Invention content
It is a primary object of the present invention to propose a kind of releasing screen locking method and mobile terminal based on speech recognition, with solutionIt is certainly existing in the prior art, based on figure and number protection password, for solve lock screen, there are safety it is low and haveHave and reveal possible technical problem, to improve for information in mobile terminal protectiveness.
In order to solve the above-mentioned technical problem, the releasing screen locking method of the invention based on speech recognition, includes the following steps：
Step S10, when receiving the operational order for locking screen interface, the display reminding information on locking screen interface, and enrollFirst voice messaging；
Step S20 matches first voice messaging with the history voice messaging in speech database；
Step S30 prompts user's input on the screen if first voice messaging and the history voice messaging successful matchEncrypted message releases the locking for the screen if the encrypted message is correct.
Preferably, in the step S30, the encrypted message includes that numerical ciphers information, finger print information or figure are closeCode information.
Preferably, the history voice messaging includes pre-stored at least two pronunciation information of user, the prompt letterBreath includes the pattern by being mixed with the font corresponding at least two pronunciation information.
Preferably, the step S20 includes step：
Step S21 extracts loudness information, timbre information and the tone information of first voice messaging；
Step S22 matches the loudness information, timbre information and tone information with corresponding pronunciation information respectively.
Preferably, further include step：
Step S40, every preset time period show a font corresponding with the pronunciation information and enroll second on the screenVoice messaging；
Step S50 verifies second voice messaging, and screen locking or maintenance are carried out to current screen based on verification resultPresent situation operates.
The present invention also provides a kind of mobile terminals, including：
First admission module, for when receiving the operational order for locking screen interface, display reminding to be believed on locking screen interfaceBreath, and enroll the first voice messaging；
First matching module, for matching first voice messaging with the history voice messaging in speech database；
Module is released, if for first voice messaging and the history voice messaging successful match, prompt on the screen is usedFamily inputs encrypted message, if the encrypted message is correct, releases the locking for the screen.
Preferably, the encrypted message includes numerical ciphers information, finger print information or graphical passwords information.
Preferably, the history voice messaging includes pre-stored at least two pronunciation information of user, the prompt letterBreath includes the pattern by being mixed with the font corresponding at least two pronunciation information.
Preferably, first matching module includes：
Extracting sub-module, loudness information, timbre information and tone information for extracting first voice messaging；
Matched sub-block, for carrying out the loudness information, timbre information and tone information with corresponding pronunciation information respectivelyMatching.
Preferably, further include：
Second admission module, a font corresponding with the pronunciation information is shown for every preset time period simultaneously on the screenEnroll the second voice messaging；
Authentication module, for being verified to second voice messaging, based on verification result to current screen carry out screen locking orPerson maintains the statusquo operation.
The invention has the advantages that：
1, the present invention is based on the first voice is enrolled, the voice based on people is unique, and compare figure and digital cryptoguard, baseWhen voice is as salvo, others can not pretend to be the voice of mobile terminal user, and figure and numerical ciphers be canWith leakage, therefore improve the protectiveness for information in mobile terminal.
2, the present invention is after voice match success, it is also necessary to encrypted message be verified, i.e., if necessary to release lockScreen is first then to be verified by encrypted message after voice match success, unlocking screen could be executed, based on voice and passwordThe combination of information further improves the protectiveness for information in mobile terminal.
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.
It should be noted that relational language such as " first ", " second " can be used for description various assemblies, but these artsLanguage is not intended to limit the component.These terms are only used to distinguish a component and another component.For example, not departing from the model of the present inventionIt encloses, first assembly can be referred to as the second component, and the second component can also similarly be referred to as first assembly.Term " and/Or " refer to continuous item and description item the combination of any one or more.
With reference to figure 1, Fig. 1 is the flow diagram of first embodiment of the invention.
As shown in Figure 1, the releasing screen locking method based on speech recognition of the present invention, includes the following steps：
Step S10, when receiving the operational order for locking screen interface, the display reminding information on locking screen interface, and enrollFirst voice messaging；
The releasing screen locking method based on speech recognition of the present invention is to be suitable for mobile terminal；The mobile terminal include mobile phone,IPAD or notebook.In general, mobile terminal does not operate meeting automatically into locking screen interface, if that is, user will execute for a long timeOperation is to need to carry out screen locking releasing, is based on this：In step slo, when receiving the operational order for locking screen interface, instituteIt includes slide and pressing HOME keys to state operational order；The display reminding information on locking screen interface, prompt message can be figuresCan also be word, be not limited to herein it is above-mentioned, as long as convenient for for seeing, being prompted for voice output；User carries out voice repetition after seeing the prompt message, and the first voice letter of user is enrolled based on the microphone in mobile terminalBreath.
Step S20 matches first voice messaging with the history voice messaging in speech database；
After executing the step S10, step S20 is executed, by the history voice in first voice messaging and speech databaseInformation is matched；The speech database is that user builds in mobile terminal in advance, the history language for storing userMessage ceases；Indicate that the history voice messaging is the history voice data that user is stored in mobile terminal.Wherein, match partyFormula is as follows：First voice messaging is parsed, to obtain corresponding with the first voice messaging first waveform information, by described theOne waveform carries out overlapping matching with the second shape information in the history voice messaging；It should be noted that being not limited toAbove-mentioned matching way, as long as waveform analysis is carried out for the first voice messaging, and with storage to the history language in mobile terminalMessage breath is matched, and the equivalents of step S20 are belonged to.
Step S30, if first voice messaging and the history voice messaging successful match, prompt user on the screenEncrypted message is inputted, if the encrypted message is correct, releases the locking for the screen.
After executing the step S20, step S30 is executed, if first voice messaging and the history voice messagingWith success, for example it is based on above-mentioned matching way, show that Duplication is more than 90%, that is, assert successful match；User is prompted on the screenEncrypted message is inputted, the encrypted message includes that the encrypted message includes numerical ciphers information, finger print information or graphical passwordsInformation, then mobile terminal verifies the encrypted message, if the encrypted message is correct, releases for the screenLocking；Complete unlock operation.The beneficial effects of the invention are as follows：The present invention is based on enrolling the first voice, the voice based on peopleIt is unique, compare figure and digital cryptoguard, and when based on voice as salvo, others can not pretend to be mobile wholeThe voice of user is held, and figure and numerical ciphers can be revealed, therefore improve the guarantor for information in mobile terminalShield property.The present invention is after voice match success, it is also necessary to encrypted message be verified, i.e., if necessary to release screen locking, beIt first after voice match success, then is verified by encrypted message, unlocking screen could be executed, based on voice and encrypted messageIn conjunction with being very important, existing encrypted message leakage be it is relatively common, voice be although with uniqueness, but it is just in case logicalIt crosses after recorder includes, and there are certain security risk, therefore the combination of the two is during for releasing screen locking, furtherImprove the protectiveness for information in mobile terminal；When executing screen lock protection, first voice, rear encrypted message inputSequence is vital, existing hacker software is invaded, it is to need to solve to be cracked based on voice in cracking voice processAnalysis process, thus for the decryption information that compares be need it is additional it is more crack time and difficulty, and when hacker software is brokenAfter having solved voice messaging, that is, behind the first layer defence line for having broken the present invention, it is still desirable to execute encrypted message and crack, this is for blackFor objective software, it is difficult to；Because existing hacker software is not provided simultaneously with speech analysis and encrypted message cracksDriving, it is excessively high based on R＆D costs, it is rare.
Wherein, the history voice messaging includes pre-stored at least two pronunciation information of user, the prompt messageIt include the pattern by being mixed with the font corresponding at least two pronunciation information.For history voice messaging and promptInformation limit, the pattern mixed by font, a kind of random combine and formed, first pass through microphone in advance with user and depositThe pronunciation information stored up in mobile terminal is not quite similar, and based on characteristics this random and without logic rules, improves languageDifficulty in sound identification process and randomness are conducive to that someone is avoided deliberately to overcome speech recognition with recorder.Wherein, English wordsMother also belongs to the equivalents of font in the present embodiment, should belong to the protection domain of the present embodiment.
With reference to figure 2, Fig. 2 is the refinement flow diagram of step S20 in first embodiment of the invention.
As shown in Figure 2, it is preferable that the step S20 includes step：
Step S21 extracts loudness information, timbre information and the tone information of first voice messaging；
Step S22 matches the loudness information, timbre information and tone information with corresponding pronunciation information respectively.
In the present embodiment, step S20 is defined, after having enrolled the first voice messaging, step is first carried outS21 extracts loudness information, timbre information and the tone information of first voice messaging, and the loudness information includes volume, thanIf the volume is 80 decibels；The timbre information includes waveform peak-to-peak value, and what the waveform peak peak value indicated is for firstAfter voice messaging parsing in acquired waveform in a cycle peak and minimum difference；The tone information includes frequencyRate, such as the frequency are 20KHZ, indicate 200,000 hertz；Then above-mentioned loudness information, timbre information and tone information are distinguishedIt is matched with corresponding pronunciation information, the history voice messaging in the speech database includes User ID and the useThe corresponding fonts of family ID, frequency corresponding with the font, peak-to-peak value and volume.In step S22, based on the sound extractedInformation, timbre information and tone information are spent to carry out and the frequency, peak-to-peak value and volume Corresponding matching；This preferred embodiment baseThe loudness information, timbre information and the tone information that are extracted in the first voice messaging is matched, and speech recognition is improvedAccuracy in the process and speed.
With reference to figure 3, Fig. 3 is the flow diagram of second embodiment of the invention.
As shown in Figure 3, it is preferable that further include step：
Step S40, every preset time period show a font corresponding with the pronunciation information and enroll second on the screenVoice messaging；
Step S50 verifies second voice messaging, and screen locking or maintenance are carried out to current screen based on verification resultPresent situation operates.
This preferred embodiment is by additional step S40, and after solution lock screen success, every preset time period is on the screenShow that a font corresponding with the pronunciation information simultaneously enrolls the second voice messaging, the preset time period is 30S, and baseIn subsequent step S50, second voice messaging is verified, screen locking or dimension are carried out to current screen based on verification resultHold present situation operation；And be for a font corresponding with the pronunciation information, it is to be extracted from speech database at randomA font to be displayed on the screen, voice input is carried out after user sees one font, one font isRandomly select, and only there are one, the great contingency for verification process；It improves and information in mobile terminal is protectedThe stability of shield.
As shown in figure 4, the present invention also provides a kind of mobile terminals, including：
First admission module 101, for when receiving the operational order for locking screen interface, the display reminding on locking screen interfaceInformation, and enroll the first voice messaging；
First matching module 102 is used for the history voice messaging progress in first voice messaging and speech databaseMatch；
Module 103 is released, if for first voice messaging and the history voice messaging successful match, is prompted on the screenUser inputs encrypted message, if the encrypted message is correct, releases the locking for the screen.
Preferably, the encrypted message includes numerical ciphers information, finger print information or graphical passwords information.
Preferably, the history voice messaging includes pre-stored at least two pronunciation information of user, the prompt letterBreath includes the pattern by being mixed with the font corresponding at least two pronunciation information.
Preferably, first matching module includes：
Extracting sub-module, loudness information, timbre information and tone information for extracting first voice messaging；
Matched sub-block, for carrying out the loudness information, timbre information and tone information with corresponding pronunciation information respectivelyMatching.
Preferably, further include：
Second admission module, a font corresponding with the pronunciation information is shown for every preset time period simultaneously on the screenEnroll the second voice messaging；
Authentication module, for being verified to second voice messaging, based on verification result to current screen carry out screen locking orPerson maintains the statusquo operation.
Above-mentioned mobile terminal is corresponding with the releasing screen locking method based on speech recognition；Included in the mobile terminalModule be that by the electronic component or device of the releasing each step of screen locking method based on speech recognition；CauseThe embodiment that this mobile terminal is included is also corresponding with the embodiment released in screen locking method based on speech recognition；HereIt no longer describes, but can realize that the device of each step of releasing screen locking method based on speech recognition or module should all belong toIn protection scope of the present invention.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hairEquivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skillsArt field, is included within the scope of the present invention.