CN106453348B - Based on the login authentication method of user interest in social networks - Google Patents
Based on the login authentication method of user interest in social networks Download PDFInfo
- Publication number
- CN106453348B CN106453348B CN201610928381.9A CN201610928381A CN106453348B CN 106453348 B CN106453348 B CN 106453348B CN 201610928381 A CN201610928381 A CN 201610928381A CN 106453348 B CN106453348 B CN 106453348B
- Authority
- CN
- China
- Prior art keywords
- user
- interest
- information
- model
- login
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0815—Network architectures or network communication protocols for network security for authentication of entities providing single-sign-on or federations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/083—Network architectures or network communication protocols for network security for authentication of entities using passwords
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Information Transfer Between Computers (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses, based on the login authentication method of user interest, the specifically social networking application scene based on Web selected first can be computer desktop terminal and be also possible to intelligent mobile terminal, and user completes registration in social networks；User information is divided into two class of more stable information and unstable information, constructs the information model of user.Registration ID of the more stable information comprising user, registion time, gender, name, age, native place etc..Unstable information includes user text, picture and the audio-video delivered and the commentary etc. made to other users；Unstable information based on user information model generates user interest model by web crawlers, word frequency statistics or Feature Extraction Technology；Finally user log-in authentication is completed using above-mentioned user interest model.The advantage of the invention is that supporting that cost is relatively low, efficiency is higher without additional hardware.By the interest and preference of user individual come the legitimacy of comprehensive judgement user identity, there is preferable safety.
Description
Technical field
The invention belongs to the crossing domain of social networks technology and information safe practice, it is related to excavating user interest preference
And it is applied to the certification and secure log technology of social network client software, and in particular to user is based in a kind of social networks
The login authentication method of interest.
Technical background
With the universal of social networks and development, user identity login authentication is most basic and be most to challenge now in the past
One of project.Presently, there are a variety of login authentication modes, and there are three types of mainstreams, one is conventional authentication mode.It is so-called
Conventional authentication mode is exactly that user inputs user name, password and other users secret information, is stored with background data base
Information is compared to pair, if correctly, just logining successfully.Second is external hard (soft) part authentication mode, refers to holding in user hand
Hardware or software the authentication information of user is stored in the hardware generally based on hardware, user no longer needs to input or fill out
Other information are write, this authentication mode is usually applied in the scenes such as U-shield and the smart card of bank.The third mode is made a living
Object feature verification mode, this mode are the authentication modes just to come into vogue recent years with the continuous development of science and technology, generally
It is the biological characteristic of user elder generation typing individual, such as the fingerprint or iris etc. of user, these user characteristics are all unique
, during certification, these biological characteristics of user need to be only acquired again, are then compared with the information of database.
If success, it will be able to smoothly log in.
These three authentication modes undeniably have the advantages that its is corresponding.For the first conventional login authentication mode
Speech, advantage be exactly it is easy to operate, low in cost, promote be easy, can be used by users.Second of outside is hard (soft)
The information of user is all integrated into an external hardware, if user needs login authentication by part authentication mode, it is only necessary to
External hardware device is connected together with Verification System, it will be able to user authentication is completed, it is easy to operate, such as want to log in silver
When row Internetbank, it is only necessary to U-shield are inserted into computer USB interface, it will be able to complete user authentication.The third authentication mode, biology are special
Levy authentication mode, the characteristics of this authentication mode is that distinctiveness is very high, such as fingerprint and iris etc., it is impossible to find two people's
Fingerprint is identical with iris, and therefore, the safety of the authentication mode is very high.
Although three kinds of above-mentioned authentication modes have the advantages that respective, there is also some very important disadvantages.It is right
In the first authentication mode, major defect is exactly that safety is not high, these user's secret informations such as username and password, is easy
It is obtained by illegal user with various means.For second of authentication mode, core is exactly external hardware, once the external hardware
Lost accidentally or obtained by criminal by user, biggish security risk may be caused to user, and make up outside this
Hardware needs certain cost.For the third authentication mode, main disadvantage is exactly at high cost.User fingerprints or iris are adopted
Collection and certification, require the support of the not cheap hardware device of price, and and not all application scenarios be all suitable for this login
Mode.
In view of the foregoing drawbacks, the trial that the specific information based on user that begins one's study carries out login authentication is had already appeared, such as
Open (bulletin) number discloses for the patent of CN101170637A, entitled " a kind of method of logging in personalized electronic program list "
A kind of method of logging in personalized electronic program list (EPG), Operation Support System is created according to customer attribute information in this method
User grouping, and specific aim business and service are distributed for each grouping；User log-in authentication success after, EPG server according to
Family essential attribute information obtains the user grouping information from Operation Support System, carries out user grouping according to user grouping information and sentences
It is disconnected, and the personalized EPG homepage URL for corresponding to the grouping is formed according to judging result, reinform set-top box (STB) load pair
The personalized EPG homepage URL of grouping described in Ying Yu enjoys the EPG so that realizing user logs on to personalized EPG homepage
Specific aim business and service corresponding to homepage.But above-mentioned customer attribute information is typed information, cannot be more anti-
Reflect the personal attribute of user.
Summary of the invention
The present invention for currently used authentication mode there are the shortcomings that, that is, safety is high, hardware is easy to be lost and biological
The problems such as feature verification is at high cost proposes to be realized according to the interest and preference of user in the social networks constantly universal epoch
The more login authentication method of safe and convenient.
To solve the above problems, the present invention proposes the login authentication method based on user interest in social networks, specifically
Technical solution comprises the steps of:
One, the specifically social networking application scene based on Web is selected, user completes registration；
Two, user information is divided into two class of more stable information and unstable information, constructs the information model of user；
Three, based on the unstable information of user information model, user interest model is generated, it is logical for generating user interest model
Cross what web crawlers, word frequency statistics or Feature Extraction Technology were realized；
Four, login mode is designed, completes user log-in authentication using above-mentioned user interest model, comprising:
The above-mentioned social networking application scene based on Web can be computer desktop terminal either intelligent mobile terminal.
Above-mentioned more stable information includes registration ID, registion time, user's gender, the name (or pet name), age, nationality of user
It passes through.
Above-mentioned unstable information includes text, picture and the audio-video and comment what other users were made that user is delivered
It states.
It is stepped on described in step 4 using three kinds below user's unrestricted choice when user interest model completion user log-in authentication
The combination of record mode must plant login mode comprising (3) in selected combination to complete to authenticate:
(1) traditional login authentication mode: pass through the user name stored in input username and password, with background data base
It is compared with password, if self-consistent, logins successfully；
(2) userspersonal information authenticates: the more stable information based on user, which is randomly selected, to go wrong, by way of question and answer
Please registrant answer, in order to prevent illegal user enter Web page consult user basic document, setting response time be X seconds,
If X seconds fail to answer out relevant issues later, login interface is closed；
(3) the picture authentication mode based on user interest model: the user information obtained with crawler, by word frequency statistics and
After classification processing, multiple types of users interest keyword is generated, these keywords may include the long-time interest of user, it is also possible to
Short time interest comprising user；It is random that interference keyword is added and generates picture at random according to these keywords；According to demand
It is arranged that select the picture time of correct user interest be X seconds, if choosing the correct figure for meeting user interest preference in X seconds
Piece then logins successfully, otherwise, login failure.
Beneficial effect
The advantages of login authentication method in social networks proposed by the present invention based on user interest, is:
1, easily legitimate user can be allowed to log in, can effectively stops illegal user.
2, this login scheme is supported without additional hardware, therefore cost is relatively low, efficiency is higher.
3, there is preferable safety by the interest of user individual and preference come the legitimacy of comprehensive judgement user identity
Property.
Detailed description of the invention
Fig. 1 is user information illustraton of model.
Fig. 2 is login authentication flow chart.
Specific embodiment
Now in conjunction with attached drawing, specific embodiments of the present invention are further described in detail.
Technical term and its important restrictions used in the present invention:
Web crawlers, be it is a kind of according to certain rules, automatically grab the program or script of web message.Using
Depth-first traversal searching algorithm regards web message node and its link as digraph, whole sections of digraph when initial
Point is not all searched, and a node of the optional digraph, which sets out, to be accessed the depth-first search recurrence of each node and can describe such as
Under: (1) it, first searches for the node that has been selected, and makes marks to node, indicate that the node has been searched；(2), then
From node, the neighbor node that successively search node is not searched.Enough WWWs are collected in this way
Information or data.
Word frequency statistics, cardinal principle are as follows: what a entry base (such as Baidu's entry) abundant prepared in advance, can be
Chinese vocabulary entry library is also possible to English word library.Then for statistics file, carry out participle operation, then with entry into
Row compares, if meeting entry, is recorded, and counts the number of entry appearance, then according to entry frequency of occurrence
Entry is shown from high to low.
Specific technical solution includes following four step:
One, the specifically social networking application scene based on Web is selected, user completes registration；
Two, user information is divided into two class of more stable information and unstable information, constructs the information model of user；
Three, based on the unstable information of user information model, user interest model is generated；
Four, login mode is designed, completes user log-in authentication using above-mentioned user interest model.
Selected specifically the social networks scene based on Web, the information model of designing user specifically include:
A: firstly, choosing the mobile social networking application scenarios based on Web (can be computer desktop terminal either intelligence
Mobile terminal).After user completes registration, so that it may issue personal information by the social network-i i-platform of mobile terminal or desktop end
And content or uploading pictures, audio and video etc., other social users can also be paid close attention to and by other social users
Concern, and all kinds of contents of other social users' publications comment etc..
B: user information is divided into two class of more stable information and unstable information, as shown in Figure 1.More stable information: refer to
It is that registration ID, registion time, user's gender, name (or pet name), age, native place and personal brief introduction of user etc. are some basic
Information, these information be it is metastable, will not change within a certain period of time in other words.Unstable information: it refers to using
The contents such as text, picture and audio-video that family is delivered and the commentary etc. that other users are made, these information each moment
It may all change.These two types of information constitute the information model of user.
Unstable information based on user information model is generated by web crawlers, word frequency statistics and Feature Extraction Technology
User interest model.It specifically includes:
C: it is based on User ID, the unstable information of user is crawled by web crawlers technology first, secondly by word frequency
Statistical technique carries out participle operation, and is classified according to participle feature, every one kind just represent the user a kind of interest or
Preference.
D: user interest model can be with is defined as: F={ (f1,β1,n1,θ1),(f2,β2,n2,θ2),...,(fm,βm,nm,
θm), T }, wherein fiRefer to the type of user interest preference, m indicates that the type of user interest preference shares m kind, the value model of i
Enclosing is positive integer between [1, m]；βiUser is represented to the favorable rating of i-th kind of interest preference type, βiValue it is bigger, then
Indicate that user is higher to the interest level of the type, it is on the contrary then opposite；niRefer to that i-th kind of interest preference type is united in word frequency
Number appeared in meter；βiIt may be defined as:In order to more accurately reflect the interest preference of user, user
Interest model be further subdivided into long-time interest and short time interest, use parameter θiIt is portrayed；Work as θiWhen=0, then table
Showing user's the i-th seed type interest, there is no variations；Work as θiWhen > 0, indicate that the i-th seed type of user interest gradually increases, if θi's
It is worth bigger, then it represents that increase degree is bigger；Work as θiWhen < 0, indicate that the i-th seed type of user interest is gradually reduced, if θiValue get over
It is small, then it represents that it is bigger to reduce degree；θiRemaining unchanged in a period of time threshold range T or increasing the then interest is long-time
Interest, on the contrary become smaller in T time threshold value then as short time interest.
A kind of specific calculating θ is given belowiMethod.It, can period in different times in user interest model
Interior statistics ni, such as time threshold range T equalization is divided into x small time cycles by us；It is directed to the i-th seed type of user
Interest,For indicating i-th kind of interest of each small time period start time appeared in word frequency statistics
Number, particularly,Indicate time of the i-th kind of interest at x-th small termination moment time cycle appeared in word frequency statistics
Number；Pass through calculatingTo reflect long-time interest and short time interest.
Login mode is designed, completes user log-in authentication using above-mentioned model, specific as follows:
G: the group of three kinds of login modes below user's unrestricted choice when user interest model completion user log-in authentication is utilized
It closes to complete to authenticate, but login mode: (1) traditional login authentication mode: by defeated must be planted comprising (3) in selected combination
Access customer name and password are compared with the username and password stored in background data base, if self-consistent, log at
Function；(2) userspersonal information authenticates: the more stable information based on user, which is randomly selected, to go wrong, and please be stepped on by way of question and answer
Record person answers, and illegal user enters the basic document that Web page consults user in order to prevent, and setting response time is X seconds, if X
Fail to answer out relevant issues after second, then closes login interface；(3) the picture authentication mode based on user interest model: with climbing
The user information that worm obtains generates multiple types of users interest keyword, these keywords after word frequency statistics and classification processing
It may include the long-time interest of user, it is also possible to the short time interest comprising user；According to these keywords, random be added is done
It disturbs keyword (non-user interest) and generates picture at random；Setting selects the picture time of correct user interest for X according to demand
Second, if choosing the correct picture for meeting user interest preference in X seconds, login successfully, otherwise, login failure.
A specific embodiment presented below, login authentication method of the invention is applied in Sina weibo scene, should
The lawful owner of Sina weibo is legitimate user.
Specific implementation steps will be described according to login process as shown in Figure 2 with this embodiment:
1. the information model of designing user
The information such as time, the pet name, native place, time, gender, age that step 1) registers microblog users are stablized as user
Information.
The information such as content of microblog, upload audio frequency and video, content of microblog comment that step 2) is sent out microblog users are as use
The unstable information in family.User is stablized into information and unstable information architecture user information model.
2. the unstable information based on user information model, raw by web crawlers, word frequency statistics and Feature Extraction Technology
At user interest model:
Step 1) starts crawlers using the ID of Sina weibo user as input parameter, obtains the specified microblogging and uses
The information at family, and user interest model is instantiated.
The unstable information for the Sina weibo user that step 2) obtains step 1) carries out word frequency statistics, analyzes each
Statistics number shared by interest, and once counted every a period of time, it can analyze out the transformation system of same hobby
Number.Word frequency statistics twice are carried out to the unstable information of the microblog users, the threshold values T between word frequency statistics is set as 7 days twice,
Specific interest classification is as shown in Table 1 and Table 2.
Table 1 first time word frequency statistics
| Interest | Word frequency number |
| Go | 19 |
| Shuttlecock | 18 |
| Qiao Xin | 12 |
| Body-building | 8 |
| Football | 7 |
Second of the word frequency statistics of table 2
The user interest that step 3) goes out word frequency statistics instantiates.
It can thus be seen that the transformation ratio of category of interest go and body-building increases, it may be considered that in time threshold T=
In 7 days, category of interest go and body-building are long-time interest.Category of interest football, shuttlecock and Qiao Xin (certain well-known movie actress)
Transformation ratio reduces, it may be considered that these three types of interest are short time interest in time threshold T=7 days.
3. designing login mode, user log-in authentication is completed using above-mentioned model
Utilize the combination of three kinds of login modes below user's unrestricted choice when user interest model completion user log-in authentication
To complete to authenticate, but login mode must be planted comprising following (3) in selected combination:
(1) traditional login authentication mode: pass through the use stored in input microblog users name and password, with background data base
Name in an account book and password are compared, if self-consistent, login successfully.
(2) userspersonal information authenticates: the more stable information based on user, which is randomly selected, to go wrong, by way of question and answer
Please registrant answer, for example, extract user birthday date and the pet name, as certification the problem of.In order to prevent illegal user into
Entering the basic document that Web page consults user, setting response time is 20 seconds, if 20 seconds fail to answer out relevant issues later,
Close login interface.
(3) the picture authentication mode based on user interest model: the user information obtained with crawler, by word frequency statistics and
After classification processing, multiple types of users interest keyword is generated, it is random that interference keyword (non-user is added according to these keywords
Interest) picture is generated at random, the short time interest of user both can be generated, the long-time interest of user also can be generated, for
User's selection.It is 30 seconds that setting, which selects the picture time of correct user interest, according to demand, meets use if chosen in 30 seconds
The correct picture of family interest preference, then login successfully, otherwise, login failure.For example, the Long-term Interest go of user can be extracted
And body-building, picture related with go and body-building is generated, then random be added interferes picture, for selection by the user correct interest figure
Piece.
The foregoing is merely a specific embodiments of the invention, are not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (1)
1. based on the login authentication method of user interest in social networks, it is characterised in that comprise the steps of:
One, the specifically social networking application scene based on Web is selected, user completes registration；
Two, user information is divided into two class of more stable information and unstable information, constructs the information model of user；
Three, based on the unstable information of user information model, user interest model is generated, generating user interest model is to pass through net
What network crawler, word frequency statistics or Feature Extraction Technology were realized；
Four, login mode is designed, completes user log-in authentication using above-mentioned user interest model, comprising:
The combination of three kinds of login modes below user's unrestricted choice when the completion user log-in authentication using user interest model
To complete to authenticate, but login mode must be planted comprising (3) in selected combination:
(1) traditional login authentication mode: by the user name stored in input username and password, with background data base and close
Code is compared, if self-consistent, logins successfully；
(2) userspersonal information authenticates: the more stable information based on user, which is randomly selected, to go wrong, and please be stepped on by way of question and answer
Record person answers, and illegal user enters the basic document that Web page consults user in order to prevent, and setting response time is X seconds, if X
Fail to answer out relevant issues after second, then closes login interface；
(3) the picture authentication mode based on user interest model: the user information obtained with crawler, by word frequency statistics and classification
After processing, multiple types of users interest keyword is generated, these keywords include the long-time interest of user and the short time of user
Interest；It is random that interference keyword is added and generates picture at random according to these keywords；Setting selection user interest according to demand
The picture time of preference is X seconds, if choosing the correct picture for meeting user interest preference in X seconds, is logined successfully, no
Then, login failure；
The social networking application scene of the Web is computer desktop terminal either intelligent mobile terminal；
The more stable information includes registration ID, registion time, user's gender, the name, the pet name, age, native place of user；
The unstable information includes user text, picture and the audio-video delivered and the commentary made to other users；
Further, based on the unstable information of user information model, by web crawlers, word frequency statistics and Feature Extraction Technology,
User interest model is generated, is defined as follows:
F={ (f1,β1,n1,θ1),(f2,β2,n2,θ2),...,(fm,βm,nm,θm), T }, wherein fiRefer to user interest preference
Type, m indicate user interest preference type share m kind, the value range of i is the positive integer between [1, m]；βiIt represents
Favorable rating of the user to i-th kind of interest preference type, βiValue it is bigger, then it represents that user gets over the interest level of the type
Height, it is on the contrary then opposite；niRefer to number of i-th kind of interest preference type appeared in word frequency statistics；βiIt may be defined as:In order to more accurately reflect the interest preference of user, when the interest model of user is further subdivided into long
Between interest and short time interest, use parameter θiIt is portrayed；Work as θiWhen=0, then it represents that user's the i-th seed type interest there is no
Variation；Work as θiWhen > 0, indicate that the i-th seed type of user interest gradually increases, if θiValue it is bigger, then it represents that increase degree is bigger；
Work as θiWhen < 0, indicate that the i-th seed type of user interest is gradually reduced, if θiValue it is smaller, then it represents that reduce degree it is bigger；θi
Remaining unchanged in a period of time threshold range T or increasing the then interest is long-time interest, otherwise is become in T time threshold value
Small is then short time interest.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610928381.9A CN106453348B (en) | 2016-10-31 | 2016-10-31 | Based on the login authentication method of user interest in social networks |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610928381.9A CN106453348B (en) | 2016-10-31 | 2016-10-31 | Based on the login authentication method of user interest in social networks |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106453348A CN106453348A (en) | 2017-02-22 |
| CN106453348B true CN106453348B (en) | 2019-11-15 |
Family
ID=58178027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610928381.9A Active CN106453348B (en) | 2016-10-31 | 2016-10-31 | Based on the login authentication method of user interest in social networks |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106453348B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107483456A (en) * | 2017-08-25 | 2017-12-15 | 北京元心科技有限公司 | Identity identifying method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101170637A (en) * | 2007-11-27 | 2008-04-30 | 中兴通讯股份有限公司 | A method for logging in personalized electronic program list |
| CN101770520A (en) * | 2010-03-05 | 2010-07-07 | 南京邮电大学 | User interest modeling method based on user browsing behavior |
| CN101833587A (en) * | 2010-05-28 | 2010-09-15 | 上海交通大学 | Network video searching system |
| CN101937524A (en) * | 2009-06-30 | 2011-01-05 | 华中师范大学 | Graduation design personalized guide system |
| CN105868267A (en) * | 2016-03-04 | 2016-08-17 | 江苏工程职业技术学院 | Modeling method for mobile social network user interests |
-
2016
- 2016-10-31 CN CN201610928381.9A patent/CN106453348B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101170637A (en) * | 2007-11-27 | 2008-04-30 | 中兴通讯股份有限公司 | A method for logging in personalized electronic program list |
| CN101937524A (en) * | 2009-06-30 | 2011-01-05 | 华中师范大学 | Graduation design personalized guide system |
| CN101770520A (en) * | 2010-03-05 | 2010-07-07 | 南京邮电大学 | User interest modeling method based on user browsing behavior |
| CN101833587A (en) * | 2010-05-28 | 2010-09-15 | 上海交通大学 | Network video searching system |
| CN105868267A (en) * | 2016-03-04 | 2016-08-17 | 江苏工程职业技术学院 | Modeling method for mobile social network user interests |
Non-Patent Citations (1)
| Title |
|---|
| 基于本体用户兴趣模型的个性化推荐系统;刁祖龙，张兴忠;《计算机应用与软件》;20131031;第30卷(第10期);第155-158页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106453348A (en) | 2017-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11385942B2 (en) | Systems and methods for censoring text inline | |
| Song et al. | Multiple social network learning and its application in volunteerism tendency prediction | |
| US8499053B2 (en) | Segmenting access to electronic message boards | |
| Qin | Hero on Twitter, traitor on news: How social media and legacy news frame Snowden | |
| US10735401B2 (en) | Online identity reputation | |
| US9152722B2 (en) | Augmenting online content with additional content relevant to user interest | |
| Wang et al. | Mashup-oriented API recommendation via random walk on knowledge graph | |
| US8666928B2 (en) | Knowledge repository | |
| Lu et al. | Privacy information security classification for internet of things based on internet data | |
| Ferrari | Fake accounts, real activism: Political faking and user-generated satire as activist intervention | |
| US20090192968A1 (en) | Enhanced knowledge repository | |
| Rupapara et al. | Improving video ranking on social video platforms | |
| Harrag et al. | Arabic fake news detection: A fact checking based deep learning approach | |
| CN110399505B (en) | Semantic tag generation method and device, and computer storage medium | |
| US20190034536A1 (en) | Cue data model implementation for adaptive presentation of collaborative recollections of memories | |
| Woo et al. | Life-experience passwords (leps) | |
| CN106453348B (en) | Based on the login authentication method of user interest in social networks | |
| Yao et al. | Topic-based rank search with verifiable social data outsourcing | |
| CN116159310A (en) | Data processing method, device, electronic equipment and storage medium | |
| Yang et al. | Detecting Multielement Algorithmically Generated Domain Names Based on Adaptive Embedding Model | |
| Poh et al. | Algorithm to estimate biometric performance change over time | |
| Yilmaz et al. | Inferring Political Alignments of Twitter Users: A case study on 2017 Turkish constitutional referendum | |
| López Hernández et al. | A Nondisturbing Service to Automatically Customize Notification Sending Using Implicit‐Feedback | |
| Kumar et al. | Protection against pornography | |
| Kang et al. | Redesigning and Implementing the Public Game Information and Rating System in South Korea |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Yuen Road Qixia District of Nanjing City, Jiangsu Province, No. 9 210003 Applicant after: Nanjing Post & Telecommunication Univ. Address before: 210003 Gulou District, Jiangsu, Nanjing new model road, No. 66 Applicant before: Nanjing Post & Telecommunication Univ. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20170222 Assignee: NUPT INSTITUTE OF BIG DATA RESEARCH AT YANCHENG Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS Contract record no.: X2021980013920 Denomination of invention: Login authentication method based on user interest in social network Granted publication date: 20191115 License type: Common License Record date: 20211202 |