CN108710788A - A kind of safety certifying method, device, terminal and storage medium - Google Patents
A kind of safety certifying method, device, terminal and storage medium Download PDFInfo
- Publication number
- CN108710788A CN108710788A CN201810496387.2A CN201810496387A CN108710788A CN 108710788 A CN108710788 A CN 108710788A CN 201810496387 A CN201810496387 A CN 201810496387A CN 108710788 A CN108710788 A CN 108710788A
- Authority
- CN
- China
- Prior art keywords
- user
- action message
- current
- target user
- sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/316—User authentication by observing the pattern of computer usage, e.g. typical user behaviour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/44—Program or device authentication
Abstract
The invention discloses a kind of safety certifying method, device, terminal and storage medium, wherein this method includes：The current time zone action message of target user is obtained based on the sensor in mobile terminal；Current time zone action message is converted into current frequency domain action message, and current frequency domain action message input feature vector is generated into model, obtains the current signature sequence corresponding with target user that feature generates model output；According to the similarity value between current signature sequence and pre-stored characteristic sequence, determine whether certification passes through.When the technical solution of the embodiment of the present invention solves in the prior art through authentification of messages such as face recognition, fingerprints, since above- mentioned information has reproducibility, cause to there is technical issues that using aforesaid way progress safety certification, realize due to the limb action information of each user have it is personalized, be difficult to replicability, when carrying out safety certification using limb action information, the technique effect of safety certification reliability is improved.
Description
Technical field
The present embodiments relate to technical field of security authentication more particularly to a kind of safety certifying method, device, terminal and
Storage medium.
Background technology
With popularizing for intelligent terminal, it is required using journey that more and more users can download user on terminal interface
Sequence, optionally, wechat, Alipay etc., these application programs may relate to user's property and privacy during use,
It is not easy to be seen and used by other users, therefore security setting can be carried out to it, optionally, pass through optics, acoustics, biology
The high-tech means such as sensor and biostatistics principle are configured it, and common includes fingerprint, face, iris, vocal print
Etc. ensureing the safety of application program.
But the authentications such as common security setting mode such as fingerprint, face, iris all have reproducibility,
Therefore safety is poor.
Invention content
A kind of safety certifying method of offer of the embodiment of the present invention, device, terminal and storage medium, to improve safety certification
Reliability.
In a first aspect, an embodiment of the present invention provides a kind of safety certifying method, this method includes：Based in mobile terminal
Sensor obtain target user current time zone action message；
The current time zone action message is converted into current frequency domain action message, and by the current frequency domain action message
Input feature vector generates model, obtains the current signature sequence corresponding with the target user that the feature generates model output
Row；
According to the similarity value between the current signature sequence and pre-stored characteristic sequence, determine whether certification leads to
It crosses.
Second aspect, the embodiment of the present invention additionally provide a kind of safety certification device, which includes：
Time domain action module is obtained, the current time zone action for obtaining target user based on the sensor in mobile terminal
Information；
Characteristic sequence generation module, for the current time zone action message to be converted to current frequency domain action message, and
The current frequency domain action message input feature vector is generated into model, the feature is obtained and generates being used with the target for model output
The corresponding current signature sequence in family；
Authentication module is used for according to the similarity value between the current signature sequence and pre-stored characteristic sequence,
Determine whether certification passes through.
The third aspect, the embodiment of the present invention additionally provide a kind of terminal, which is characterized in that the terminal includes：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors so that one or more of processing
Device realizes the safety certifying method as described in any in the embodiment of the present invention.
Fourth aspect, the embodiment of the present invention additionally provides a kind of storage medium including computer executable instructions, described
Computer executable instructions by computer processor when being executed for executing the safety as described in any in the embodiment of the present invention
Authentication method.
The technical solution of the embodiment of the present invention obtains the current of target user by the sensor being set in mobile terminal
Current time zone action message is converted to current frequency domain action message by time domain action message, and current frequency domain action message is defeated
Enter feature and generate model, obtains the corresponding current signature sequence of target user, the time domain action message that each user makes
Has unicity, further according to the similarity value between current signature sequence and pre-stored characteristic sequence whether in preset
Within threshold range, to judge whether certification passes through, solve in the prior art through face recognition, the information such as fingerprint, pupil
When being authenticated, since fingerprint, pupil and facial information have reproducibility, cause to carry out safety certification using aforesaid way
There is technical issues that, realize due to the limb action information of each user have it is personalized, be difficult to replicability,
When carrying out safety certification using limb action information, the technique effect of safety certification reliability is improved.
Description of the drawings
In order to clearly illustrate the technical solution of exemplary embodiment of the present, below to required in description embodiment
The attached drawing to be used does a simple introduction.Obviously, the attached drawing introduced is a part of the embodiment of the invention to be described
Attached drawing, rather than whole attached drawings without creative efforts, may be used also for those of ordinary skill in the art
To obtain other attached drawings according to these attached drawings.
A kind of safety certifying method flow diagram that Fig. 1 is provided by the embodiment of the present invention one；
A kind of safety certifying method flow diagram that Fig. 2 is provided by the embodiment of the present invention two；
A kind of safety certification device structural schematic diagram that Fig. 3 is provided by the embodiment of the present invention three；
A kind of structural schematic diagram for terminal that Fig. 4 is provided by the embodiment of the present invention four.
Specific implementation mode
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limitation of the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
A kind of safety certifying method flow diagram that Fig. 1 is provided by the embodiment of the present invention one, the present embodiment are applicable
The application program installed in mobile terminal to user carry out authentication situation, this method can by safety certification device Lai
It executes, which can be realized by the form of software and/or hardware.
As described in Figure 1, the method for the embodiment of the present invention includes：
S110, the current time zone action message that target user is obtained based on the sensor in mobile terminal.
Wherein, mobile terminal refers to the computer equipment that can be used on the move, optional mobile phone, tablet computer etc..It passes
Sensor is a kind of detection device, can detect the information of object being measured, and can turn the information detected according to certain rules
It is changed to electric signal or is converted to the message form output needed for user, to meet the needs of different user.It is set in the sensor
In mobile terminal, the time domain action message for obtaining user.
The current time zone action message that target user is obtained based on the sensor in mobile terminal can be based on mobile whole
Acceleration transducer in end obtains the current time zone action message of target user；And/or based on the gyroscope in mobile terminal
Sensor obtains the current time zone action message of target user.Can be understood as the time domain action message of user can be built in shifting
Acceleration transducer and/or gyro sensor in terminal are moved to obtain.
Time domain is the relationship for describing mathematical function or physical signal to the time, that is, for describing the action got letter
Cease the relationship that changes with time.Wherein, no matter the time is discrete type or continuous type, the function or signal in time domain it is each from
The numerical value for dissipating time point or random time point is datum, therefore can be interpreted as time domain action message：When arbitrary
Between the action message made of the user that can get of point sensor.
As long as user carry in be equipped with the mobile terminal of sensor, the sensor in mobile terminal can point at any time
The time domain action message of user is acquired, it should be understood that, do not need to all time domain actions collected to sensor
Information is handled, and after only triggering certain application program in user, is just needed to act the collected time domain of sensor and be believed
Breath it is further is handled, certainly when certification by and not in setting change acts of authentication when, even if user is made that accordingly
Action and sensor also collected the time domain action message of user, also need not collected time domain action letter as to this
Breath is handled.
To ensureing the time domain action message got and time domain action message being done the accuracy further converted,
In, action message can be that the action message that the positions such as user's arm, hand or ankle are made illustratively holds mobile terminal
Each shake of arm or so make a movement or wrist rotation one is inferior.It should be noted that the action message that user is made only needs
The sensor met in mobile terminal is able to detect that, is specifically action which position is made and action is
What, does not limit herein.
Illustratively, the position that target user makes action is left arm, acts the process enclosed for left arm rotation one,
Target user can hold mobile terminal with left hand during rotation, or mobile terminal is fixed on to the left finesse of target user
On, optionally, mobile terminal is tied up on the left finesse of user, accurately to detect the time domain action message of user, in turn
Improve the accuracy of certification.
Obtaining the time domain action message of target user can be specifically：When certain move is made at a certain position of target user
When making, sensor in the terminal, which is arranged, can obtain the time domain action message of user.Illustratively, target user's
During left arm rotates, target user can hold mobile terminal with left hand, and mobile terminal can also be fixed on to target use
The force application part at family is to detect limb action information that target user makes, optionally, the rotation of target user's left arm
Frequency, the information such as rotation amplitude.
The data of the current time zone action message got at this time by the sensor in mobile terminal are initial data,
That is there are the data of noise, in order to further increase the treatment effect of data, denoising can be carried out to initial data,
Optionally, the initial data got is handled using low pass filtering method, is acted with obtaining the less current time zone of noise
Information.
S120, the current time zone action message is converted into current frequency domain action message, and the current frequency domain is moved
Make information input feature and generate model, obtains the current spy corresponding with the target user that the feature generates model output
Levy sequence.
Wherein, when carrying out time-domain analysis to the time domain action message got, it is understood that there may be the time domain parameter of some information
It is identical, but can not illustrate that the time-domain information got is identical.Because time-domain information not only only changes over time, also with
The information such as frequency, phase are related, this just needs the frequency structure for further analyzing the time domain action message got, and in frequency
Action message is described in domain.Frequency domain is also referred to as frequency domain, and independent variable is frequency, i.e., horizontal axis is frequency, and the longitudinal axis is the frequency
The amplitude of rate signal, that is, the spectrogram usually said, spectrogram describes the frequency structure of signal and frequency is believed with the frequency
The relationship of number amplitude.Time domain action message is converted to frequency domain action message can be real by fourier series and Fourier transform
It is existing, when it is cyclical signal to get time-domain information, Fourier series transform may be used, time-domain information is converted into frequency domain
Information；If the time-domain information got is aperiodic time-domain information, Fourier transformation may be used and convert time-domain information
For frequency domain information.Therefore, after getting the time domain action message of user, time domain action letter is got in order to more fully reflect
Breath, it is also necessary to which time domain action message is converted into frequency domain action message.Since the action message that user makes is continuous and is had
It is standby periodical, therefore user can be converted the time domain action message got using Fourier space, by time domain action message
Frequency domain action message is converted to, that is, is converted to frequency spectrum corresponding with time domain action message.
Wherein, feature generates model and can be understood as：When target user is by frequency domain action message, that is, with target user
When corresponding frequency spectrum inputs this feature generation model, this feature generates model and can handle the spectrum information of input,
Optionally, feature generation model can extract opposite with target user according to frequency domain action message corresponding with target user
The characteristic sequence answered, and the characteristic sequence extracted is exported.Wherein, the action that characteristic sequence can be with user makes is opposite
The image answered can also be a series of sequence numbers corresponding with user makes action message, optionally, 2.1,3.5,7,
8….The characteristic sequence of each user difference.
S130, according to the similarity value between the current signature sequence and pre-stored characteristic sequence, determine certification
Whether pass through.
It should be noted that before the application program installed in the terminal is authenticated using action authentication mode,
The limb action information that target user needs typing in advance certain, that is to say, that target user to by action message come into
Row safety certification is needed first to trigger the application program, optionally, be triggered by button, or clicks the icon etc. of application program,
It also needs to trigger the corresponding security setting option in application program after opening application program, optionally, password set-up mode, action
Certification, face authenticating, finger print identifying etc..When user selects action authentication, corresponding dialog box can be popped up to prompt user
Typing limb action information.User makes corresponding action, and sensor also collects the time domain action message of user, that is, passes
The time domain action message of sensor typing user.The time domain action message of typing obtains and time domain action message phase through a series of processing
Corresponding characteristic sequence, and using the characteristic sequence information obtained at this time as pre-stored characteristic sequence information.Certainly, it obtains
It also needs to handle characteristic sequence using single class vector machine algorithm after to corresponding characteristic sequence, obtains similarity
With model, the similarity mode model is stored in the database, when user before the program using verifying, Ke Yicong
Similarity mode model corresponding with target user is transferred in database.Wherein, which can be used for sentencing
The disconnected characteristic sequence after feature generates model treatment and the similarity value between pre-stored characteristic sequence.
Illustratively, when the wechat downloaded in mobile terminal needs action authentication, before carrying out safety certification, target is used
Family opens wechat and triggers the action authentication mode in security setting option, can pop up the dialog box of typing action message, mesh
Corresponding action, optional one circle of left arm rotation can be arranged according to custom by marking user.In order to ensure ultimate criterion data
Comprehensive, target user can make time domain action message at least three times, and the action needs made every time certainly are identical, at this time
More fully data information can be got, optionally, the angle information in each rotation process between arm and horizontal plane
Deng, the time domain action message data got at this time are noisy information, using low pass filtering method to the data of Noise into
Row processing obtains the time domain action message after denoising.The time domain action message got is carried out a series of processing to obtain and target
The one corresponding characteristic sequence of circle of user's left arm rotation, and using the characteristic sequence obtained at this time as pre-stored feature sequence
Row, that is, standard feature sequence.This characteristic sequence is obtained turning with target user's left arm using single class vector machine algorithm
Dynamic one encloses corresponding similarity mode model.
When target user uses the application program, need by judging the current time zone information of target user and recording in advance
Whether the time domain action message entered matches, so come judge certification whether by and whether can use the application program.Show
Example property, target user triggers wechat application program, and holds mobile terminal and make the action consistent with pre-setting, optional
, current action left arm rotation one is enclosed, and the current time zone action that sensor obtains one circle of target user's left arm rotation is believed
Breath becomes target user's left arm of changing commanders to further obtain the characteristic sequence of one circle of left arm rotation using Fourier space
The current frequency domain action message that the current time zone action message of one circle of rotation is converted to one circle of left arm rotation is generated through feature again
After model, the current signature sequence of one circle of target user's left arm rotation is obtained.
In order to which whether the user for judging to operate the application program is target user, transferred from database and target user's phase
Corresponding pre-stored similarity mode model, it should be noted that during user's typing time domain action message, all
There is unique number corresponding with user, therefore similarity mode corresponding with target user can be transferred from database
Model, and by obtained current signature sequence sequence inputting to the similarity mode model being previously obtained.Similarity mode model can
With judge and export between current characteristic sequence and pre-stored characteristic sequence whether similar and corresponding similarity value.
When similarity value is within preset threshold range, optionally, preset threshold range is 0.8 to 1.0, that is to say, that
When similarity value is within the scope of 0.8 to 1.0, certification passes through, and user can open the application program and use；Work as similarity
Value is when except preset threshold range, that is to say, that the similarity value of output is less than 0.8, then judges it is not target user, test
Card failure, and user is prompted, optionally, user is prompted to re-start verification etc..
The technical solution of the embodiment of the present invention obtains the current of target user by the sensor being set in mobile terminal
Current time zone action message is converted to current frequency domain action message by time domain action message, and current frequency domain action message is defeated
Enter feature and generate model, obtains the corresponding current signature sequence of target user, the limb action thing that each user makes
Has unicity, further according to the similarity value between current signature sequence and pre-stored characteristic sequence whether in preset
Within threshold range, to judge whether certification passes through, solve in the prior art through face recognition, the information such as fingerprint, pupil
When being authenticated, since fingerprint, pupil and facial information have reproducibility, cause to carry out safety certification using aforesaid way
There is technical issues that, realize due to the limb action information of each user have it is personalized, be difficult to replicability,
When carrying out safety certification using limb action information, the technique effect of safety certification reliability is improved.
Embodiment two
Before the current time zone action message for obtaining target user based on the sensor in mobile terminal, it is also necessary to obtain
Feature generates model, and characteristic sequence corresponding with each user is obtained so that each user generates model by feature, to
Establish similarity mode model corresponding with each user.A kind of safety certification that Fig. 2 is provided by the embodiment of the present invention two
Method flow schematic diagram, as described in Figure 2, the method for the embodiment of the present invention includes：
S210, the time domain action message for obtaining at least one user, and the time domain of at least one user is acted and is believed
Breath is handled, and frequency domain action message corresponding at least one user is obtained.
It needs to train by big data it should be noted that establishing feature and generating model, therefore to obtain at least one use
The time domain action message at family, optionally, a user, two users etc., when the time domain action message instruction for only obtaining a user
When the feature got generates model, which has certain limitation.When second user using this feature generate model,
When obtaining the characteristic sequence of user and being compared with true characteristic sequence, there may be larger error, therefore can be by
The frequency domain information of one user and second user are combined together training and obtain feature generation model, it is therefore desirable at least one
The time domain action message of user, and at least one time domain action message got is converted to obtain and institute using Fourier space
State the corresponding frequency domain action message of at least one time domain action message.
S220, using the frequency domain action message of at least one user as first sample data, using depth nerve net
Network algorithm trains to obtain feature generation model, wherein the feature generates model for the frequency domain action message life based on user
The characteristic sequence at family is applied in pairs.
Wherein, first sample data are that at least one time domain action message of at least one user is become using Fourier space
At least one frequency domain action message obtained after changing.Deep neural network algorithm is one handled first sample data
Algorithm can obtain feature generation model after algorithm training study.Can be using first sample data as depth nerve
The fan-in evidence of network algorithm generates model using deep neural network algorithm to the feature constituted based on convolutional neural networks
It is trained to obtain feature generation model.Illustratively, before the time domain action message for obtaining at least 1000 users, to extremely
Few 1000 users are marked, that is to say, that it are numbered, subsequently to use.Obtain at least 1000 users when
Domain action message, at least 1000 time domain action messages got carry out processing respectively obtain at least 1000 users when
The corresponding frequency domain action message of domain action message, that is, at least 1000 users spectrogram；It again will at least 1000 use
Fan-in evidence of the spectrogram at family as deep neural network algorithm, by being obtained to the processing of at least 1000 spectral images
Feature generates model.
In order to verify the accuracy that the feature trained through big data generates model, it is also necessary to at least 1000 users
Different users generates model through this feature and obtains characteristic sequence corresponding with each user, optionally, obtains 100 users
Time domain action message and through feature generate model obtain characteristic sequence corresponding with 100 users, it is carried out verification
Match, if the error rate of theoretic matching result and legitimate reading exceeds default error range, optionally, error range
One thousandth is within 3/1000ths, then it is assumed that this feature generates model and also needs to carry out learning training, optionally, obtains more
The time domain action message of user repeats S210, S220, until the mistake after the characteristic sequence obtained through feature generation model is matched
Rate is within default error range, that is to say, that acquire the time domain action message of more users and to carrying out learning training until
Feature gives birth to model convergence.
After the frequency domain action message of user is input to feature generation model, can it obtain corresponding with the user
Characteristic sequence.
S230, by the time domain action message of the advance typing of arbitrary user through the feature generate model treatment after obtain with
The corresponding characteristic sequence of arbitrary user as the second sample data, using one-class support vector machines algorithm obtain with it is described
The corresponding similarity mode model of arbitrary user.
The time domain action message of the user got can be obtained and user's phase after feature generates model treatment
Corresponding characteristic sequence illustratively obtains at least 1000 users and at least 1000 after feature generates model treatment
A corresponding characteristic sequence of user.When being verified to user, it is also necessary to model corresponding with individual subscriber is obtained, and
Determine whether target user by this model, therefore obtained characteristic sequence will be handled as the second sample data, using list
Class vector machine algorithm establishes similarity mode model corresponding with each user.Wherein, which can connect
Characteristic sequence input by user is received, and can also be used to judge and export the feature sequence of the characteristic sequence and advance typing of input
Similarity value between row.
S240, the current time zone action message that target user is obtained based on the sensor in mobile terminal.
When the application program setting action authentication mode downloaded in target user is to mobile terminal carries out safety certification, mesh
Mark user needs that the time domain action message to be inputted is arranged in advance, it can be understood as, before using the application program, need to carry
Before set open the program action, and using the action being arranged in advance as standard comparison action, optionally, the action of setting
For one circle of left arm rotation, during left arm rotates, user can hold mobile terminal with left hand, be used to acquire target
The time domain action message at family, and collected time domain action message is handled, it obtains corresponding with time domain action message
Frequency domain action message.Frequency domain action message is input to feature again and generates model, obtains spy corresponding with frequency domain action message
Levy sequence.Certainly, using similarity mode model can be obtained after single class vector machine algorithm.It should be noted that will be in advance
Typing namely will be known as pre-stored characteristic sequence as the characteristic sequence of standard comparison, which can
To store in the database, similarity mode model corresponding with target user can be transferred from database when using.
When user will use the application program for being provided with action safety certification, user first triggers application program, according to pre-
If action when doing one time, sensor will detect the current time zone action message of user.
S250, the current time zone action message is converted into current frequency domain action message, and the current frequency domain is moved
Make information input feature and generate model, obtains the current spy corresponding with the target user that the feature generates model output
Levy sequence.
Collected current time zone action message is changed to obtain using Fourier space and is matched with time domain action message
Current frequency domain action message, the obtained frequency domain action message input feature vector of processing is generated in model, is obtained and target user
Corresponding current signature sequence.
S260, by the current signature sequence inputting of target user similarity mode mould corresponding with the target user
Type obtains between the current signature sequence that the similarity mode model exports and the pre-stored characteristic sequence
Similarity value.
Further, similarity mode model corresponding with target user is transferred from database, then by characteristic sequence
Be input in similarity mode model corresponding with target user, similarity mode model to the characteristic sequence of input in advance
The characteristic sequence obtained after the characteristic sequence of storage, that is, advance typing time domain action message is compared, and obtains current
Similarity value between characteristic sequence and pre-stored characteristic sequence, while the similarity value for also obtaining processing exports.
S270, similarity value is judged whether within the scope of preset, if it is not, executing S280；If so, executing S290.
Similarity mode model can carry out the current signature sequence of target user and the characteristic sequence being previously obtained
With comparing, if the similarity value of similarity mode model output is within preset threshold range, optionally, similarity is preset
Threshold range is 0.8 to 1.0, then illustrates that using the program be target user, S290 is executed, if being not in preset threshold value model
Within enclosing, illustrates not to be target user in the action message made using the application program or target user and make in advance
Action message difference is larger, then executes S280.
S280, authentification failure, and user is prompted.
When similarity value is in except preset threshold range, then illustrate be not target user the application program either
Difference between the limb action information that target user makes and the limb action information made in advance is larger, and target user can be with
Re-start certification, can optionally, on the page of application program pop up whether the dialog box of re-authentication, target user can root
It is selected according to actual demand, such as when user's selection is, then returns and execute S240；If user's selection is no, certification can be popped up
Failure page is to prompt user authentication failure.It should be noted that in order to ensure that user uses the safety of the application program, when
When user repeats authentication operation at least twice, optionally three times, similarity value is when except preset range, using journey
Authentification failure can be popped up on the page of sequence, the information that please be try again later, or authentication mode please be replace etc..
S290, certification pass through.
When similarity value is within preset similarity dimensions, then it is assumed that be that target user will can using the application program
Passed through with certification.
The technical solution of the embodiment of the present invention obtains the current of target user by the sensor being set in mobile terminal
Current time zone action message is converted to current frequency domain action message by time domain action message, and current frequency domain action message is defeated
Enter feature and generate model, obtains the corresponding current signature sequence of target user, the limb action thing that each user makes
Has unicity, further according to the similarity value between current signature sequence and pre-stored characteristic sequence whether in preset
Within threshold range, to judge whether certification passes through, solve in the prior art through face recognition, the information such as fingerprint, pupil
When being authenticated, since fingerprint, pupil and facial information have reproducibility, cause to carry out safety certification using aforesaid way
There is technical issues that, realize due to the limb action information of each user have it is personalized, be difficult to replicability,
When carrying out safety certification using limb action information, the technique effect of safety certification reliability is improved.
Embodiment three
A kind of safety certification device structural schematic diagram that Fig. 3 is provided by the embodiment of the present invention three, the device include：It obtains
Time domain action module 310, characteristic sequence generation module 320 and authentication module 330.
Wherein, time domain action module 310 is obtained, for obtaining the current of target user based on the sensor in mobile terminal
Time domain action message；Characteristic sequence generation module 320, for the current time zone action message to be converted to current frequency domain action
Information, and the current frequency domain action message input feature vector is generated into model, obtain that the feature generates model output with institute
State the corresponding current signature sequence of target user；Authentication module 330, for according to the current signature sequence with prestore
Characteristic sequence between similarity value, determine whether certification passes through.
Based on the above technical solution, described device further includes：Model training module 340, in the acquisition
Before time domain action module 310 obtains the current time zone action message of target user, the time domain action of at least one user is obtained
Information, and the time domain action message of at least one user is handled, it obtains corresponding at least one user
Frequency domain action message；Using the frequency domain action message of at least one user as first sample data, using depth nerve
Network algorithm trains to obtain feature generation model；Wherein, the feature generates model and is used for the frequency domain action message based on user
Generate the characteristic sequence of corresponding user.
On the basis of above-mentioned each technical solution, described device further includes：Model generation module 350, for recognizing described
Module 330 is demonstrate,proved according to the similarity value between the current signature sequence and pre-stored characteristic sequence, whether determines certification
By before, the time domain action message of the advance typing of arbitrary user is obtained after the feature generates model treatment with it is described
The arbitrary corresponding characteristic sequence of user is obtained and the arbitrary user as the second data using one-class support vector machines algorithm
Corresponding similarity mode model；Wherein, the similarity mode model is used to judge and export the feature sequence of corresponding user
Similarity value between row and pre-stored characteristic sequence.
On the basis of above-mentioned each technical solution, the authentication module is additionally operable to：By the current signature of the target user
Sequence inputting similarity mode model corresponding with the target user obtains described the working as of the similarity mode model output
Similarity value between preceding characteristic sequence and the pre-stored characteristic sequence；If the similarity value preset range it
Interior, then certification passes through；If the similarity value exceeds within preset range, authentification failure, and prompts user.
On the basis of above-mentioned each technical solution, the acquisition time domain action module 310 is additionally operable to：Based in mobile terminal
Acceleration transducer obtain target user current time zone action message；And/or based on the gyro sensors in mobile terminal
Device obtains the current time zone action message of target user.
The technical solution of the embodiment of the present invention obtains the current of target user by the sensor being set in mobile terminal
Current time zone action message is converted to current frequency domain action message by time domain action message, and current frequency domain action message is defeated
Enter feature and generate model, obtains the corresponding current signature sequence of target user, the limb action thing that each user makes
Has unicity, further according to the similarity value between current signature sequence and pre-stored characteristic sequence whether in preset
Within threshold range, to judge whether certification passes through, solve in the prior art through face recognition, the information such as fingerprint, pupil
When being authenticated, since fingerprint, pupil and facial information have reproducibility, cause to carry out safety certification using aforesaid way
There is technical issues that, realize due to the limb action information of each user have it is personalized, be difficult to replicability,
When carrying out safety certification using limb action information, the technique effect of safety certification reliability is improved.
The safety certification device that the embodiment of the present invention is provided, which can perform the safety that any embodiment of the present invention is provided, to be recognized
Card method has the corresponding function module of execution method and advantageous effect.
It is worth noting that, each unit and module included by above-mentioned apparatus are only divided according to function logic
, but it is not limited to above-mentioned division, as long as corresponding function can be realized；In addition, the specific name of each functional unit
Claim also only to facilitate mutually differentiation, is not intended to restrict the invention the protection domain of embodiment.
Example IV
Fig. 4 is a kind of structural schematic diagram for terminal that the embodiment of the present invention four provides.Fig. 4 is shown suitable for being used for realizing this
The block diagram of the exemplary terminal 40 of inventive embodiments embodiment.The terminal 40 that Fig. 4 is shown is only an example, should not be to this
The function and use scope of inventive embodiments bring any restrictions.
As shown in figure 4, terminal 40 is showed in the form of general-purpose computations terminal.The component of terminal 40 may include but unlimited
In：One or more processor or processing unit 401, system storage 402, connection different system component (including system
Memory 402 and processing unit 401) bus 403.
Bus 403 indicates one or more in a few class bus structures, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using the arbitrary bus structures in a variety of bus structures.It lifts
For example, these architectures include but not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Terminal 40 typically comprises a variety of computer system readable media.These media can be it is any can be by terminal 40
The usable medium of access, including volatile and non-volatile media, moveable and immovable medium.
System storage 402 may include the computer system readable media of form of volatile memory, such as deposit at random
Access to memory (RAM) 404 and/or cache memory 405.Terminal 40 may further include other removable/not removable
Dynamic, volatile/non-volatile computer system storage medium.Only as an example, storage system 406 can be used for read and write can not
Mobile, non-volatile magnetic media (Fig. 4 do not show, commonly referred to as " hard disk drive ").Although not shown in fig 4, Ke Yiti
For the disc driver for being read and write to moving non-volatile magnetic disk (such as " floppy disk "), and to moving non-volatile light
The CD drive of disk (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driver
It can be connected with bus 403 by one or more data media interfaces.Memory 402 may include at least one program production
There is one group of (for example, at least one) program module, these program modules to be configured to perform of the invention each for product, the program product
The function of embodiment.
Program/utility 408 with one group of (at least one) program module 407, can be stored in such as memory
In 402, such program module 407 includes but not limited to operating system, one or more application program, other program modules
And program data, the realization of network environment may be included in each or certain combination in these examples.Program module 407
Usually execute the function and/or method in embodiment described in the invention.
Terminal 40 can also be logical with one or more external equipments 409 (such as keyboard, sensing equipment, display 410 etc.)
Letter can also enable a user to terminal interact with the terminal 40 with one or more and communicate, and/or with enable the terminal 40
Any equipment (such as network interface card, modem etc.) communication communicated with one or more of the other computing terminal.It is this
Communication can be carried out by input/output (I/O) interface 411.Also, terminal 40 can also pass through network adapter 412 and one
A or multiple networks (such as LAN (LAN), wide area network (WAN) and/or public network, such as internet) communication.Such as figure
Shown, network adapter 412 is communicated by bus 403 with other modules of terminal 40.It should be understood that although not shown in fig 4,
Other hardware and/or software module can be used in conjunction with terminal 40, including but not limited to：Microcode, device driver, at redundancy
Manage unit, external disk drive array, RAID system, tape drive and data backup storage system etc..
Processing unit 401 is stored in program in system storage 402 by operation, to perform various functions using with
And data processing, such as realize the safety certifying method that the embodiment of the present invention is provided.
Embodiment five
The embodiment of the present invention five also provides a kind of storage medium including computer executable instructions, and the computer can be held
Row instruction by computer processor when being executed for executing safety certifying method.
The arbitrary of one or more computer-readable media may be used in the computer storage media of the embodiment of the present invention
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or the arbitrary above combination.The more specific example (non exhaustive list) of computer readable storage medium includes：Tool
There are one or the electrical connection of multiple conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium, which can be any, includes or the tangible medium of storage program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media may include in a base band or as the data-signal that a carrier wave part is propagated,
Wherein carry computer-readable program code.Diversified forms may be used in the data-signal of this propagation, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By instruction execution system, device either device use or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
Can with one or more programming languages or combinations thereof come write for execute the embodiment of the present invention operation
Computer program code, described program design language include object oriented program language-such as Java,
Smalltalk, C++ further include conventional procedural programming language --- such as " C " language or similar program design language
Speech.Program code can be executed fully, partly be executed on the user computer, as an independence on the user computer
Software package execute, part on the user computer part execute on the remote computer or completely in remote computer or
It is executed on server.In situations involving remote computers, remote computer can pass through the network of any kind --- packet
It includes LAN (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as profit
It is connected by internet with ISP).
Note that above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The present invention is not limited to specific embodiments described here, can carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out to the present invention by above example
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
May include other more equivalent embodiments, and the scope of the present invention is determined by scope of the appended claims.
Claims (10)
1. a kind of safety certifying method, which is characterized in that including：
The current time zone action message of target user is obtained based on the sensor in mobile terminal；
The current time zone action message is converted into current frequency domain action message, and the current frequency domain action message is inputted
Feature generates model, obtains the current signature sequence corresponding with the target user that the feature generates model output；
According to the similarity value between the current signature sequence and pre-stored characteristic sequence, determine whether certification passes through.
2. according to the method described in claim 1, it is characterized in that, obtaining target in the sensor based in mobile terminal
Before the current time zone action message of user, further include：
Obtain the time domain action message of at least one user, and to the time domain action message of at least one user at
Reason obtains frequency domain action message corresponding at least one user；
Using the frequency domain action message of at least one user as first sample data, trained using deep neural network algorithm
It obtains feature and generates model；
Wherein, the feature generates the characteristic sequence that model generates corresponding user for the frequency domain action message based on user.
3. according to the method described in claim 1, it is characterized in that, it is described according to the current signature sequence with prestore
Characteristic sequence between similarity value further include before determining whether certification passes through：
The time domain action message of the advance typing of arbitrary user is obtained after the feature generates model treatment with it is described arbitrary
The corresponding characteristic sequence of user is obtained and the arbitrary user as the second sample data using one-class support vector machines algorithm
Corresponding similarity mode model；
Wherein, the similarity mode model is used to judge and export the characteristic sequence of corresponding user and pre-stored feature sequence
Similarity value between row.
4. according to the method described in claim 3, it is characterized in that, it is described according to the current signature sequence with it is pre-stored
Similarity value between characteristic sequence, determines whether certification passes through, including：
By the current signature sequence inputting of target user similarity mode model corresponding with the target user, institute is obtained
State the similarity value between the current signature sequence and the pre-stored characteristic sequence of similarity mode model output；
If the similarity value is within preset range, certification passes through；
If the similarity value exceeds preset range, authentification failure, and prompts user.
5. according to the described method of any one of claim 1-4, which is characterized in that the sensor based in mobile terminal
The current time zone action message of target user is obtained, including：
The current time zone action message of target user is obtained based on the acceleration transducer in mobile terminal；And/or
The current time zone action message of target user is obtained based on the gyro sensor in mobile terminal.
6. a kind of safety certification device, which is characterized in that including：
Time domain action module is obtained, the current time zone for obtaining target user based on the sensor in mobile terminal acts letter
Breath；
Characteristic sequence generation module, for the current time zone action message to be converted to current frequency domain action message, and by institute
It states current frequency domain action message input feature vector and generates model, it is generating model output with target user's phase to obtain the feature
Corresponding current signature sequence；
Authentication module, for according to the similarity value between the current signature sequence and pre-stored characteristic sequence, determining
Whether certification passes through.
7. device according to claim 6, which is characterized in that described device further includes：Model generation module, in institute
Authentication module is stated according to the similarity value between the current signature sequence and pre-stored characteristic sequence, whether determines certification
By before, the time domain action message of the advance typing of arbitrary user is obtained after the feature generates model treatment with it is described
The arbitrary corresponding characteristic sequence of user is obtained and the arbitrary user as the second data using one-class support vector machines algorithm
Corresponding similarity mode model；
Wherein, the similarity mode model is used to judge and export the characteristic sequence of corresponding user and pre-stored feature sequence
Similarity value between row.
8. device according to claim 7, which is characterized in that the authentication module is used for：
By the current signature sequence inputting of target user similarity mode model corresponding with the target user, institute is obtained
State the similarity value between the current signature sequence and the pre-stored characteristic sequence of similarity mode model output；
If the similarity value is within preset range, certification passes through；
If the similarity value exceeds within preset range, authentification failure, and prompts user.
9. a kind of terminal, which is characterized in that the terminal includes：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors so that one or more of processors are real
The now safety certifying method as described in any in claim 1-5.
10. a kind of storage medium including computer executable instructions, the computer executable instructions are by computer disposal
For executing the safety certifying method as described in any in claim 1-5 when device executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810496387.2A CN108710788A (en) | 2018-05-22 | 2018-05-22 | A kind of safety certifying method, device, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810496387.2A CN108710788A (en) | 2018-05-22 | 2018-05-22 | A kind of safety certifying method, device, terminal and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108710788A true CN108710788A (en) | 2018-10-26 |
Family
ID=63868393
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810496387.2A Pending CN108710788A (en) | 2018-05-22 | 2018-05-22 | A kind of safety certifying method, device, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108710788A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109886084A (en) * | 2019-01-03 | 2019-06-14 | 广东数相智能科技有限公司 | Face authentication method, electronic equipment and storage medium based on gyroscope |
| CN110070037A (en) * | 2019-04-22 | 2019-07-30 | 深圳力维智联技术有限公司 | Smooth upgrading method, device and the readable storage medium storing program for executing of human face recognition model |
| CN111292087A (en) * | 2020-01-20 | 2020-06-16 | 北京沃东天骏信息技术有限公司 | Identity verification method and device, computer readable medium and electronic equipment |
| CN112333165A (en) * | 2020-10-27 | 2021-02-05 | 支付宝(杭州)信息技术有限公司 | Identity authentication method, device, equipment and system |
| CN113630369A (en) * | 2020-05-08 | 2021-11-09 | 杭州海康威视数字技术股份有限公司 | Identity authentication method, identity authentication device and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103280219A (en) * | 2013-05-16 | 2013-09-04 | 中山大学 | Android platform-based voiceprint recognition method |
| CN103594091A (en) * | 2013-11-15 | 2014-02-19 | 深圳市中兴移动通信有限公司 | Mobile terminal and voice signal processing method thereof |
| WO2016145993A1 (en) * | 2015-03-13 | 2016-09-22 | 阿里巴巴集团控股有限公司 | Method and system for user device identification |
| CN106850955A (en) * | 2016-12-20 | 2017-06-13 | 陕西尚品信息科技有限公司 | A kind of mobile phone identity verification method based on Gait Recognition |
| CN106951751A (en) * | 2017-03-24 | 2017-07-14 | 电子科技大学 | A kind of sensor-based smart mobile phone unlocking recognition methods |
| CN106971203A (en) * | 2017-03-31 | 2017-07-21 | 中国科学技术大学苏州研究院 | Personal identification method based on characteristic on foot |
| CN107103297A (en) * | 2017-04-20 | 2017-08-29 | 武汉理工大学 | Gait identification method and system based on mobile phone acceleration sensor |
| CN107122704A (en) * | 2017-03-16 | 2017-09-01 | 华南理工大学 | A kind of gait recognition method based on motion sensor |
| CN107305604A (en) * | 2016-04-25 | 2017-10-31 | 腾讯科技（深圳）有限公司 | Terminal unlock method and device |
| CN107315354A (en) * | 2017-06-27 | 2017-11-03 | 苏州楚博生物技术有限公司 | A kind of intelligent domestic system based on radio sensing network |
| CN107682642A (en) * | 2017-09-19 | 2018-02-09 | 广州艾美网络科技有限公司 | Identify the method, apparatus and terminal device of special video effect triggered time point |
-
2018
- 2018-05-22 CN CN201810496387.2A patent/CN108710788A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103280219A (en) * | 2013-05-16 | 2013-09-04 | 中山大学 | Android platform-based voiceprint recognition method |
| CN103594091A (en) * | 2013-11-15 | 2014-02-19 | 深圳市中兴移动通信有限公司 | Mobile terminal and voice signal processing method thereof |
| WO2016145993A1 (en) * | 2015-03-13 | 2016-09-22 | 阿里巴巴集团控股有限公司 | Method and system for user device identification |
| CN107305604A (en) * | 2016-04-25 | 2017-10-31 | 腾讯科技（深圳）有限公司 | Terminal unlock method and device |
| CN106850955A (en) * | 2016-12-20 | 2017-06-13 | 陕西尚品信息科技有限公司 | A kind of mobile phone identity verification method based on Gait Recognition |
| CN107122704A (en) * | 2017-03-16 | 2017-09-01 | 华南理工大学 | A kind of gait recognition method based on motion sensor |
| CN106951751A (en) * | 2017-03-24 | 2017-07-14 | 电子科技大学 | A kind of sensor-based smart mobile phone unlocking recognition methods |
| CN106971203A (en) * | 2017-03-31 | 2017-07-21 | 中国科学技术大学苏州研究院 | Personal identification method based on characteristic on foot |
| CN107103297A (en) * | 2017-04-20 | 2017-08-29 | 武汉理工大学 | Gait identification method and system based on mobile phone acceleration sensor |
| CN107315354A (en) * | 2017-06-27 | 2017-11-03 | 苏州楚博生物技术有限公司 | A kind of intelligent domestic system based on radio sensing network |
| CN107682642A (en) * | 2017-09-19 | 2018-02-09 | 广州艾美网络科技有限公司 | Identify the method, apparatus and terminal device of special video effect triggered time point |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109886084A (en) * | 2019-01-03 | 2019-06-14 | 广东数相智能科技有限公司 | Face authentication method, electronic equipment and storage medium based on gyroscope |
| CN110070037A (en) * | 2019-04-22 | 2019-07-30 | 深圳力维智联技术有限公司 | Smooth upgrading method, device and the readable storage medium storing program for executing of human face recognition model |
| CN110070037B (en) * | 2019-04-22 | 2022-11-01 | 深圳力维智联技术有限公司 | Smooth upgrading method and device for face recognition model and readable storage medium |
| CN111292087A (en) * | 2020-01-20 | 2020-06-16 | 北京沃东天骏信息技术有限公司 | Identity verification method and device, computer readable medium and electronic equipment |
| CN113630369A (en) * | 2020-05-08 | 2021-11-09 | 杭州海康威视数字技术股份有限公司 | Identity authentication method, identity authentication device and storage medium |
| CN112333165A (en) * | 2020-10-27 | 2021-02-05 | 支付宝(杭州)信息技术有限公司 | Identity authentication method, device, equipment and system |
| CN112333165B (en) * | 2020-10-27 | 2022-09-23 | 支付宝(杭州)信息技术有限公司 | Identity authentication method, device, equipment and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108710788A (en) | A kind of safety certifying method, device, terminal and storage medium | |
| US11847199B2 (en) | Remote usage of locally stored biometric authentication data | |
| US10360412B2 (en) | Contextual contemporaneous gesture and keyboard entry authentication | |
| US20220075856A1 (en) | Identifying and authenticating users based on passive factors determined from sensor data | |
| KR102501838B1 (en) | Authentication apparatus and method based on electrocardiographic signals | |
| Buriro et al. | Itsme: Multi-modal and unobtrusive behavioural user authentication for smartphones | |
| Blanco‐Gonzalo et al. | Performance evaluation of handwritten signature recognition in mobile environments | |
| CN109660509A (en) | Login method, device, system and storage medium based on recognition of face | |
| CN109684806A (en) | Auth method, device, system and medium based on physiological characteristic information | |
| CN109997185A (en) | Method and apparatus for the biometric authentication in electronic equipment | |
| US10878071B2 (en) | Biometric authentication anomaly detection | |
| US11699449B2 (en) | In-ear liveness detection for voice user interfaces | |
| EP2817601A1 (en) | System and method for speaker recognition on mobile devices | |
| CN108847941A (en) | Identity identifying method, device, terminal and storage medium | |
| JP2018010625A (en) | Method and apparatus for verifying user using plural biometric verifiers | |
| WO2019001566A1 (en) | Authentication method and device | |
| CN112861082A (en) | Integrated system and method for passive authentication | |
| CN112084476A (en) | Biological identification identity verification method, client, server, equipment and system | |
| CN113826135A (en) | System and method for contactless authentication using voice recognition | |
| US20050286761A1 (en) | Ported system for personal identity verification | |
| Wu et al. | CaiAuth: Context-aware implicit authentication when the screen is awake | |
| CN108550368B (en) | Voice data processing method | |
| CN108447491B (en) | Intelligent voice recognition method | |
| Gattulli et al. | Touch events and human activities for continuous authentication via smartphone | |
| JP2021039749A (en) | On-device training based user recognition method and apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181026 |
|
| RJ01 | Rejection of invention patent application after publication |