CN107368717A - The method and terminal of a kind of identification - Google Patents
The method and terminal of a kind of identification Download PDFInfo
- Publication number
- CN107368717A CN107368717A CN201710420556.XA CN201710420556A CN107368717A CN 107368717 A CN107368717 A CN 107368717A CN 201710420556 A CN201710420556 A CN 201710420556A CN 107368717 A CN107368717 A CN 107368717A
- Authority
- CN
- China
- Prior art keywords
- data
- cluster
- point
- terminal
- sample
- 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.)
- Withdrawn
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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Collating Specific Patterns (AREA)
Abstract
The embodiment of the invention discloses a kind of method of identification and terminal, wherein method includes:If detecting, user grips terminal, obtains and grips data;Extract the grip features of the gripping data;If the grip features meet the cluster feature of the k sample point to prestore, confirm that the identity of the user is legal;Wherein, the k sample point is divided into m data cluster, and the k is positive integer, and the m is the integer more than 1 and less than or equal to 10.The embodiment of the present invention can effectively reflect that user grips the custom of terminal by way of extracting grip features, the identity of user can be identified according to cluster analysis so that only needing user to pick up terminal, user is not needed to pay substantial amounts of running cost, improve the efficiency of identification, in the absence of the risk of password leakage, and do not restricted by environmental factor, improve the security of identification.
Description
Technical field
The present invention relates to the method and terminal of electronic technology field, more particularly to a kind of identification.
Background technology
Increasingly paid attention to the extensive use of intelligent terminal, the problem of its information security, by user
Identification can effectively protect the information security on intelligent terminal.
At present, user identity is identified usually using modes such as password or fingerprints, but using password as recognition mechanism,
User needs to pay a large amount of running costs, and is once cracked or is known by other people unintentionally, and the privacy of user will be exposed to
Among risk, and using fingerprint as recognition mechanism, intelligent terminal is needed to configure the related hardware of fingerprint, and increase is manufactured into
This, and fingerprint recognition rate is restricted by many factors, such as finger injuries fingerprint has on damaged, finger water oil etc., all can
Its discrimination is influenceed, causes to perplex to user, meanwhile, the generation of fingerprint film also allows the security of fingerprint to be had a greatly reduced quality.
The content of the invention
The embodiment of the present invention provides a kind of method and terminal of identification, and the habit of terminal device can be gripped according to user
It is used, the identity of user is identified by the cluster analysis to grip features, improves the security and recognition efficiency of identification.
In a first aspect, the embodiments of the invention provide a kind of method of identification, this method includes:
If detecting, user grips terminal, obtains and grips data;
Extract the grip features of the gripping data;
If the grip features meet the cluster feature of the k sample point to prestore, confirm that the identity of the user is legal;
Wherein, the k sample point is divided into m data cluster, and the k is positive integer, and the m is more than 1 and is less than or equal to
10 integer.
On the other hand, the embodiments of the invention provide a kind of terminal, the terminal to include:
Data acquisition unit, if for detecting that user grips terminal, obtain and grip data;
Feature extraction unit, for extracting the grip features of the gripping data;
Identity recognizing unit, if the cluster feature for k sample point for meeting to prestore for the grip features, confirms institute
The identity for stating user is legal;Wherein, the k sample point is divided into m data cluster, and the k is positive integer, and the m is
Integer more than 1 and less than or equal to 10.
The embodiment of the present invention obtains when detecting that user grips terminal and grips data, and extract holding for the gripping data
Feature is held, by the grip features compared with the cluster feature to prestore, confirms to use if the grip features meet cluster feature
The identity at family is legal, by the method for the embodiment of the present invention, can effectively reflect user by the way of grip features are extracted
Grip the custom of terminal so that only needing user to pick up terminal the identity of user can be identified according to cluster analysis, no
Need user to pay substantial amounts of running cost, improve the efficiency of identification, in the absence of the risk of password leakage, and not by ring
Border factor restricts, and improves the security of identification.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, it is required in being described below to embodiment to use
Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the present invention, general for this area
For logical technical staff, on the premise of not paying creative work, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of schematic flow diagram of the method for identification that the embodiment of the present invention one provides;
Fig. 2 be a kind of identification provided in an embodiment of the present invention method in grip features coordinate system schematic diagram;
Fig. 3 be a kind of identification provided in an embodiment of the present invention method in grip schematic diagram;
A kind of schematic flow diagram of the method for identification that Fig. 4 embodiment of the present invention two provides;
Fig. 5 is a kind of schematic block diagram for terminal that the embodiment of the present invention three provides;
Fig. 6 is a kind of schematic block diagram for terminal that the embodiment of the present invention four provides;
Fig. 7 is a kind of schematic block diagram for terminal that the embodiment of the present invention five provides.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is part of the embodiment of the present invention, rather than whole embodiments.Based on this hair
Embodiment in bright, the every other implementation that those of ordinary skill in the art are obtained under the premise of creative work is not made
Example, belongs to the scope of protection of the invention.
It should be appreciated that ought be in this specification and in the appended claims in use, term " comprising " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but it is not precluded from one or more of the other feature, whole
Body, step, operation, element, component and/or its presence or addition for gathering.
It is also understood that the term used in this description of the invention is merely for the sake of the mesh for describing specific embodiment
And be not intended to limit the present invention.As used in description of the invention and appended claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singulative, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and appended claims is
Refer to any combinations of one or more of the associated item listed and be possible to combine, and including these combinations.
As used in this specification and in the appended claims, term " if " can be according to context quilt
Be construed to " when ... " or " once " or " in response to determining " or " in response to detecting ".Similarly, phrase " if it is determined that " or
" if detecting [described condition or event] " can be interpreted to mean according to context " once it is determined that " or " in response to true
It is fixed " or " once detecting [described condition or event] " or " in response to detecting [described condition or event] ".
In the specific implementation, the terminal described in the embodiment of the present invention is including but not limited to such as with touch sensitive surface
The mobile phone, laptop computer or tablet PC of (for example, touch-screen display and/or touch pad) etc it is other just
Portable device.It is to be further understood that in certain embodiments, the equipment is not portable communication device, but with tactile
Touch the desktop computer of sensing surface (for example, touch-screen display and/or touch pad).
In discussion below, the terminal including display and touch sensitive surface is described.It is, however, to be understood that
It is that terminal can include one or more of the other physical user-interface device of such as physical keyboard, mouse and/or control-rod.
Terminal supports various application programs, such as one or more of following:Drawing application program, demonstration application journey
Sequence, word-processing application, website create application program, disk imprinting application program, spreadsheet applications, game application
Program, telephony application, videoconference application, email application, instant messaging applications, exercise
Support application program, photo management application program, digital camera application program, digital camera application program, web-browsing application
Program, digital music player application and/or video frequency player application program.
The various application programs that can be performed in terminal can use at least one public of such as touch sensitive surface
Physical user-interface device.It can adjust and/or change among applications and/or in corresponding application programs and touch sensitive table
The corresponding information shown in the one or more functions and terminal in face.So, the public physical structure of terminal is (for example, touch
Sensing surface) the various application programs with user interface directly perceived and transparent for a user can be supported.
Embodiment one:
Referring to Fig. 1, Fig. 1 is a kind of schematic flow diagram of the method for identification that the embodiment of the present invention one provides, this
The executive agent of embodiment can be the equipment such as smart mobile phone or other intelligent terminals.The method of identification shown in Fig. 1
It may comprise steps of:
If S101, detecting that user grips terminal, obtain and grip data.
Specifically, gripping data can be obtained by sensors such as touch sensor or pressure sensors.In terminal
Install sensor is distinguished in the positions such as left frame, left frame and lower frame, and the sensor can be obtained when user grips terminal to end
Pressure data caused by end.When user grips terminal, the sensor detects that the finger of user touches terminal, collects each
The gripping data of touch point, the gripping data include the positional information of contact point and the pressure data of contact point.
S102, extraction grip the grip features of data.
Specifically, as shown in Fig. 2 using the terminal A lower left corner as the origin of coordinates, the direction where lower frame is X-axis, the left side
Direction where frame is Y-axis, establishes three-dimensional system of coordinate.In the three-dimensional system of coordinate, by holding for the gripping data of each touch point
Feature is held to be represented with a three-dimensional coordinate (x, y, z), wherein, x represents vertical range of the contact point apart from Y-axis, and y represents contact point
Apart from the vertical range of X-axis, z represents the contact dynamics of contact point, and the pressure data that contact dynamics is got according to sensor enters
Row calculating is converted to.
It should be noted that because user is when gripping terminal, generally a contact surface be present between finger and terminal, i.e.,
Each multiple contact points between finger and terminal be present.Therefore, extraction grip data grip features when, to it is each with it is whole
The finger of end in contact extracts the grip features of a target contact point.For example, as shown in figure 3, when user is with the gesture in Fig. 3
When gripping terminal, target contact point is 5, and the grip features extracted are 5.
, can be by the more of the finger to each finger contacted with terminal when extracting the grip features of target contact point
The contact point in center is as target contact point in individual contact point, or by curable grip in multiple contact points of the finger
Maximum contact point is spent as target contact point, can also carry out algorithm by the grip features of multiple contact points to the finger
After synthesis, the grip features of obtained synthesis grip features as target contact point.The mode of specifically chosen target contact point can
It is configured with the needs according to practical application, is not limited herein.
When the grip features of multiple contact points on to a contact surface carry out algorithm synthesis, can be put down using arithmetic
, weighted average, geometric average, local weighted, and Naive Bayes Classifier (Naive Bayesian Classifier,
) etc. NBC multiple grip features are calculated, obtains integrating grip features.
If S103, grip features meet the cluster feature of the k sample point to prestore, confirm that the identity of user is legal;Its
In, k sample point is divided into m data cluster, and k is positive integer, and m is the integer more than 1 and less than or equal to 10.
Specifically, terminal has prestored the cluster feature of k sample point, and each sample point is comprising target contact point
Grip features, should by obtaining the grip features of k contact point after being extracted to the grip features of the multiple gripping of validated user
The grip features of k contact point can be used and extracted with identical extracting mode in step S102.Terminal passes through to k sample
This point carries out cluster analysis and the k sample point is divided into m data cluster, and m is the quantity for the finger for gripping terminal, per number
According to the grip features of the corresponding finger of cluster.M is the integer more than 1 and less than or equal to 10, i.e., minimum 2 fingers contact is eventually
End, most 10 fingers contact terminal.
If the cluster feature for the k sample point that the grip features satisfaction that step S102 obtains active user prestores, i.e., current
The grip features that user grips the target contact point of each finger of terminal can be clustered in m data cluster, then are confirmed
The identity of active user is legal.
The method of the identification of the embodiment of the present invention can apply to unlocking screen, using unblock etc., when passing through this hair
After the personal identification method of bright embodiment judges that user identity is legal, terminal can authorize the user to check this terminal,
The manipulations such as editor, deletion.
Because the hand-characteristics such as the hand size of different user and finger length are different so that grip the gripping of terminal
Feature is different, for example, can singlehanded, both hands or single both hands alternately hold, the small user of palm grips the inclined mobile phone bottom of contact point
Portion, the big user's gripping contact point of palm is relatively top, and the dynamics that different user grips terminal also varies.Therefore, pass through
Extraction grip features can effectively reflect that user grips the custom of terminal, and then pass through the body of cluster analysis accurate judgement user
Whether part is legal.
It was found from the method for the identification of above-mentioned Fig. 1 examples, in the present embodiment, when detecting that user grips terminal,
Obtained by sensor and grip data, and extract the grip features of the gripping data, the grip features and the cluster to prestore are special
Sign is compared, and is confirmed that the identity of user is legal if the grip features meet cluster feature, is passed through the side of the embodiment of the present invention
Method, it can effectively reflect that user grips the custom of terminal by the way of grip features are extracted so that only need user to pick up
Terminal the identity of user can be identified according to cluster analysis, it is not necessary to which user pays substantial amounts of running cost, improves body
The efficiency of part identification, in the absence of the risk of password leakage, and is not restricted by environmental factor, improves the security of identification.
Embodiment two:
Referring to Fig. 4, Fig. 4 is a kind of schematic flow diagram of the method for identification that the embodiment of the present invention two provides, this
The executive agent of embodiment can be the equipment such as smart mobile phone or other intelligent terminals.The method of identification shown in Fig. 4
It may comprise steps of:
S201, obtain sample data.
Specifically, sample data can be obtained by sensors such as touch sensor or pressure sensors.In terminal
Install sensor is distinguished in the positions such as left frame, left frame and lower frame, and the sensor can be obtained when user grips terminal to end
Pressure data caused by end.When user grips terminal, the sensor detects that the finger of user touches terminal, collects each
The gripping data of touch point, the gripping data include the positional information of contact point and the pressure data of contact point.
Using the lower left corner of terminal as the origin of coordinates, the direction where lower frame is X-axis, and the direction where left frame is Y-axis,
Three-dimensional system of coordinate is established, as shown in Figure 2.In the three-dimensional system of coordinate, the grip features of the gripping data of each touch point are used
One three-dimensional coordinate (x, y, z) expression, wherein, x represents vertical range of the contact point apart from Y-axis, and y represents contact point apart from X-axis
Vertical range, z represent contact point contact dynamics, the pressure data that contact dynamics is got according to sensor carry out calculate turn
Get in return.
It should be noted that because user is when gripping terminal, generally a contact surface be present between finger and terminal, i.e.,
Each multiple contact points between finger and terminal be present.Therefore, extraction grip data grip features when, to it is each with it is whole
The finger of end in contact extracts the grip features of a target contact point.For example, as shown in figure 3, when user is with the gesture in Fig. 3
When gripping terminal, target contact point is 5, and the grip features extracted are 5.
, can be by the more of the finger to each finger contacted with terminal when extracting the grip features of target contact point
The contact point in center is as target contact point in individual contact point, or by curable grip in multiple contact points of the finger
Maximum contact point is spent as target contact point, can also carry out algorithm by the grip features of multiple contact points to the finger
After synthesis, the grip features of obtained synthesis grip features as target contact point.The mode of specifically chosen target contact point can
It is configured with the needs according to practical application, is not limited herein.
When the grip features of multiple contact points on to a contact surface carry out algorithm synthesis, can be put down using arithmetic
, weighted average, geometric average, local weighted, and NBC etc. are calculated multiple grip features, obtain it is comprehensive grip it is special
Sign.
According to features described above extracting mode, terminal after being extracted to the grip features of the multiple gripping of validated user by obtaining
To the sample data of k sample point, each sample data includes the grip features of a target contact point.
S202, using K- means clustering algorithms cluster analysis is carried out to sample data, obtain the cluster spy of k sample point
Sign so that the k sample point is divided into m data cluster.
K mean cluster algorithm is first to randomly select K object as initial cluster centre, then calculate each object with
The distance between each seed cluster centre, each object is distributed to the cluster centre nearest apart from it.Cluster centre and
Distribute to their object and just represent a cluster.Once whole objects are all assigned, the cluster centre each clustered can root
It is recalculated according to existing object in cluster.This process is repeated continuous until meeting some end condition, the termination bar
Part can be that no object is reassigned to different clusters, or no cluster centre changes again.
M is the quantity for the finger for gripping terminal, and each aggregate of data corresponds to the grip features of a finger.M be more than 1 and
Integer less than or equal to 10, i.e., minimum 2 fingers contact terminal, most 10 fingers contact terminal.
Specifically, cluster analysis is carried out to sample data using K- means clustering algorithms, the cluster for obtaining k sample point is special
Sign so that the k sample point, which is divided into m data cluster, to be realized by step S2021 to step S2025, specifically
It is bright as follows:
S2021, the target value for determining by calculating silhouette coefficient m.
Silhouette coefficient (Silhouette Coefficient) is used to assess Clustering Effect, and it combines cohesion degree
(Cohesion) and two kinds of factors of separating degree (Separation), silhouette coefficient is bigger represents that Clustering Effect is better.
Specifically, determine that m target value can be with a1 as follows by calculating silhouette coefficient) to step a4) real
It is existing, describe in detail as follows:
A1) under every kind of m possibility value condition, k sample point is clustered using exhaustive mode.
Specifically, to m value, traveled through from 2 to 10, under every kind of m value, using exhaustive mode to k sample
This point is clustered.
If for example, m=2, k=4, then the aggregate of data after clustering is 2,2 aggregates of data is named as into a1 and a2, by k sample
This point is named as k1, k2, k3 and k3, and the cluster mode obtained by exhaustive mode includes:
Cluster mode 1:A1={ k1 };A2={ k2, k3, k4 }
Cluster mode 2:A1={ k2 };A2={ k1, k3, k4 }
Cluster mode 3:A1={ k3 };a2:{ k1, k2, k4 }
Cluster mode 4:A1={ k4 };a2:{ k1, k2, k3 }
Cluster mode 5:A1={ k1, k3 };A2={ k2, k4 }
Cluster mode 6:A1={ k2, k3 };A2={ k1, k4 }
Cluster mode 7:A1={ k1, k2 };A2={ k3, k4 }
A2) under every kind of cluster mode, the silhouette coefficient of each sample point is calculated, obtains k silhouette coefficient.
Specifically, under every kind of cluster mode, the method for its silhouette coefficient is calculated for each sample point ki to be passed through
Following steps a21) to step a23) realize, describe in detail as follows:
A21 the distance between other sample points kj where) calculating ki and ki in aggregate of data s average value c1.
Distance s can be calculated by Euclidean distance formula.Assuming that sample point ki grip features are (xi, yi, zi),
Other sample points kj grip features are (xj, yj, zj), then the distance between ki and kj s calculation formula is:
Arithmetic average is carried out to the k distance obtained according to above-mentioned formula, obtains average value c1.
A22 the minimum distance c2 between other aggregates of data in addition to) calculating ki and the aggregate of data where the ki.
To other each aggregates of data in addition to aggregate of data where ki, calculate in ki and the aggregate of data between each sample point
Euclidean distance, and take being averaged for these Euclidean distances to be worth to the distance between ki and the aggregate of data, take ki with except where ki
The minimum value of the distance between other each aggregates of data outside aggregate of data, as minimum distance c2.
A23 each sample point ki silhouette coefficient g) is calculated according to equation below:
A3) under every kind of cluster mode, the average value of k silhouette coefficient, the monolithic wheel as every kind of cluster mode are calculated
Wide coefficient.
Specifically, under every kind of cluster mode, according in step a2) in obtained k silhouette coefficient of k sample point,
The average value of this k silhouette coefficient is calculated, the monolithic wheel storehouse coefficient as every kind of cluster mode.
A4 target value of the value as m that the maximum cluster mode of overall profile coefficient corresponds to m) is chosen.
Specifically, according to step a1) to step a3) obtain the entirety of every kind of cluster mode under every kind of m value conditions
In silhouette coefficient, target value of the value of m corresponding to the maximum cluster mode of body silhouette coefficient as m is chosen.
M target value is final data number of clusters mesh when being clustered to k sample point.
The starting central point of m S2022, random selection sample point as m data cluster.
Specifically, according to the step S2021 m determined target value, m sample point is randomly choosed from k sample point
Starting central point as m data cluster.
K S2023, traversal sample point, each sample point are divided into the starting central point closest with the sample point
In the aggregate of data at place.
Specifically, k sample point is traveled through, each sample point is calculated its with m starting central point Euclidean away from
From, and in m Euclidean distance being calculated, take starting central point corresponding to minimum Eustachian distance as with the sample point away from
From nearest starting central point, the sample point is divided into the aggregate of data where the starting central point
S2024, each aggregate of data of renewal starting central point.
Specifically, the aggregate of data obtained according to step S2023, the average value each clustered is calculated, i.e., in each aggregate of data
The average value of the middle grip features for calculating each sample point, every one-dimensional coordinate is calculated to the three-dimensional coordinate of each sample point respectively
Arithmetic averageWithAnd the three-dimensional coordinate that will be obtainedStarting central point after the horizontal renewal as the aggregate of data
Grip features.
S2025, continue to travel through k sample point, untill m starting central point no longer changes.
Specifically, repeat step S2023 to step S2024, continue to travel through k sample point, until in m starting
Untill the grip features of heart point no longer change.
By taking the holding mode shown in Fig. 3 as an example, cluster point is carried out to k sample point by step S2021 to step S2025
After analysis, 5 aggregates of data will be obtained, k sample point is divided into this 5 aggregates of data.
It should be noted that terminal has the ability of self-teaching, i.e. validated user is during using terminal, terminal
The grip features of the validated user got every time constantly will be all clustered in corresponding aggregate of data, so as to be continuously increased sample
Point, improve the accuracy of cluster analysis and the discrimination of identification.
If S203, detecting that user grips terminal, obtain and grip data.
Specifically, when the user of identity to be verified grips terminal, terminal is held by each touch point of sensor collection
Data are held, the gripping data include the positional information of contact point and the pressure data of contact point.
S204, extraction grip the grip features of data.
Specifically, grip features include the characteristic of n contact point between the user of identity to be verified and terminal, n
For the positive integer more than 1.To grip data grip features extraction can use with step S201 identical extracting modes, this
Place repeats no more.
If S205, n are equal to m, n contact point is traveled through, calculates each contact point and each aggregate of data in cluster feature
Minimum Eustachian distance between central point.
Specifically, m is the aggregate of data number to being obtained after sample data progress cluster analysis, and n is the use of identity to be verified
Contact point number between family and terminal, if n is not equal to m, illustrate what is contacted between the user of identity to be verified and terminal
Finger number and aggregate of data number are unequal, then assert that the user of identity to be verified is illegal, and terminal refuses the user to terminal
Manipulation request, if the user carrying out unlocking screen or application unblock etc. operation, terminal refusal be unlocked, flow
Journey terminates.
If n is equal to m, that is, represent the finger number and aggregate of data number contacted between the user of identity to be verified and terminal
It is equal, then n contact point is traveled through, calculates the central point for each aggregate of data that each contact point obtains with step S202 cluster analyses
Between Euclidean distance, and take in m obtained Euclidean distance minimum value as minimum Euclidean corresponding to each contact point away from
From.
The central point of each aggregate of data is no longer to change in the m data cluster that step S202 is obtained by cluster analysis
Originate central point.
S206, to each contact point, calculate between the sample point and central point in aggregate of data corresponding to minimum Eustachian distance
Maximum Euclidean distance.
Specifically, to each contact point, the minimum Eustachian distance obtained according to step S205, the minimum Eustachian distance is calculated
Euclidean distance between the central point of each sample point and the aggregate of data in corresponding aggregate of data, and in obtained Euclidean distance
Middle area's maximum is as maximum Euclidean distance corresponding to the aggregate of data.
S207, to each contact point, if minimum Eustachian distance is less than maximum Euclidean distance, confirm the feature of the contact point
Data meet cluster feature.
Specifically, to each contact point, if the minimum Eustachian distance that step S205 is obtained is less than what step S206 was obtained
Maximum Euclidean distance, then confirm that the contact point belongs to the characteristic of aggregate of data corresponding to minimum Eustachian distance, the i.e. contact point
Meet the cluster feature for the k sample point that step S202 is obtained.Flow continues executing with step S208.
If minimum Eustachian distance is more than or equal to maximum Euclidean distance, confirm that the contact point is not belonging to minimum Euclidean
Aggregate of data corresponding to distance, and the characteristic of the contact point are unsatisfactory for the cluster feature of the k sample point that step S202 is obtained,
Therefore confirm that the user of identity to be verified is illegal, terminal refuses manipulation request of the user to terminal, if the user is
The operation such as unlocking screen or application unblock is carried out, then terminal refusal is unlocked, and flow terminates.
It is understood that in embodiments of the present invention, to each contact point, if minimum Eustachian distance is less than maximum Euclidean
Distance, then confirm that the characteristic of the contact point meets cluster feature, connect in other inventive embodiments or to each
Contact, if minimum Eustachian distance is less than or equal to maximum Euclidean distance, confirm that the characteristic of the contact point meets cluster
Feature.
If the characteristic of S208, n contact points is satisfied by cluster feature, confirm that the identity of user is legal.
Specifically, after being traveled through to n contact point according to step S205 to step S207, if the spy of each contact point
Sign data are satisfied by the cluster feature for the k sample point that S202 is obtained, then confirm that the identity of the user of the identity to be verified is legal.
The method of the identification of the embodiment of the present invention can apply to unlocking screen, using unblock etc., when passing through this hair
After the personal identification method of bright embodiment judges that user identity is legal, terminal can authorize the user to check this terminal,
The manipulations such as editor, deletion.
It was found from the method for the identification of above-mentioned Fig. 4 examples, in the present embodiment, first, terminal is obtained by sensor
Sample data, and cluster analysis is carried out to the sample data using K- means clustering algorithms, the cluster for obtaining k sample point is special
Sign so that the k sample point is divided into m data cluster.Then, when the user for detecting identity to be verified grips terminal
When, obtained by sensor and grip data, extraction grips the grip features of n contact point of data, if n is equal to m, travels through n
Individual contact point, to each contact point, calculate the minimum Europe between the central point of each aggregate of data in the contact point and cluster feature
The maximum Euclidean distance between sample point and central point in family name's distance, and aggregate of data corresponding to the minimum Eustachian distance, if
First minimum Eustachian distance is less than maximum Euclidean distance, then confirms that the characteristic of the contact point meets cluster feature, if n connect
The characteristic of contact is satisfied by cluster feature, then confirms that the identity of user is legal, can by the way of grip features are extracted
Effective reflection user grips the custom of terminal so that only needs user to pick up the body that terminal can be according to cluster analysis to user
Part is identified, it is not necessary to which user pays substantial amounts of running cost, improves the efficiency of identification, in the absence of the wind of password leakage
Danger, and do not restricted by environmental factor, improve the security of identification.Meanwhile using K- means clustering algorithms to sample number
The feature that can accurately obtain user according to cluster analysis is carried out and grip terminal, the data number of clusters of cluster is determined by silhouette coefficient
Mesh, it is possible to increase to the Clustering Effect of sample data, improve the accuracy that K- means clustering algorithms carry out cluster analysis so that
The user of identity to be identified is judged by cluster feature to improve the accuracy rate of identification during identity legitimacy.
Embodiment three:
Referring to Fig. 5, Fig. 5 is a kind of terminal schematic block diagram that the embodiment of the present invention three provides.For convenience of description, only show
The part related to the embodiment of the present invention is gone out.The terminal 300 of Fig. 5 examples can be a kind of identity that previous embodiment one provides
Know the executive agent of method for distinguishing.The terminal 300 of Fig. 5 examples mainly includes:Data acquisition unit 31, the and of feature extraction unit 32
Identity recognizing unit 33.Each unit describes in detail as follows:
Data acquisition unit 31, if for detecting that user grips terminal, obtain and grip data;
Feature extraction unit 32, the grip features of the gripping data for extracting the acquisition of data acquisition unit 31;
Identity recognizing unit 33, if k sample point for meeting to prestore for the grip features that feature extraction unit 32 is extracted
Cluster feature, then confirm user identity it is legal;Wherein, k sample point is divided into m data cluster, and k is positive integer, m
For the integer more than 1 and less than or equal to 10.
Each unit realizes the process of respective function in a kind of terminal 300 that the present embodiment provides, and specifically refers to earlier figures 1
The description of illustrated embodiment, here is omitted.
It was found from the terminal 300 of above-mentioned Fig. 5 examples, in the present embodiment, when detecting that user grips terminal, pass through sensing
Device, which obtains, grips data, and extracts the grip features of the gripping data, and the grip features are compared with the cluster feature to prestore
Compared with confirming that the identity of user is legal if the grip features meet cluster feature, by the method for the embodiment of the present invention, using carrying
Taking the mode of grip features can effectively reflect that user grips the custom of terminal so that only needing user to pick up terminal can root
The identity of user is identified according to cluster analysis, it is not necessary to which user pays substantial amounts of running cost, improves the effect of identification
Rate, in the absence of the risk of password leakage, and do not restricted by environmental factor, improve the security of identification.
Example IV:
Referring to Fig. 6, Fig. 6 is a kind of terminal schematic block diagram that the embodiment of the present invention four provides.For convenience of description, only show
The part related to the embodiment of the present invention is gone out.The terminal 400 of Fig. 6 examples can be a kind of identity that previous embodiment two provides
Know the executive agent of method for distinguishing.The terminal 400 of Fig. 6 examples mainly includes:Data acquisition unit 41, the and of feature extraction unit 42
Identity recognizing unit 43.Each unit describes in detail as follows:
Data acquisition unit 41, if for detecting that user grips terminal, obtain and grip data;
Feature extraction unit 42, the grip features of the gripping data for extracting the acquisition of data acquisition unit 41;
Identity recognizing unit 43, if k sample point for meeting to prestore for the grip features that feature extraction unit 42 is extracted
Cluster feature, then confirm user identity it is legal;Wherein, k sample point is divided into m data cluster, and k is positive integer, m
For the integer more than 1 and less than or equal to 10.
Further, grip features include the characteristic of n contact point between user and the terminal, and n is more than 1
Positive integer, identity recognizing unit 43 includes:
First computing unit 431, if being equal to m for n, n contact point is traveled through, calculates each contact point and the k to prestore
Minimum Eustachian distance in the cluster feature of individual sample point between the central point of each aggregate of data;
Second computing unit 432, for each contact point, calculate minimum Euclidean that the first computing unit 431 obtains away from
From the maximum Euclidean distance between the sample point and central point in corresponding aggregate of data;
First judging unit 433, for each contact point, if the minimum Eustachian distance that the first computing unit 431 obtains
The maximum Euclidean distance obtained less than the second computing unit 432, then confirm that the characteristic of the contact point meets cluster feature;
Second judging unit 434, if the characteristic for n contact point is satisfied by cluster feature, confirm user's
Identity is legal.
Further, terminal 400 also includes:
Sample collection unit 44, for obtaining sample data;
Cluster analysis unit 45, the sample data for being obtained using K- means clustering algorithms to sample collection unit 44 are entered
Row cluster analysis, obtain the cluster feature of k sample point so that k sample point is divided into m data cluster.
Further, cluster analysis unit 45 includes:
Computing unit 451, for determining m target value by calculating silhouette coefficient;
Unit 452 is chosen, for randomly choosing starting central point of the m sample point as m data cluster;
Division unit 453, for traveling through k sample point, each sample point is divided into closest with the sample point
In aggregate of data where starting central point;
Updating block 454, for updating the starting central point of each aggregate of data;
Traversal Unit 455, for continuing to travel through k sample point, turned to until m starting central point no longer becomes
Only.
Further, computing unit 451 is additionally operable to:
Under every kind of m possibility value condition, k sample point is clustered using exhaustive mode;
Under every kind of cluster mode, the silhouette coefficient of each sample point is calculated, obtains k silhouette coefficient;
Under every kind of cluster mode, the average value of k silhouette coefficient, the overall profile system as every kind of cluster mode are calculated
Number.
Choose target value of the value of m corresponding to the maximum cluster mode of overall profile coefficient as m.
Each unit realizes the process of respective function in a kind of terminal 400 that the present embodiment provides, and specifically refers to earlier figures 3
The description of illustrated embodiment, here is omitted.
It was found from the terminal 300 of above-mentioned Fig. 5 examples, in the present embodiment, first, terminal obtains sample number by sensor
According to, and cluster analysis is carried out to the sample data using K- means clustering algorithms, obtain the cluster feature of k sample point so that
The k sample point is divided into m data cluster.Then, when the user for detecting identity to be verified grips terminal, biography is passed through
Sensor, which obtains, grips data, and extraction grips the grip features of n contact point of data, if n is equal to m, travels through n contact point,
To each contact point, the minimum Eustachian distance between the central point of each aggregate of data in the contact point and cluster feature is calculated, with
And the maximum Euclidean distance between the sample point and central point in aggregate of data corresponding to the minimum Eustachian distance, if the first minimum Europe
Family name's distance is less than maximum Euclidean distance, then confirms that the characteristic of the contact point meets cluster feature, if the feature of n contact point
Data are satisfied by cluster feature, then confirm that the identity of user is legal, can effectively be reflected by the way of grip features are extracted
User grips the custom of terminal so that only needing user to pick up terminal can know according to cluster analysis to the identity of user
Not, it is not necessary to user pays substantial amounts of running cost, improves the efficiency of identification, in the absence of the risk of password leakage, and
Do not restricted by environmental factor, improve the security of identification.Meanwhile sample data is gathered using K- means clustering algorithms
Alanysis can accurately obtain the feature that user grips terminal, and the aggregate of data number of cluster, Neng Gouti are determined by silhouette coefficient
The high Clustering Effect to sample data, improve the accuracy that K- means clustering algorithms carry out cluster analysis so as to be identified
The user of identity judges to improve the accuracy rate of identification during identity legitimacy by cluster feature.
Embodiment five:
Referring to Fig. 7, Fig. 7 is a kind of terminal schematic block diagram that the embodiment of the present invention five provides.The present embodiment shown in Fig. 7
In terminal 500 can include:One or more processors 501 (only show one) in Fig. 5;One or more input equipments
502 (one is only shown in Fig. 5), one or more output equipments 503 (one is only shown in Fig. 5), memory 504.Above-mentioned place
Reason device 501, input equipment 502, output equipment 503 and memory 504 are connected by bus 505.Memory 504 refers to for storage
Order, processor 501 are used for the instruction for performing the storage of memory 504.
Wherein, processor 501 is used for:
If detecting, user grips terminal, obtains and grips data;
Extraction grips the grip features of data;
If grip features meet the cluster feature of the k sample point to prestore, confirm that the identity of user is legal;Wherein, k
Sample point is divided into m data cluster, and k is positive integer, and m is the integer more than 1 and less than or equal to 10.
Further, grip features include the characteristic of n contact point between user and terminal, and n is more than 1 just
Integer, processor 501 are additionally operable to:
If n is equal to m, n contact point is traveled through, calculates the central point of each contact point and each aggregate of data in cluster feature
Between minimum Eustachian distance;
To each contact point, the maximum between the sample point and central point in aggregate of data corresponding to minimum Eustachian distance is calculated
Euclidean distance;
To each contact point, if minimum Eustachian distance is less than maximum Euclidean distance, the characteristic of the contact point is confirmed
Meet cluster feature;
If the characteristic of n contact point is satisfied by cluster feature, confirm that the identity of user is legal.
Further, processor 501 is additionally operable to:
Obtain sample data;
Cluster analysis is carried out to sample data using K- means clustering algorithms, obtains the cluster feature of k sample point so that
K sample point is divided into m data cluster.
Further, processor 501 is additionally operable to:
M target value is determined by calculating silhouette coefficient;
Randomly choose starting central point of the m sample point as m data cluster;
K sample point is traveled through, the sample point is divided into where the starting central point closest with the sample point
In aggregate of data;
Update the starting central point of each aggregate of data;
Continue to travel through k sample point, untill m starting central point no longer changes.
Further, processor 501 is additionally operable to:
Under every kind of m possibility value condition, k sample point is clustered using exhaustive mode;
Under every kind of cluster mode, the silhouette coefficient of each sample point is calculated, obtains k silhouette coefficient;
Under every kind of cluster mode, the average value of k silhouette coefficient, the overall profile system as every kind of cluster mode are calculated
Number.
Choose target value of the value of m corresponding to the maximum cluster mode of overall profile coefficient as m.
It should be appreciated that in embodiments of the present invention, alleged processor 501 can be CPU (Central
Processing Unit, CPU), the processor can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other FPGAs
Device, discrete gate or transistor logic, discrete hardware components etc..General processor can be microprocessor or this at
It can also be any conventional processor etc. to manage device.
Input equipment 502 can include Trackpad, fingerprint collecting sensor (is used for the finger print information and fingerprint for gathering user
Directional information), the light sensor intensity of light (be used for detect), microphone etc., output equipment 503 can include display
(LCD etc.), loudspeaker etc..
The memory 504 can include read-only storage and random access memory, and to processor 501 provide instruction and
Data.The a part of of memory 504 can also include nonvolatile RAM.For example, memory 504 can also be deposited
Store up the information of device type.
In the specific implementation, the processor 501 described in the embodiment of the present invention can perform the embodiment of the present invention one and implement
Implementation described by a kind of method for identification that example two provides, it also can perform the embodiment of the present invention three and example IV
The implementation of described terminal, will not be repeated here.
Those of ordinary skill in the art are it is to be appreciated that the list of each example described with reference to the embodiments described herein
Member and algorithm steps, it can be realized with electronic hardware, computer software or the combination of the two, in order to clearly demonstrate hardware
With the interchangeability of software, the composition and step of each example are generally described according to function in the above description.This
A little functions are performed with hardware or software mode actually, application-specific and design constraint depending on technical scheme.Specially
Industry technical staff can realize described function using distinct methods to each specific application, but this realization is not
It is considered as beyond the scope of this invention.
It is apparent to those skilled in the art that for convenience of description and succinctly, the end of foregoing description
End and the specific work process of unit, may be referred to the corresponding process in preceding method embodiment, will not be repeated here.
In several embodiments provided herein, it should be understood that disclosed terminal and method, it can be passed through
Its mode is realized.For example, device embodiment described above is only schematical, for example, the division of the unit, only
Only a kind of division of logic function, there can be other dividing mode when actually realizing, such as multiple units or component can be tied
Another system is closed or is desirably integrated into, or some features can be ignored, or do not perform.In addition, shown or discussed phase
Coupling or direct-coupling or communication connection between mutually can be INDIRECT COUPLING or the communication by some interfaces, device or unit
Connection or electricity, the connection of mechanical or other forms.
Step in present invention method can be sequentially adjusted, merged and deleted according to actual needs.
Unit in terminal of the embodiment of the present invention can be combined, divided and deleted according to actual needs.
The unit illustrated as separating component can be or may not be physically separate, show as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize scheme of the embodiment of the present invention according to the actual needs
Purpose.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also
It is that unit is individually physically present or two or more units are integrated in a unit.It is above-mentioned integrated
Unit can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and is used as independent production marketing or use
When, it can be stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially
The part to be contributed in other words to prior art, or all or part of the technical scheme can be in the form of software product
Embody, the computer software product is stored in a storage medium, including some instructions are causing a computer
Equipment (can be personal computer, server, or network equipment etc.) performs the complete of each embodiment methods described of the present invention
Portion or part steps.And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, various equivalent modifications can be readily occurred in or replaced
Change, these modifications or substitutions should be all included within the scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection domain be defined.
Claims (10)
- A kind of 1. method of identification, it is characterised in that methods described includes:If detecting, user grips terminal, obtains and grips data;Extract the grip features of the gripping data;If the grip features meet the cluster feature of the k sample point to prestore, confirm that the identity of the user is legal;Its In, the k sample point is divided into m data cluster, and the k is positive integer, and the m is more than 1 and less than or equal to 10 Integer.
- 2. according to the method for claim 1, it is characterised in that the grip features include the user and the terminal it Between n contact point characteristic, the n is positive integer more than 1, if the grip features meet k to prestore The cluster feature of sample point, then confirm the user identity it is legal including:If the n is equal to the m, the n contact point is traveled through, is calculated every in each contact point and the cluster feature Minimum Eustachian distance between the central point of the individual aggregate of data;To each contact point, calculate between the sample point and central point in aggregate of data corresponding to the minimum Eustachian distance Maximum Euclidean distance;To each contact point, if the minimum Eustachian distance is less than the maximum Euclidean distance, the contact point is confirmed The characteristic meet the cluster feature;If the characteristic of the n contact point is satisfied by the cluster feature, confirm that the identity of the user is legal.
- 3. method according to claim 1 or 2, it is characterised in that if described detect that user grips terminal, acquisition is held Before holding data, methods described also includes:Obtain sample data;Cluster analysis is carried out to the sample data using K- means clustering algorithms, obtains the cluster feature of the k sample point, So that the k sample point is divided into m data cluster.
- 4. according to the method for claim 3, it is characterised in that described to use K- means clustering algorithms to the sample data Cluster analysis is carried out, obtains the cluster feature of the k sample point so that the k sample point is divided into m data cluster Including:The target value of the m is determined by calculating silhouette coefficient;Randomly choose starting central point of the m sample point as the m data cluster;The k sample point is traveled through, each sample point is divided into the starting central point institute closest with the sample point Aggregate of data in;The starting central point of each aggregate of data of renewal;Continue to travel through the k sample point, untill the m starting central points no longer change.
- 5. according to the method for claim 4, it is characterised in that the target that the m is determined by calculating silhouette coefficient Value includes:Under every kind of m possibility value condition, the k sample point is clustered using exhaustive mode;Under every kind of cluster mode, the silhouette coefficient of each sample point is calculated, obtains k silhouette coefficient;Under every kind of cluster mode, the average value of the k silhouette coefficient is calculated, as the whole of every kind of cluster mode Body silhouette coefficient.Choose target value of the value of the m corresponding to the maximum cluster mode of the overall profile coefficient as the m.
- 6. a kind of terminal, it is characterised in that the terminal includes:Data acquisition unit, if for detecting that user grips terminal, obtain and grip data;Feature extraction unit, for extracting the grip features of the gripping data;Identity recognizing unit, if the cluster feature for k sample point for meeting to prestore for the grip features, confirms the use The identity at family is legal;Wherein, the k sample point is divided into m data cluster, and the k is positive integer, and the m is more than 1 And the integer less than or equal to 10.
- 7. terminal according to claim 6, it is characterised in that the grip features include the user and the terminal it Between n contact point characteristic, the n is positive integer more than 1, and the identity recognizing unit includes:First computing unit, if being equal to the m for the n, the n contact point is traveled through, calculate each contact point With the minimum Eustachian distance between the central point of each aggregate of data in the cluster feature;Second computing unit, for each contact point, calculating the sample in aggregate of data corresponding to the minimum Eustachian distance Maximum Euclidean distance between this point and central point;First judging unit, for each contact point, if the minimum Eustachian distance is less than the maximum Euclidean distance, Then confirm that the characteristic of the contact point meets the cluster feature;Second judging unit, if the characteristic for the n contact point is satisfied by the cluster feature, confirm institute The identity for stating user is legal.
- 8. the terminal according to claim 6 or 7, it is characterised in that the terminal also includes:Sample collection unit, for obtaining sample data;Cluster analysis unit, for carrying out cluster analysis to the sample data using K- means clustering algorithms, obtain the k The cluster feature of sample point so that the k sample point is divided into m data cluster.
- 9. terminal according to claim 8, it is characterised in that the cluster analysis unit includes:Computing unit, for determining the target value of the m by calculating silhouette coefficient;Unit is chosen, for randomly choosing starting central point of the m sample point as the m data cluster;Division unit, for traveling through the k sample point, each sample point is divided into closest with the sample point In aggregate of data where starting central point;Updating block, for updating the starting central point of each aggregate of data;Traversal Unit, for continuing to travel through the k sample point, turned to until the m starting central points no longer become Only.
- 10. terminal according to claim 9, it is characterised in that the computing unit is additionally operable to:Under every kind of m possibility value condition, the k sample point is clustered using exhaustive mode;Under every kind of cluster mode, the silhouette coefficient of each sample point is calculated, obtains k silhouette coefficient;Under every kind of cluster mode, the average value of the k silhouette coefficient is calculated, as the whole of every kind of cluster mode Body silhouette coefficient.Choose target value of the value of the m corresponding to the maximum cluster mode of the overall profile coefficient as the m.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710420556.XA CN107368717A (en) | 2017-06-05 | 2017-06-05 | The method and terminal of a kind of identification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710420556.XA CN107368717A (en) | 2017-06-05 | 2017-06-05 | The method and terminal of a kind of identification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107368717A true CN107368717A (en) | 2017-11-21 |
Family
ID=60305561
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710420556.XA Withdrawn CN107368717A (en) | 2017-06-05 | 2017-06-05 | The method and terminal of a kind of identification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107368717A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108810253A (en) * | 2018-05-18 | 2018-11-13 | 联想(北京)有限公司 | A kind of method, apparatus and electronic equipment of identification |
CN109886017A (en) * | 2019-01-24 | 2019-06-14 | 国网浙江省电力有限公司电力科学研究院 | A kind of mobile phone feature inspection optimization innovatory algorithm based on C4.5 decision tree |
CN111143910A (en) * | 2019-12-25 | 2020-05-12 | 惠州Tcl移动通信有限公司 | Anti-theft detection method and device, storage medium and terminal |
CN111738319A (en) * | 2020-06-11 | 2020-10-02 | 佳都新太科技股份有限公司 | Clustering result evaluation method and device based on large-scale samples |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106254597A (en) * | 2016-09-29 | 2016-12-21 | 努比亚技术有限公司 | A kind of gripping identification system based on proximity transducer |
CN106293328A (en) * | 2016-07-28 | 2017-01-04 | 乐视控股(北京)有限公司 | Icon display method and device |
CN106453424A (en) * | 2016-12-09 | 2017-02-22 | 深圳市金立通信设备有限公司 | Identity authenticating method and terminal |
-
2017
- 2017-06-05 CN CN201710420556.XA patent/CN107368717A/en not_active Withdrawn
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106293328A (en) * | 2016-07-28 | 2017-01-04 | 乐视控股(北京)有限公司 | Icon display method and device |
CN106254597A (en) * | 2016-09-29 | 2016-12-21 | 努比亚技术有限公司 | A kind of gripping identification system based on proximity transducer |
CN106453424A (en) * | 2016-12-09 | 2017-02-22 | 深圳市金立通信设备有限公司 | Identity authenticating method and terminal |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108810253A (en) * | 2018-05-18 | 2018-11-13 | 联想(北京)有限公司 | A kind of method, apparatus and electronic equipment of identification |
CN109886017A (en) * | 2019-01-24 | 2019-06-14 | 国网浙江省电力有限公司电力科学研究院 | A kind of mobile phone feature inspection optimization innovatory algorithm based on C4.5 decision tree |
CN111143910A (en) * | 2019-12-25 | 2020-05-12 | 惠州Tcl移动通信有限公司 | Anti-theft detection method and device, storage medium and terminal |
CN111143910B (en) * | 2019-12-25 | 2022-03-25 | 惠州Tcl移动通信有限公司 | Anti-theft detection method and device, storage medium and terminal |
CN111738319A (en) * | 2020-06-11 | 2020-10-02 | 佳都新太科技股份有限公司 | Clustering result evaluation method and device based on large-scale samples |
CN111738319B (en) * | 2020-06-11 | 2021-09-10 | 佳都科技集团股份有限公司 | Clustering result evaluation method and device based on large-scale samples |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CA2954516C (en) | Touch classification | |
Jain et al. | Exploring orientation and accelerometer sensor data for personal authentication in smartphones using touchscreen gestures | |
Meng et al. | Touch gestures based biometric authentication scheme for touchscreen mobile phones | |
CN107368717A (en) | The method and terminal of a kind of identification | |
CN103814351B (en) | Collaborative gesture-based input language | |
CN104778397B (en) | Information processor and its method | |
KR101189078B1 (en) | User identification apparatus and method with means for sensing touch input | |
CN106446786A (en) | Fingerprint identifying method, fingerprint identifying apparatus and terminal device | |
Blanco‐Gonzalo et al. | Performance evaluation of handwritten signature recognition in mobile environments | |
CN1797305A (en) | Reducing accidental touch-sensitive device activation | |
Jain et al. | Gender recognition in smartphones using touchscreen gestures | |
Seo et al. | A novel biometric identification based on a user's input pattern analysis for intelligent mobile devices | |
Yoon et al. | Lightful user interaction on smart wearables | |
CN109240554A (en) | Detect finger existing method and system near no touch screen | |
WO2017019390A1 (en) | Universal keyboard | |
US9392093B2 (en) | Multi-finger user identification | |
CN115271931A (en) | Credit card product recommendation method and device, electronic equipment and medium | |
Sturgess et al. | Watchauth: User authentication and intent recognition in mobile payments using a smartwatch | |
Hossain et al. | Incorporating deep learning into capacitive images for smartphone user authentication | |
Shen et al. | IncreAuth: Incremental-Learning-Based Behavioral Biometric Authentication on Smartphones | |
CN109298809A (en) | A kind of touch action recognition methods, device and terminal device | |
US11468153B2 (en) | Terminal device management method and terminal device | |
CN106484295A (en) | A kind of password method for retrieving and terminal | |
Nixon et al. | User classification and authentication for mobile device based on gesture recognition | |
CN106033536B (en) | The registered fingerprint data-updating method and electronic device of fingerprint recognition |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20171121 |
|
WW01 | Invention patent application withdrawn after publication |