs described first operation.

Embodiment of the method five:

Described method comprises:

Step S120: store and resolve described first voice, generates analysis result

Mode one:

As shown in Figure 2, described method also comprises:

Described step S150 comprises:

Mode two:

Described step S150 comprises:

Described step S120 stores described first voice, comprising:

Step S121: the first voice receiving user's input, form the first voice signal;

Described method also comprises:

Described step S122, comprising: described analog voice signal is changed into audio digital signals.

After digital-to-analog conversion, the data volume of the audio digital signals formed is less than the data volume of described analog voice signal greatly, the data volume storing and transmit can be reduced, the response speed of information processing can be improved, reduce the response delay that described electronic equipment performs described first operation.

Embodiment of the method six:

Described method comprises:

Step S120: store and resolve described first voice, generates analysis result

Mode one:

As shown in Figure 2, described method also comprises:

Described step S150 comprises:

Mode two:

Described step S150 comprises:

Described step S120 stores described first voice, comprising:

Step S121: the first voice receiving user's input, form the first voice signal;

Described method also comprises:

Described first voice signal is analog voice signal, and described second voice signal is audio digital signals.

Described step S122 specifically can comprise: described analog voice signal is changed into audio digital signals;

Compress described audio digital signals, again to reduce the amount of voice data of storage and to be transferred to the time of described voice recognition unit, from the response speed that again can improve electronic equipment, so that the operation voice of user can be responded fast, perform the first operation.

Embodiment of the method seven:

Described method comprises:

Step S120: store and resolve described first voice, generates analysis result

Described instruction voice part divides Part I and Part II by parsing order;

Described method also comprises:

When described first voice also comprise described Part II, described voice wakeup unit controls described electronic equipment and is switched to described second duty from described handover preparation state, when described first voice do not comprise described Part II, described voice wakeup unit controls described electronic equipment and returns in described first duty.

Concrete as, when described first voice be " reading electronic book " xx " " wherein, described " reading electronic book " according to parsing order, can be split as two parts, and a part is " reading ", and another part is " e-book ".Usual electronic equipment, when carrying out the parsing of the first voice, can simulate the understanding of people to voice semanteme usually, splits described first voice with natural statement.

According to the method described in the present embodiment, then when being resolved to described first voice and comprising " reading ", described voice wakeup unit, controls described electronic equipment and is switched to handover preparation state from the first duty; When detecting that described " e-book " determines described instruction voice part simultaneously for waking the voice of described electronic equipment up for the moment, controlling described electronic equipment and being switched to described second duty from described handover preparation state.

Method described in obvious employing the present embodiment, if described first voice comprise when described electronic equipment can be made to be switched to the instruction voice part of the second duty from the first duty, adopt the method described in the present embodiment, the Part I that the initial time that state switches analytically comprises instruction voice part to described first voice starts; If do not adopt the method described in the present embodiment but start after the Part I be resolved in described first voice and Part II, the initial time that obvious state switches obviously is later than the initial time of the method described in the present embodiment.Now, if the switching duration that hypothesis is switched to the second duty from the first duty is certain, obviously more early starts to carry out state switching, just more early can enter the second duty, thus improve the speed of described first voice of electronic equipment response.

Certainly follow-up to the first speech analysis time, find the Part I only comprising specified speech part in described first voice, do not comprise Part II and then return described first duty, so still can ensure the advantage of the low-power consumption of described first electronic equipment.

When specific implementation, the power consumption that described electronic equipment is in described handover preparation state be less than described electronic equipment be in described second duty under power consumption, may be more than or equal to described electronic equipment be in the first duty under power consumption.

Described handover preparation state for corresponding to various states, can below provide two kinds of optional status:

State one: described handover preparation state can be the intermediateness between described first duty and described second duty; Namely described handover preparation state is intermediate state.

Concrete as, described first duty is dormant state, and described second duty is state of activation, for smart mobile phone; Smart mobile phone is switched to state of activation from dormant state, will inevitably in some chien shih central processing unit be switched to state of activation by dormant state or light screen, to activate image processor user-friendly etc.Usually the display pages such as desktop can be shown after lighting screen; The content of concrete display can be determined by image processor.When described handover preparation state be described first duty to described second duty time, need respectively to described central processing unit, image processor and screen send activation signal; Now, described handover preparation state can for have sent activation signal to described image processor, makes described image processor be switched to duty and the structure such as described central processing unit and screen also remains on the duty of off working state from off working state.

When specific implementation, the problems such as the switching time of duty can be switched to according to the power consumption size of all parts after being switched to duty or all parts from off working state, first carry out by the switching of off working state to duty under described handover preparation state.

State two:

Described handover preparation state also, the state of the execution preparatory function that can switch to the second duty for acceleration first duty.

Concrete as, it is very long to add the response time making components A be switched to duty from off working state, its response time has directly elongated electronic equipment is switched to the second duty average duration from the first duty, and the state now first can carrying out described components A switches.Obviously, in the duty handoff procedure of components A, the process of experience is described electronic equipment from described first state to an intermediateness of described second state switching.

Described electronic equipment is switched to described second duty from the first duty, such as need to generate and trigger described electronic equipment is switched to the second duty trigger pip from the first duty, and described trigger pip is sent to as after System on Chip/SoC, make described electronic equipment be switched to the second duty from described first duty; When described handover preparation state is the state of the execution preparatory function that acceleration first duty switches to the second duty, under described handover preparation state, described voice wakeup unit will generate described trigger pip; When described first voice comprise described Part II, described trigger pip is being sent to System on Chip/SoC, so just can wake described electronic equipment fast up, described electronic equipment is being completed fast and is switched to the second duty from the first duty.

By resolving the portions of specified speech part in obvious the present embodiment, described electronic equipment can be accelerated and be switched to the second duty, thus the speed of response to the first voice can be accelerated.

Apparatus embodiments one:

As shown in Figure 5, the present embodiment provides a kind of electronic equipment, and described electronic equipment comprises or is connected with in the electronic equipment of voice wakeup unit 110; The duty of described electronic equipment comprises the first duty and the second duty; When described electronic equipment is in described first duty, described voice wakeup unit 110 is in running order; Power consumption when described electronic equipment is in the first duty is lower than power consumption when being in described second duty;

Described electronic equipment also comprises storing and resolving unit 120, voice recognition unit 130 and performance element 140;

Described voice wakeup unit 110, specifically for when described electronic equipment is in the first duty, detects the first voice of user's input;

Described storing and resolving unit 120, for storing and resolving described first voice, generates analysis result

Described voice wakeup unit 110, time also for showing that when analysis result described first voice comprise instruction voice part, performing wake operation according to described instruction voice part, making described electronic equipment be switched to described second duty from the first duty; Described instruction voice part is used to indicate described first electronic equipment and performs the first operation;

Described voice recognition unit 130, during for showing when described analysis result also to comprise content phonological component in the first voice, identifies that after described electronic equipment is switched to described second duty described first voice form recognition result; Described content phonological component is used to indicate described first electronic equipment and determines to perform the operating parameter with described first operative association; Described recognition result comprises described operating parameter;

Performance element 140, performs the first operation for controlling described electronic equipment according to described recognition result based on described operating parameter.

Described voice wakeup unit 110 can comprise phonographic recorder; Described phonographic recorder at least can be used for the first voice described in buffer memory;

Described storing and resolving unit 120 specifically can comprise storage medium and speech analysis device, for storing described first voice; Described speech analysis device can comprise again database and process chip or processor; Described process chip is used for according to the feature of the speech analysis stored in described database to resolve described first voice.

The concrete structure of described voice recognition unit 130 can comprise processor or the process chip of speech recognition database and speech recognition.

Described performance element can comprise processor, concrete as performed the various first application processor operated or central processing unit.

Processor in the wakeup unit of voice described in the present embodiment and speech recognition, can be the processor that microprocessor or digital signal processor or programmable array etc. have processing capacity, is preferably the processor of low-power consumption.

It is the information processing method described in embodiment of the method one that electronic equipment described in the present embodiment is used for, and provide and realize hardware, same has intelligent height, electronic equipment be utilized better and the high advantage of user's user satisfaction.

Apparatus embodiments two:

As shown in Figure 6, the present embodiment provides a kind of electronic equipment, and described electronic equipment comprises or is connected with in the electronic equipment of voice wakeup unit 110; The duty of described electronic equipment comprises the first duty and the second duty; When described electronic equipment is in described first duty, described voice wakeup unit 110 is in running order; Power consumption when described electronic equipment is in the first duty is lower than power consumption when being in described second duty;

Described voice recognition unit 130 is in off working state when described electronic equipment is in described first state, in running order when described electronic equipment is in described second duty;

Described storing and resolving unit 120 is a part for described voice wakeup unit 110, for storing described first voice;

Described voice wakeup unit 110, also for when described first voice comprise described instruction voice part, generates and wakes mark up;

Described voice recognition unit, sends described content phonological component for receiving described voice wakeup unit, and identifies described content phonological component;

Described voice recognition unit 130, for receiving described content phonological component; And identify described content phonological component, form described recognition result;

Described performance element 140, for waking mark and described recognition result described in foundation up, controlling described electronic equipment and performing the first operation.

Described storing and resolving unit is a part for described voice wakeup unit in the present embodiment; Described voice wakeup unit can comprise speech analysis processor and storage medium; It is low power processor that usual described voice wake chip up; Described storage medium can be connected by the communication interface of the chip internals such as bus with described speech analysis processor.Described storage medium stores executable instruction, and described speech analysis processor by performing described executable instruction, can resolve described first voice, and described storage medium also can be used for storing described first voice simultaneously.

In the storage medium of described voice wakeup unit in the present embodiment, also may store each instruction voice part corresponding wake mark up; When being resolved to described first voice and comprising specific instruction phonological component, by the record by inquiry correspondence, described in determining, wake mark up.This wakes the first operation that mark may be used for determining that described instruction voice part instruction electronic equipment performs up.

After described electronic equipment is waken up, described electronic equipment is switched to the second duty from the first duty, then described voice recognition unit is switched to duty from off working state, now, described voice recognition unit, for receiving the content phonological component in described first voice from described voice wakeup unit, and identify described content phonological component, at least one parameter of the first operation that electronic equipment performs can be determined." to Zhang San " in concrete identification first voice determine be calling Zhang San but not Li Si or other people.

The concrete structure of described voice recognition unit see apparatus embodiments one, just no longer can be repeated at this.In addition, the annexation between described voice wakeup unit and voice recognition unit and the handoff relation of duty see Fig. 3 and embodiment of the method two, just no longer can be repeated at this.

Present embodiments provide a kind of electronic equipment, may be used for, for the information processing method described in embodiment of the method two, providing and realizing hardware, the simple and intelligent high advantage of the structure with electronic equipment.

Apparatus embodiments three:

Described voice recognition unit 130, for receiving described first voice that described voice wakeup unit sends; And identify that described instruction voice part and described content phonological component form described recognition result.

The present embodiment and a upper apparatus embodiments unlike, the voice recognition unit 130 in the present embodiment will receive complete described first voice from described voice recognition unit, but not is full of content phonological component; But wake mark up described in can not receiving from described voice wakeup unit; The wakeup unit of voice described in the present embodiment 130 is for after identifying described first voice, and described recognition result comprises the recognition result to instruction voice part and content phonological component.Described instruction voice part can be used for the concrete operations type determining the first operation, and described content phonological component can be used for determining that whom performs first to operates, concrete as made a phone call to Zhang San; Be Sina's microblogging as what browse, what consult is the last item note etc.Adopt the structure of electronic equipment described in the present embodiment, then described performance element can perform the first operation by recognition result described in direct basis.

Electronic equipment described in the present embodiment can be used for any one technical scheme in implementation method embodiment three, and same have intelligent height and the high advantage of user's user satisfaction.

Apparatus embodiments four:

Described voice recognition unit 130, for receiving described first voice that described voice wakeup unit sends; And identify that described instruction voice part and described content phonological component form described recognition result;

Or

In addition, described voice wakeup unit 110, specifically for receiving the first voice of user's input, forms the first voice signal; Data processing is carried out to described first voice signal, forms the second voice signal; Wherein, the data volume of described second voice signal is less than the data volume of described first voice;

Described voice wakeup unit 110, also for after described electronic equipment is switched to described second state from described first state, gives described recognition unit by described second transmitting voice signal.

The wakeup unit of voice described in the present embodiment, after receiving described first voice, also by the first voice signal corresponding to described first voice, carries out signal transacting to form the second few voice signal of more described first voice signal of data volume; The storage medium of such voice wakeup unit, specifically for storing described second voice signal.And in described voice wakeup unit, what transmit to described voice recognition unit is the second voice signal, the storage space of described voice wakeup unit can be saved like this, the more important thing is, voice wakeup unit can be reduced after voice recognition unit is waken up and is switched to duty, to the data volume of its transmission, thus response efficiency can be improved.

Described voice wakeup unit specifically comprises the processor or process chip with data processing function.Processor described in the embodiment of the present invention or process chip, can comprise the structure such as application processor or process chip AP, Micro-processor MCV or programmable array, and be preferably the lower chip of power consumption.

Electronic equipment described in the present embodiment is the information processing method described in embodiment of the method four, provide and realize hardware, can be used for technical scheme described arbitrarily in implementation method embodiment four, electronic equipment not only has intelligent high advantage, also has the high advantage of the speed of response simultaneously.

Apparatus embodiments five:

Or

Described voice wakeup unit comprises D/A converter module, is used in when carrying out data processing, specifically can be used for the first speech conversion for simulating signal to become digital signal second voice.Described D/A converter module can comprise digital to analog converter.The data volume of the second voice of digital signal is less than the data volume of the second voice of described simulating signal.

Comprehensively above-mentioned, what the present embodiment provided a kind of voice wakeup unit based on a upper embodiment realizes structure, to reduce data volume corresponding to the first voice by digital-to-analog conversion.

Further, described voice wakeup unit 110, also for compressing described audio digital signals, forms described second voice to the present embodiment.Described voice wakeup unit 110 also can comprise signal compression structure, can compress the second voice signal further, reduces the data volume that voice wakeup unit is transmitted to voice recognition unit further, to improve the speed of response of electronic equipment further.

Apparatus embodiments six:

As shown in Figure 1, the present embodiment is the further improvement on the basis of apparatus embodiments one, apparatus embodiments two or apparatus embodiments three, the electronic equipment described in the present embodiment, and described electronic equipment comprises or is connected with in the electronic equipment of voice wakeup unit 110; The duty of described electronic equipment comprises the first duty and the second duty; When described electronic equipment is in described first duty, described voice wakeup unit 110 is in running order; Power consumption when described electronic equipment is in the first duty is lower than power consumption when being in described second duty;

Described instruction voice part divides Part I and Part II by parsing order;

Described voice wakeup unit 110, also for when being resolved to described first voice and comprising described Part I, controls described electronic equipment and is in described handover preparation state;

Described voice wakeup unit 120, also for when described first voice also comprise described Part II, control described electronic equipment and be switched to described second duty from described handover preparation state, when described first voice do not comprise described Part II, control described electronic equipment and return described first duty.

Voice wakeup unit 120 described in the present embodiment is when resolving described first voice, the state of electronic equipment described in execute in steps toggle switches, by the introducing of described handover preparation state, the switching of described first duty to described second duty can be started in advance, when described first voice comprise Part I and the Part II of instruction voice part, can make as early as possible electronic equipment more early enter described second duty, thus accelerate the speed of described first voice of described electronic equipment response.

Electronic equipment described in the present embodiment can be used for, for the information processing method described in embodiment of the method seven, providing and realizing hardware, has intelligent height and the high advantage of user satisfaction, also has the high advantage of the speed of response simultaneously.

In several embodiments that the application provides, should be understood that disclosed equipment and method can realize by another way.Apparatus embodiments described above is only schematic, such as, the division of described unit, be only a kind of logic function to divide, actual can have other dividing mode when realizing, and as: multiple unit or assembly can be in conjunction with, maybe can be integrated into another system, or some features can be ignored, or do not perform.In addition, the coupling each other of shown or discussed each ingredient or direct-coupling or communication connection can be by some interfaces, and the indirect coupling of equipment or unit or communication connection can be electrical, machinery or other form.

The above-mentioned unit illustrated as separating component or can may not be and physically separates, and the parts as unit display can be or may not be physical location, namely can be positioned at a place, also can be distributed in multiple network element; Part or all of unit wherein can be selected according to the actual needs to realize the object of the present embodiment scheme.

In addition, each functional unit in various embodiments of the present invention can all be integrated in a processing module, also can be each unit individually as a unit, also can two or more unit in a unit integrated; Above-mentioned integrated unit both can adopt the form of hardware to realize, and the form that hardware also can be adopted to add SFU software functional unit realizes.

One of ordinary skill in the art will appreciate that: all or part of step realizing said method embodiment can have been come by the hardware that programmed instruction is relevant, aforesaid program can be stored in a computer read/write memory medium, this program, when performing, performs the step comprising said method embodiment; And aforesaid storage medium comprises: movable storage device, ROM (read-only memory) (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. various can be program code stored medium.

The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of described claim.

Claims

1. an information processing method, is applied in the electronic equipment comprising or be connected with voice wakeup unit; The duty of described electronic equipment comprises the first duty and the second duty; When described electronic equipment is in described first duty, described voice wakeup unit is in running order; Power consumption when described electronic equipment is in the first duty is lower than power consumption when being in described second duty;

Described method comprises:

Store and resolve described first voice, generating analysis result;

When analysis result shows that described first voice comprise instruction voice part, described voice wakeup unit performs wake operation according to described instruction voice part, makes described electronic equipment be switched to described second duty from the first duty; Wherein, described instruction voice part is used to indicate described first electronic equipment and performs the first operation;

2. method according to claim 1, is characterized in that,

Described method also comprises:

3. method according to claim 1, is characterized in that,

4. according to the method in claim 2 or 3, it is characterized in that,

Described first voice of described storage, comprising:

Receive the first voice of user's input, form the first voice signal;

Described method also comprises:

5. method according to claim 4, is characterized in that,

Described analog voice signal is changed into audio digital signals.

6. method according to claim 5, is characterized in that,

Compress described audio digital signals, form described second voice.

7. the method according to claim 1,2 or 3, is characterized in that,

Described instruction voice part divides Part I and Part II by parsing order;

Described method also comprises:

8. an electronic equipment, described electronic equipment comprises or is connected with in the electronic equipment of voice wakeup unit; The duty of described electronic equipment comprises the first duty and the second duty; When described electronic equipment is in described first duty, described voice wakeup unit is in running order; Power consumption when described electronic equipment is in the first duty is lower than power consumption when being in described second duty;

Described storing and resolving unit, for storing and resolving described first voice, generates analysis result;

9. electronic equipment according to claim 8, is characterized in that,

Described voice wakeup unit, also for

10. electronic equipment according to claim 8, is characterized in that,

11. electronic equipments according to claim 9 or 10, is characterized in that,

12. electronic equipments according to claim 11, is characterized in that,

13. electronic equipments according to claim 12, is characterized in that,

Electronic equipment described in 14. according to Claim 8,9 or 10, is characterized in that,

Described instruction voice part divides Part I and Part II by parsing order;