CN110009519A - A kind of community detection method based on block chain social platform - Google Patents
A kind of community detection method based on block chain social platform Download PDFInfo
- Publication number
- CN110009519A CN110009519A CN201910086732.XA CN201910086732A CN110009519A CN 110009519 A CN110009519 A CN 110009519A CN 201910086732 A CN201910086732 A CN 201910086732A CN 110009519 A CN110009519 A CN 110009519A
- Authority
- CN
- China
- Prior art keywords
- point
- relationship
- vertex
- block chain
- transferring accounts
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
A kind of community detection method based on block chain social platform disclosed by the invention, the following steps are included: 1. obtain all station address and its transfer information in block chain social platforms, and the relationship of transferring accounts is established according to the relationship of transferring accounts between each station address and is transferred accounts relationship digraph;2. finding out the relationship of transferring accounts to transfer accounts the abnormal point occurred in relationship digraph and/or off path, and according to abnormal point and/or the off path confirmation found in the presence of the abnormal user information of abnormal behavior of transferring accounts;3. obtaining operation information of all users in block chain social platform;4. carrying out clustering to the operation information got according to time dimension, find and the biggish user information that peels off of normal behaviour mode discrimination;5. pair abnormal user information and the user information that peels off are polymerize in a manner of weighted sum, the lower user information of non-genuine and/or liveness is obtained.The present invention is effective and reasonably has detected the abnormal behaviour of user, to judge the authenticity and validity of user.
Description
Technical field
The present invention relates to block chain social platform technical field more particularly to a kind of community based on block chain social platform
Detection method.
Background technique
In PC epoch and mobile internet era, community detection method is generallyd use to the true of the user in social platform
Property and effective activity detected, at present community detection method be mainly according to the device hardware information of user grabbed and
Software use information.Wherein, device hardware information mainly includes network appliance address, IP address, equipment Serial Number of user etc.;
Software use information is then determined by the specific software that user uses, and in general includes log-on message, the usage record of user
Deng.After getting these information by certain means, the data model of customer analysis is set up according to domain knowledge, thus quantitative
Ground judges the authenticity and validity of user.Above-mentioned community detection method achieves certain effect in traditional social platform
Fruit, but when being applied in block chain social platform, some unconformable situations are produced, this is mainly by block chain
Caused by technical characteristic.
Important technology feature that there are three block chain tools is immutableness respectively, trace to the source and distribution is known together, compared to existing
Using Facebook as traditional social networks of representative, the social networks of new generation based on block chain at least has two major features:
Feature first is that the network structure of decentralization.As coeval mainstream company, existing Facebook without
Doubting is also centralized network, and Facebook itself plays huge medium platform function, and block chain is technically one
The solution of distributed account book can not distort record, ensure that genuine and believable property.For ordinary user, it is substantially
It is exactly a no meta network platform trusty, and uses to social networks, is exactly trusty point-to-point social flat
Platform.
Feature second is that user information it is highly confidential.The data of traditional social networks are all previously stored the clothes of platform side
It is engaged on device, early in 2012, Data Center Knowledge estimation Facebook shared 180000 servers, if this
A little servers are attacked, and consequence is difficult to imagine.And under block chain environment, social networks allows user to transport in oneself equipment
Row node simultaneously accesses network, interconnects in real time between node and node, and user information stores on the network node in an encrypted form, shape
At a distribution clouds.For block chain technology, data redundancy storage and data have only been grasped the user of code key and can just have been looked into
It sees.
Based on the above feature, need to design the completely new community detection method of one kind to adapt to block chain social platform.For this purpose,
The applicant passes through beneficial exploration and research, has found solution to the problems described above, technical solution described below
It generates in this background.
Summary of the invention
It is an object of the invention to: a kind of authenticity for detecting the user in block chain social platform and effectively is provided
The community detection method based on block chain social platform of liveness.
To achieve the goals above, the present invention can adopt the following technical scheme that realize:
A kind of community detection method based on block chain social platform, comprising the following steps:
Step S10 obtains station address and its transfer information all in block chain social platform, and according to each user
Relationship of transferring accounts between address establishes the relationship of transferring accounts and transfers accounts relationship digraph;
Step S20 finds out the relationship of transferring accounts and transfers accounts the abnormal point occurred in relationship digraph and/or off path, and
According to abnormal point and/or the off path confirmation found in the presence of the abnormal user information of abnormal behavior of transferring accounts;
Step S30 obtains operation information of all users in block chain social platform;
Step S40 carries out clustering to the operation information got according to time dimension, finds and normal behaviour mode
Distinguish the biggish user information that peels off;
Step S50 peels off to what is searched out in the abnormal user information and the step S40 confirmed in the step S20
User information is polymerize in a manner of weighted sum, and it is lower to obtain non-genuine and/or liveness in the block chain social platform
User information.
In a preferred embodiment of the invention, in the step S20, the abnormal point is convergent point or dispersion
Point, the convergent point be the relationship of transferring accounts transfer accounts in-degree in relationship digraph be more than defined threshold vertex, the spaced point
For the relationship of transferring accounts transfer accounts out-degree in relationship digraph be more than defined threshold vertex.
In a preferred embodiment of the invention, in the step S20, the off path is circular path or length
Path, the circular path refers to that some vertex is set out as starting point in the relationship digraph of transferring accounts, along directed edge time
A paths of starting point can be returned to after going through, the long path refers to that the vertex undergone in the relationship digraph of transferring accounts is more than
The path of defined threshold.
In a preferred embodiment of the invention, in the step S30, the operation information include user information,
Operating time, action type and device address.
In a preferred embodiment of the invention, in step s 40, according to time dimension to the operation information got
Carry out clustering, comprising the following steps:
Step S41 determines radius r and minimal point minPoints;
Step S42 since relationship digraph of transferring accounts any not visited vertex, and judges with this vertex
Centered on, the quantity on vertex that includes in the circle that r is radius whether be greater than or equal to minimal point minPoints;If being judged as
More than or equal to minimal point minPoints, then this vertex is marked as central point;If being judged as less than minimal point
MinPoints, then this vertex is marked as noise point;
Step S43 repeats step S42, until vertex all in relationship digraph of transferring accounts all is accessed;
Step S44, judge each noise point with the presence or absence of centered on any central point, r is in the circle of radius;If depositing
Then the noise point is marked as marginal point;If it does not exist, then the noise point is still marked as noise point;
Step S45 will regard as the user with normal behaviour mode labeled as user corresponding to the vertex of central point,
It will be regarded as and the biggish use that peels off of normal behaviour mode discrimination labeled as user corresponding to the vertex of marginal point or noise point
Family.
Due to using technical solution as above, the beneficial effects of the present invention are: the present invention passes through relationship analysis of transferring accounts
The behavioural information of customer relationship and acquisition user carry out multidimensional analysis, require no knowledge about the true identity of user, effectively and rationally
Ground has detected the abnormal behaviour of user, to judge the authenticity and validity of user.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the flow chart of community detection method of the invention.
Fig. 2 is the structural schematic diagram of the convergent point of relationship digraph of transferring accounts of the invention.
Fig. 3 is the structural schematic diagram of the spaced point of relationship digraph of transferring accounts of the invention.
Fig. 4 is the structural schematic diagram of the circular path of relationship digraph of transferring accounts of the invention.
Fig. 5 is the structural schematic diagram in the long path of relationship digraph of transferring accounts of the invention.
Fig. 6 is the structural schematic diagram of coordinate system used by clustering of the invention.
Specific embodiment
In order to be easy to understand the technical means, the creative features, the aims and the efficiencies achieved by the present invention, tie below
Conjunction is specifically illustrating, and the present invention is further explained.
Referring to Fig. 1, what is provided in figure is a kind of community detection method based on block chain social platform, including following step
It is rapid:
Step S10 obtains station address and its transfer information all in block chain social platform, and according to each user
Relationship of transferring accounts between address establishes relationship digraph of transferring accounts.Wherein, relationship of transferring accounts digraph is by several vertex and several
Directed edge is constituted, and all station address are as the vertex in relationship digraph of transferring accounts, if station address A has a record of transferring accounts
To station address B, then generated between vertex corresponding to the vertex corresponding to station address A and station address B one it is oriented
Side, the weight of this directed edge are the number transferred accounts.
Step S20 finds out the relationship of transferring accounts and transfers accounts the abnormal point occurred in relationship digraph and/or off path, and
According to abnormal point and/or the off path confirmation found in the presence of the abnormal user information of abnormal behavior of transferring accounts.Wherein, abnormal point is
Convergent point or spaced point.Convergent point be the relationship of transferring accounts transfer accounts in-degree in relationship digraph be more than defined threshold vertex, such as Fig. 2 institute
Show.Spaced point be transfer accounts out-degree in relationship digraph be more than defined threshold vertex, as shown in Figure 3.Off path is round
Diameter or long path.Circular path refers to that transferring accounts in relationship digraph some vertex as starting point in the relationship of transferring accounts sets out, along having
A paths of starting point can be returned to after to side traversal, as shown in Figure 4.Long path refers to transfers accounts relationship digraph in the relationship of transferring accounts
The vertex of middle experience is more than the path of defined threshold, as shown in Figure 5.Four kinds of abnormal patterns defined above: convergent point, dispersion
Point, circular path and long path represent a kind of behavior pattern of potential abnormal user, represent abnormal behavior of transferring accounts.
Step S30 obtains operation information of all users in block chain social platform, and the operation information includes user
Information, operating time, action type and device address.
Step S40 carries out clustering to the operation information got according to time dimension, finds and normal behaviour mode
Distinguish the biggish user information that peels off.In step s 40, the effect of clustering be with normal behaviour mode discrimination it is biggish from
Group's user information, that is, behavior pattern differ the biggish user that peels off with normal users, and this kind of user that peels off will be counted as
User non-genuine and with lower liveness.
Step S50, to the user that peels off searched out in the abnormal user information and the step S40 confirmed in step S20
Information is polymerize in a manner of weighted sum, obtains the lower use of non-genuine and/or liveness in the block chain social platform
Family information.Specifically, the customer analysis based on block block transfer information obtained in step S20 is as a result, reflect user in area
The authenticity operated in block chain social platform is enlivened with effective, and the user with special relationship of transferring accounts is considered abnormal user;Step
The customer analysis based on block chain social platform operation data has been obtained as a result, reflecting user in block chain society in rapid S40
Hand over the authenticity on platform with effectively actively, the outlier user of algorithm detection is considered exception.
In step s 40, clustering is carried out to the operation information got according to time dimension, comprising the following steps:
Step S41 determines radius r and minimal point minPoints;
Step S42 since relationship digraph of transferring accounts any not visited vertex, and judges with this vertex
Centered on, the quantity on vertex that includes in the circle that r is radius whether be greater than or equal to minimal point minPoints, such as Fig. 6 institute
Show;If being judged as, more than or equal to minimal point minPoints, this vertex is marked as central point;It is less than if being judged as
Minimal point minPoints, then this vertex is marked as noise point;
Step S43 repeats step S42, until vertex all in relationship digraph of transferring accounts all is accessed;
Step S44, judge each noise point with the presence or absence of centered on any central point, r is in the circle of radius;If depositing
Then the noise point is marked as marginal point;If it does not exist, then the noise point is still marked as noise point.
Step S45 will regard as the user with normal behaviour mode labeled as user corresponding to the vertex of central point,
It will be regarded as and the biggish use that peels off of normal behaviour mode discrimination labeled as user corresponding to the vertex of marginal point or noise point
Family.This is because central point has reacted large-scale similar users behavior set, based on normal users in block chain social platform
It occupies most it is assumed that the corresponding user of central point can be regarded as normal users.Noise point and marginal point are all regarded as algorithm inspection
The outlier come is measured, the user behavior that this part represents has deviated significantly from subject user behavioural characteristic.
The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its
Equivalent thereof.
Claims (5)
1. a kind of community detection method based on block chain social platform, which comprises the following steps:
Step S10 obtains station address and its transfer information all in block chain social platform, and according to each station address
Between relationship of transferring accounts establish the relationship of transferring accounts and transfer accounts relationship digraph;
Step S20 finds out the relationship of transferring accounts and transfers accounts the abnormal point occurred in relationship digraph and/or off path, and according to
Abnormal user information of abnormal point and/or the off path confirmation found in the presence of abnormal behavior of transferring accounts;
Step S30 obtains operation information of all users in block chain social platform;
Step S40 carries out clustering to the operation information got according to time dimension, finds and normal behaviour mode discrimination
The biggish user information that peels off;
Step S50, to the user that peels off searched out in the abnormal user information and the step S40 confirmed in the step S20
Information is polymerize in a manner of weighted sum, obtains the lower use of non-genuine and/or liveness in the block chain social platform
Family information.
2. the community detection method as described in claim 1 based on block chain social platform, which is characterized in that in the step
In S20, the abnormal point is convergent point or spaced point, and the convergent point is that the relationship of transferring accounts is transferred accounts in-degree in relationship digraph
More than the vertex of defined threshold, the spaced point is that the relationship of transferring accounts out-degree in relationship digraph of transferring accounts is more than defined threshold
Vertex.
3. the community detection method as described in claim 1 based on block chain social platform, which is characterized in that in the step
In S20, the off path is circular path or long path, and the circular path refers in the relationship digraph of transferring accounts certain
A vertex is set out as starting point, and a paths of starting point can be returned to after traversing along directed edge, and the long path refers in institute
State the path that the vertex undergone in relationship digraph of transferring accounts is more than defined threshold.
4. the community detection method as described in claim 1 based on block chain social platform, described in the step S30
Operation information includes user information, operating time, action type and device address.
5. the community detection method according to any one of claims 1 to 4 based on block chain social platform, feature exist
In in step s 40, according to time dimension to the operation information progress clustering got, comprising the following steps:
Step S41 determines radius r and minimal point minPoints;
Step S42, since relationship digraph of transferring accounts any not visited vertex, and judge with this vertex be
Whether the quantity on the vertex for including in the heart, the circle that r is radius is greater than or equal to minimal point minPoints;It is greater than if being judged as
Or being equal to minimal point minPoints, then this vertex is marked as central point;If being judged as less than minimal point
MinPoints, then this vertex is marked as noise point;
Step S43 repeats step S42, until vertex all in relationship digraph of transferring accounts all is accessed;
Step S44, judge each noise point with the presence or absence of centered on any central point, r is in the circle of radius;If it exists, then
The noise point is marked as marginal point;If it does not exist, then the noise point is still marked as noise point;
Step S45 will regard as the user with normal behaviour mode labeled as user corresponding to the vertex of central point, will mark
User corresponding to the vertex of marginal point or noise point is denoted as to regard as and the biggish user that peels off of normal behaviour mode discrimination.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910086732.XA CN110009519B (en) | 2019-01-29 | 2019-01-29 | Community detection method based on block chain social platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910086732.XA CN110009519B (en) | 2019-01-29 | 2019-01-29 | Community detection method based on block chain social platform |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110009519A true CN110009519A (en) | 2019-07-12 |
CN110009519B CN110009519B (en) | 2023-04-07 |
Family
ID=67165597
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910086732.XA Active CN110009519B (en) | 2019-01-29 | 2019-01-29 | Community detection method based on block chain social platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110009519B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111985927A (en) * | 2020-08-14 | 2020-11-24 | 上海朝夕网络技术有限公司 | Block chain address authentication method and block chain transaction method based on social network |
CN113588195A (en) * | 2021-08-10 | 2021-11-02 | 同济大学 | Collision blockage detection method and device |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108053315A (en) * | 2017-11-29 | 2018-05-18 | 广东中科南海岸车联网技术有限公司 | Method of commerce and system based on block chain Internet of Things |
CN108446720A (en) * | 2018-02-27 | 2018-08-24 | 华青融天(北京)技术股份有限公司 | Abnormal deviation data examination method and system |
CN108550052A (en) * | 2018-04-03 | 2018-09-18 | 杭州呯嘭智能技术有限公司 | Brush list detection method and system based on user behavior data feature |
CN108805561A (en) * | 2017-04-27 | 2018-11-13 | 中思博安科技(北京)有限公司 | It may have access to the execution method and system of the intelligent contract of multiple block chains |
CN109146669A (en) * | 2018-08-24 | 2019-01-04 | 阿里巴巴集团控股有限公司 | Detection method, device and the server of abnormal funds transfer plan |
CN109145109A (en) * | 2017-06-19 | 2019-01-04 | 国家计算机网络与信息安全管理中心 | User group's message propagation anomaly analysis method and device based on social networks |
-
2019
- 2019-01-29 CN CN201910086732.XA patent/CN110009519B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108805561A (en) * | 2017-04-27 | 2018-11-13 | 中思博安科技(北京)有限公司 | It may have access to the execution method and system of the intelligent contract of multiple block chains |
CN109145109A (en) * | 2017-06-19 | 2019-01-04 | 国家计算机网络与信息安全管理中心 | User group's message propagation anomaly analysis method and device based on social networks |
CN108053315A (en) * | 2017-11-29 | 2018-05-18 | 广东中科南海岸车联网技术有限公司 | Method of commerce and system based on block chain Internet of Things |
CN108446720A (en) * | 2018-02-27 | 2018-08-24 | 华青融天(北京)技术股份有限公司 | Abnormal deviation data examination method and system |
CN108550052A (en) * | 2018-04-03 | 2018-09-18 | 杭州呯嘭智能技术有限公司 | Brush list detection method and system based on user behavior data feature |
CN109146669A (en) * | 2018-08-24 | 2019-01-04 | 阿里巴巴集团控股有限公司 | Detection method, device and the server of abnormal funds transfer plan |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111985927A (en) * | 2020-08-14 | 2020-11-24 | 上海朝夕网络技术有限公司 | Block chain address authentication method and block chain transaction method based on social network |
CN111985927B (en) * | 2020-08-14 | 2024-04-26 | 上海朝夕网络技术有限公司 | Block chain address authentication method and block chain transaction method based on social network |
CN113588195A (en) * | 2021-08-10 | 2021-11-02 | 同济大学 | Collision blockage detection method and device |
CN113588195B (en) * | 2021-08-10 | 2022-07-26 | 同济大学 | Collision blockage detection method and device |
Also Published As
Publication number | Publication date |
---|---|
CN110009519B (en) | 2023-04-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Li et al. | Privacy leakage via de-anonymization and aggregation in heterogeneous social networks | |
Burbeck et al. | Adaptive real-time anomaly detection with incremental clustering | |
CN110442458A (en) | Scaling calculates cluster | |
KR20110131094A (en) | Identifying communities in an information network | |
CN104348817B (en) | The guard method of user account number and device | |
CN104158748B (en) | A kind of topological detecting method towards system for cloud computing | |
CN110009519A (en) | A kind of community detection method based on block chain social platform | |
Wählisch et al. | Exposing a nation-centric view on the German internet–a change in perspective on AS-level | |
Lim et al. | A topological approach for detecting twitter communities with common interests | |
CN114580009B (en) | Block chain data management method, system and storage medium based on federal learning | |
Cerroni et al. | Decentralized detection of network attacks through P2P data clustering of SNMP data | |
Ma et al. | DNSRadar: Outsourcing malicious domain detection based on distributed cache-footprints | |
Peng et al. | Seed and grow: An attack against anonymized social networks | |
Ntuli et al. | Detecting router cache snooping in named data networking | |
Chen et al. | Integrating community and role detection in information networks | |
CN103916859B (en) | The detection method of cognition wireless network malice busy channel user | |
Guo et al. | Safer: Social capital-based friend recommendation to defend against phishing attacks | |
Carbunar et al. | A survey of privacy vulnerabilities and defenses in geosocial networks | |
Baumann et al. | Vulnerability against internet disruptions–a graph-based perspective | |
CN111125747B (en) | Commodity browsing privacy protection method and system for commercial website user | |
Kim et al. | DRAINCLoG: Detecting Rogue Accounts with Illegally-obtained NFTs using Classifiers Learned on Graphs | |
CN101442466B (en) | Superpose network and implementing method | |
Wang et al. | Look deep into the new deep network: a measurement study on the ZeroNet | |
Liu et al. | Shapley values and meta-explanations for probabilistic graphical model inference | |
Hamrouni et al. | Context-Aware Service Discovery: Graph Techniques for IoT Network Learning and Socially Connected Objects |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |