A kind of unlocking method and device, storage mediumTechnical field
The present invention relates to the unlocking technology of field of communication technology more particularly to a kind of unlocking method and device, storage mediums.
Background technology
In order to ensure to store the safety of information in terminal, unlocking function is usually set in terminal, after only unlocking successfullyTerminal could enter working condition；In addition, for the application in terminal, in order to ensure to correspond to each user's on the application functionThe safety of user information, when user need to use this in application, the mode that generally use logs in enters the application.However, whetherThe login function applied on unlocking function or terminal in terminal is required to information depending on the user's operation and is solved to terminalLock operation.Currently, sound lock is widely used in terminal.
In the prior art, the sound lock used in terminal mainly by recording specific sentence and therefrom obtaining in advanceThese specific sentences are supplied to active user by the voice messaging of user in the unlocking request for receiving active user, willVoice messaging when active user reads the particular statement is matched with the voice messaging obtained before, and when successful match unlocksSuccess.However, during above-mentioned use sound lock is unlocked, the voice messaging of active user is to pass through use when due to unlockFamily reads what particular statement obtained, has specific requirement to user, user experience is low, in addition, user is when saying particular statementIt is possible that mispronounce, skip the phenomenon that, cause unlock accuracy rate and success rate it is low.
Invention content
In order to solve the above technical problems, an embodiment of the present invention is intended to provide a kind of unlocking method and device, storage medium, energyIt is enough to simplify unlock operation, user experience is promoted, unlock accuracy rate and success rate are improved.
The technical proposal of the invention is realized in this way：
An embodiment of the present invention provides a kind of unlocking method, the method includes：
When detecting unlocking request, the voice messaging of active user is obtained；
According to the voice messaging, default sound lock model and default universal model, comparison information is obtained；
When the comparison information meets default comparison threshold value, it is unlocked processing.
In the above scheme, described when detecting unlocking request, before the voice messaging for obtaining active user, the sideMethod further includes：
Locking processing is carried out according to the default sound lock model.
In the above scheme, it is described locking processing is carried out according to the default sound lock model before, the method further includes：
History voice messaging is collected by voice device；
The acoustics of speech feature of at least one dimension is extracted from the history voice messaging；
According to the acoustics of speech feature of at least one dimension and the default universal model, the default sound lock is obtainedModel.
In the above scheme, the acoustics of speech feature of at least one dimension includes：Vocal print feature, lexical characteristics, rhythmRestrain feature, at least one of language feature and voice source.
In the above scheme, the acoustics of speech feature according at least one dimension and the default Universal DieType obtains the default sound lock model, including：
Using adaptive algorithm, the acoustics of speech feature of at least one dimension is input to the default universal modelIn be trained, obtain the default sound lock model.
In the above scheme, described according to the voice messaging, default sound lock model and default universal model, it is comparedInformation, including：
The voice messaging and the default sound lock model are subjected to likelihood score comparison, obtain the first likelihood value；
The voice messaging and the default universal model are subjected to likelihood score comparison, obtain the second likelihood value；
According to first likelihood value and second likelihood value, the comparison information is obtained.
In the above scheme, described when the comparison information meets default comparison threshold value, it is unlocked after processing, instituteThe method of stating further includes：
According to the voice messaging, the default sound lock model is updated.
In the above scheme, described to be unlocked processing when the comparison information meets default comparison threshold value, including：
When the comparison information meets the default comparison threshold value, processing is unlocked to terminal or application.
An embodiment of the present invention provides a kind of tripper, described device includes：Processor, memory, receiver andCommunication bus；The communication bus is logical for realizing the connection between the processor, the memory and the receiverLetter；The processor and the receiver are for executing the data transmission program stored in the memory, to execute following stepSuddenly：
When detecting unlocking request, the voice messaging of active user is obtained；According to the voice messaging, default sound lock mouldType and default universal model, obtain comparison information；When the comparison information meets default comparison threshold value, it is unlocked processing.
An embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable recording medium storage hasOne or more program, one or more of programs can be executed by one or more processor, to realize above-mentioned instituteThe method stated.
An embodiment of the present invention provides a kind of unlocking method and device, storage mediums, first, when detecting unlocking requestWhen, obtain the voice messaging of active user；Then, according to voice messaging, default sound lock model and default universal model, comparedTo information；Finally, when comparison information meets default comparison threshold value, it is unlocked processing.Using above-mentioned technic relization scheme, byDuring being unlocked using sound lock, the acquisition of the voice messaging of active user be when detecting unlocking request,It is obtained in the arbitrary statement said from active user, requirement when reducing unlock to user, avoids active user's readingMispronounced in particular statement, skip the phenomenon that, simplify unlock operation, the user experience is improved, improve unlock accuracy rate and atPower.
Description of the drawings
A kind of hardware architecture diagram of Fig. 1 optional mobile terminals of each embodiment to realize the present invention；
Fig. 2 is a kind of communications network system Organization Chart provided in an embodiment of the present invention；
Fig. 3 is a kind of implementation process schematic diagram of unlocking method provided in an embodiment of the present invention；
Fig. 4 is illustrative terminal unlocking schematic diagram provided in an embodiment of the present invention；
Fig. 5 is that illustrative application provided in an embodiment of the present invention unlocks schematic diagram；
Fig. 6 is the implementation process schematic diagram for another unlocking method that the embodiment of the present invention proposes；
Fig. 7 is a kind of structural schematic diagram of tripper provided in an embodiment of the present invention.
Specific implementation mode
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
In subsequent description, using for indicating that the suffix of such as " module ", " component " or " unit " of element is onlyThe explanation for being conducive to the present invention, itself does not have a specific meaning.Therefore, " module ", " component " or " unit " can mixGround uses.
Terminal can be implemented in a variety of manners.For example, terminal described in the present invention may include such as mobile phone, tabletComputer, laptop, palm PC, personal digital assistant (Personal Digital Assistant, PDA), portableThe shiftings such as media player (Portable Media Player, PMP), navigation device, wearable device, Intelligent bracelet, pedometerThe fixed terminals such as dynamic terminal, and number TV, desktop computer.
It will be illustrated by taking mobile terminal as an example in subsequent descriptions, it will be appreciated by those skilled in the art that in addition to specialExcept element for moving purpose, construction according to the embodiment of the present invention can also apply to the terminal of fixed type.
Referring to Fig. 1, its to realize the present invention a kind of optional mobile terminal of each embodiment hardware configuration signalFigure, the mobile terminal 100 may include：Radio frequency (Radio Frequency, RF) unit 101, Wireless Fidelity (Wireless-Fidelity, Wi-Fi) it is module 102, audio output unit 103, audio/video (A/V) input unit 104, sensor 105, aobviousShow the components such as unit 106, user input unit 107, interface unit 108, memory 109, processor 110 and power supply 111.It will be understood by those skilled in the art that mobile terminal structure shown in Fig. 1 does not constitute the restriction to mobile terminal, it is mobile wholeEnd may include either combining certain components or different components arrangement than illustrating more or fewer components.
The all parts of mobile terminal are specifically introduced with reference to Fig. 1：
Radio frequency unit 101 can be used for receiving and sending messages or communication process in, signal sends and receivees, specifically, by base stationDownlink information receive after, to processor 110 handle；In addition, uplink is shown to base station.In general, radio frequency unit 101 includesBut be not limited to antenna, at least one amplifier, transceiver, coupler, low-noise amplifier, duplexer etc..In addition, radio frequency listMember 101 can also be communicated with network and other equipment by radio communication.Above-mentioned wireless communication can use any communication standardOr agreement, including but not limited to global system for mobile communications (Global System of Mobile communication,GSM), general packet radio service (General Packet Radio Service, GPRS), CDMA 2000 (CodeDivision Multiple Access 2000, CDMA2000), wideband code division multiple access (Wideband Code DivisionMultiple Access, WCDMA), TD SDMA (Time Division-Synchronous CodeDivision Multiple Access, TD-SCDMA), frequency division duplex long term evolution (Frequency DivisionDuplexing-Long Term Evolution, FDD-LTE) and time division duplex long term evolution (Time DivisionDuplexing-Long Term Evolution, TDD-LTE) etc..
Wi-Fi belongs to short range wireless transmission technology, and mobile terminal can help user to receive and dispatch by Wi-Fi module 102Email, browsing webpage and access streaming video etc., it has provided wireless broadband internet to the user and has accessed.Although Fig. 1Show Wi-Fi module 102, but it is understood that, and it is not belonging to must be configured into for mobile terminal, it completely can basisIt needs to omit in the range for the essence for not changing invention.
Audio output unit 103 can be in call signal reception pattern, call mode, record mould in mobile terminal 100When under the isotypes such as formula, speech recognition mode, broadcast reception mode, it is that radio frequency unit 101 or Wi-Fi module 102 are received orThe audio data that person stores in memory 109 is converted into audio signal and exports to be sound.Moreover, audio output unit103 can also provide executed with mobile terminal 100 the relevant audio output of specific function (for example, call signal receive sound,Message sink sound etc.).Audio output unit 103 may include loud speaker, buzzer etc..
A/V input units 104 are for receiving audio or video signal.A/V input units 104 may include graphics processor(Graphics Processing Unit, GPU) 1041 and microphone 1042, graphics processor 1041 is in video acquisition modeOr the image data of the static images or video obtained by image capture apparatus (such as camera) in image capture mode carries outReason.Treated, and picture frame may be displayed on display unit 106.Through graphics processor 1041, treated that picture frame can be depositedStorage is sent in memory 109 (or other storage mediums) or via radio frequency unit 101 or Wi-Fi module 102.MikeWind 1042 can connect in telephone calling model, logging mode, speech recognition mode etc. operational mode via microphone 1042Quiet down sound (audio data), and can be audio data by such acoustic processing.Audio that treated (voice) data canTo be converted to the format output that can be sent to mobile communication base station via radio frequency unit 101 in the case of telephone calling model.Microphone 1042 can implement various types of noises elimination (or inhibition) algorithms and send and receive sound to eliminate (or inhibition)The noise generated during frequency signal or interference.
Mobile terminal 100 further includes at least one sensor 105, such as optical sensor, motion sensor and other biographiesSensor.Specifically, optical sensor includes ambient light sensor and proximity sensor, wherein ambient light sensor can be according to environmentThe light and shade of light adjusts the brightness of display panel 1061, and proximity sensor can close when mobile terminal 100 is moved in one's earDisplay panel 1061 and/or backlight.As a kind of motion sensor, accelerometer sensor can detect in all directions (generalFor three axis) size of acceleration, size and the direction of gravity are can detect that when static, can be used to identify the application of mobile phone posture(such as horizontal/vertical screen switching, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, percussion) etc.；The fingerprint sensor that can also configure as mobile phone, pressure sensor, iris sensor, molecule sensor, gyroscope, barometer,The other sensors such as hygrometer, thermometer, infrared sensor, details are not described herein.
Display unit 106 is for showing information input by user or being supplied to the information of user.Display unit 106 can wrapDisplay panel 1061 is included, liquid crystal display (Liquid Crystal Display, LCD), Organic Light Emitting Diode may be usedForms such as (Organic Light-Emitting Diode, OLED) configure display panel 1061.
User input unit 107 can be used for receiving the number or character information of input, and generate the use with mobile terminalFamily is arranged and the related key signals input of function control.Specifically, user input unit 107 may include touch panel 1071 withAnd other input equipments 1072.Touch panel 1071, also referred to as touch screen collect user on it or neighbouring touch operation(for example user uses any suitable objects or attachment such as finger, stylus on touch panel 1071 or in touch panel 1071Neighbouring operation), and corresponding attachment device is driven according to preset formula.Touch panel 1071 may include touch detectionTwo parts of device and touch controller.Wherein, the touch orientation of touch detecting apparatus detection user, and detect touch operation bandThe signal come, transmits a signal to touch controller；Touch controller receives touch information from touch detecting apparatus, and by itIt is converted into contact coordinate, then gives processor 110, and order that processor 110 is sent can be received and executed.In addition, canTo realize touch panel 1071 using multiple types such as resistance-type, condenser type, infrared ray and surface acoustic waves.In addition to touch panel1071, user input unit 107 can also include other input equipments 1072.Specifically, other input equipments 1072 can wrapIt includes but is not limited in physical keyboard, function key (such as volume control button, switch key etc.), trace ball, mouse, operating lever etc.It is one or more, do not limit herein specifically.
Further, touch panel 1071 can cover display panel 1061, when touch panel 1071 detect on it orAfter neighbouring touch operation, processor 110 is sent to determine the type of touch event, is followed by subsequent processing device 110 according to touch thingThe type of part provides corresponding visual output on display panel 1061.Although in Fig. 1, touch panel 1071 and display panel1061 be to realize the function that outputs and inputs of mobile terminal as two independent components, but in certain embodiments, canThe function that outputs and inputs of mobile terminal is realized so that touch panel 1071 and display panel 1061 is integrated, is not done herein specificallyIt limits.
Interface unit 108 be used as at least one external device (ED) connect with mobile terminal 100 can by interface.For example,External device (ED) may include wired or wireless headphone port, external power supply (or battery charger) port, wired or nothingLine data port, memory card port, the port for connecting the device with identification module, audio input/output (I/O) endMouth, video i/o port, ear port etc..Interface unit 108 can be used for receiving the input from external device (ED) (for example, numberIt is believed that breath, electric power etc.) and the input received is transferred to one or more elements in mobile terminal 100 or can be withFor the transmission data between mobile terminal 100 and external device (ED).
Memory 109 can be used for storing software program and various data.Memory 109 can include mainly storing program areaAnd storage data field, wherein storing program area can storage program area, application program (such as the sound needed at least one functionSound playing function, image player function etc.) etc.；Storage data field can store according to mobile phone use created data (such asAudio data, phone directory etc.) etc..In addition, memory 109 may include high-speed random access memory, can also include non-easyThe property lost memory, a for example, at least disk memory, flush memory device or other volatile solid-state parts.
Processor 110 is the control centre of mobile terminal, utilizes each of various interfaces and the entire mobile terminal of connectionA part by running or execute the software program and/or module that are stored in memory 109, and calls and is stored in storageData in device 109 execute the various functions and processing data of mobile terminal, to carry out integral monitoring to mobile terminal.PlaceReason device 110 may include one or more processing units；Preferably, processor 110 can integrate application processor and modulatedemodulate is mediatedManage device, wherein the main processing operation system of application processor, user interface and application program etc., modem processor is mainProcessing wireless communication.It is understood that above-mentioned modem processor can not also be integrated into processor 110.
Mobile terminal 100 can also include the power supply 111 (such as battery) powered to all parts, it is preferred that power supply 111Can be logically contiguous by power-supply management system and processor 110, to realize management charging by power-supply management system, putThe functions such as electricity and power managed.
Although Fig. 1 is not shown, mobile terminal 100 can also be including bluetooth module etc., and details are not described herein.
Embodiment to facilitate the understanding of the present invention, below to the communications network system that is based on of mobile terminal of the present invention intoRow description.
Referring to Fig. 2, Fig. 2 is a kind of communications network system Organization Chart provided in an embodiment of the present invention, the communication network systemSystem is the LTE system of universal mobile communications technology, which includes communicating the user equipment (User of connection successivelyEquipment, UE) 201, evolved UMTS Terrestrial radio access network (Evolved UMTS Terrestrial RadioAccess Network, E-UTRAN) 202, evolved packet-based core networks (Evolved Packet Core, EPC) 203 and operationThe IP operation 204 of quotient.
Specifically, UE201 can be above-mentioned terminal 100, and details are not described herein again.
E-UTRAN202 includes eNodeB2021 and other eNodeB2022 etc..Wherein, eNodeB2021 can be by returningJourney (backhaul) (such as X2 interface) is connect with other eNodeB2022, and eNodeB2021 is connected to EPC203,ENodeB2021 can provide the access of UE201 to EPC203.
EPC203 may include mobility management entity (Mobility Management Entity, MME) 2031, ownershipClient server (Home Subscriber Server, HSS) 2032, other MME2033, gateway (Serving GateWay, SGW) 2034, grouped data network gateway (PDN Gate Way, PGW) 2035 and policy and rate functional entity(Policy and Charging Rules Function, PCRF) 2036 etc..Wherein, MME2031 be processing UE201 andThe control node of signaling, provides carrying and connection management between EPC203.HSS2032 is all to manage for providing some registersSuch as the function of home location register (not shown) etc, and some are preserved in relation to use such as service features, data ratesThe dedicated information in family.All customer data can be sent by SGW2034, and PGW2035 can provide the IP of UE 201Address is distributed and other functions, and PCRF2036 is strategy and the charging control strategic decision-making of business data flow and IP bearing resourcesPoint, it selects and provides available strategy and charging control decision with charge execution function unit (not shown) for strategy.
IP operation 204 may include internet, Intranet, IP multimedia subsystem (IP MultimediaSubsystem, IMS) or other IP operations etc..
Although above-mentioned be described by taking LTE system as an example, those skilled in the art it is to be understood that the present invention not onlySuitable for LTE system, be readily applicable to other wireless communication systems, such as GSM, CDMA2000, WCDMA, TD-SCDMA withAnd the following new network system etc., it does not limit herein.
Based on above-mentioned mobile terminal hardware configuration and communications network system, each embodiment of the method for the present invention is proposed.
It should be noted that terminal includes the other-ends such as mobile terminal, each embodiment being listed below is to be with terminalThe explanation that example carries out.
Embodiment one
An embodiment of the present invention provides a kind of unlocking method, Fig. 3 is a kind of unlocking method that the embodiment of the present invention proposesImplementation process schematic diagram, as shown in figure 3, in embodiments of the present invention, which may comprise steps of：
S301, when detecting unlocking request, obtain the voice messaging of active user；
In embodiments of the present invention, after terminal and the application in terminal lock, on the one hand, terminal needs to carry outWorking condition could be entered after unlock, on the other hand, application could complete the login of user after need to unlocking.
Here, it when terminal detects the unlocking function of terminal or the application function in terminal starts, that is, detectsUnlocking request is arrived.For example, user starts application by pressing bright locked screen or user by touch control operations such as clicksDeng the embodiment of the present invention is not specifically limited this.
It should be noted that voice messaging contains the acoustics of speech feature of at least one dimension, specifically include：Vocal print is specialSign, lexical characteristics, prosodic features, at least one of language feature and voice source.Voice messaging can be electroacoustics instrumentThe sound wave spectrum information for the carrying voice messaging that device is shown.The acoustics of speech feature for including in voice messaging not only has specificProperty, and have the characteristics of relative stability.After adult, the sound of people can keep relatively stablizing for a long time constant.It is demonstrated experimentally that nothingIt is deliberately to imitate other people sound and the tone, or whisper in sb.'s ear is softly talked by talker, even if imitating remarkably true to life, phonetic soundFeature is learned but to differ always.In addition, the voice messaging for containing acoustics of speech feature obtains conveniently, naturally, acoustics of speech featureExtraction can unconsciously complete, therefore the acceptance level of user is also high, and the identification for obtaining voice is of low cost,Using simple a, microphone, without additional sound pick-up outfit when using communication apparatus.Therefore, voice can be believedCease the foundation as bio-identification, referred to as speech recognition.Speech recognition include with the relevant speech recognition of text and with text withoutTwo kinds of the speech recognition of pass.Speech recognition with text dependent needs user to read specific content, and then specific according to readingThe sound that sends out of content establish the speech model of the user, and while identifying, also must be read out specific content, therefore, it is necessary toFamily coordinates, if the pronunciation of user is not met with specific content, can not correctly identify the user.And the language unrelated with textSound identifies the pronunciation content for not providing speaker then, establishes speech model by any sentence that user says, user is facilitated to makeWith.For example, can be used in bank transaction with the relevant speech recognition of text because user oneself is to be ready when being tradedCooperation；And criminal investigation or intercept application in can use the speech recognition unrelated with text because suspicion of crime can not be requiredPeople or the people being listened coordinate.
In embodiments of the present invention, which is to preset sound lock model based on the speech recognition unrelated with textFoundation and the acquisition of present user speech do not need user and read specific sentence.Only detecting that unlock is asked when terminalWhen asking, the voice messaging that active user is obtained in arbitrary acoustic information is sent out from active user.Here, the sound that active user sends outMessage breath is any vocabulary or the phrase etc. that active user says, and the embodiment of the present invention is not specifically limited this.
Terminal be should be noted when parsing the voice messaging of active user, to reduce the influence of channel disturbance, oftenUsing channel compensation algorithm, for example, linear discriminant analysis (Linear Discriminant Analysis, LDA) algorithm, probabilityLinear discriminant analysis (Probabilistic Linear Discriminant Analysis, PLDA) algorithm, the present invention are implementedExample is not specifically limited this.
It is understood that not only included the information of active user in the voice messaging of active user but also included channel information,And the information of only active user is only the object of analysis.That is, due to the presence of channel information, to the letter of active userBreath produces interference, by channel compensation algorithm, reduces the influence of channel information, improves the accuracy rate and successfully of speech recognitionRate.
In embodiments of the present invention, terminal can be the electronic equipments such as mobile phone, tablet computer, the embodiment of the present invention to this notMake concrete restriction.
S302, according to voice messaging, default sound lock model and default universal model, obtain comparison information；
It should be noted that after terminal obtains the voice messaging of active user, need the voice messaging of active userIt is compared with default sound lock model.Here, it refers to voice mould pre-establishing, belonging to specific user to preset sound lock modelType, terminal is by comparing the voice messaging of active user and default sound lock model, it can be determined that whether specific active user isUser.Furthermore, it is contemplated that the voice messaging of specific user is few based on when default sound lock model foundation, the default sound lock of foundationModel can be incomplete, and therefore, terminal also needs to the voice messaging of active user being compared with default universal model.ThisIn, contain universal, ordinary acoustics of speech feature in default universal model, by the voice messaging of active user with it is defaultUniversal model is compared, and can further judge that active user is specific user.
Preferably, the embodiment of the present invention selects universal background model (Universal Background Model, UBM) to makeTo preset universal model.UBM is the model that the feature unrelated with speaker is indicated for training, and UBM training datas are a channelsUnder all voice data, rather than as the speech model of specific user be reflect particular person feature distribution.
In embodiments of the present invention, terminal by the voice messaging of active user respectively with default sound lock model and default generalModel is compared, and obtains comparison information, specially：Voice messaging and default sound lock model are carried out likelihood score comparison by terminal,Obtain the first likelihood value；Voice messaging and default universal model are carried out likelihood score comparison by terminal, obtain the second likelihood value；TerminalAccording to the first likelihood value and the second likelihood value, comparison information is obtained.
It should be noted that the acoustics of speech feature due to containing active user in the voice messaging of active user：SoundLine feature, lexical characteristics, prosodic features, at least one of language feature and voice source, and default sound lock model is rootAccording to the acoustics of speech feature of specific user：In vocal print feature, lexical characteristics, prosodic features, language feature and voice sourceWhat at least one training obtained, therefore, the voice messaging of active user is input to default sound lock model by terminal, passes through each languageThe comparison of the information such as acoustic feature can obtain the similarity information of the voice messaging and the default sound lock model of active user,That is the first likelihood value.Similarly, default universal model is the acoustics of speech feature according to numerous users：Vocal print feature, morphology are specialSign, prosodic features, the training of at least one of language feature and voice source obtain, and terminal is by the voice of active userInformation input can obtain the voice of active user to default universal model by the comparison of the information such as each acoustics of speech featureThe similarity information of information and the default universal model, i.e. the second likelihood value.Preferably, terminal is by the first likelihood value and the second phaseLogarithm is taken after removing again, obtains a log-likelihood ratio, which is exactly a comparison information.
Here, terminal is in the voice messaging phase with default sound lock model and default universal model respectively for calculating active userIt, can be and current by the acoustics of speech feature for including in the voice messaging of active user and default sound lock model when like degree informationThe acoustics of speech feature and default universal model that include in the voice messaging of user are updated to the default likelihood function for seeking similarity,The corresponding voice messaging for obtaining characterization active user is current with the first likelihood value of default sound lock distortion and characterization respectivelyThe voice messaging of user the second likelihood value with default universal model similarity respectively.
It is understood that terminal by the voice messaging of active user respectively with default sound lock model and default universal modelIt is compared, it can be determined that the voice messaging of active user is closer with default sound lock model, or is more connect with UBM modelClosely, the comparison foundation to be unlocked, improves the accuracy rate of speech unlocking to a certain extent.
S303, when comparison information meet it is default compare threshold value when, be unlocked processing.
Terminal judge can be unlocked processing when, need by the voice messaging of active user respectively with default sound lock mouldThe comparison information of type and default universal model compares threshold value and is compared with default.Here, it is according to reality to preset and compare threshold valueA numberical range or a concrete numerical value for situation setting, when comparison information is in the numberical range or equal to the concrete numerical valueWhen, i.e., comparison information meets default comparison threshold value, is unlocked processing, unlocks successfully；Conversely, unlock failure.
Illustratively, set compare threshold value be 0.5, obtained comparison information be 0.7, since comparison information 0.7 meets greatlyThreshold value 0.5 is compared in default, therefore characterizes comparison information and meets default comparison threshold value, terminal is unlocked processing at this time；Such asIt is 0.5 that fruit, which sets and compares threshold value, and obtained comparison information is 0, since comparison information 0 is unsatisfactory for being more than default comparison threshold value 0.5,Therefore it characterizes comparison information and is unsatisfactory for default comparison threshold value, terminal unlocking fails at this time.
In embodiments of the present invention, when comparison information meets default comparison threshold value, terminal is unlocked after processing, shouldUnlocking method further includes：Terminal updates according to the voice messaging of active user and presets sound lock model.Specifically, terminal will be currentData of the voice messaging of user as the default sound lock model of training improve default sound according to the voice messaging of the active userMode-locking type.
In embodiments of the present invention, when comparison information meets default comparison threshold value, terminal is unlocked processing, specificallyFor：When comparison information meets default comparison threshold value, terminal-pair terminal or application are unlocked processing.
It should be noted that terminal is also referred to as terminal device, it is the equipment that network outermost is in computer network, mainlyFor the input of user information and the output etc. of handling result.In early stage computer system, since main frame is expensive,Therefore a host can generally configure multiple terminals, these terminals itself do not have computing capability, and it is defeated only to undertake information inputThe work gone out, operation and processing are completed by host.In the personal computer epoch, personal computer can run referred to as terminalThe program of emulator imitates the work of a terminal.With the development of mobile network, mobile terminal (such as mobile phone, PAD) obtainsTo being widely applied.At this point, terminal can not only undertake the work of input and output, while it can also carry out certain operation and placeReason realizes part system function.
Mobile terminal refers to the equipment that can be used on the move, broad sense say including mobile phone, notebook, tablet computer,POS machine, or even including vehicle-mounted computer.But refer in most cases mobile phone or the intelligent hand with a variety of application functionsMachine and tablet computer.As network and technology are towards the development in more and more broadband direction, Mobile Communication Industry will trendThe real mobile message epoch.On the other hand, with the rapid development of integrated circuit technique, the processing capacity of mobile terminal isHave powerful processing capacity, mobile terminal becomes an integrated information processing platform from simple call tool.ThisAlso more wide development space is increased to mobile terminal.Mobile terminal is as simple communication equipment with Mobile Communication DevelopmentHas the history of decades.Mobile intelligent terminal is almost changed into the crucial entrance of Internet service and main wound between a flashNew platform, new media, e-commerce and information service platform, Internet resources, mobile network resource and environmental interaction resourceMost important hinge, operating system and processor chips are even as the strategy system of current entire information and communication technology (ICT) industryHigh point.Mobile intelligent terminal can be referred to as intelligent terminal, and mobile intelligent terminal possesses access the Internet capability, usually carry eachKind operating system can customize various functions according to user demand.In life common intelligent terminal include mobile intelligent terminal,Vehicle intelligent terminal, smart television, wearable device etc..
Here, using the application program (Application, APP) for referring generally to be mounted on intelligent terminal.This apply journeyIn sequence, each user is corresponding with account and password, and when being logged in using sound lock, the password of the user is exactly the userVoice messaging.
Illustratively, Fig. 4 is illustrative terminal unlocking schematic diagram provided in an embodiment of the present invention, as shown in figure 4, terminalIt can either be drawn a design by inputting fingerprint or the unlock of sound lock progress terminal screen is pressed when locking unlock with soundFirmly " lock and unlock " that button speaks with sound, terminal carries out the speak acoustic information of generation of active user and is acquired at this time,The voice messaging of active user is obtained, which is compared with default sound lock model and UBM model, obtains a comparisonValue carries out the unlock of terminal screen if the comparison value meets default comparison threshold value, conversely, unlock failure；For another example, Fig. 5 is thisThe illustrative application unlock schematic diagram that inventive embodiments provide, as shown in figure 5, the login for the wechat application installed in terminal canIt is logged in, can also be pinned and " locked with sound when user selects sound lock to log in wechat by password login with being locked by soundLogging in " button speaks, and terminal carries out the speak acoustic information of generation of active user and is acquired at this time, obtains active userVoice messaging, which is compared with default sound lock model and UBM model, a comparison value is obtained, if the comparison valueMeet default comparison threshold value, then the wechat for carrying out active user's corresponding account logs in, conversely, login failure.
It is understood that due to during being unlocked using sound lock, the voice messaging of active user obtainsTaking is obtained in the arbitrary statement said from active user when detecting unlocking request, to user's when reducing unlockIt is required that avoid active user read particular statement in mispronounce, skip the phenomenon that, simplify unlock operation, improve user's bodyIt tests, improves unlock accuracy rate and success rate.
Embodiment two
The embodiment of the present invention additionally provides another unlocking method, and Fig. 6 is another unlock that the embodiment of the present invention proposesThe implementation process schematic diagram of method, as shown in fig. 6, in embodiments of the present invention, which may comprise steps of：
S601, history voice messaging is collected by voice device；
In embodiments of the present invention, voice data based on default sound lock model foundation, automatically records from terminalUser's operation terminal when the history voice messaging that generates.The user's operation can be but be not limited to answer/make phone behaviourMake, the history voice messaging that short message, wechat and QQ voice/videos generate when conversing.Therefore, terminal needs to receive by voice deviceCollect history voice messaging.Here, voice device can be microphone, 1042 in specific corresponding diagram 1.
In general, the history voice messaging of collection is the history voice messaging of the user of terminal, can be a useThe history voice messaging at family, or the history voice messaging of multiple users.Specifically, terminal can going through different userHistory voice messaging is classified, and corresponding different default sound lock model is established, so that multiple with can realize at unlock per familyReason.In the embodiment of the present invention, to be illustrated for collecting the history voice messaging of a user.
Illustratively, when user is conversed using terminal, terminal can be the microphone in user's press-to-talk keyOpen the collection to the voice messaging of user；When user is using in the terminal using voice transmission is carried out, terminal can be withIt is the collection that microphone opens to the voice messaging of user when user presses and speaks button；When user records, terminalCan be that press record button in user be that microphone opens collection to the voice messaging of user.
In embodiments of the present invention, terminal can be the electronic equipments such as mobile phone, tablet computer, the embodiment of the present invention to this notMake concrete restriction.
S602, the acoustics of speech feature that at least one dimension is extracted from history voice messaging；
It should be noted that the acoustics of speech feature of multiple dimensions of user is contained in the history voice messaging of user,Data foundation of the acoustics of speech feature as the default sound lock model foundation of user, is by being extracted from history voice messagingWhat the acoustics of speech feature of at least one dimension was established.
Specifically, the acoustics of speech feature of at least one dimension includes：Vocal print feature, lexical characteristics, prosodic features, languageAt least one of feature and voice source.
Illustratively, vocal print feature, such as cepstrum, cepstrum refer to doing scramble spectral transformation to power spectrum signal, in this wayBe because on cepstrum can more easily identification signal constituent；Lexical characteristics, such as words and phrases, mouth that user often saysHead buddhist etc.；Prosodic features, such as word speed, language etc. that user speaks；Language feature, such as the languages of user, accent and dialectDeng；Voice source, such as oral account, recording etc..
It should be noted that terminal therefrom extracts the language of at least one dimension in the history voice messaging of parsing userWhen acoustic feature, to reduce the influence of channel disturbance, frequently with channel compensation algorithm, for example, LDA algorithm, PLDA algorithms, this hairBright embodiment is not specifically limited this.
It is understood that due to not only including the information of user in the history voice messaging of user but also including channel information,And the information of only user is only the object of analysis.That is, due to the presence of channel information, the information of user is producedInterference, by channel compensation algorithm, reduces the influence of channel information, improves the accuracy rate and success rate of speech recognition.
S603, the acoustics of speech feature according at least one dimension and default universal model obtain default sound lock model；
In embodiments of the present invention, the foundation for presetting sound lock model is unrelated with text, and considers voice messagingThe Sparse Problems of middle data, acoustics of speech feature and default universal model of the terminal according at least one dimension obtain default soundMode-locking type.Here, it presets in universal model and contains universal, ordinary acoustics of speech feature, pass through the history voice of userInformation carries out the training of default sound lock model with default universal model, can obtain more perfect default sound lock model.In addition, eventuallyHold the acoustics of speech feature by extracting at least one dimension from history voice messaging, according to each acoustics of speech feature andThe weight training of each acoustics of speech feature presets sound lock model.
Preferably, the embodiment of the present invention selects UBM model as default universal model.UBM model is indicated for trainingThe model of the feature unrelated with speaker, the training data of UBM model is all voice data under a channel, rather than pictureThe default solution mode-locking type of specific user equally only reflects the feature distribution of particular person.
Specifically, acoustics of speech feature and default universal model of the terminal according at least one dimension obtains default sound lockModel, including：Using adaptive algorithm, the acoustics of speech feature of at least one dimension is input in default universal model by terminalIt is trained, obtains default sound lock model.
Here, adaptive algorithm can be maximal posterior probability algorithm, the linear regression algorithm of maximum likelihood etc., and the present invention is realExample is applied to be not specifically limited this.
It should be noted that adaptive algorithm refers in processing and analytic process, according to the data characteristics of processing dataAdjust automatically processing method, processing sequence, processing parameter, boundary condition or constraints, so that the statistics with handled dataDistribution characteristics, structure feature are adapted, to obtain best treatment effect.
Illustratively, terminal by the dimension number of acoustics of speech feature, acoustics of speech feature, acoustics of speech feature weight,The training data of UBM model and maximal posterior probability algorithm as the default sound lock model of training obtains default sound lock model, and willThe voice messaging sample of multiple known users is input in the default sound lock model, when unlocking success rate 99% or more, tableIt levies the default sound lock model and has trained completion；If the voice messaging sample of multiple known users is input to the default sound by terminalIn mode-locking type, unlock success rate is less than or equal to 99%, then readjusts training data, be specifically as follows the power of each training dataWeight, processing sequence etc. terminate to preset sound lock mould when the default sound lock solution to model trained locks success rate 99% or moreThe training of type, and this is preset into default sound lock model of the sound lock model as the embodiment of the present invention.
It should be noted that the number of the default sound lock model in the embodiment of the present invention can be one, or moreIt is a.When default sound lock model is one, only there are one users to be unlocked processing by sound lock for characterization；When default soundWhen mode-locking type has multiple, characterization, which is corresponding with multiple users, to be unlocked processing by sound lock.
It is understood that terminal extracts the acoustics of speech feature of at least one dimension from the history voice messaging of userAs the training data of default sound lock model, the default sound lock model of foundation combines the acoustics of speech feature of multiple dimensions, fromAnd make the default sound lock model established more perfect, further improve the accuracy rate and success rate of unlock.
S604, locking processing is carried out according to default sound lock model；
It is corresponding every in the safety and application function to ensure to store information in terminal after obtaining default sound lock modelThe safety of the user information of a user, terminal can be used sound lock and carry out locking processing, i.e., according to pre- when carrying out locking processingIf sound lock model carries out locking processing.
S605, when detecting unlocking request, obtain the voice messaging of active user；
In embodiments of the present invention, step S605 realizes that the description of process realizes process with step S301 in embodiment oneDescription is consistent, and details are not described herein again.
S606, according to voice messaging, default sound lock model and default universal model, obtain comparison information；
In embodiments of the present invention, step S606 realizes that the description of process realizes process with step S302 in embodiment oneDescription is consistent, and details are not described herein again.
S607, when comparison information meet it is default compare threshold value when, be unlocked processing.
In embodiments of the present invention, step S607 realizes that the description of process realizes process with step S303 in embodiment oneDescription is consistent, and details are not described herein again.
It is understood that due to during being unlocked using sound lock, the voice messaging of active user obtainsTaking is obtained in the arbitrary statement said from active user when detecting unlocking request, to user's when reducing unlockIt is required that avoid active user read particular statement in mispronounce, skip the phenomenon that, simplify unlock operation, improve user's bodyIt tests, in addition, the foundation of default sound lock model is obtained according to the call-information and voice messaging constantly improve of user, improvesUnlock accuracy rate and success rate.
Embodiment three
Same inventive concept based on embodiment one and embodiment two, Fig. 7 are a kind of solution provided in an embodiment of the present inventionThe structural schematic diagram of locking device, as shown in fig. 7, the tripper includes：Processor 71, memory 72, receiver 73 and logicalBelieve bus 74.
In embodiments of the present invention, the communication bus 74 for realizing the processor 71, the memory 72 andConnection communication between the receiver 73；The processor 71 and the receiver 73 are deposited for executing in the memory 72The data transmission program of storage, to execute following steps：
When detecting unlocking request, the voice messaging of active user is obtained；According to the voice messaging, default sound lock mouldType and default universal model, obtain comparison information；When the comparison information meets default comparison threshold value, it is unlocked processing.
In embodiments of the present invention, further, the processor 71 is additionally operable to be carried out according to the default sound lock modelLocking processing.
In embodiments of the present invention, further, the processor 71 is additionally operable to collect history voice by voice deviceInformation；The acoustics of speech feature of at least one dimension is extracted from the history voice messaging；According at least one dimensionAcoustics of speech feature and the default universal model, obtain the default sound lock model.
In embodiments of the present invention, further, the acoustics of speech feature of at least one dimension includes：Vocal print is specialSign, lexical characteristics, prosodic features, at least one of language feature and voice source.
In embodiments of the present invention, further, the processor 71 is specifically used for utilizing adaptive algorithm, will be describedThe acoustics of speech feature of at least one dimension is input in the default universal model and is trained, and obtains the default sound lock mouldType.
In embodiments of the present invention, further, the processor 71, be specifically used for by the voice messaging with it is described pre-If sound lock model carries out likelihood score comparison, the first likelihood value is obtained；The voice messaging and the default universal model are carried outLikelihood score compares, and obtains the second likelihood value；According to first likelihood value and second likelihood value, the comparison letter is obtainedBreath.
In embodiments of the present invention, further, the processor 71 is additionally operable to, according to the voice messaging, update instituteState default sound lock model.
In embodiments of the present invention, further, the processor 71 is specifically used for working as described in comparison information satisfactionWhen default comparison threshold value, processing is unlocked to terminal or application.
It should be noted that in an embodiment of the present invention, processor 71 and memory 72 in Fig. 7 correspond to above-mentioned respectivelyProcessor 110 in Fig. 1 and memory 109, receiver 73 correspond to the radio frequency unit 101 in above-mentioned Fig. 1.In specific embodimentIn the process, above-mentioned processor 71 can be application-specific IC (Application Specific IntegratedCircuit, ASIC), digital signal processor (Digital Signal Processor, DSP), digital signal processing device(Digital Signal Processing Device, DSPD), programmable logic device (Programmable LogicDevice, PLD), field programmable gate array (Field Programmable Gate Array, FPGA), central processing unitAt least one of (Central Processing Unit, CPU), controller, microcontroller, microprocessor.It is appreciated thatGround, for different equipment, the electronic device for realizing above-mentioned processor function can also be other, the embodiment of the present invention pairThis is not especially limited.
An embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable recording medium storage hasOne or more program, one or more of programs can be executed by one or more processor, to realize as implementedMethod described in example one and embodiment two.
Specifically, the corresponding program instruction of a kind of unlocking method in the embodiment of the present invention can be stored in CD, firmlyDisk, on the storage mediums such as USB flash disk, when program instruction corresponding with a kind of unlocking method is read by an electronic equipment in storage mediumOr be performed, include the following steps：
When detecting unlocking request, the voice messaging of active user is obtained；According to the voice messaging, default sound lock mouldType and default universal model, obtain comparison information；When the comparison information meets default comparison threshold value, it is unlocked processing.
In embodiments of the present invention, further, described when detecting unlocking request, obtain the voice letter of active userBefore breath, either multiple programs are executed said one by said one or multiple processors, implement following steps：
Locking processing is carried out according to the default sound lock model.
In embodiments of the present invention, further, it is described locking processing is carried out according to the default sound lock model before, onIt states one or more program to be executed by said one or multiple processors, implements following steps：
History voice messaging is collected by voice device；The language of at least one dimension is extracted from the history voice messagingSay acoustic feature；According to the acoustics of speech feature of at least one dimension and the default universal model, obtain described defaultSound lock model.
In embodiments of the present invention, further, the acoustics of speech feature of at least one dimension includes：Vocal print is specialSign, lexical characteristics, prosodic features, at least one of language feature and voice source.
In embodiments of the present invention, further, the acoustics of speech feature and institute according at least one dimensionState default universal model, when obtaining the default sound lock model, said one either multiple programs by said one or multipleProcessor executes, and implements following steps：
Using adaptive algorithm, the acoustics of speech feature of at least one dimension is input to the default universal modelIn be trained, obtain the default sound lock model.
In embodiments of the present invention, further, described according to the voice messaging, default sound lock model and default generalModel, when obtaining comparison information, either multiple programs are executed said one by said one or multiple processors, specific implementationFollowing steps：
The voice messaging and the default sound lock model are subjected to likelihood score comparison, obtain the first likelihood value；It will be describedVoice messaging carries out likelihood score comparison with the default universal model, obtains the second likelihood value；According to first likelihood value andSecond likelihood value, obtains the comparison information.
In embodiments of the present invention, further, described when the comparison information meets default comparison threshold value, it is solvedLock processing, either multiple programs are executed said one by said one or multiple processors, implement following steps：
According to the voice messaging, the default sound lock model is updated.
In embodiments of the present invention, further, described when the comparison information meets default comparison threshold value, it is solvedWhen lock processing, either multiple programs are executed said one by said one or multiple processors, implement following steps：
When the comparison information meets the default comparison threshold value, processing is unlocked to terminal or application.
It is understood that due to during being unlocked using sound lock, the voice messaging of active user obtainsTaking is obtained in the arbitrary statement said from active user when detecting unlocking request, to user's when reducing unlockIt is required that avoid active user read particular statement in mispronounce, skip the phenomenon that, simplify unlock operation, improve user's bodyIt tests, in addition, the foundation of default sound lock model is obtained according to the call-information and voice messaging constantly improve of user, improvesUnlock accuracy rate and success rate.
It should be noted that herein, the terms "include", "comprise" or its any other variant are intended to non-rowHis property includes, so that process, method, article or device including a series of elements include not only those elements, andAnd further include other elements that are not explicitly listed, or further include for this process, method, article or device institute it is intrinsicElement.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including thisThere is also other identical elements in the process of element, method, article or device.
The embodiments of the present invention are for illustration only, can not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment sideMethod can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many casesThe former is more preferably embodiment.Based on this understanding, technical scheme of the present invention substantially in other words does the prior artGoing out the part of contribution can be expressed in the form of software products, which is stored in a storage mediumIn (such as ROM/RAM, magnetic disc, CD), including some instructions are used so that a station terminal (can be mobile phone, computer, serviceDevice, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The embodiment of the present invention is described with above attached drawing, but the invention is not limited in above-mentioned specificEmbodiment, the above mentioned embodiment is only schematical, rather than restrictive, those skilled in the artUnder the inspiration of the present invention, without breaking away from the scope protected by the purposes and claims of the present invention, it can also make very muchForm, all of these belong to the protection of the present invention.