CN110610073A - Terminal unlocking verification method and device - Google Patents
Terminal unlocking verification method and device Download PDFInfo
- Publication number
- CN110610073A CN110610073A CN201910891523.2A CN201910891523A CN110610073A CN 110610073 A CN110610073 A CN 110610073A CN 201910891523 A CN201910891523 A CN 201910891523A CN 110610073 A CN110610073 A CN 110610073A
- Authority
- CN
- China
- Prior art keywords
- user
- unlocking
- data
- characteristic
- verification
- 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
- 238000012795 verification Methods 0.000 title claims abstract description 115
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000013528 artificial neural network Methods 0.000 claims abstract description 35
- 238000012549 training Methods 0.000 claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 10
- 230000006399 behavior Effects 0.000 claims description 143
- 230000008569 process Effects 0.000 claims description 9
- 230000008921 facial expression Effects 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 2
- 230000009471 action Effects 0.000 abstract description 4
- 210000003811 finger Anatomy 0.000 description 53
- 210000003813 thumb Anatomy 0.000 description 11
- 238000010586 diagram Methods 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 230000009191 jumping Effects 0.000 description 2
- 208000008454 Hyperhidrosis Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000037315 hyperhidrosis Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 244000144985 peep Species 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
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
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
- H04M1/72463—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions to restrict the functionality of the device
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a terminal unlocking verification method and a terminal unlocking verification device, wherein the method comprises the following steps: receiving user characteristic data and user behavior data; obtaining a user feature matching rate between the user feature data and the unlocking feature comparison data; when the user feature matching rate does not reach a feature verification threshold, carrying out neural network training on the user behavior data to obtain user behavior feature data; matching the user behavior characteristic data with the user behavior habit characteristic data to obtain a user behavior matching rate; carrying out weighting processing on the user characteristic matching rate and the user behavior matching rate to obtain an unlocking weight; and if the unlocking weight is larger than the weight threshold, the unlocking verification is successful, otherwise, the unlocking verification fails. The invention expands the free use degree of the unlocking action, and the behavior habit of the user is extremely difficult to be imitated by other people, so the terminal unlocking verification method and the device can meet the requirement of the unlocking safety of the mobile phone terminal.
Description
Technical Field
The invention relates to the technical field of identity recognition, in particular to a terminal unlocking verification method and device.
Background
The existing mobile phone screen unlocking method generally manually performs preset operation on a touch screen, performs screen unlocking after actions meet preset related unlocking requirements, and generally adopts an unlocking mode based on biological characteristics such as fingerprint characteristics, facial characteristics, voice characteristics, iris characteristics and the like. The current mainstream unlocking methods include inputting a digital password, a pattern password, a gesture track, a biological feature and the like.
In the conventional unlocking control process, multiple attempts are made in an unlocking mode until unlocking is successful. If the unlocking failure exceeds a certain number of times, the mobile phone is locked for a certain time to ensure the safety. However, as described above, there are various existing terminal unlocking methods, and the unlocking control process can be cyclically executed in only one unlocking method, and such a single unlocking method is poor in degree of freedom and easy to be cracked violently, and therefore, the security is still to be improved.
Another unlocking control procedure is to switch to another unlocking mode for an attempt when one unlocking mode is unsuccessful, for example, to switch to a password unlocking mode when fingerprint unlocking is unsuccessful, which is slightly better than the single unlocking mode described above. But under the special condition that both modes can not be normally unlocked, great inconvenience is brought to users, the password unlocking operation is relatively complicated, and meanwhile, the password unlocking operation is easy to peep and steal in public occasions, and the free use degree is poor.
The pattern password unlocking mode can cause the situation of wrong pattern drawing due to insufficient screen sensitivity, misoperation of a user and the like, negative experience is brought to unlocking operation, even key moments can cause that a mobile phone cannot be used in time and the opportunity of the key moments is missed due to incapability of unlocking, and the free use degree is poor.
In addition, specific unlocking operation can be performed only by pressing the power key of the mobile phone to light the screen to enter an unlocking interface when the mobile phone is turned off, the password unlocking mode and the pattern unlocking mode are complicated in operation, and when the mobile phone is frequently and repeatedly turned off and unlocked, the mobile phone power key is repeatedly pressed to cause the mobile phone power key to be used excessively and to be out of order, so that the free use degree is poor.
Currently, one unlocking approach that is relatively high in usage is biometric unlocking.
The fingerprint unlocking mode is the most mainstream biological characteristic unlocking mode at present, can be directly unlocked to the main page from the screen state naturally, and is convenient and simple. However, the biometric identification unlocking method still has a certain problem in actual use, for example, for the fingerprint unlocking method, when the fingerprint characteristics of the user are abnormal due to weather, seasonal variation, special scenes, a hyperhidrosis system and the like, the user often cannot use the fingerprint for unlocking, and in this case, the user experience is very poor and the free use degree is poor.
Another commonly used biometric unlocking method is facial feature unlocking. The safety of the face feature unlocking mode is poor, when makeup and the like of a user change, the unlocking recognition rate is low, the user experience is poor, different individuals with extremely similar faces are difficult to distinguish in the face feature unlocking mode, and the free use degree is poor.
Yet another biometric unlocking method is iris feature unlocking. However, in the current stage, the magic cube feature recognition cost is high, and the magic cube feature recognition method is only applied to few high-end mobile phone devices and some special devices. When the mobile phone adopts iris feature recognition, certain requirements are made on the angle and the distance between the mobile phone and the face of a user during unlocking, user experience is poor, and the free use degree is poor.
As described above, the degree of freedom in use is lowered by the influence of factors such as a single unlocking means factor, a password which is easily peeped, a natural environment factor, and a user biometric factor. Therefore, how to improve the free use degree of unlocking while satisfying the unlocking security of the mobile phone terminal becomes an urgent problem to be solved.
Disclosure of Invention
In view of this, the invention provides a terminal unlocking verification method and device, so as to improve the unlocking free use degree while meeting the unlocking security of a mobile phone terminal.
The technical scheme of the invention is realized as follows:
a terminal unlocking verification method comprises the following unlocking verification processes:
receiving user characteristic data and user behavior data corresponding to the user characteristic data;
matching the user characteristic data with stored unlocking characteristic comparison data to obtain a user characteristic matching rate between the user characteristic data and the unlocking characteristic comparison data;
comparing the user feature matching rate with a feature verification threshold, and performing neural network training on the user behavior data to obtain user behavior feature data when the user feature matching rate does not reach the feature verification threshold;
matching the user behavior characteristic data with the user behavior habit characteristic data to obtain a user behavior matching rate;
carrying out weighting processing on the user characteristic matching rate and the user behavior matching rate to obtain an unlocking weight;
and comparing the unlocking weight with a preset weight threshold, if the unlocking weight is greater than the weight threshold, the unlocking verification is successful, otherwise, the unlocking verification fails.
Preferably, the user behavior habit characteristic data is obtained by the following method:
collecting user behavior data of the user when the user successfully unlocks each time to form a user behavior habit data set;
and performing the neural network training on the user behavior habit data set to obtain the user behavior habit characteristic data.
Preferably, the weighting the user characteristic matching rate and the user behavior matching rate to obtain an unlocking weight includes obtaining the unlocking weight by using the following formula:
Q＝(a×μ+b×v)/(a+b)
wherein Q is the unlocking weight, mu is the user characteristic matching rate, v is the user behavior matching rate, a is a weighting coefficient of the user characteristic matching rate, and b is a weighting coefficient of the user behavior matching rate.
Preferably, the unlocking manner of the terminal includes:
a user fingerprint unlocking mode, a user face identification unlocking mode, a user iris identification unlocking mode and a touch screen input unlocking mode;
the user characteristic data comprises:
user fingerprint data corresponding to the user fingerprint unlocking mode, user face data corresponding to the user face identification unlocking mode, user iris data corresponding to the user iris identification unlocking mode and touch screen input data corresponding to the touch screen input unlocking mode;
the user behavior data includes:
when the terminal is unlocked by adopting the user fingerprint unlocking mode, fingerprint area data, fingerprint block data, finger pressing force data and finger ID corresponding to the user fingerprint data;
when the terminal is unlocked by adopting the user face identification unlocking mode, distance data, angle data, eye opening and closing degree data, facial expression characteristic data and makeup characteristic data which correspond to the user face data and are between the user face and a terminal camera are obtained;
when the terminal is unlocked by adopting the user iris identification unlocking mode, distance data, angle data, eye opening and closing degree data, facial expression characteristic data and makeup characteristic data which correspond to the user iris data and are used between the user face and a terminal camera are obtained;
and when the terminal is unlocked by adopting the touch screen input unlocking mode, the force exertion degree data of each point in the operation track, the acceleration data between each point in the operation track, the speed data between each point in the operation track and the initial point position data of the operation track, which correspond to the input data of the touch screen, of the user are left in the operation track of the touch screen.
Preferably, the terminal unlocking verification method further includes:
the user fingerprint unlocking mode, the user face identification unlocking mode, the user iris identification unlocking mode and the touch screen input unlocking mode are subjected to priority sequencing;
and when the unlocking verification is carried out on the terminal, sequentially executing the unlocking verification process in each unlocking mode from the highest priority to the lowest priority until the unlocking verification is successful or the unlocking verification of all the unlocking modes fails.
Preferably, the terminal unlocking verification method further includes:
when the unlocking verification is successful, executing unlocking operation on the terminal;
and when the unlocking verification fails, maintaining the locking state of the terminal.
Preferably, the terminal unlocking verification method further includes:
and when the unlocking verification is successful, updating the user behavior data to the user habit data set, and performing the neural network training on the updated user habit data set again to obtain updated user behavior habit characteristic data.
Preferably, the terminal unlocking verification method further includes:
and if the user characteristic data is successfully matched with the stored unlocking characteristic comparison data, the unlocking verification is successful.
A terminal unlock verification device, comprising:
the data receiving module is used for receiving user characteristic data and user behavior data corresponding to the user characteristic data;
the characteristic data matching module is used for matching the user characteristic data with stored unlocking characteristic comparison data to obtain a user characteristic matching rate between the user characteristic data and the unlocking characteristic comparison data;
the characteristic verification module is used for comparing the user characteristic matching rate with a characteristic verification threshold value;
the neural network training module is used for carrying out neural network training on the user behavior data to obtain user behavior feature data when the user feature matching rate does not reach a feature verification threshold value;
the behavior data matching module is used for matching the user behavior characteristic data with the user behavior habit characteristic data to obtain a user behavior matching rate;
the matching rate recording module is used for recording the user characteristic matching rate and the user behavior matching rate;
the weighting processing module is used for weighting the user characteristic matching rate and the user behavior matching rate to obtain an unlocking weight; and
and the verification adjudication module is used for comparing the unlocking weight with a preset weight threshold, if the unlocking weight is greater than the weight threshold, the adjudication unlocking verification is successful, and otherwise, the adjudication unlocking verification fails.
Preferably, the terminal unlocking verification device further comprises a behavior data collection module, which is used for collecting user behavior data of the user when the user successfully unlocks each time to form a user behavior habit data set;
the neural network training module is further configured to perform the neural network training on the user behavior habit data set to obtain the user behavior habit characteristic data.
An electronic device, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the steps of the terminal unlock verification method as described in any one of the above.
According to the terminal unlocking verification method and device, when the user characteristic matching rate does not meet the unlocking requirement, the neural network training is carried out on the user behavior data to obtain the user behavior matching rate reflecting the matching degree with the habit behavior of the user during unlocking, the user characteristic matching rate and the user behavior matching rate are weighted to obtain the unlocking weight, and whether the unlocking verification is successful or not is determined by comparing the unlocking weight with the set weight threshold. By the method, under special conditions, when a user cannot unlock the terminal by adopting the existing method, behavior reference for assisting unlocking is provided, the free use degree of unlocking action is expanded, and the behavior habit of the user is extremely difficult to imitate by others, so that the terminal unlocking verification method and the device can meet the requirement of unlocking safety of the mobile phone terminal.
Drawings
Fig. 1 is a flowchart of a terminal unlocking verification method according to an embodiment of the present invention;
FIG. 2 is a control flow chart of a user unlocking a terminal in multiple unlocking modes in the embodiment of the present invention;
fig. 3 is a flowchart illustrating a method for a user to execute a terminal unlocking verification method in any unlocking mode according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a terminal unlocking verification apparatus according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an electronic device according to an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and examples.
As shown in fig. 1, the terminal unlocking verification method according to the embodiment of the present invention includes the following unlocking verification processes:
step 1, receiving user characteristic data and user behavior data corresponding to the user characteristic data;
step 2, matching the user characteristic data with stored unlocking characteristic comparison data to obtain a user characteristic matching rate between the user characteristic data and the unlocking characteristic comparison data;
step 3, comparing the user characteristic matching rate with a characteristic verification threshold, and performing neural network training on the user behavior data to obtain user behavior characteristic data when the user characteristic matching rate does not reach the characteristic verification threshold;
step 4, matching the user behavior characteristic data with the user behavior habit characteristic data to obtain a user behavior matching rate;
step 5, weighting the user characteristic matching rate and the user behavior matching rate to obtain an unlocking weight;
and 6, comparing the unlocking weight with a preset weight threshold, wherein if the unlocking weight is greater than the weight threshold, the unlocking verification is successful, and otherwise, the unlocking verification fails.
In the embodiment of the present invention, the user characteristic data refers to information data for unlocking, which is received by the terminal and is input by a user, for example, for a fingerprint unlocking mode, the user characteristic data is fingerprint characteristic information of the user received by the terminal, and for a password unlocking mode, the user characteristic data is password information input by the user received by the terminal. The user behavior data refers to data in the aspect of user operation behavior received by the terminal when the user performs an unlocking operation, for example, for a fingerprint unlocking mode, the user behavior data includes fingerprint area data, fingerprint block data, finger pressing force, finger ID (number) and the like of the user received by the terminal.
In an alternative embodiment, the user behavior habit characteristic data is obtained by the following method:
collecting user behavior data of each successful unlocking of the user to form a user behavior habit data set;
and carrying out neural network training on the user behavior habit data set to obtain user behavior habit characteristic data.
Taking fingerprint unlocking as an example, the behavior habit characteristic data of the user with fingerprint unlocking is obtained by the following method:
when the user successfully unlocks in the fingerprint mode each time, corresponding user behavior data such as fingerprint area data and fingerprint block data are collected, and the user behavior data such as the fingerprint area data and the fingerprint block data when the user successfully unlocks in the fingerprint mode each time form a user behavior habit data set about user fingerprint mode unlocking;
and performing neural network training on the user behavior habit data set unlocked in the user fingerprint mode to obtain user behavior habit characteristic data unlocked in the user fingerprint mode.
The neural network training method adopted in the embodiment of the present invention can be implemented by using the existing technology, and meanwhile, the method for matching the user behavior characteristic data after being trained by using the neural network and the user behavior habit characteristic data can also be implemented by using the related technology in the technical field of the neural network, and details are not repeated here.
In an optional embodiment, the step 5 of weighting the user characteristic matching rate and the user behavior matching rate to obtain the unlocking weight includes obtaining the unlocking weight by using the following formula:
Q＝(a×μ+b×v)/(a+b)
wherein Q is an unlocking weight, mu is a user characteristic matching rate, v is a user behavior matching rate, a is a weighting coefficient of the user characteristic matching rate, and b is a weighting coefficient of the user behavior matching rate.
In the embodiment of the invention, the unlocking mode of the terminal can comprise a user fingerprint unlocking mode, a user face identification unlocking mode, a user iris identification unlocking mode and a touch screen input unlocking mode. Further, the user characteristic data includes: user fingerprint data corresponding to the user fingerprint unlocking mode, user face data corresponding to the user face identification unlocking mode, user iris data corresponding to the user iris identification unlocking mode, and touch screen input data corresponding to the touch screen input unlocking mode. User behavior data includes, but is not limited to: when the terminal is unlocked by adopting a user fingerprint unlocking mode, fingerprint area data, fingerprint block data, finger pressing force data, finger ID and the like corresponding to the user fingerprint data; when the terminal is unlocked by adopting a user face identification unlocking mode, distance data, angle data, eye opening and closing degree data, facial expression characteristic data, makeup characteristic data and the like between the user face corresponding to the user face data and a terminal camera are obtained; when the terminal is unlocked by adopting the user iris recognition unlocking mode, the data is consistent with the data acquired by the terminal unlocking by adopting the user face recognition unlocking mode, namely when the terminal is unlocked by adopting the user iris recognition unlocking mode, the distance data, the angle data, the eye opening and closing degree data, the facial expression characteristic data, the makeup characteristic data and the like during unlocking at different time periods are obtained between the user face and the terminal camera corresponding to the user iris data; when the terminal is unlocked by adopting a touch screen input unlocking mode, the force exertion degree data of each point in an operation track, the acceleration data between each point in the operation track, the speed data between each point in the operation track, the initial point position data of the operation track and the like which are left by a user in the touch screen and correspond to the input data of the touch screen.
When the terminal is unlocked by adopting a user fingerprint unlocking mode, the finger ID corresponding to the user fingerprint data can be obtained by the following method: and matching the user fingerprint data during the fingerprint unlocking with the stored fingerprint feature comparison data respectively to obtain a plurality of user fingerprint matching rates between the user fingerprint data during the fingerprint unlocking and the fingerprint feature comparison data respectively, and taking the finger ID corresponding to the fingerprint feature comparison data with the highest user fingerprint matching rate in the user fingerprint matching rates as the finger ID corresponding to the user fingerprint data during the fingerprint unlocking. The fingerprint feature comparison data are obtained by the following method: when the fingerprint feature comparison data is recorded, the fingerprint features of a plurality of fingers of the user are respectively obtained, the fingers of the user are numbered to obtain finger IDs, and the obtained fingerprint features of the fingers of the user and the corresponding finger IDs are used as the fingerprint feature comparison data.
For example, when the fingerprint feature comparison data is recorded, fingerprint features of a thumb, an index finger and a middle finger of the right hand of the user are respectively acquired, the thumb, the index finger and the middle finger of the right hand of the user are numbered to acquire respective finger IDs of the thumb, the index finger and the middle finger, and the fingerprint features of the thumb, the index finger and the middle finger of the right hand of the user and the finger IDs of the thumb, the index finger and the middle finger of the corresponding right hand are respectively bound to be used as right-hand thumb fingerprint feature comparison data, right-hand index finger fingerprint feature comparison data and right-hand middle finger fingerprint feature comparison data; when fingerprint unlocking is carried out, user fingerprint data during the fingerprint unlocking is respectively matched with stored right-hand thumb fingerprint feature comparison data, right-hand index finger fingerprint feature comparison data and right-hand middle finger fingerprint feature comparison data to obtain a right-hand thumb fingerprint matching rate, a right-hand index finger fingerprint matching rate and a right-hand middle finger fingerprint matching rate during the fingerprint unlocking, the finger ID corresponding to the highest fingerprint matching rate of the right-hand thumb fingerprint matching rate, the right-hand index finger fingerprint matching rate and the right-hand middle finger fingerprint matching rate is used as the finger ID corresponding to the user fingerprint data during the fingerprint unlocking, namely, the finger ID of the right-hand thumb is used as the finger ID during the fingerprint unlocking if the right-hand thumb fingerprint matching rate is the highest, the finger ID of the right-hand index finger is used as the finger ID during the fingerprint unlocking if the right-hand fingerprint matching rate is the highest, and if the fingerprint matching rate of the right middle finger is the highest, taking the finger ID of the right middle finger as the finger ID when the fingerprint is unlocked.
In combination with the above unlocking manner of the terminal, in the embodiment of the present invention, the terminal unlocking verification method further includes the following steps:
carrying out priority ordering on a user fingerprint unlocking mode, a user face identification unlocking mode, a user iris identification unlocking mode and a touch screen input unlocking mode;
when the unlocking verification is carried out on the terminal, the unlocking verification process is sequentially executed in each unlocking mode from the highest priority to the lowest priority until the unlocking verification is successful or the unlocking verification of all the unlocking modes fails.
In an optional embodiment, the user fingerprint unlocking mode, the user face recognition unlocking mode, the user iris recognition unlocking mode and the touch screen input unlocking mode can be prioritized according to the use frequency of the user fingerprint unlocking mode, the user face recognition unlocking mode, the user iris recognition unlocking mode and the touch screen input unlocking mode, and the user fingerprint unlocking mode, the user face recognition unlocking mode, the user iris recognition unlocking mode and the touch screen input unlocking mode can also be prioritized according to the selection of a user.
In an optional embodiment, the terminal unlocking verification method further includes: when the unlocking verification is successful, executing unlocking operation on the terminal; and when the unlocking verification fails, maintaining the locking state of the terminal.
In an optional embodiment, the terminal unlocking verification method further includes: and when the unlocking verification is successful, updating the user behavior data into the user habit data set, and performing neural network training on the updated user habit data set again to obtain updated user behavior habit characteristic data. In this way, the neural network training learning about the behavior habits of the user can be continuously carried out, thereby achieving the purpose of improving the accuracy.
In an optional embodiment, the terminal unlocking verification method further includes: and if the user characteristic data is successfully matched with the stored unlocking characteristic comparison data, the unlocking verification is successful.
When the terminal unlocking verification method provided by the embodiment of the invention is adopted, a user can perform priority sequencing among several modes (such as a fingerprint unlocking mode, a face recognition unlocking mode, an iris recognition unlocking mode and a touch screen input unlocking mode) capable of unlocking a terminal (such as a smart phone), for example, the priority sequencing is performed according to the use frequency of various unlocking modes or the priority sequencing is performed according to the preference of the user, and then the unlocking verification processes of the steps 1 to 6 are sequentially performed in various unlocking modes according to the sequence from the highest priority to the lowest priority until the unlocking is successful or the unlocking verification fails in all the unlocking modes. Hereinafter, the terminal unlocking verification method according to the present invention will be described with reference to fig. 2 and 3, taking a fingerprint unlocking manner, a face recognition unlocking manner, and a touch screen password input unlocking manner as examples.
As shown in fig. 2, the control flow for the user to perform terminal unlocking in multiple unlocking manners includes the following steps.
Step a1, the user executes unlocking operation by adopting a fingerprint unlocking mode, and then the step a2 is carried out;
step a2, judging whether the fingerprint unlocking is successful, if so, entering step a8, otherwise, entering step a 3;
step a3, jumping to a face recognition unlocking mode to execute an unlocking operation, and then entering step a 4;
step a4, judging whether the face recognition unlocking is successful, if so, entering step a8, otherwise, entering step a 5;
step a5, jumping to a touch screen input password unlocking mode to execute unlocking operation, and then entering step a 6;
step a6, judging whether the unlocking of the touch screen input password is successful, if so, entering step a8, otherwise, entering step a 7;
step a7, prompting relevant unlocking failure information;
and step a8, the terminal enters an unlocked interface.
As shown in fig. 3, the flow of executing the terminal unlocking verification method in any unlocking mode includes the following steps.
Step b1, receiving the user characteristic data of the unlocking and the user behavior data of the unlocking corresponding to the user characteristic data, and then entering step b 2.
Taking a fingerprint unlocking mode as an example, in the step b1, the user characteristic data is user fingerprint data, and the user behavior data is fingerprint area data, fingerprint block data, finger pressing force data, finger ID, and the like, and further, in the fingerprint unlocking mode, the step b1 executes: and receiving the user fingerprint data during unlocking, and fingerprint area data, fingerprint block data, finger pressing force data, finger ID and the like corresponding to the user fingerprint data during unlocking.
Step b2, matching the user characteristic data of the unlocking with the stored unlocking characteristic comparison data to obtain the user characteristic matching rate between the user characteristic data of the unlocking and the unlocking characteristic comparison data, and then entering step b 3.
In the fingerprint unlocking mode, step b2 performs: and matching the user fingerprint data during the unlocking with the stored fingerprint feature comparison data to obtain the user fingerprint matching rate between the user fingerprint data during the unlocking and the fingerprint feature comparison data.
And b3, judging whether the user feature matching rate reaches a feature verification threshold, if so, entering the step b8, and otherwise, entering the step b 4.
In the fingerprint unlocking mode, step b3 performs: and judging whether the fingerprint matching rate of the user reaches a fingerprint verification threshold value. The fingerprint verification threshold can adopt a fingerprint verification threshold used in an existing fingerprint unlocking mode.
B4, performing neural network training on the user behavior data during the unlocking to obtain the user behavior characteristic data during the unlocking, and then entering the step b 5.
In the fingerprint unlocking mode, step b4 performs: and (4) carrying out neural network training on the fingerprint area data, the fingerprint block data, the finger pressing force data, the finger ID and the like during unlocking to obtain the user fingerprint unlocking behavior characteristic data during unlocking.
And b5, matching the user behavior characteristic data during unlocking with the user behavior habit characteristic data to obtain a user behavior matching rate, and then entering the step b 6.
In the fingerprint unlocking mode, step b5 performs: and matching the characteristic data of the user fingerprint unlocking behavior during the unlocking with the characteristic data of the user fingerprint unlocking behavior habit to obtain the matching rate of the user fingerprint unlocking behavior.
The fingerprint unlocking behavior habit characteristic data of the user is obtained by the following method:
collecting fingerprint area data, fingerprint block data, finger pressing force data, finger ID and the like of a user when the fingerprint unlocking is successful each time to form a user fingerprint unlocking behavior habit data set;
and performing neural network training on the user fingerprint unlocking behavior habit data set to obtain the user fingerprint unlocking behavior habit characteristic data.
And b6, carrying out weighting processing on the user characteristic matching rate and the user behavior matching rate to obtain an unlocking weight, and then entering the step b 7.
If the user characteristic matching rate is mu, the user behavior matching rate is v, the unlocking weight is Q, the weighting coefficient of the user characteristic matching rate is a, and the weighting coefficient of the user behavior matching rate is b, the unlocking weight is obtained according to the following formula:
Q＝(a×μ+b×v)/(a+b)
in the fingerprint unlocking mode, step b6 performs: and weighting the user fingerprint matching rate and the user fingerprint unlocking behavior matching rate to obtain a fingerprint unlocking weight.
And b7, comparing the unlocking weight value with a preset weight value threshold, if the unlocking weight value is greater than the weight value threshold, entering the step b8, otherwise, entering the step b 9.
In the fingerprint unlocking mode, step b7 performs: and comparing the fingerprint unlocking weight with a preset fingerprint weight threshold. The fingerprint weight threshold value can be set based on the expected unlocking operation accuracy.
And b8, judging that the unlocking is successful, updating the user behavior data during the unlocking to a user fingerprint unlocking habit data set, and performing neural network training on the updated user fingerprint unlocking habit data set again to obtain updated user behavior habit characteristic data.
In the fingerprint unlocking mode, step b8 performs: and judging that the unlocking is successful, updating the fingerprint area data and the fingerprint block data during the unlocking to the user habit data set, and performing neural network training on the updated user habit data set again to obtain updated user fingerprint unlocking behavior habit characteristic data.
And b9, judging that the unlocking fails.
The embodiment of the invention also provides a terminal unlocking verification device, which comprises a data receiving module 11, a feature data matching module 12, a feature verification module 13, a neural network training module 14, a behavior data matching module 15, a matching rate recording module 16, a weighting processing module 17 and a verification adjudication module 18, as shown in fig. 4. The data receiving module 11 is configured to receive user characteristic data and user behavior data corresponding to the user characteristic data. The feature data matching module 12 is configured to match the user feature data with the stored unlocking feature comparison data, and obtain a user feature matching rate between the user feature data and the unlocking feature comparison data. The feature verification module 13 is configured to compare the user feature matching rate with a feature verification threshold. The neural network training module 14 is configured to perform neural network training on the user behavior data to obtain user behavior feature data when the user feature matching rate does not reach the feature verification threshold. The behavior data matching module 15 is configured to match the user behavior feature data with the user behavior habit feature data to obtain a user behavior matching rate. The matching rate recording module 16 is used for recording a user feature matching rate and a user behavior matching rate. The weighting processing module 17 is configured to perform weighting processing on the user characteristic matching rate and the user behavior matching rate to obtain an unlocking weight. The verification adjudication module 18 is configured to compare the unlocking weight with a preset weight threshold, and if the unlocking weight is greater than the weight threshold, adjudicate that the unlocking verification is successful, otherwise, adjudicate that the unlocking verification fails.
In an optional embodiment, the terminal unlocking verification apparatus further includes a behavior data collection module 19, configured to collect user behavior data of each successful unlocking by the user, and form a user behavior habit data set. In this alternative embodiment, the neural network training module 14 is further configured to perform neural network training on the user behavior habit data set to obtain user behavior habit feature data.
An embodiment of the present invention further provides an electronic device, a structure of which can be seen in fig. 5, where the electronic device includes: at least one processor 21; and a memory 22 communicatively coupled to the at least one processor 21; wherein the memory 22 stores instructions executable by the at least one processor 21, the instructions being executable by the at least one processor 21 to cause the at least one processor 21 to perform the steps of the terminal unlock verification method according to any one of the embodiments.
An embodiment of the present invention further provides a non-volatile computer-readable storage medium, which stores instructions that, when executed by a processor, cause the processor to perform the steps in the terminal unlock verification method as described in the above embodiments.
According to the terminal unlocking verification method and device, when the user characteristic matching rate does not meet the unlocking requirement, neural network training is carried out on user behavior data to obtain the user behavior matching rate reflecting the matching degree with the habit behavior of the user during unlocking, weighting processing is carried out on the user characteristic matching rate and the user behavior matching rate to obtain the unlocking weight, and whether unlocking verification is successful or not is determined by comparing the unlocking weight with the set weight threshold. By the method, under special conditions, when a user cannot unlock the terminal by adopting the existing method, behavior reference for assisting unlocking is provided, the free use degree of unlocking action is expanded, and the behavior habit of the user is extremely difficult to be imitated by other people, so that the terminal unlocking verification method and the device provided by the embodiment of the invention can meet the requirement on unlocking safety of the mobile phone terminal. The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (11)
1. A terminal unlocking verification method comprises the following unlocking verification processes:
receiving user characteristic data and user behavior data corresponding to the user characteristic data;
matching the user characteristic data with stored unlocking characteristic comparison data to obtain a user characteristic matching rate between the user characteristic data and the unlocking characteristic comparison data;
comparing the user feature matching rate with a feature verification threshold, and performing neural network training on the user behavior data to obtain user behavior feature data when the user feature matching rate does not reach the feature verification threshold;
matching the user behavior characteristic data with the user behavior habit characteristic data to obtain a user behavior matching rate;
carrying out weighting processing on the user characteristic matching rate and the user behavior matching rate to obtain an unlocking weight;
and comparing the unlocking weight with a preset weight threshold, if the unlocking weight is greater than the weight threshold, the unlocking verification is successful, otherwise, the unlocking verification fails.
2. The terminal unlocking verification method according to claim 1, wherein the user behavior habit characteristic data is obtained by the following method:
collecting user behavior data of the user when the user successfully unlocks each time to form a user behavior habit data set;
and performing the neural network training on the user behavior habit data set to obtain the user behavior habit characteristic data.
3. The method according to claim 1, wherein the weighting the user characteristic matching rate and the user behavior matching rate to obtain the unlocking weight comprises obtaining the unlocking weight by using the following formula:
Q＝(a×μ+b×v)/(a+b)
wherein Q is the unlocking weight, mu is the user characteristic matching rate, v is the user behavior matching rate, a is a weighting coefficient of the user characteristic matching rate, and b is a weighting coefficient of the user behavior matching rate.
4. The terminal unlock verification method according to claim 1, wherein:
the unlocking mode of the terminal comprises the following steps:
a user fingerprint unlocking mode, a user face identification unlocking mode, a user iris identification unlocking mode and a touch screen input unlocking mode;
the user characteristic data comprises:
user fingerprint data corresponding to the user fingerprint unlocking mode, user face data corresponding to the user face identification unlocking mode, user iris data corresponding to the user iris identification unlocking mode and touch screen input data corresponding to the touch screen input unlocking mode;
the user behavior data includes:
when the terminal is unlocked by adopting the user fingerprint unlocking mode, fingerprint area data, fingerprint block data, finger pressing force data and finger ID corresponding to the user fingerprint data;
when the terminal is unlocked by adopting the user face identification unlocking mode, distance data, angle data, eye opening and closing degree data, facial expression characteristic data and makeup characteristic data which correspond to the user face data and are between the user face and a terminal camera are obtained;
when the terminal is unlocked by adopting the user iris identification unlocking mode, distance data, angle data, eye opening and closing degree data, facial expression characteristic data and makeup characteristic data which correspond to the user iris data and are used between the user face and a terminal camera are obtained;
and when the terminal is unlocked by adopting the touch screen input unlocking mode, the force exertion degree data of each point in the operation track, the acceleration data between each point in the operation track, the speed data between each point in the operation track and the initial point position data of the operation track, which correspond to the input data of the touch screen, of the user are left in the operation track of the touch screen.
5. The terminal unlock verification method according to claim 4, further comprising:
the user fingerprint unlocking mode, the user face identification unlocking mode, the user iris identification unlocking mode and the touch screen input unlocking mode are subjected to priority sequencing;
and when the unlocking verification is carried out on the terminal, sequentially executing the unlocking verification process in each unlocking mode from the highest priority to the lowest priority until the unlocking verification is successful or the unlocking verification of all the unlocking modes fails.
6. The terminal unlock verification method according to claim 1, further comprising:
when the unlocking verification is successful, executing unlocking operation on the terminal;
and when the unlocking verification fails, maintaining the locking state of the terminal.
7. The terminal unlock verification method according to claim 2, further comprising:
and when the unlocking verification is successful, updating the user behavior data to the user habit data set, and performing the neural network training on the updated user habit data set again to obtain updated user behavior habit characteristic data.
8. The terminal unlock verification method according to claim 1, further comprising:
and if the user characteristic data is successfully matched with the stored unlocking characteristic comparison data, the unlocking verification is successful.
9. A terminal unlocking verification device is characterized by comprising:
the data receiving module is used for receiving user characteristic data and user behavior data corresponding to the user characteristic data;
the characteristic data matching module is used for matching the user characteristic data with stored unlocking characteristic comparison data to obtain a user characteristic matching rate between the user characteristic data and the unlocking characteristic comparison data;
the characteristic verification module is used for comparing the user characteristic matching rate with a characteristic verification threshold value;
the neural network training module is used for carrying out neural network training on the user behavior data to obtain user behavior feature data when the user feature matching rate does not reach a feature verification threshold value;
the behavior data matching module is used for matching the user behavior characteristic data with the user behavior habit characteristic data to obtain a user behavior matching rate;
the matching rate recording module is used for recording the user characteristic matching rate and the user behavior matching rate;
the weighting processing module is used for weighting the user characteristic matching rate and the user behavior matching rate to obtain an unlocking weight; and
and the verification adjudication module is used for comparing the unlocking weight with a preset weight threshold, if the unlocking weight is greater than the weight threshold, the adjudication unlocking verification is successful, and otherwise, the adjudication unlocking verification fails.
10. The terminal unlock verification device according to claim 9, wherein:
the terminal unlocking verification device also comprises a behavior data collection module which is used for collecting user behavior data when the user successfully unlocks each time to form a user behavior habit data set;
the neural network training module is further configured to perform the neural network training on the user behavior habit data set to obtain the user behavior habit characteristic data.
11. An electronic device, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the steps in the terminal unlock verification method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910891523.2A CN110610073A (en) | 2019-09-20 | 2019-09-20 | Terminal unlocking verification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910891523.2A CN110610073A (en) | 2019-09-20 | 2019-09-20 | Terminal unlocking verification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110610073A true CN110610073A (en) | 2019-12-24 |
Family
ID=68892947
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910891523.2A Pending CN110610073A (en) | 2019-09-20 | 2019-09-20 | Terminal unlocking verification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110610073A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022079A (en) * | 2016-07-27 | 2016-10-12 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and terminal |
| CN107451451A (en) * | 2017-07-28 | 2017-12-08 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
| CN107451449A (en) * | 2017-07-21 | 2017-12-08 | 广东欧珀移动通信有限公司 | Bio-identification unlocking method and Related product |
| CN109948311A (en) * | 2019-02-22 | 2019-06-28 | 维沃移动通信有限公司 | A kind of unlocking screen method and device |
-
2019
- 2019-09-20 CN CN201910891523.2A patent/CN110610073A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022079A (en) * | 2016-07-27 | 2016-10-12 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and terminal |
| CN107451449A (en) * | 2017-07-21 | 2017-12-08 | 广东欧珀移动通信有限公司 | Bio-identification unlocking method and Related product |
| CN107451451A (en) * | 2017-07-28 | 2017-12-08 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
| CN109948311A (en) * | 2019-02-22 | 2019-06-28 | 维沃移动通信有限公司 | A kind of unlocking screen method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yi et al. | Glassgesture: Exploring head gesture interface of smart glasses | |
| JP4340618B2 (en) | Biometric information authentication apparatus and method, biometric information authentication program, and computer-readable recording medium recording the biometric information authentication program | |
| CN104796857B (en) | Location-based security system for portable electronic device | |
| CN104123161B (en) | The method that a kind of unlocking screen of utilization human eye fixation point and application start | |
| US6983061B2 (en) | Personal authentication system and method using biometrics information, and registering apparatus, authenticating apparatus and pattern information input medium for the system | |
| CN101494690A (en) | Mobile terminal and unlocking method thereof | |
| US20150049922A1 (en) | Method for logging a user in to a mobile device | |
| CN104573458A (en) | Identity recognition method, device and system based on electrocardiogram signals | |
| TW201113741A (en) | Lock-state switching method, electronic apparatus and computer program product | |
| CN103761502A (en) | Safety certification device and method | |
| CN105068743A (en) | Mobile terminal user identity authentication method based on multi-finger touch behavior characteristics | |
| CN103617385A (en) | Terminal and method for unlocking screen | |
| CN103324947B (en) | Authentication method and authentication method | |
| CN106843987B (en) | Method and device based on fingerprint recognition starting associated application | |
| JP2008079680A (en) | Biological information authentication apparatus and personal authentication method using biological information | |
| CN109670413A (en) | Face living body verification method and device | |
| KR102514036B1 (en) | Electronic device and method for controlling the same | |
| CN109814964A (en) | A kind of method for showing interface, terminal device and computer readable storage medium | |
| JP2015106386A (en) | Biological information extraction device, biological information extraction method, and biological information extraction program | |
| JP6919381B2 (en) | Authentication device | |
| Pozo et al. | Exploring a statistical method for touchscreen swipe biometrics | |
| CN112989937B (en) | Method and device for user identity authentication | |
| CN103984415B (en) | A kind of information processing method and electronic equipment | |
| CN105335853A (en) | Mobile terminal payment method and system based on palmprint recognition, and mobile terminal | |
| CN110610073A (en) | Terminal unlocking verification method and device |
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: 20191224 |
|
| RJ01 | Rejection of invention patent application after publication |