CN108880815A

CN108880815A - Auth method, device and system

Info

Publication number: CN108880815A
Application number: CN201710335664.7A
Authority: CN
Inventors: 蒋伟
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2017-05-12
Filing date: 2017-05-12
Publication date: 2018-11-23

Abstract

This application discloses a kind of auth methods, device and system.Wherein, which includes：Fingerprint acquisition device, the finger print information of the target object for acquiring the fingerprint typing region typing in current display interface；Voice acquisition device, for acquiring the voice messaging of current typing, wherein the voice messaging of current typing is the information of the content in target object reading display interface and typing；Processor, for to typing finger print information and voice messaging pre-process respectively, obtain pre-processed results, similarity score is being carried out to pre-processed results, after obtaining the finger print information of typing and the appraisal result of voice messaging, comprehensive score is carried out by the appraisal result of finger print information and voice messaging to typing, verifies the identity of target object.Present application addresses technical problems low based on the auth method accuracy of single creature feature in the prior art.

Description

Auth method, device and system

Technical field

This application involves field of biological recognition, in particular to a kind of auth method, device and system.

Background technique

Biometric authentication technology, including pass through computer and optics, acoustics, biosensor and biostatistics principle Etc. high-tech means be intimately associated, using the intrinsic physiological property of human body, (such as fingerprint, face as, iris) and behavioural characteristic is (such as Person's handwriting, sound, gait etc.) carry out the identification of personal identification.Existing biometric authentication technology mainly includes：Single sound Line verifying and single fingerprint authentication, still, single voice print verification are easy by user there are recognition performance and acquire equipment It influences, and the shortcomings that extracting vocal print feature is not easy for complex environment；Single fingerprint authentication is less for fingerprint characteristic Situation, it is difficult to be imaged, and finger mark has a possibility that being used to duplication fingerprint.

For problem low based on the auth method accuracy of single creature feature in the prior art, not yet mention at present Effective solution scheme out.

Summary of the invention

The embodiment of the present application provides a kind of auth method, device and system, at least to solve base in the prior art In the low technical problem of the auth method accuracy of single creature feature.

According to the one aspect of the embodiment of the present application, a kind of authentication system is provided, including：Fingerprint acquisition device, For acquiring the finger print information of the target object of the fingerprint typing region typing in current display interface；Voice acquisition device, For acquiring the voice messaging of current typing, wherein the voice messaging of current typing is that target object reads current display interface In content and the information of typing；Processor, for typing finger print information and voice messaging pre-process respectively, obtain Pre-processed results are carrying out similarity score to pre-processed results, are obtaining the finger print information of typing and the scoring knot of voice messaging After fruit, comprehensive score is carried out by the appraisal result of finger print information and voice messaging to typing, verifies the body of target object Part.

According to the another aspect of the embodiment of the present application, a kind of auth method is additionally provided, including：Synchronous acquisition target The information of at least two biological characteristics of object；The information of at least two biological characteristics is pre-processed, obtains at least two The pre-processed results of biological characteristic；Similarity score is carried out to the pre-processed results of at least two biological characteristics, obtains every kind of life The appraisal result of object feature；Comprehensive score is carried out by the appraisal result to every kind of biological characteristic, verifies the identity of target object.

According to the another aspect of the embodiment of the present application, a kind of auth method is additionally provided, including：On currently display circle The finger print information of fingerprint typing region typing target object in face, and acquire the voice messaging of current typing, wherein current record The voice messaging entered is the information of the content in target object reading current display interface and typing；To the finger print information of typing and Voice messaging is pre-processed respectively, obtains pre-processed results；Similarity score is carried out to pre-processed results, obtains the finger of typing The appraisal result of line information and voice messaging；Synthesis is carried out by the appraisal result of finger print information and voice messaging to typing to comment Point, verify the identity of target object.

According to the another aspect of the embodiment of the present application, a kind of authentication means are additionally provided, including：Acquisition unit is used In the information of at least two biological characteristics of synchronous acquisition target object；Processing unit, for at least two biological characteristics Information is pre-processed, and the pre-processed results of at least two biological characteristics are obtained；Score unit, for special at least two biologies The pre-processed results of sign carry out similarity score, obtain the appraisal result of every kind of biological characteristic；Authentication unit, for by every The appraisal result of kind biological characteristic carries out comprehensive score, verifies the identity of target object.

According to the another aspect of the embodiment of the present application, a kind of authentication means are additionally provided, including：Acquisition unit is used In the finger print information of the fingerprint typing region typing target object in current display interface, and acquire the voice letter of current typing Breath, wherein the voice messaging of current typing is the information of the content in target object reading current display interface and typing；Processing Unit, for typing finger print information and voice messaging pre-process respectively, obtain pre-processed results；Score unit, uses In carrying out similarity score to pre-processed results, the finger print information of typing and the appraisal result of voice messaging are obtained；Authentication unit, For carrying out comprehensive score by the appraisal result of finger print information and voice messaging to typing, the identity of target object is verified.

According to the another aspect of the embodiment of the present application, a kind of storage medium is additionally provided, storage medium includes the journey of storage Sequence, wherein equipment where control storage medium executes the auth method in above-described embodiment in program operation.

According to the another aspect of the embodiment of the present application, a kind of processor is additionally provided, including：, processor is for running journey Sequence, wherein program executes the auth method in above-described embodiment when running.

According to the another aspect of the embodiment of the present application, a kind of system is additionally provided, including：Processor；And memory, with Processor connection, for providing the instruction for handling following processing step for processor：At least two of synchronous acquisition target object The information of biological characteristic；The information of at least two biological characteristics is pre-processed, the pre- place of at least two biological characteristics is obtained Manage result；Similarity score is carried out to the pre-processed results of at least two biological characteristics, obtains the scoring knot of every kind of biological characteristic Fruit；Comprehensive score is carried out by the appraisal result to every kind of biological characteristic, verifies the identity of target object.

In the embodiment of the present application, it is recorded by fingerprint typing region of the fingerprint acquisition device acquisition in current display interface The finger print information of the target object entered, meanwhile, the voice messaging of current typing is acquired by voice acquisition device, passes through processor Finger print information and voice messaging to typing pre-process respectively, obtain pre-processed results, are carrying out phase to pre-processed results It scores like degree, after obtaining the finger print information of typing and the appraisal result of voice messaging, passes through the finger print information and language to typing The appraisal result of message breath carries out comprehensive score, verifies the identity of target object, tests to reach and carry out identity to target object The purpose of card.

It is easily noted that, since finger print information and voice messaging can acquire simultaneously, i.e., to the acquisition of finger print information With the acquisition to voice messaging be it is synchronous execute, and to finger print information and voice messaging carry out respectively similarity score it Afterwards, comprehensive score can be carried out according to two appraisal results, to reach the accuracy for improving authentication, promotes safety verification Level promotes the effect of user's likability.

Therefore, the scheme provided by the above embodiments of the present application can solve special based on single creature in the prior art The low technical problem of the auth method accuracy of sign.

Detailed description of the invention

The drawings described herein are used to provide a further understanding of the present application, constitutes part of this application, this Shen Illustrative embodiments and their description please are not constituted an undue limitation on the present application for explaining the application.In the accompanying drawings：

Fig. 1 is the schematic diagram according to a kind of authentication system of the embodiment of the present application；

Fig. 2 is showing for the current display interface according to one kind of the embodiment of the present application optionally based on vocal print and fingerprint authentication It is intended to；

Fig. 3 is the schematic diagram according to a kind of optional authentication system of the embodiment of the present application；

Fig. 4 is the schematic diagram according to a kind of optional the Mel frequency and linear frequency relationship of the embodiment of the present application；

Fig. 5 is the schematic diagram according to a kind of optional MFCC extraction process of the embodiment of the present application；

Fig. 6 is the schematic diagram of the centre frequency and m relationship according to a kind of optional triangular filter of the embodiment of the present application；

Fig. 7 is a kind of flow chart optionally based on vocal print and fingerprint authentication according to the embodiment of the present application；

Fig. 8 is a kind of flow chart optionally based on vocal print and fingerprint collecting according to the embodiment of the present application；

Fig. 9 is showing for the current display interface according to one kind of the embodiment of the present application optionally based on vocal print and fingerprint collecting It is intended to；

Figure 10 is according to a kind of hardware configuration frame of the mobile device for realizing auth method of the embodiment of the present application Figure；

Figure 11 is the flow chart according to a kind of auth method of the embodiment of the present application；

Figure 12 is the flow chart according to another auth method of the embodiment of the present application；

Figure 13 is the schematic diagram according to a kind of authentication means of the embodiment of the present application；

Figure 14 is the schematic diagram according to another authentication means of the embodiment of the present application；And

Figure 15 is the structural block diagram according to a kind of mobile terminal of the embodiment of the present application.

Specific embodiment

In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only The embodiment of the application a part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people Member's every other embodiment obtained without making creative work, all should belong to the model of the application protection It encloses.

It should be noted that the description and claims of this application and term " first " in above-mentioned attached drawing, " Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way Data be interchangeable under appropriate circumstances, so as to embodiments herein described herein can in addition to illustrating herein or Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product Or other step or units that equipment is intrinsic.

Firstly, the part noun or term that occur during the embodiment of the present application is described are suitable for following solution It releases：

Biological characteristic：Including the intrinsic physiological property of human body (such as fingerprint, face are as, iris etc.) and behavioural characteristic (such as Person's handwriting, sound, gait etc.).

MD5：Message Digest 5 is the abbreviation of Message Digest Algorithm, for ensuring that information transfers It is whole consistent, it can be another fixed-length value by data (such as Chinese character) operation.

Embodiment 1

According to the embodiment of the present application, a kind of embodiment of authentication system is provided.

Fig. 1 is according to a kind of schematic diagram of authentication system of the embodiment of the present application, as shown in Figure 1, the system can be with Including：

Fingerprint acquisition device 102, for acquiring the target object of the fingerprint typing region typing in current display interface Finger print information.

Specifically, above-mentioned fingerprint acquisition device can be set on the mobile apparatus, and setting position depends on mobile device The design of manufacturer, including：Preposition fingerprint device, postposition fingerprint device, the application are not especially limited this, and mobile device can be with Including：The equipment such as smart phone (including Android phone, IOS mobile phone), IPAD, tablet computer, palm PC；Above-mentioned works as Preceding display interface may include the interface for carrying out authentication；Above-mentioned fingerprint typing region can be setting in mobile device and refer to The position of line acquisition device；Above-mentioned target object may include the user for needing to carry out authentication.

Voice acquisition device 104, for acquiring the voice messaging of current typing, wherein the voice messaging of current typing is Target object reads the information of the content in current display interface and typing.

Specifically, above-mentioned voice acquisition device can be microphone, the channel etc. of setting on the mobile apparatus；Above-mentioned Content in current display interface can be to user carry out voice print verification prompt information, may include Chinese character, English word, English alphabet, number, one section of song etc., the application is not especially limited this, and user's reading tip information can issue voice, To which voice acquisition device can collect voice messaging.

It should be noted that since the complexity of fingerprint is capable of providing enough features for being verified, and scan Speed is fast, easy to use, also, the acquisition of vocal print facilitates, naturally, user's acceptable degree is high, and cost is relatively low, therefore, at this Apply being combined above two verification mode in embodiment, by the joint verification mode of vocal print and fingerprint, to user into Row authentication.

Processor 106, for typing finger print information and voice messaging pre-process respectively, obtain pretreatment knot Fruit is carrying out similarity score to pre-processed results, after obtaining the finger print information of typing and the appraisal result of voice messaging, is leading to It crosses and comprehensive score is carried out to the finger print information of typing and the appraisal result of voice messaging, verify the identity of target object.

Specifically, above-mentioned pretreatment may include finger print information and voice messaging are split, feature extraction and add Close processing.

In a kind of optional scheme, when user enters system interface or the application interface APP by mobile device, triggering Authentication, so that mobile device can show that verifying interface as shown in Figure 2, verifying interface are wrapped from top to bottom on a display screen It includes：The information (information of " sequentially reading following text or number after fingerprint please be press " as shown in Figure 2) of user's operation is prompted, Content that user needs to read (contents of as shown in Figure 2 " we all the paradise Ai Baba "), voice indicates icon, for prompting Whether user carries out voice messaging typing.Finger can be placed on the position of fingerprint acquisition device by user, so that user is referring to Typing finger print information on line typing region, while can be acquired at the same time by reading content typing voice messaging, mobile device To after finger print information and voice messaging, finger print information and voice messaging can be pre-processed, it then will be pretreated Information (including finger print information and voice messaging) and pre-stored information carry out similarity score, are finally calculated according to comprehensive score Method model is weighted scoring to appraisal result, and judges this time to verify whether to pass through, i.e. judgement currently carries out authentication Whether user is to be proved to be successful.

In the above embodiments of the present application, the fingerprint typing area in current display interface is acquired by fingerprint acquisition device The finger print information of the target object of domain typing, meanwhile, the voice messaging of current typing is acquired by voice acquisition device, passes through place Reason device the finger print information and voice messaging of typing are pre-processed respectively, obtain pre-processed results, to pre-processed results into Row similarity score passes through the finger print information to typing after obtaining the finger print information of typing and the appraisal result of voice messaging Comprehensive score is carried out with the appraisal result of voice messaging, verifies the identity of target object, body is carried out to target object to reach The purpose of part verifying.

Optionally, in the above embodiments of the present application, processor 106 is also used at least the two of synchronous acquisition target object Before the information of kind biological characteristic, at least one text is extracted at random from the recorded message prestored, and show the text extracted Word；In the case where fingerprint acquisition device senses the operation of typing fingerprint, sound-recording function is opened.

Optionally, in the above embodiments of the present application, fingerprint acquisition device 102 is also used to according to the typing fingerprint sensed Operation, record the current typing of target object finger print information；Voice acquisition device 104 is also used to synchronous acquisition target object and reads Read the voice messaging of the text extracted and typing.

Optionally, in the above embodiments of the present application, processor 106 is also used to open the preparatory typing of fingerprint input function extremely A few recorded message, and open fingerprint acquisition device and acquire at least one finger print information in advance, wherein the recording of preparatory typing Information and finger print information execute similarity score as pre-processed results of the reference information at least two biological characteristics.

Optionally, in the above embodiments of the present application, processor 106 is also used to recorded message and fingerprint to preparatory typing Information executes following at least one processing：Dividing processing, feature extraction processing and encryption.

Optionally, in the above embodiments of the present application, processor 106 is also used at least the two of synchronous acquisition target object Before the information of kind biological characteristic, signal-to-noise ratio metric model is used to obtain the level of noise in target object region；In target Level of noise in object region is above standard in the case where value, issues prompt information, wherein prompt information includes prompt mesh The noise for marking object region is exceeded；In the case that level of noise in target object region is less than standard value, read Take the finger print information and recorded message of preparatory typing.

Optionally, in the above embodiments of the present application, processor 106 is also used to divide the information of every kind of biological characteristic Cut processing, the biological information after being divided；Feature extraction is carried out from the biological information after segmentation, is obtained at least The feature extraction result of two kinds of biological characteristics.

Optionally, in the above embodiments of the present application, processor 106 is also used to obtain at least two biological characteristics prestored Reference information；The feature extraction result of at least two biological characteristics is carried out similarity with corresponding reference information to compare, it will The similarity comparison result of each biological characteristic is as appraisal result.

Optionally, in the above embodiments of the present application, processor 106 is also used to obtain the predefined weight of each biological characteristic Value；It is weighted summation according to the similarity comparison result of each biological characteristic and corresponding predefined weight value, mesh is calculated Mark the comprehensive score of object；In the case where the comprehensive score of target object is more than predetermined value, the body of verifying target object is determined Part passes through.

Fig. 3 is according to a kind of schematic diagram of optional authentication system of the embodiment of the present application, as shown in figure 3, this is The detailed architecture of system includes：Data collection layer, data analysis layer, machine learning algorithm model layer and verifying decision-making level, data are adopted Collecting the corresponding component of layer includes：(i.e. above-mentioned voice is adopted for fingerprint equipment (i.e. above-mentioned fingerprint acquisition device) and vocal print equipment Acquisition means)；The corresponding component of data analysis layer includes：MD5 information encryption and decryption, DSP Digital Signal Processing and information characteristics mention It takes；The corresponding component of machine learning algorithm model layer includes：SNR signal-to-noise ratio metric model, PNCC noise eliminate model, MFCC plum Er Dun rate cepstrum coefficient model and personalized fingerprint segmentation model；Verifying the corresponding component of decision-making level includes：Fingerprint and vocal print The comprehensive analysis that scores and comprehensive score Analysis of Policy Making.Above-mentioned data analysis layer, machine learning algorithm model layer and verifying is determined The corresponding component of plan layer may each be the module in mobile device controller.

Optionally, for SNR signal-to-noise ratio metric model, Signal to Noise Ratio (SNR) can be an electronic equipment or electronic system The ratio of middle signal and noise, wherein signal can be the electronic signal handled from device external, and noise can be with Not existing random extra (or information) in original signal, and this kind of signal not with the variation of original signal and Variation.

The size of signal-to-noise ratio can pass through the logarithm of available signal power (or voltage) and noise power (or voltage) ratio Come what is indicated.The unit of signal-to-noise ratio is known as " Bell ", in actual use, since Bell's unit is larger, by using it / 10th i.e. " decibel " is used as unit.

Signal-to-noise ratio metric model is defined as follows：

Wherein, Signal power is available signal power, and Noise power is noise power, Signal voltage For useful signal voltage, Signal R is useful signal resistance, and Noise voltage is noise voltage, and Noise R is noise electricity Resistance.

Optionally, model is eliminated for PNCC noise, due to sensor in different vocal print equipment and signal acquisition circuit Difference generates different noise of equipment, these noise of equipment are blended in formation " machine fingerprint " in voice messaging, and can adopt Machine fingerprint is extracted and identified with peculiar algorithm.

Optionally, for MFCC mel-frequency cepstrum coefficient model, mel cepstrum coefficients (Mel-scale Frequency Cepstral Coefficients, abbreviation MFCC) it is the cepstrum parameter extracted in Mel scale frequency domain, Mel scale is retouched The nonlinear characteristic of human ear frequency is stated, the relationship of it and frequency is as shown in figure 4, following formula approximate representation can be used：

F is frequency, unit Hz in formula.

MFCC extraction process is as shown in figure 5, specifically comprise the following steps：

Step S51, preemphasis.

It is alternatively possible to become the frequency spectrum of signal to promote high frequency section by high-pass filter voice signal It is flat, low frequency is maintained at into the entire frequency band of high frequency, is able to use same signal-to-noise ratio and is sought frequency spectrum.Meanwhile eliminating sounding The effect of vocal cords and lip in the process, to compensate the high frequency section that voice messaging is inhibited by articulatory system, thus prominent high The formant of frequency, specific formula are as follows：

H (Z)=1- μ z^-1,

Wherein, the value of μ usually takes 0.97 between 0.9-1.0.

Step S52, framing.

It is alternatively possible to which N number of sampling point set is first synthesized an observation unit, referred to as frame.The value of N is under normal conditions 256 or 512, the time covered is about 20-30ms or so.In order to avoid the variation of adjacent two frame is excessive, two consecutive frames can be allowed Between have one section of overlapping region, this overlapping region contains M sample point, and the value of usual M is about the 1/2 or 1/3 of N.Usual language Sound identifies that the sample frequency of used voice messaging is 8KHz or 16KHz, for 8KHz, if frame length is 256 sampled points, Then corresponding time span is 256/8000 × 1000=32ms.

Step S53, adding window (Hamming Window).

It is alternatively possible to by each frame multiplied by Hamming window, to increase the continuity of frame left end and right end.Assuming that after framing Signal is S (n), n=0,1 ..., and N-1, N are the size of frame, then after multiplied by Hamming window S ' (n)=S (n) × W (n), W (n) shape Formula is as follows：

Wherein, different a values can generate different Hamming windows, take 0.46 by a.

Step S54, Fast Fourier Transform (FFT).

Optionally, since the transformation of signal in the time domain can not find out the characteristic of signal, frequency domain can be converted a signal into On Energy distribution, different Energy distributions can represent the characteristic of different phonetic information, and after multiplied by Hamming window, Every frame is also needed by Fast Fourier Transform (FFT) to obtain the Energy distribution on frequency spectrum, can be believed each frame after framing adding window Number carrying out Fast Fourier Transform (FFT) obtains the frequency spectrum of each frame, and obtains the function of voice signal to the frequency spectrum modulus square of voice messaging Rate spectrum.For example, it is assumed that the DFT of voice signal is：

In formula, x (n) is the voice signal of input, and N indicates the points of Fourier transformation.

Step S55, triangle bandpass filter.

It is alternatively possible to which energy spectrum to be passed through to the triangle filter group of one group of Mel scale, can preset comprising M The filter group (number of filter and the number of critical band are close) of a filter, the filter used for triangular filter, Centre frequency is f (m), m=1,2 ..., M, and M usually takes 22-26.Interval between each f (m) is reduced with the reduction of m value, It is broadening with the increase of m value, as shown in Figure 6.

The frequency response of triangular filter is defined as:

Wherein,

Frequency spectrum can be smoothed by triangle bandpass filter, and harmonic carcellation, highlight the resonance of original voice Peak reduces operand.Therefore, the tone or pitch of one section of voice is that will not be presented in MFCC parameter, that is, being with MFCC The voice identification system of feature can't be influenced by the tone difference for inputting voice.

Step S56, the logarithmic energy for calculating each filter group output are：

Step S57 obtains MFCC coefficient through discrete cosine transform (DCT)：

It is alternatively possible to bring above-mentioned logarithmic energy into discrete cosine transform, the Mel-scale of L rank is found out Cepstrum parameter, L rank refer to MFCC coefficient order, usually take 12-16, wherein M is triangular filter number.

Step S58, logarithmic energy.

Optionally, it due to the volume (i.e. energy) of a frame and the important feature of voice, and is very easy to calculate, because This, the logarithmic energy that can increase by a frame (wherein, by calculating the quadratic sum of signal in a frame, is then calculated with 10 the bottom of as Logarithm is finally calculated multiplied by 10), the phonetic feature for allowing each frame basic increases one-dimensional, including logarithmic energy With remaining parameters of cepstrum.

It should be noted that other phonetic features are added if necessary to test discrimination, can also in step@58 into Row increases, and other phonetic features may include pitch, zero-crossing rate and formant etc..

Step S59, the extraction (including first-order difference and second differnce) of dynamic difference parameter.

Optionally, the cepstrum parameter MFCC of standard only reflects the static characteristic of speech parameter, and the dynamic characteristic of voice can To be described by the Difference Spectrum of static nature.The calculating of differential parameter can use following formula：

In formula, dt indicates t-th of first-order difference, and Ct indicates that t-th of cepstrum coefficient, Q indicate the order of cepstrum coefficient, K table Show the time difference of first derivative, can use 1 or 2.The result of above formula is substituted into the parameter that can be obtained by second differnce again.

Optionally, for personalized fingerprint segmentation, original image can once be decomposed using wavelet transform, benefit Adaptivenon-uniform sampling is carried out to 1/4 obtained low frequency ll channel picture with mathematical morphology amoeba method, by the subgraph after segmentation Using wavelet reconstruction, restore to original image size.The specific implementation steps are as follows：The data of original image are stored as floating type, and 2-d discrete wavelet linear transformation is carried out, its 1/4 low frequency ll channel picture is obtained；By 3 × 3 pixels (radius 1.5) as most Big structure member, calculates the morphology amoeba structural elements of each pixel in low frequency ll channel picture；It is resulting according to above-mentioned steps Amoeba structural elements carry out morphology amoeba etching operation to low frequency subgraph picture, and picture progress hole is filled out to treated The removal with independent luminous point is filled, segmentation template image is obtained；The gray difference in template image will be divided as foundation, to original 1/ 4 low-frequency images are split, the subgraph after being divided；After after the information progress weakening process of other 3 high frequency imagings, Subgraph after segmentation is subjected to discrete wavelet reconstruction；Picture after reconstruction is post-processed, flash and partial impurities area are removed Domain.

Optionally, vocal print is divided, in time series, the length for needing to compare two sections of time serieses of similitude can Can be unequal, it is different in the word speed that field of speech recognition can show as different people.Since voice messaging is with biggish random Property, i.e. the same person issues identical sound in different moments, it is also not possible to have complete time span.Moreover, with a list The rate of articulation of different phonemes in word is also different, for example, some users can spin out " A " this sound, or " i " is subtracted It is short.In these complex cases, between two time serieses that can not be effectively asked using traditional Euclidean distance away from From (or similitude).

Summarizing in a kind of optional scheme, can be set two time serieses Q and C, length is n and m respectively, one of them For sequence as reference template, another sequence is test template, and the value of each point in sequence is each frame in voice sequence Characteristic value, such as voice sequence Q share n frame, and the characteristic value (number or a vector) of the i-th frame is qi, by using Europe Formula distance, d (qi, cj)=(qi-cj) 2, wherein the alignment of each matrix element (i, j) expression point qi and cj.

Optionally, it scores comprehensive analysis for fingerprint and vocal print, can be weighting evaluation model, it can will be in evaluation object Indices project according to the significance level of evaluation index, give different weighted values, i.e., the significance level of each factor done It treats with a certain discrimination, formula is

Optionally, for comprehensive score Analysis of Policy Making, the ratio of environment SNR signal and noise can be acquired according to vocal print, If vocal print, which acquires environment, is greater than some coefficient, vocal print is reduced in the decision weights factor；If it is preferable that vocal print acquires environment, Vocal print and fingerprint decision weights maintain an equal level, i.e., vocal print coefficient of determination and fingerprint coefficient of determination are greater than some threshold value and then pass through, it is on the contrary then Verifying does not pass through.

The identity identifying method that above system can execute includes：Based on vocal print and fingerprint authentication and it is based on vocal print and fingerprint Acquisition, Fig. 7 are a kind of flow charts optionally based on vocal print and fingerprint authentication according to the embodiment of the present application, and Fig. 8 is according to this Apply for a kind of flow chart optionally based on vocal print and fingerprint collecting of embodiment, Fig. 9 is one kind according to the embodiment of the present application The schematic diagram of optional current display interface.

As shown in fig. 7, may include steps of based on the method that vocal print and fingerprint carry out authentication：

Step S71 judges local environment according to SNR (being the abbreviation of Signal Noise Ratio) signal-to-noise ratio metric model It is whether noisy.

Optionally, it opens vocal print to record, judges whether user's local environment is noisy using SNR signal-to-noise ratio metric, it can The level of noise in user region is obtained using SNR signal-to-noise ratio metric model, according to the comparison result of level of noise and standard value, Determine whether the noise of user region is exceeded, if it is determined that noise is exceeded, that is, determines that user is in noisy environment, then enter Step S711；If it is determined that noise is not exceeded, that is, determines that user is not in noisy environment, then can enter step S72.

Step S72 extracts several texts at random from the voice messaging prestored, and is loaded onto current display interface.

It is alternatively possible to several texts be extracted by random algorithm from the voice messaging recorded in advance, by arranging at random Current display interface is loaded onto after column.

Step S73, user read the character that screen is shown after pressing fingerprint.

Optionally, after user presses fingerprint, the character that screen is shown can be read according to interface prompt content, movement is set Standby to open sound-recording function when detecting the operation of typing fingerprint, the content read to user is recorded, and obtains voice letter Breath.

Step S74, after the completion of reading, user's finger is removed from fingerprint equipment.

Optionally, after reading completion, user can be removed finger, complete entire voice messaging collection process.

Step S75 reads the finger print information and voice messaging prestored, and is decrypted by MD5 algorithm.

It is alternatively possible to read pre-stored finger print information and voice messaging from database, and obtain the ginseng prestored Information is examined, since above- mentioned information carry out encrypting storing, the information read can be decrypted by MD5 algorithm, thus side Just postorder matching process, and S76 and S78 are entered step simultaneously.

Step S76 is split processing to finger print information by fingerprint segmentation model.

Specifically, above-mentioned fingerprint segmentation model can be personalized fingerprint segmentation model.

It is alternatively possible to by personalized fingerprint segmentation model, the finger print information recorded in advance is split and feature It extracts.

Step S77 carries out feature extraction to the reference information of finger print information and fingerprint, and right by particular fingerprint algorithm Similarity scores.

Specifically, the reference information of above-mentioned fingerprint can be pre-stored finger print information.

It is alternatively possible to be carried out to record in advance and this collected finger print information special by particular fingerprint algorithm Sign is extracted, and is scored similarity, after having executed above-mentioned steps, enters step S710.

Step S78 is split processing to voice messaging by sound parted pattern.

Specifically, above-mentioned sound parted pattern can be sound word for word parted pattern.

It is alternatively possible to by sound, word for word parted pattern is split collected voice messaging respectively and feature mentions It takes.

Step S79 carries out feature extraction to voice messaging and phonetic reference information, and to phase by specific vocal print algorithm It scores like degree.

Specifically, the reference information of above-mentioned voice can be pre-stored voice messaging.

It is alternatively possible to which record in advance and this acquisition voice messaging is carried out feature and is mentioned by specific vocal print algorithm It takes, and scores similarity.

Step S710 is weighted scoring to two appraisal results, judgement is this time verified according to comprehensive score algorithm model Whether pass through.

It is alternatively possible to be weighted according to comprehensive score algorithm model to fingerprint appraisal result and vocal print appraisal result Scoring, for example, the weighted value of available fingerprint characteristic and vocal print feature, is weighted summation for weighted value and appraisal result, Comprehensive score is obtained, and comprehensive score is compared with predetermined value, therefore, it is determined that this time verifying whether to pass through, wherein above-mentioned Predetermined value can be preparatory equipment be verified corresponding comprehensive score score value.

Step S711 prompts user's local environment noisy.

Alternatively, if it is determined that user is in noisy environment, then can display reminding information on a display screen, prompt to use Family local environment is noisy, and walk to quiet environment is needed to complete vocal print acquisition.

Further, it before carrying out authentication to user, needs to be acquired the fingerprint and vocal print of user, such as scheme Shown in 8, the method for carrying out authentication based on vocal print and fingerprint can also include the following steps：

Step S81 judges whether local environment is noisy according to SNR signal-to-noise ratio metric model.

Optionally, it opens vocal print to record, judges whether user's local environment is noisy using SNR signal-to-noise ratio metric model, have Body deterministic process is identical as step S71, if it is noisy environment, prompts user's walk to quiet environment to complete vocal print and records.

Step S82, user read random display character recorded speech information.

Optionally, mobile device can show current display interface as shown in Figure 9 on a display screen, and verifying interface is from upper Include under：The information of prompt user's operation be (" sequentially reading following text or number after please pressing fingerprint " as shown in Figure 9 Information), content that user needs to read (content of as shown in Figure 9 " my family of bar Ba Leyuan we all like him "), voice refers to Diagram mark carries out voice messaging typing for prompting the user whether.Finger can be placed on the position of fingerprint acquisition device by user While setting, the content as shown in Fig. 9 can be read, thus typing voice messaging.

It should be noted that in voice messaging recording process, user will be as far as possible in order to improve the accuracy of authentication It remains a constant speed, clearly reading tip content.

Step S83 is split processing to voice messaging by sound parted pattern.

Optionally, the step is identical as the implementation of step S78, and this will not be repeated here.

Step S84 is encrypted and is stored to voice messaging by MD5 algorithm.

Optionally, voice messaging is split, after feature extraction, MD5 algorithm can be used, voice messaging is carried out It encrypts and stores, as the reference information in postorder verification process.

Step S85, user prerecord complete finger print information.

Optionally, fingerprint being opened to record, user can record fingerprint according to the information that current interface prompts, in order to Fingerprint recognition accuracy is improved, the center to identical finger, upper edge, lower edge, left edge, right edge is needed to carry out multi collect, acquisition Stress position according to above-mentioned acquisition 5 to fingerprint afterwards to merge, obtains complete finger print information.

Step S86 is split processing to finger print information by fingerprint segmentation model.

Optionally, the step is identical as the implementation of step S76, and this will not be repeated here.

Step S87 is encrypted and is stored to finger print information by MD5 algorithm.

Optionally, finger print information is split, after feature extraction, MD5 algorithm can be used, finger print information is added It is close and store, as the reference information in postorder verification process.

Through the above scheme, the joint-detection and authentication mode of vocal print and fingerprint based on intelligence mobile device, can be effective It avoids bypassing voice print verification using sound reproduction when single voice print verification, it is lower in one of vocal print or fingerprint dimension acquisition quality In the case where can pass through algorithm weights judgement and carry out comprehensive verification, while user experience can be promoted, it is quasi- to promote verifying It is horizontal to improve safety verification for exactness.

Embodiment 2

According to the embodiment of the present application, a kind of embodiment of auth method is additionally provided, it should be noted that in attached drawing Process the step of illustrating can execute in a computer system such as a set of computer executable instructions, although also, Logical order is shown in flow charts, but in some cases, can be executed with the sequence for being different from herein it is shown or The step of description.

Embodiment of the method provided by the embodiment of the present application one can be in mobile terminal, terminal or similar fortune It calculates and is executed in device.Figure 10 is according to a kind of hardware knot of the mobile device for realizing auth method of the embodiment of the present application Structure block diagram.As shown in Figure 10, mobile device 100 may include it is one or more (using 1002a, 1002b ... ... in figure, 1002n is shown) (processor 1002 can include but is not limited to Micro-processor MCV or programmable logic device to processor 1002 The processing unit of FPGA etc.), memory 1004 for storing data and the transmitting device 1006 for communication function.It removes Other than this, can also include：Display, input/output interface (I/O interface), the port universal serial bus (USB) (can be made Included for a port in the port of I/O interface), power supply and/or camera.It will appreciated by the skilled person that Structure shown in Fig. 10 is only to illustrate, and does not cause to limit to the structure of above-mentioned electronic device.For example, mobile device 100 is also It may include more perhaps less component or with the configuration different from shown in Figure 10 than shown in Figure 10.

It is to be noted that said one or multiple processors 1002 and/or other data processing circuits lead to herein Can often " data processing circuit " be referred to as.The data processing circuit all or part of can be presented as software, hardware, firmware Or any other combination.In addition, data processing circuit for single independent processing module or all or part of can be integrated to shifting In any one in other elements in dynamic equipment 100.Such as processor involved in the embodiment of the present application, at the data Circuit is managed as a kind of processor and controls (such as the selection for the variable resistance end path connecting with interface).

Memory 1004 can be used for storing the software program and module of application software, such as the identity in the embodiment of the present application Corresponding program instruction/the data storage device of verification method, processor 1002 are stored in soft in memory 1004 by operation Part program and module realize above-mentioned auth method thereby executing various function application and data processing.Storage Device 1004 may include high speed random access memory, may also include nonvolatile memory, as one or more magnetic storage device, Flash memory or other non-volatile solid state memories.In some instances, memory 1004 can further comprise relative to processing The remotely located memory of device 1002, these remote memories can pass through network connection to terminal 100.Above-mentioned network Example include but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.

Transmitting device 1006 is used to that data to be received or sent via a network.Above-mentioned network specific example may include The wireless network that the communication providers of mobile terminal 100 provide.In an example, transmitting device 1006 includes that a network is suitable Orchestration (Network Interface Controller, NIC), can be connected by base station with other network equipments so as to Internet is communicated.In an example, transmitting device 1006 can be radio frequency (Radio Frequency, RF) module, For wirelessly being communicated with internet.

Display can such as touch-screen type liquid crystal display (LCD), the liquid crystal display aloow user with The user interface of mobile device 100 interacts.

Herein it should be noted that in some optional embodiments, above-mentioned mobile device shown in Fig. 10 may include hard Part element (including circuit), software element (including the computer code that may be stored on the computer-readable medium) or hardware element With the combination of both software elements.It should be pointed out that Figure 10 is only an example of particular embodiment, and it is intended to show that It may be present in the type of the component in above-mentioned mobile device.

Under above-mentioned running environment, this application provides auth methods as shown in figure 11.Figure 11 is according to this Shen Please embodiment a kind of auth method flow chart.As shown in figure 11, the above method may include steps of：

Step S1102, the information of at least two biological characteristics of synchronous acquisition target object.

Optionally, in the above embodiments of the present application, at least two biological characteristics include：The fingerprint harmony of target object Sound.

Specifically, above-mentioned target object may include the user for needing to carry out authentication.

Step S1104 pre-processes the information of at least two biological characteristics, obtains the pre- of at least two biological characteristics Processing result.

Step S1106 carries out similarity score to the pre-processed results of at least two biological characteristics, it is special to obtain every kind of biology The appraisal result of sign.

Step S1108 carries out comprehensive score by the appraisal result to every kind of biological characteristic, verifies the body of target object Part.

In the above embodiments of the present application, the information of at least two biological characteristics of synchronous acquisition target object, at least The information of two kinds of biological characteristics is pre-processed, and the pre-processed results of at least two biological characteristics are obtained, at least two biologies The pre-processed results of feature carry out similarity score, the appraisal result of every kind of biological characteristic are obtained, by every kind of biological characteristic Appraisal result carry out comprehensive score, verify the identity of target object, thus reach to target object carry out authentication mesh 's.

Optionally, in the above embodiments of the present application, in the letter of at least two biological characteristics of synchronous acquisition target object Before breath, this method further includes：It extracts at least one text at random from the recorded message prestored, and shows the text extracted Word；In the case where fingerprint acquisition device senses the operation of typing fingerprint, sound-recording function is opened.

Optionally, in the above embodiments of the present application, the information of at least two biological characteristics of synchronous acquisition target object, Including：According to the operation of the typing fingerprint sensed, the finger print information of the current typing of target object, and synchronous acquisition target are recorded Object reads the voice messaging of the text extracted and typing.

Optionally, in the above embodiments of the present application, at least one text is being extracted at random from the recorded message prestored, And before showing the text extracted, this method further includes：At least one recorded message of the preparatory typing of fingerprint input function is opened, And open fingerprint acquisition device and acquire at least one finger print information in advance, wherein the recorded message and finger print information of preparatory typing Similarity score is executed as pre-processed results of the reference information at least two biological characteristics.

Optionally, in the above embodiments of the present application, recorded message to preparatory typing and finger print information execute such as down toward A kind of few processing：Dividing processing, feature extraction processing and encryption.

Optionally, in the above embodiments of the present application, in the letter of at least two biological characteristics of synchronous acquisition target object Before breath, this method further includes：The level of noise in target object region is obtained using signal-to-noise ratio metric model；In target pair As the level of noise in region is above standard in the case where value, prompt information is issued, wherein prompt information includes prompt target The noise of object region is exceeded；In the case that level of noise in target object region is less than standard value, read The finger print information and recorded message of preparatory typing.

Optionally, in the above embodiments of the present application, the information of at least two biological characteristics is pre-processed, obtain to The pre-processed results of few two kinds of biological characteristics, including：Processing is split to the information of every kind of biological characteristic, after being divided Biological information；Feature extraction is carried out from the biological information after segmentation, obtains the feature of at least two biological characteristics Extract result.

Optionally, in the above embodiments of the present application, similarity is carried out to the pre-processed results of at least two biological characteristics Scoring, obtains the appraisal result of every kind of biological characteristic, including：Obtain the reference information of at least two biological characteristics prestored；It will The feature extraction result of at least two biological characteristics carries out similarity with corresponding reference information and compares, by each biological characteristic Similarity comparison result is as appraisal result.

Optionally, in the above embodiments of the present application, comprehensive score is carried out by the appraisal result to every kind of biological characteristic, The identity of target object is verified, including：Obtain the predefined weight value of each biological characteristic；According to the similarity of each biological characteristic Comparison result and corresponding predefined weight value are weighted summation, and the comprehensive score of target object is calculated；In target object Comprehensive score be more than predetermined value in the case where, determine verifying target object identity pass through.

It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of Combination of actions, but those skilled in the art should understand that, the application is not limited by the described action sequence because According to the application, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art should also know It knows, the embodiments described in the specification are all preferred embodiments, related actions and modules not necessarily the application It is necessary.

Through the above description of the embodiments, those skilled in the art can be understood that according to above-mentioned implementation The method of example can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but it is very much In the case of the former be more preferably embodiment.Based on this understanding, the technical solution of the application is substantially in other words to existing The part that technology contributes can be embodied in the form of software products, which is stored in a storage In medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be mobile phone, calculate Machine, server or network equipment etc.) execute each embodiment of the application method.

Embodiment 3

Figure 12 is the flow chart according to another auth method of the embodiment of the present application.As shown in figure 12, above-mentioned side Method may include steps of：

Step S1202, the finger print information of the fingerprint typing region typing target object in current display interface, and acquire The voice messaging of current typing, wherein the voice messaging of current typing is the content in target object reading current display interface And the information of typing.

Specifically, above-mentioned current display interface may include carrying out the interface of authentication；Above-mentioned fingerprint typing area Domain can be the position that fingerprint acquisition device is arranged in mobile device；Above-mentioned target object may include needing to carry out identity to test The user of card；Content in above-mentioned current display interface can be the prompt information that voice print verification is carried out to user, can wrap Chinese character, English word, English alphabet, number, one section of song etc. are included, the application is not especially limited this, user's reading tip Information can issue voice, so as to collect voice messaging.

Step S1204, finger print information and voice messaging to typing pre-process respectively, obtain pre-processed results.

Step S1206 carries out similarity score to pre-processed results, obtains the finger print information of typing and commenting for voice messaging Divide result.

Step S1208 carries out comprehensive score by the appraisal result of finger print information and voice messaging to typing, verifies mesh Mark the identity of object.

In the above embodiments of the present application, the fingerprint of the fingerprint typing region typing target object in current display interface Information, and the voice messaging of current typing is acquired, the finger print information and voice messaging to typing pre-process respectively, obtain pre- Processing result carries out similarity score to pre-processed results, obtains the finger print information of typing and the appraisal result of voice messaging, leads to It crosses and comprehensive score is carried out to the finger print information of typing and the appraisal result of voice messaging, the identity of target object is verified, to reach To the purpose for carrying out authentication to target object.

Embodiment 4

According to the embodiment of the present application, additionally provide it is a kind of for implementing the authentication means of above-mentioned auth method, As shown in figure 13, which includes：Acquisition unit 1302, processing unit 1304, score unit 1306 and authentication unit 1308。

Wherein, information of the acquisition unit 1302 at least two biological characteristics of synchronous acquisition target object；Processing is single Member 1304 obtains the pretreatment knot of at least two biological characteristics for pre-processing to the information of at least two biological characteristics Fruit；The unit 1306 that scores is used to carry out similarity score to the pre-processed results of at least two biological characteristics, obtains every kind of biology The appraisal result of feature；Authentication unit 1308 is used to carry out comprehensive score, verifying by the appraisal result to every kind of biological characteristic The identity of target object.

Herein it should be noted that above-mentioned acquisition unit 1302, processing unit 1304, score unit 1306 and authentication unit 1308 correspond to the step S1102 to step S1108 in embodiment 2, example that four units and corresponding step are realized and Application scenarios are identical, but are not limited to the above embodiments 1 disclosure of that.It should be noted that above-mentioned module is as device A part may operate in the mobile terminal 100 of the offer of embodiment 1.

Optionally, in the above embodiments of the present application, which further includes：Extraction unit and opening unit, wherein extract Unit shows the text extracted for extracting at least one text at random from the recorded message prestored；Opening unit is used In the case where sensing the operation of typing fingerprint in fingerprint acquisition device, sound-recording function is opened.

Optionally, in the above embodiments of the present application, acquisition unit 1302 includes：Acquisition module, wherein acquisition module is used In the operation according to the typing fingerprint sensed, the finger print information of the current typing of target object, and synchronous acquisition target pair are recorded Voice messaging as reading the text extracted and typing.

Optionally, in the above embodiments of the present application, which further includes：Opening unit, wherein opening unit is for opening At least one recorded message of the preparatory typing of fingerprint input function is opened, and opens fingerprint acquisition device and acquires at least one fingerprint in advance Information, wherein pretreatment of the recorded message and finger print information of preparatory typing as reference information at least two biological characteristics As a result similarity score is executed.

Optionally, in the above embodiments of the present application, processing unit 1304 be also used to the recorded message of preparatory typing and Finger print information executes following at least one processing：Dividing processing, feature extraction processing and encryption.

Optionally, in the above embodiments of the present application, which further includes：Acquiring unit and prompt unit, wherein obtain Unit is used to obtain the level of noise in target object region using signal-to-noise ratio metric model；Prompt unit is used in target pair As the level of noise in region is above standard in the case where value, prompt information is issued, wherein prompt information includes prompt target The noise of object region is exceeded；In the case that level of noise in target object region is less than standard value, read The finger print information and recorded message of preparatory typing.

Optionally, in the above embodiments of the present application, processing unit 1304 includes：Divide module and extraction module, wherein Segmentation module is for being split processing to the information of every kind of biological characteristic, the biological information after being divided；Extract mould Block obtains the feature extraction knot of at least two biological characteristics for carrying out feature extraction from the biological information after segmentation Fruit.

Optionally, in the above embodiments of the present application, scoring unit 1306 includes：First obtains module and comparison module, Wherein, the first acquisition module is used to obtain the reference information of at least two biological characteristics prestored；Comparison module is used for will at least The feature extraction result of two kinds of biological characteristics carries out similarity with corresponding reference information and compares, by the similar of each biological characteristic Comparison result is spent as appraisal result.

Optionally, in the above embodiments of the present application, authentication unit 1308 includes：Second obtain module, computing module and Determining module, wherein the second acquisition module is used to obtain the predefined weight value of each biological characteristic；Computing module is used for according to every The similarity comparison result of a biological characteristic and corresponding predefined weight value are weighted summation, and the comprehensive of target object is calculated Close scoring；Determining module is used to determine verifying target object in the case where the comprehensive score of target object is more than predetermined value Identity passes through.

Embodiment 5

According to the embodiment of the present application, additionally provide it is a kind of for implementing the authentication means of above-mentioned auth method, As shown in figure 14, which includes：Acquisition unit 1402, processing unit 1404, score unit 1406 and authentication unit 1408。

Wherein, fingerprint of the acquisition unit 1402 for the fingerprint typing region typing target object in current display interface Information, and acquire the voice messaging of current typing, wherein the voice messaging of current typing is that target object reads current display circle Content and the information of typing in face；Processing unit 1404 for locating the finger print information and voice messaging of typing in advance respectively Reason, obtains pre-processed results；The unit 1406 that scores is used to carry out similarity score to pre-processed results, obtains the fingerprint letter of typing The appraisal result of breath and voice messaging；Authentication unit 1408 is used for the scoring knot by finger print information and voice messaging to typing Fruit carries out comprehensive score, verifies the identity of target object.

Herein it should be noted that above-mentioned acquisition unit 1402, processing unit 1404, score unit 1406 and authentication unit 1408 correspond to the step S1202 to step S1208 in embodiment 3, example that four units and corresponding step are realized and Application scenarios are identical, but are not limited to the above embodiments 3 disclosure of that.It should be noted that above-mentioned module is as device A part may operate in the mobile terminal 100 of the offer of embodiment 1.

Embodiment 6

According to the embodiment of the present application, additionally provide it is a kind of for implementing the system of above-mentioned auth method, including：Processing Device；And memory, it is connect with processor, for providing the instruction for handling following processing step for processor：Synchronous acquisition mesh Mark the information of at least two biological characteristics of object；The information of at least two biological characteristics is pre-processed, obtains at least two The pre-processed results of kind biological characteristic；Similarity score is carried out to the pre-processed results of at least two biological characteristics, obtains every kind The appraisal result of biological characteristic；Comprehensive score is carried out by the appraisal result to every kind of biological characteristic, verifies the body of target object Part.

Embodiment 7

Embodiments herein can provide a kind of mobile terminal, which can be any in mobile terminal group One mobile terminal device.Optionally, in the present embodiment, above-mentioned mobile terminal also could alternatively be the terminals such as terminal Equipment.

Optionally, in the present embodiment, above-mentioned mobile terminal can be located in multiple network equipments of mobile network extremely Few network equipment.

In the present embodiment, above-mentioned mobile terminal can execute the program code of following steps in auth method：Together The information of at least two biological characteristics of step acquisition target object；The information of at least two biological characteristics is pre-processed, is obtained To the pre-processed results of at least two biological characteristics；Similarity score is carried out to the pre-processed results of at least two biological characteristics, Obtain the appraisal result of every kind of biological characteristic；Comprehensive score is carried out by the appraisal result to every kind of biological characteristic, verifies target The identity of object.

Optionally, Figure 15 is the structural block diagram according to a kind of mobile terminal of the embodiment of the present application.As shown in figure 15, the shifting Moving terminal 150 may include：One or more (one is only shown in figure) processors 1502, memory 1504 and transmission dress Set 1506.

Wherein, memory can be used for storing software program and module, such as the security breaches detection in the embodiment of the present application Corresponding program instruction/the module of method and apparatus, the software program and module that processor is stored in memory by operation, Thereby executing various function application and data processing, that is, realize above-mentioned auth method.Memory may include high speed with Machine memory, can also include nonvolatile memory, such as one or more magnetic storage device, flash memory or other are non- Volatile solid-state.In some instances, memory can further comprise the memory remotely located relative to processor, These remote memories can pass through network connection to terminal 150.The example of above-mentioned network includes but is not limited to internet, enterprise Intranet, local area network, mobile radio communication and combinations thereof.

Processor can call the information and application program of memory storage by transmitting device, to execute following step： The information of at least two biological characteristics of synchronous acquisition target object；The information of at least two biological characteristics is pre-processed, Obtain the pre-processed results of at least two biological characteristics；Similarity is carried out to the pre-processed results of at least two biological characteristics to comment Point, obtain the appraisal result of every kind of biological characteristic；Comprehensive score is carried out by the appraisal result to every kind of biological characteristic, verifies mesh Mark the identity of object.

Optionally, the program code of following steps can also be performed in above-mentioned processor：At least two biological characteristics include：Mesh Mark the fingerprint and sound of object.

Optionally, the program code of following steps can also be performed in above-mentioned processor：Synchronous acquisition target object extremely Before the information of few two kinds of biological characteristics, at least one text is extracted at random from the recorded message prestored, and show and extract Text；In the case where fingerprint acquisition device senses the operation of typing fingerprint, sound-recording function is opened.

Optionally, the program code of following steps can also be performed in above-mentioned processor：According to the typing fingerprint sensed Operation, records the finger print information of the current typing of target object, and synchronous acquisition target object reads the text that extracts and typing Voice messaging.

Optionally, the program code of following steps can also be performed in above-mentioned processor：From the recorded message prestored with Machine extracts at least one text, and before showing the text extracted, opens at least one record of the preparatory typing of fingerprint input function Message breath, and opens fingerprint acquisition device and acquires at least one finger print information in advance, wherein the recorded message of preparatory typing and refers to Line information executes similarity score as pre-processed results of the reference information at least two biological characteristics.

Optionally, the program code of following steps can also be performed in above-mentioned processor：To the recorded message of preparatory typing and Finger print information executes following at least one processing：Dividing processing, feature extraction processing and encryption.

Optionally, the program code of following steps can also be performed in above-mentioned processor：Synchronous acquisition target object extremely Before the information of few two kinds of biological characteristics, the level of noise in target object region is obtained using signal-to-noise ratio metric model；? Level of noise in target object region is above standard in the case where value, issues prompt information, wherein prompt information includes mentioning Show that the noise of target object region is exceeded；The case where level of noise in target object region is less than standard value Under, read the finger print information and recorded message of preparatory typing.

Optionally, the program code of following steps can also be performed in above-mentioned processor：To the information of every kind of biological characteristic into Row dividing processing, the biological information after being divided；Feature extraction is carried out from the biological information after segmentation, is obtained The feature extraction result of at least two biological characteristics.

Optionally, the program code of following steps can also be performed in above-mentioned processor：Obtain at least two biologies prestored The reference information of feature；The feature extraction result of at least two biological characteristics is subjected to similarity ratio with corresponding reference information It is right, using the similarity comparison result of each biological characteristic as appraisal result.

Optionally, the program code of following steps can also be performed in above-mentioned processor：Obtain the predetermined of each biological characteristic Weighted value；It is weighted summation according to the similarity comparison result of each biological characteristic and corresponding predefined weight value, is calculated To the comprehensive score of target object；In the case where the comprehensive score of target object is more than predetermined value, verifying target object is determined Identity pass through.

Using the embodiment of the present application, the information of at least two biological characteristics of synchronous acquisition target object, at least two The information of biological characteristic is pre-processed, and the pre-processed results of at least two biological characteristics are obtained, at least two biological characteristics Pre-processed results carry out similarity score, the appraisal result of every kind of biological characteristic is obtained, by commenting every kind of biological characteristic Divide result to carry out comprehensive score, verify the identity of target object, to achieve the purpose that carry out authentication to target object.

It will appreciated by the skilled person that structure shown in figure 15 is only to illustrate, mobile terminal is also possible to intelligence It can mobile phone (such as Android phone, iOS mobile phone), tablet computer, applause computer and mobile internet device (Mobile Internet Devices, MID), the terminal devices such as PAD.Figure 15 it does not cause to limit to the structure of above-mentioned electronic device.Example Such as, mobile terminal 150 may also include the more or less component (such as network interface, display device) than shown in Figure 15, Or with the configuration different from shown in Figure 15.

Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can It is completed with instructing the relevant hardware of terminal device by program, which can store in a computer readable storage medium In, storage medium may include：Flash disk, read-only memory (Read-Only Memory, ROM), random access device (Random Access Memory, RAM), disk or CD etc..

Embodiment 8

Embodiments herein additionally provides a kind of storage medium.Optionally, in the present embodiment, above-mentioned storage medium can For saving program code performed by auth method provided by above-described embodiment one.

Optionally, in the present embodiment, above-mentioned storage medium can be located in computer network in computer terminal group In any one terminal, or in any one mobile terminal in mobile terminal group.

Optionally, in the present embodiment, storage medium is arranged to store the program code for executing following steps：Together The information of at least two biological characteristics of step acquisition target object；The information of at least two biological characteristics is pre-processed, is obtained To the pre-processed results of at least two biological characteristics；Similarity score is carried out to the pre-processed results of at least two biological characteristics, Obtain the appraisal result of every kind of biological characteristic；Comprehensive score is carried out by the appraisal result to every kind of biological characteristic, verifies target The identity of object.

Optionally, above-mentioned storage medium is also configured to store the program code for executing following steps：At least two Biological characteristic includes：The fingerprint and sound of target object.

Optionally, above-mentioned storage medium is also configured to store the program code for executing following steps：It is adopted synchronizing Before the information for collecting at least two biological characteristics of target object, at least one text is extracted at random from the recorded message prestored Word, and show the text extracted；In the case where fingerprint acquisition device senses the operation of typing fingerprint, recording function is opened Energy.

Optionally, above-mentioned storage medium is also configured to store the program code for executing following steps：According to induction The operation of the typing fingerprint arrived records the finger print information of the current typing of target object, and synchronous acquisition target object is read and extracted The text that arrives and the voice messaging of typing.

Optionally, above-mentioned storage medium is also configured to store the program code for executing following steps：From prestoring Recorded message in extract at least one text at random, and before showing the text extracted, it is preparatory to open fingerprint input function At least one recorded message of typing, and open fingerprint acquisition device and acquire at least one finger print information in advance, wherein preparatory typing Recorded message and finger print information as reference information similarity score is executed to the pre-processed results of at least two biological characteristics.

Optionally, above-mentioned storage medium is also configured to store the program code for executing following steps：To preparatory record The recorded message and finger print information entered executes following at least one processing：Dividing processing, feature extraction processing and encryption.

Optionally, above-mentioned storage medium is also configured to store the program code for executing following steps：It is adopted synchronizing Before the information for collecting at least two biological characteristics of target object, target object region is obtained using signal-to-noise ratio metric model Interior level of noise；Level of noise in target object region be above standard value in the case where, issue prompt information, wherein Prompt information includes prompting the noise of target object region exceeded；Level of noise in target object region is less than In the case where standard value, the finger print information and recorded message of preparatory typing are read.

Optionally, above-mentioned storage medium is also configured to store the program code for executing following steps：To every kind of life The information of object feature is split processing, the biological information after being divided；From the biological information after segmentation into Row feature extraction obtains the feature extraction result of at least two biological characteristics.

Optionally, above-mentioned storage medium is also configured to store the program code for executing following steps：Acquisition prestores At least two biological characteristics reference information；By the feature extraction result of at least two biological characteristics and corresponding reference information Similarity comparison is carried out, using the similarity comparison result of each biological characteristic as appraisal result.

Optionally, above-mentioned storage medium is also configured to store the program code for executing following steps：It obtains each The predefined weight value of biological characteristic；Added according to the similarity comparison result of each biological characteristic and corresponding predefined weight value Power summation, is calculated the comprehensive score of target object；In the case where the comprehensive score of target object is more than predetermined value, determine The identity of verifying target object passes through.

Above-mentioned the embodiment of the present application serial number is for illustration only, does not represent the advantages or disadvantages of the embodiments.

In above-described embodiment of the application, all emphasizes particularly on different fields to the description of each embodiment, do not have in some embodiment The part of detailed description, reference can be made to the related descriptions of other embodiments.

In several embodiments provided herein, it should be understood that disclosed technology contents can pass through others Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, such as the division of the unit, only A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of unit or module It connects, can be electrical or other forms.

The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme 's.

It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list Member both can take the form of hardware realization, can also realize in the form of software functional units.

If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product When, it can store in a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words It embodies, which is stored in a storage medium, including some instructions are used so that a computer Equipment (can for personal computer, server or network equipment etc.) execute each embodiment the method for the application whole or Part steps.And storage medium above-mentioned includes：USB flash disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic or disk etc. be various to can store program code Medium.

The above is only the preferred embodiment of the application, it is noted that for the ordinary skill people of the art For member, under the premise of not departing from the application principle, several improvements and modifications can also be made, these improvements and modifications are also answered It is considered as the protection scope of the application.

Claims

1. a kind of authentication system, which is characterized in that including：

Fingerprint acquisition device, the fingerprint letter of the target object for acquiring the fingerprint typing region typing in current display interface Breath；

Voice acquisition device, for acquiring the voice messaging of current typing, wherein the voice messaging of the current typing is described Target object reads the information of the content in the current display interface and typing；

Processor, for typing the finger print information and the voice messaging pre-process respectively, obtain pretreatment knot Fruit is carrying out similarity score to the pre-processed results, is obtaining the finger print information of typing and commenting for the voice messaging Divide after result, the appraisal result for passing through the finger print information and the voice messaging to typing carries out comprehensive score, verifying The identity of the target object.

2. a kind of auth method, which is characterized in that including：

The information of at least two biological characteristics of synchronous acquisition target object；

The information of at least two biological characteristic is pre-processed, the pretreatment knot of at least two biological characteristic is obtained Fruit；

Similarity score is carried out to the pre-processed results of at least two biological characteristic, obtains the scoring knot of every kind of biological characteristic Fruit；

Comprehensive score is carried out by the appraisal result to every kind of biological characteristic, verifies the identity of the target object.

3. according to the method described in claim 2, it is characterized in that, at least two biological characteristic includes：The target pair The fingerprint and sound of elephant.

4. according to the method described in claim 3, it is characterized in that, synchronous acquisition target object at least two biological characteristics Information before, the method also includes：

It extracts at least one text at random from the recorded message prestored, and shows the text extracted；

In the case where fingerprint acquisition device senses the operation of typing fingerprint, sound-recording function is opened.

5. according to the method described in claim 4, it is characterized in that, at least two biological characteristics of synchronous acquisition target object Information, including：

According to the operation of the typing fingerprint sensed, the finger print information of the current typing of the target object is recorded, and synchronous Acquire the voice messaging of the text extracted described in the target object reading and typing.

6. according to the method described in claim 4, it is characterized in that, extracting at least one at random from the recorded message prestored Text, and before showing the text that extracts, the method also includes：

Open at least one described recorded message of the preparatory typing of fingerprint input function, and open fingerprint acquisition device acquire in advance to A few finger print information, wherein the recorded message and finger print information of the preparatory typing are as reference information to described at least two The pre-processed results of kind biological characteristic execute similarity score.

7. according to the method described in claim 6, it is characterized in that, recorded message and finger print information to the preparatory typing are held The following at least one processing of row：Dividing processing, feature extraction processing and encryption.

8. according to the method described in claim 2, it is characterized in that, synchronous acquisition target object at least two biological characteristics Information before, the method also includes：

The level of noise in the target object region is obtained using signal-to-noise ratio metric model；

Level of noise in the target object region be above standard value in the case where, issue prompt information, wherein it is described Prompt information includes prompting the noise of the target object region exceeded；

In the case that level of noise in the target object region is less than standard value, the fingerprint letter of preparatory typing is read Breath and recorded message.

9. method as claimed in any of claims 2 to 8, which is characterized in that at least two biological characteristic Information pre-processed, obtain the pre-processed results of at least two biological characteristic, including：

Processing is split to the information of every kind of biological characteristic, the biological information after being divided；

Feature extraction is carried out from the biological information after the segmentation, the feature for obtaining at least two biological characteristic mentions Take result.

10. according to the method described in claim 9, it is characterized in that, pre-processed results at least two biological characteristic Similarity score is carried out, the appraisal result of every kind of biological characteristic is obtained, including：

Obtain the reference information of at least two biological characteristic prestored；

The feature extraction result of at least two biological characteristic is carried out similarity with corresponding reference information to compare, it will be each The similarity comparison result of the biological characteristic is as the appraisal result.

11. according to the method described in claim 10, it is characterized in that, by the appraisal result to every kind of biological characteristic into Row comprehensive score verifies the identity of the target object, including：

Obtain the predefined weight value of each biological characteristic；

It is weighted summation according to the similarity comparison result of each biological characteristic and corresponding predefined weight value, is calculated To the comprehensive score of the target object；

In the case where the comprehensive score of the target object is more than predetermined value, the identity for verifying the target object is determined Pass through.

12. a kind of auth method, which is characterized in that including：

The finger print information of fingerprint typing region typing target object in current display interface, and acquire the voice of current typing Information, wherein the voice messaging of the current typing be the target object read the content in the current display interface and The information of typing；

The finger print information and the voice messaging of typing are pre-processed respectively, obtain pre-processed results；

Similarity score is carried out to the pre-processed results, obtains the scoring of the finger print information and the voice messaging of typing As a result；

Comprehensive score is carried out by the appraisal result of the finger print information and the voice messaging to typing, verifies the target The identity of object.

13. a kind of authentication means, which is characterized in that including：

Acquisition unit, the information of at least two biological characteristics for synchronous acquisition target object；

Processing unit is pre-processed for the information at least two biological characteristic, obtains at least two biology The pre-processed results of feature；

Score unit, carries out similarity score for the pre-processed results at least two biological characteristic, obtains every kind of life The appraisal result of object feature；

Authentication unit verifies the target pair for carrying out comprehensive score by the appraisal result to every kind of biological characteristic The identity of elephant.

14. a kind of authentication means, which is characterized in that including：

Acquisition unit for the finger print information of the fingerprint typing region typing target object in current display interface, and acquires The voice messaging of current typing, wherein the voice messaging of the current typing is that the target object reads the current display Content and the information of typing in interface；

Processing unit, for typing the finger print information and the voice messaging pre-process respectively, pre-processed As a result；

Score unit, for carrying out similarity score to the pre-processed results, obtains the finger print information of typing and described The appraisal result of voice messaging；

Authentication unit is commented for carrying out synthesis by the appraisal result of the finger print information and the voice messaging to typing Point, verify the identity of the target object.

15. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein run in described program When control the storage medium where equipment perform claim require any one of 2 to 12 described in auth method.

16. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run Benefit require any one of 2 to 12 described in auth method.

17. a kind of system, which is characterized in that including：

Processor；And

Memory is connected to the processor, for providing the instruction for handling following processing step for the processor：It synchronizes and adopts Collect the information of at least two biological characteristics of target object；The information of at least two biological characteristic is pre-processed, is obtained To the pre-processed results of at least two biological characteristic；The pre-processed results of at least two biological characteristic are carried out similar Degree scoring, obtains the appraisal result of every kind of biological characteristic；Synthesis is carried out by the appraisal result to every kind of biological characteristic to comment Point, verify the identity of the target object.