CN104881594B - It is a kind of based on the smart mobile phone ownership detection method precisely drawn a portrait - Google Patents
It is a kind of based on the smart mobile phone ownership detection method precisely drawn a portrait Download PDFInfo
- Publication number
- CN104881594B CN104881594B CN201510227495.6A CN201510227495A CN104881594B CN 104881594 B CN104881594 B CN 104881594B CN 201510227495 A CN201510227495 A CN 201510227495A CN 104881594 B CN104881594 B CN 104881594B
- Authority
- CN
- China
- Prior art keywords
- user
- deviation
- portrait
- targeted customer
- characteristic vector
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 9
- 230000003542 behavioural effect Effects 0.000 claims abstract description 9
- 230000006399 behavior Effects 0.000 claims abstract description 6
- 239000013598 vector Substances 0.000 claims description 29
- 230000002776 aggregation Effects 0.000 claims description 12
- 238000004220 aggregation Methods 0.000 claims description 12
- 230000000052 comparative effect Effects 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 claims description 2
- 230000007246 mechanism Effects 0.000 abstract description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006855 networking 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Telephonic Communication Services (AREA)
- Mobile Radio Communication Systems (AREA)
- Telephone Function (AREA)
Abstract
The invention discloses a kind of based on the smart mobile phone ownership detection method precisely drawn a portrait, user's Figure Characteristics are collected into by identification, calculate the Figure Characteristics of user and the deviation of active user's behavioural characteristic, regular job behavior based on active autonomous learning cellphone subscriber, accurate user's portrait is carried out for cellphone subscriber, precisely portrait can turn into and differentiate whether the people that mobile device is being currently used is worth real equipment owner, and so as to prevent information to be stolen, equipment is abused;Meanwhile in the security mechanism of existing mobile device, while not influenceing the normal users experience of cellphone subscriber, then add extra real-time guard.
Description
Technical field
The invention belongs to mobile computing, data knowledge excavation applications, and in particular to a kind of based on the intelligent hand precisely drawn a portrait
Machine ownership detection method.
Background technology
Mobile computing, such as intelligent terminal, smart mobile phone, wearable smart machine etc., based on towards individual service
Calculating field has been achieved for great success, and has revolution in the routine work of people, trip, and the various aspects of life
The development of property.Current mobile computing characteristic, strong attraction is suffered to personal and enterprise customer.Modern intelligent mobile
Terminal, or wearable smart machine all largely store various personal or enterprise the sensitive informations of this user, such as short message, video
Picture, contact person, Email, social networks account, calendar put into practice meeting, Bank Account Number, stock exchange number etc..These letters
Breath be all to be easiest to be attacked and obtained in mobile computing, once mobile phone ownership by attack leak after, may give user with
Carry out great economic loss or individual privacy leakage.
In the prior art, the ownership of Intelligent Measurement mobile phone is also capable of without effective method.
The content of the invention
The invention provides a kind of based on the smart mobile phone ownership detection method precisely drawn a portrait, use is collected into by identification
Family Figure Characteristics, the Figure Characteristics of user and the deviation of active user's behavioural characteristic are calculated, used based on active autonomous learning mobile phone
The regular job behavior at family, accurate user's portrait is carried out for cellphone subscriber, precisely shifting can be being currently used as discriminating in portrait
Whether the people of dynamic equipment is worth real equipment owner, and so as to prevent information to be stolen, equipment is abused.
In order to solve the above-mentioned technical problem, the present invention includes following technical scheme:
It is a kind of based on the smart mobile phone ownership detection method precisely drawn a portrait, it is characterised in that comprise the following steps,
S1, when cellphone subscriber initially uses smart mobile phone, collect the use information of user;
S2, Active Learning is triggered, identification is collected into user's Figure Characteristics, and the Figure Characteristics of user are concluded in study;User's
Figure Characteristics refer to the use feature of user, i.e., draw up user by the use character modules of user and draw a portrait;
S3, the Figure Characteristics of user and the deviation of active user's behavioural characteristic are calculated, and calculate aggregation deviation;
S4, the aggregation deviation is compared with expected operation;
S5, if comparative result is outside threshold range described in step S4, calls licensing scheme to examine the identity of user, enter
Enter step S6;If comparative result is in threshold range, it is expected that operation will be started as scheduled;
S6, licensing scheme examines user identity, if identity verification is errorless, starts it is expected that operation is normal, is otherwise expected
Operation is terminated.
More preferably, the use information described in step S1 includes equipment angle, typewriting frequency, the typewriting appearance when user typewrites
Gesture, the use pattern of application program, based on timeliness using pattern and based on environment using pattern.
Specifically, the Figure Characteristics of user are concluded in step S2 study, specifically include following steps,
In targeted customer H training mode, targeted customer H m input behavior is obtained, calculates targeted customer's template
By m j-th of the feature deviation σ tested outj;
Figure Characteristics are represented by characteristic vector, it is assumed that give n the D feature vectors X, characteristic vector X of a unknown sample
Deviation d acquisition is calculated from the characteristic vector of n Figure Characteristics;
Wherein, XQ,jIt is characteristic vector XQJth feature, Xi,jIt is characteristic vector XiJ-th of feature, XQNeighbour it is minimum
Measurement module of the distance as targeted customer, d (XQ,Xi) represent characteristic vector XQWith characteristic vector XiDeviation.
Specifically, step S3 calculates aggregation deviation and specifically includes following steps,
(301) Figure Characteristics of user and the deviation of active user's behavioural characteristic, are calculated, it is assumed that the deviation is vector
d1,d2,…dn, n is the number of Figure Characteristics;
(302), it is assumed that the characteristic vector of current sample data is X={ X1,X2,…Xi,…,Xn},XiRepresent i-th of portrait
Feature, the template representation of targeted customer is T={ T1,T2,…,Tn};
(303), σjRepresent to pass through m j-th of the feature deviation tested out in targeted customer's template, then assemble deviation D
Calculation formula be:
Wherein, D (X, T) represents characteristic vector X and targeted customer T aggregation deviation.
Compared with prior art, the present invention includes following beneficial effect:
User's Figure Characteristics are collected into by identification, calculate the inclined of the Figure Characteristics of user and active user's behavioural characteristic
Difference, based on the regular job behavior of active autonomous learning cellphone subscriber, accurate user's portrait is carried out for cellphone subscriber, precisely portrait
It can turn into and differentiate whether the people that mobile device is being currently used is worth real equipment owner, so as to prevent information to be stolen
Take, equipment is abused;Meanwhile in the security mechanism of existing mobile device, the normal users experience of cellphone subscriber is not influenceed
Meanwhile then add extra real-time guard.
Brief description of the drawings
Fig. 1 is the workflow diagram of the present invention.
Embodiment
To make the purpose of the present invention, technical scheme, advantage clearer, below in conjunction with the accompanying drawings to the specific implementation of the present invention
Mode is described in detail.
Below with reference to the accompanying drawing of the present invention, clear, complete description is carried out to the technical scheme in the embodiment of the present invention
And discussion, it is clear that as described herein is only a part of example of the present invention, is not whole examples, based on the present invention
In embodiment, the every other implementation that those of ordinary skill in the art are obtained on the premise of creative work is not made
Example, belongs to protection scope of the present invention.
It is as shown in figure 1, a kind of based on the smart mobile phone ownership detection method precisely drawn a portrait, it is characterised in that including with
Lower step,
S1, when cellphone subscriber initially uses smart mobile phone, collect the use information of user;
Use information described in step S1 include equipment angle when user typewrites, typewriting frequency, typewriting posture, using journey
The use pattern of sequence, based on timeliness using pattern and based on environment using pattern.Application program uses mould
Formula specifically includes application call instruction, initial landing mailbox, then logs in social networking application;Based on timeliness using pattern
Being specifically included in the lunchtime browses mail etc.;The occasion for having wifi that is included in using pattern based on environment sees video
Deng.
S2, Active Learning is triggered, identification is collected into user's Figure Characteristics, and the Figure Characteristics of user are concluded in study;
Specifically, the Figure Characteristics of user are concluded in step S2 study, specifically include following steps,
In targeted customer H training mode, targeted customer H m input behavior is obtained, calculates targeted customer's template
By m j-th of the feature deviation σ tested outj;
Figure Characteristics are represented by characteristic vector, it is assumed that give n the D feature vectors X, characteristic vector X of a unknown sample
Deviation d acquisition is calculated from the characteristic vector of n Figure Characteristics;
Wherein, XQ,jIt is characteristic vector XQJth feature, Xi,jIt is characteristic vector XiJ-th of feature, XQNeighbour it is minimum
Measurement module of the distance as targeted customer.
S3, the Figure Characteristics of user and the deviation of active user's behavioural characteristic are calculated, and calculate aggregation deviation;
Specifically, step S3 calculates aggregation deviation and specifically includes following steps,
(301) Figure Characteristics of user and the deviation of active user's behavioural characteristic, are calculated, it is assumed that the deviation is vector
d1,d2,…dn, n is the number of Figure Characteristics;
(302), it is assumed that the characteristic vector of current sample data is X={ X1,X2,…Xi,…,Xn},XiRepresent i-th of portrait
Feature, the template representation of targeted customer is T={ T1,T2,…,Tn};
(303), σjRepresent to pass through m j-th of the feature deviation tested out in targeted customer's template, then assemble deviation D
Calculation formula be:
Wherein, D (X, T) represents characteristic vector X and targeted customer T aggregation deviation.
S4, the aggregation deviation is compared with expected operation.
S5, if comparative result is outside threshold range described in step S4, calls licensing scheme to examine the identity of user, enter
Enter step S6;If comparative result is in threshold range, it is expected that operation will be started as scheduled.Threshold value is by setting accuracy will
Ask and configured.
S6, licensing scheme examines user identity, if identity verification is errorless, starts it is expected that operation is normal, is otherwise expected
Operation is terminated.Licensing scheme refers to the specific startup task operating of cellphone subscriber.
It the above is only the preferred embodiment of the present invention, it should be pointed out that:Come for those skilled in the art
Say, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications also should be regarded as
Protection scope of the present invention.
Claims (2)
- It is 1. a kind of based on the smart mobile phone ownership detection method precisely drawn a portrait, it is characterised in that comprise the following steps,S1, when cellphone subscriber initially uses smart mobile phone, collect the use information of user;S2, Active Learning is triggered, identification is collected into user's Figure Characteristics, and the Figure Characteristics of user are concluded in study;S3, the Figure Characteristics of user and the deviation of active user's behavioural characteristic are calculated, and calculate aggregation deviation;S4, the aggregation deviation is compared with expected operation;S5, if step S4 comparative results outside threshold range, call licensing scheme to examine the identity of user, into step S6;If comparative result is in threshold range, it is expected that operation will be started as scheduled;S6, licensing scheme examines user identity, if identity verification is errorless, starts it is expected that operation is normal, otherwise expected operation It is terminated;The Figure Characteristics of user are concluded in step S2 study, specifically include following steps,In targeted customer H training mode, targeted customer H m input behavior is obtained, calculates targeted customer's template process M j-th of the feature deviation σ tested outj;Figure Characteristics are represented by characteristic vector, it is assumed that give the n D feature vectors X of a unknown sample, characteristic vector X's is inclined Poor d calculates acquisition from the characteristic vector of n Figure Characteristics;Wherein, XQ,jIt is characteristic vector XQJth feature, Xi,jIt is characteristic vector XiJ-th of feature, XQNeighbour's minimum range Measurement module as targeted customer;Step S3 calculates aggregation deviation and specifically includes following steps,(301) Figure Characteristics of user and the deviation of active user's behavioural characteristic, are calculated, it is assumed that the deviation is vector d1, d2,…dn, n is the number of Figure Characteristics;(302), it is assumed that the characteristic vector of current sample data is X={ X1,X2,…Xi,…,Xn},XiRepresent that i-th of portrait is special Sign, the template representation of targeted customer is T={ T1,T2,…,Tn};(303), σjRepresent to pass through m j-th of the feature deviation tested out in targeted customer's template, then assemble the calculating of deviation D Formula is:Wherein, D (X, T) represents characteristic vector X and targeted customer T aggregation deviation.
- It is 2. according to claim 1 a kind of based on the smart mobile phone ownership detection method precisely drawn a portrait, it is characterised in thatUse information described in step S1 includes equipment angle when user typewrites, typewriting frequency, typewriting posture, application program Use pattern, based on timeliness using pattern and based on environment using pattern.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510227495.6A CN104881594B (en) | 2015-05-06 | 2015-05-06 | It is a kind of based on the smart mobile phone ownership detection method precisely drawn a portrait |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510227495.6A CN104881594B (en) | 2015-05-06 | 2015-05-06 | It is a kind of based on the smart mobile phone ownership detection method precisely drawn a portrait |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104881594A CN104881594A (en) | 2015-09-02 |
CN104881594B true CN104881594B (en) | 2018-04-03 |
Family
ID=53949087
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510227495.6A Active CN104881594B (en) | 2015-05-06 | 2015-05-06 | It is a kind of based on the smart mobile phone ownership detection method precisely drawn a portrait |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104881594B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018000281A1 (en) * | 2016-06-29 | 2018-01-04 | 深圳狗尾草智能科技有限公司 | User portrait representation learning system and method based on deep neural network |
CN108960988A (en) * | 2018-06-28 | 2018-12-07 | 北京金山安全软件有限公司 | Personalized wallpaper recommendation method and device, terminal device and storage medium |
CN109618342A (en) * | 2018-12-27 | 2019-04-12 | 上海碳蓝网络科技有限公司 | It is a kind of for determining the method and apparatus of the operation permission information of user |
CN109992982A (en) * | 2019-04-11 | 2019-07-09 | 北京信息科技大学 | Big data access authorization methods, device and big data platform |
CN111565390B (en) * | 2020-07-16 | 2020-12-15 | 深圳市云盾科技有限公司 | Internet of things equipment risk control method and system based on equipment portrait |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103699822A (en) * | 2013-12-31 | 2014-04-02 | 同济大学 | Application system and detection method for users' abnormal behaviors in e-commerce based on mouse behaviors |
CN104580091A (en) * | 2013-10-21 | 2015-04-29 | 深圳市腾讯计算机***有限公司 | Identity verification method, device and system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8312157B2 (en) * | 2009-07-16 | 2012-11-13 | Palo Alto Research Center Incorporated | Implicit authentication |
-
2015
- 2015-05-06 CN CN201510227495.6A patent/CN104881594B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104580091A (en) * | 2013-10-21 | 2015-04-29 | 深圳市腾讯计算机***有限公司 | Identity verification method, device and system |
CN103699822A (en) * | 2013-12-31 | 2014-04-02 | 同济大学 | Application system and detection method for users' abnormal behaviors in e-commerce based on mouse behaviors |
Also Published As
Publication number | Publication date |
---|---|
CN104881594A (en) | 2015-09-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104881594B (en) | It is a kind of based on the smart mobile phone ownership detection method precisely drawn a portrait | |
Shi et al. | Implicit authentication through learning user behavior | |
AU2012202777B2 (en) | Retrieving contact information based on image recognition searches | |
CN103530543A (en) | Behavior characteristic based user recognition method and system | |
CN105956518A (en) | Face identification method, device and system | |
WO2014078154A4 (en) | Generating challenge questions inferred from user history data | |
CN106713579B (en) | Telephone number identification method and device | |
CN103218557A (en) | Biological-recognition-based system theme recognition method and device | |
CN104268481A (en) | Method and device for realizing early warning of smart phone | |
CN109194689B (en) | Abnormal behavior recognition method, device, server and storage medium | |
CN104184653B (en) | A kind of method and apparatus of message screening | |
CN106485476A (en) | A kind of staff attendance system based on video | |
CN106534463A (en) | Strange incoming call processing method, device, terminal and server | |
CN103995997A (en) | Method and equipment for distributing user rights | |
CN105872250A (en) | Method and device for automatically recognizing owner identity of mobile terminal | |
CN103870502A (en) | Enterprise mobile social network system based on face recognition | |
CN105790948B (en) | A kind of identity identifying method and device | |
CN106504360B (en) | A kind of running supervisory practice and system | |
CN105844168B (en) | Method for secret protection and device for intelligent perception | |
CN103412885A (en) | Contact person photo setting method and device | |
WO2015165331A1 (en) | Information processing method and apparatus | |
CN104980409A (en) | Internet behavior management method and device | |
CN106331281A (en) | Mobile terminal and information processing method | |
CN109145633A (en) | Track data method for secret protection, electronic equipment, storage medium and system | |
CN109088873A (en) | A kind of login system based on recognition of face big data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
EXSB | Decision made by sipo to initiate substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20240416 Address after: Room 106, 3rd Floor, No. 118 Xuefu Road, Zhenjiang City, Jiangsu Province, 212000 Patentee after: Jiangsu Shangyun Network Technology Co.,Ltd. Country or region after: China Address before: Room 702, Xinminzhou Government Building, Zhenjiang City, Jiangsu Province, 212000 Patentee before: ZHENJIANG LEYOU NETWORK TECHNOLOGY Co.,Ltd. Country or region before: China |
|
TR01 | Transfer of patent right |