CN108295476A - The method and apparatus for determining abnormal interactive account - Google Patents
The method and apparatus for determining abnormal interactive account Download PDFInfo
- Publication number
- CN108295476A CN108295476A CN201810182329.2A CN201810182329A CN108295476A CN 108295476 A CN108295476 A CN 108295476A CN 201810182329 A CN201810182329 A CN 201810182329A CN 108295476 A CN108295476 A CN 108295476A
- Authority
- CN
- China
- Prior art keywords
- account
- interactive
- group
- interaction
- internet
- 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
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
- A63F13/70—Game security or game management aspects
- A63F13/75—Enforcing rules, e.g. detecting foul play or generating lists of cheating players
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
- A63F13/70—Game security or game management aspects
- A63F13/79—Game security or game management aspects involving player-related data, e.g. identities, accounts, preferences or play histories
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F2300/00—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game
- A63F2300/50—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game characterized by details of game servers
- A63F2300/53—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game characterized by details of game servers details of basic data processing
- A63F2300/535—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game characterized by details of game servers details of basic data processing for monitoring, e.g. of user parameters, terminal parameters, application parameters, network parameters
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F2300/00—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game
- A63F2300/50—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game characterized by details of game servers
- A63F2300/55—Details of game data or player data management
- A63F2300/5586—Details of game data or player data management for enforcing rights or rules, e.g. to prevent foul play
Abstract
The invention discloses a kind of method and apparatus of the determining interactive account of exception.Wherein, this method includes：Obtain the interaction data between multiple accounts；Based on interaction data, the crucial account of at least one of the Internet and Internet of multiple accounts is determined；Determine that at least one of Internet includes the interaction group of crucial account；Based on the characteristic information of interaction group, determine whether interaction group is extremely interactive group, wherein include abnormal interactive account in extremely interactive group.The present invention solves the prior art only in accordance with the quantity of interaction content between account to determine the technical problem for causing result precision relatively low in the presence of extremely interactive account.
Description
Technical field
The present invention relates to computer internet field, in particular to a kind of method of the determining interactive account of exception and
Device.
Background technology
In the economic field of society, there is the economic crimes behaviors such as including money laundering.On the internet, Yong Huke
To carry out the behaviors such as brush is single, pours water by registering many accounts, internet order has been seriously affected.By taking game as an example, network trip
Play is a virtual micro- society, has various contacts between player.Economic system in game can also exist various
Means of accumulating wealth by unfair means, the wealth in progressive games in an out-of-the-way, seriously affected game fairness and economic system it is flat
Weighing apparatus property.In the virtual world of game, exist sometimes some it is difficult to predict economic loophole, these usual loopholes can not be by me
Directly perceive.Under normal circumstances, the transaction between role and role is Approximate Fair, and each role obtains wealth by transaction
Richness is relative equilibrium, and the game credits that single role can save bit by bit are always relatively limited.But there is certain evils in playing
Anticipate arbitrage player, these players can operate multiple roles simultaneously, and then carrying out aggregation to game credits realizes profit.Currently, trip
The mode of most typical accelerated accumulation wealth, exactly registers multiple accounts, then cooperation in play, by the trip in multiple accounts
Play coin is pooled to one or a small amount of several accounts, and wealth in game is rapidly completed and accumulates.The abnormal distribution meeting pair of game credits
The economic system of game causes prodigious impact.Such exception player will complete the aggregation of game credits, inherently be related to handing over
Easy link.By monitoring trading network, can note abnormalities player in time；The behavior for the related side that merchandises is studied simultaneously,
More valuable information can be obtained, assist to find system vulnerability, safeguard game balance.
Currently, the prior art being the discovery that based on the discovery merchandised extremely for abnormal player, is filtered by block trade
Or the mode of suspicious transaction filtering is come the transaction that notes abnormalities.Specifically, directly the Transaction Information of game the inside is counted,
Using transaction limit as screening criteria, extraction transaction log is distinguished again.Since the transaction in game is multifarious, if only
It goes to filter above amount, amount is big to lose many true abnormal Transaction Informations；Amount is small just to will produce flood tide
Transaction data, to be difficult to obtain effective information.Meanwhile there is no exact areas in amount for abnormal transaction and arm's length dealing
Point, sufficient argument does not support abnormal judgement for the doubtful abnormal transaction filtered out, thus corresponding abnormal player does not have yet
There are enough confidence levels.Meanwhile in the case where group is practised fraud, the transaction data of some game role is individually observed, usually
It cannot find any abnormal, single role's transaction data can not react the distribution of entire group game credits.
It is determined for the above-mentioned prior art in the presence of extremely interactive account only in accordance with the quantity of interaction content between account
Lead to the problem that result precision is relatively low, currently no effective solution has been proposed.
Invention content
An embodiment of the present invention provides a kind of method and apparatus of the determining interactive account of exception, at least to solve the prior art
The skill for causing result precision relatively low in the presence of extremely interactive account is determined only in accordance with the quantity of interaction content between account
Art problem.
One side according to the ... of the embodiment of the present invention provides a kind of method of the interactive account of determining exception, including：It obtains
Interaction data between multiple accounts；Based on interaction data, determine in the Internet and the Internet of multiple accounts extremely
A few crucial account；Determine that at least one of Internet includes the interaction group of crucial account；Based on interaction group
Characteristic information determines whether interaction group is extremely interactive group, wherein include abnormal interactive account in extremely interactive group
Family.
Further, it is based on interaction data, determines at least one of the Internet and Internet of multiple accounts
Crucial account, including：Based on interaction data, using each account as node, and using the interactive information between account as side, generate more
The Internet of a account；The Internet is divided into multiple connected graphs；Obtain the Centroid of each connected graph, wherein in
The corresponding account of heart node is crucial account.
Further, the Internet is divided into multiple connected graphs, including：Each node in the Internet is traversed, is obtained
To all connected graphs；Based on the number of nodes that each connected graph includes, the multiple connected graphs for meeting preset condition are filtered out.
Further, the number of nodes for including based on each connected graph filters out the multiple connected graphs for meeting preset condition, packet
It includes：Deletion of node number is less than the connected graph of first threshold；It is more than the connected graph of second threshold to number of nodes based on modularity algorithm
Cutting is carried out, is equal to second threshold until the number of nodes of each connected graph is respectively less than；By number of nodes be more than or equal to first threshold and
Less than or equal to the connected graph of second threshold as the multiple connected graphs for meeting preset condition.
Further, the Centroid of each connected graph is obtained, including：Following at least one section based on each connected graph
Point attribute, determines the Centroid of each connected graph：Dependence of the accumulative interactive quantity, each node of each node to other nodes
The propagation effect degree of degree, each node.
Further, it is determined that at least one of Internet includes the interaction group of crucial account, including：It obtains default
Depth, wherein size of the predetermined depth for determining interaction group；It is traversed, is obtained in the Internet according to predetermined depth
At least one interaction group for including crucial account.
Further, the characteristic information based on interaction group determines whether interaction group is extremely interactive group, packet
It includes：According to the sequence of pre-set priority, the characteristic information of each interactive group is analyzed；According to analysis result, determine every
Whether a interactive group is extremely interactive group.
Further, characteristic information includes at least one following：Similarity, interaction group in interaction group between account
Internet protocol IP information used in middle account, its in the corresponding Role Information of each account, interaction group in interaction group
Interactive information between the corresponding account of his node account corresponding with Centroid.
Further, the interaction data between multiple accounts is obtained, including：Obtain the daily record data of multiple accounts；It is based on
The daily record data of multiple accounts extracts the interaction data between multiple accounts, wherein interaction data includes at least one following：
The each interaction time between the account information of account, the attribute information of each account, account, the interaction content between account.
Another aspect according to the ... of the embodiment of the present invention additionally provides a kind of device of the interactive account of determining exception, including：It obtains
Unit is taken, for obtaining the interaction data between multiple accounts；First determination unit determines multiple for being based on interaction data
At least one of Internet and the Internet of account key account；Second determination unit, for determining the Internet
At least one of include the interaction group of crucial account；Third determination unit, for the characteristic information based on interaction group, really
Whether surely interactive group is extremely interactive group, wherein includes abnormal interactive account in extremely interactive group.
Another aspect according to the ... of the embodiment of the present invention, additionally provides a kind of storage medium, and storage medium includes the journey of storage
Sequence, wherein equipment where controlling storage medium when program is run execute any one of above method embodiment it is optional or
The preferred method for determining abnormal interactive account.
Another aspect according to the ... of the embodiment of the present invention additionally provides a kind of processor, and processor is used to run program,
In, the side that any one of above method embodiment optionally or preferably determines abnormal interactive account is executed when program is run
Method.
Another aspect according to the ... of the embodiment of the present invention additionally provides a kind of terminal, including：One or more processors are deposited
Reservoir, display device and one or more program, wherein one or more programs are stored in memory, and by with
It is set to and is executed by one or more processors, one or more programs include for executing any one of above method embodiment
The optional or preferred method for determining abnormal interactive account.
In embodiments of the present invention, by obtaining the interaction data between multiple accounts；Based on interaction data, determine multiple
At least one of Internet and the Internet of account key account；Determine that at least one of Internet includes to close
The interaction group of key account；Based on the characteristic information of interaction group, determine whether interaction group is extremely interactive group,
In, comprising abnormal interactive account in extremely interactive group, reaches and determined abnormal interactive account according to group interaction characteristic
The purpose at family, to realize the abnormal interactive account of positioning accuracy technique effect, and then solve the prior art only according to
Determine that the technology for causing result precision relatively low in the presence of extremely interactive account is asked according to the quantity of interaction content between account
Topic.
Description of the drawings
Attached drawing described herein is used to provide further understanding of the present invention, and is constituted part of this application, this hair
Bright illustrative embodiments and their description are not constituted improper limitations of the present invention for explaining the present invention.In the accompanying drawings：
Fig. 1 is a kind of method flow diagram of determining interactive account of exception according to the ... of the embodiment of the present invention；
Fig. 2 is a kind of method flow diagram of optional determining abnormal interactive account according to the ... of the embodiment of the present invention；
Fig. 3 is a kind of method flow diagram of optional determining abnormal interactive account according to the ... of the embodiment of the present invention；
Fig. 4 is a kind of method flow diagram of optional determining abnormal interactive account according to the ... of the embodiment of the present invention；
Fig. 5 is a kind of schematic diagram of optional number of nodes connected graph bigger than normal according to the ... of the embodiment of the present invention；
Fig. 6 be it is according to the ... of the embodiment of the present invention it is a kind of optionally based on the modularity algorithm connected graph bigger than normal to number of nodes into
The schematic diagram of connected graph after row cutting；
It is that a kind of optional independent communication diagram according to the ... of the embodiment of the present invention is intended to shown in Fig. 7；
Fig. 8 is a kind of method flow diagram of optional determining abnormal interactive account according to the ... of the embodiment of the present invention；
Fig. 9 is a kind of method flow diagram of optional determining abnormal interactive account according to the ... of the embodiment of the present invention；
Figure 10 is the method flow diagram that exception player is determined in a kind of preferred game according to the ... of the embodiment of the present invention；And
Figure 11 is a kind of schematic device of determining interactive account of exception according to the ... of the embodiment of the present invention.
Specific implementation mode
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The every other embodiment that member is obtained without making creative work should all belong to the model that the present invention protects
It encloses.
It should be noted that term " first " in description and claims of this specification and above-mentioned attached drawing, "
Two " etc. be for distinguishing similar object, without being used to describe specific sequence or precedence.It should be appreciated that using in this way
Data can be interchanged in the appropriate case, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " comprising " and " having " and their any deformation, it is intended that cover
It includes to be not necessarily limited to for example, containing the process of series of steps or unit, method, system, product or equipment to cover non-exclusive
Those of clearly list step or unit, but may include not listing clearly or for these processes, method, product
Or the other steps or unit that equipment is intrinsic.
According to embodiments of the present invention, a kind of embodiment of the method for the interactive account of determining exception is provided, it should be noted that
Step shown in the flowchart of the accompanying drawings can execute in the computer system of such as a group of computer-executable instructions, and
It, in some cases, can be to execute institute different from sequence herein and although logical order is shown in flow charts
The step of showing or describing.
Fig. 1 is a kind of method flow diagram of determining interactive account of exception according to the ... of the embodiment of the present invention, as shown in Figure 1, should
Method includes the following steps：
Step S102 obtains the interaction data between multiple accounts.
Specifically, above-mentioned account can be but not limited to the account of any one the Internet, applications, for example, QQ accounts；On
It can be that multiple accounts interact generated data, including but not limited to interactive particular content and friendship to state interaction data
Mutual behavioral data, for example, chat content, access information etc. between QQ user.
As a kind of optional embodiment, the application is illustrated for playing.In gaming, player is in order to accumulate
Wealth value, it will usually register multiple game accounts to earn ideal money, and the ideal money that will be earned in multiple game accounts
It focuses on some or certain several roles.Since the randomness merchandised between game role is bigger, obtained using pure regular fashion
Abnormal transaction compare coarseness and in isolation analysis transaction underuse its relevance, the abnormal player identified also lacks
Enough logic supports.The application identifies abnormal economical flow by the group transactional nature between game role, in turn
Identify abnormal player.
Step S104 is based on interaction data, determines at least one of the Internet and Internet of multiple accounts
Crucial account.
Specifically, the above-mentioned Internet can be the network for characterizing the interactive relation between multiple accounts, optionally,
Can in a manner of scheming transaction data between tissue game role, the transaction data between organizational roles in graph form, with game
Role's (account) is node, is that the transaction data in game is expressed as handing over by side with the transaction (interaction data) between game role
Then easy network carries out figure calculating the Centroid (pivotal player) obtained in trade network, to combine Centroid
The method of the abnormal player of adjacent node information identification.
Step S106 determines that at least one of Internet includes the interaction group of crucial account.
Specifically, above-mentioned interactive group is the small trade network of the node centered on crucial account in entire trade network,
After determining the crucial account of at least one of Internet, it may be determined that at least one of trade network includes crucial account
Interaction group, for example, there are the interaction groups of interactive relation for node centered on each key user.
Step S108 determines whether interaction group is extremely interactive group based on the characteristic information of interaction group,
In, abnormal interactive account is included in extremely interactive group.
It should be noted that the prior art relies on the turnover individually merchandised to determine whether there is abnormal transaction, for example,
The both parties for by turnover being more than certain amount are determined as abnormal player, and this list role transaction can not react group trip
The Wealthy distribution of play, by individually observing the transaction data of some game role, is for example, in the case where group is practised fraud
It is difficult that discovery is any abnormal.In addition, the restriction of the filter condition for transaction limit, can also influence determining abnormal player's
Accuracy, for example, amount is big to lose many true abnormal Transaction Informations；The small number of deals that just will produce flood tide of amount
According to be difficult to obtain effective information.
The application determines after determining the crucial account of at least one of trade network and at least one in the Internet includes
The interaction group (for example, interaction group centered on each crucial account) of crucial account, and analyze each interaction group
Group characteristic information (include but not limited to the transaction limit between account, the frequency of interaction between account can also be analyzed, with
And with the presence or absence of multiple accounts situation about interacting is concentrated with an account), determine whether each interaction group is extremely interactive
Group.
From the foregoing, it will be observed that in the above embodiments of the present application, the interaction data between getting multiple accounts to be analyzed
Afterwards, the Internet between multiple accounts is built according to the interaction data between multiple accounts, and passes through the friendship between account
Mutual data are analyzed, and determine the crucial account of one or more of trade network, are then saved centered on each crucial account
Point determines that at least one of Internet interacts group, and analyzes the characteristic information of each interactive group, determines every
Whether a interactive group is that extremely interactive group has reached to determine abnormal interactive account according to group interaction characteristic
Determine the purpose of abnormal interactive account, to realize positioning abnormal interactive account accuracy technique effect, and then solve
The prior art of having determined causes result accurate to determine only in accordance with the quantity of interaction content between account in the presence of extremely interactive account
Spend relatively low technical problem.
In a kind of optional embodiment, as shown in Fig. 2, be based on interaction data, determine the Internet of multiple accounts with
And the crucial account of at least one of Internet, it may include steps of：
Step S202 is based on interaction data, raw using each account as node, and using the interactive information between account as side
At the Internet of multiple accounts；
The Internet is divided into multiple connected graphs by step S204；
Step S206 obtains the Centroid of each connected graph, wherein the corresponding account of Centroid is crucial account.
It specifically, can be using account as node, between account after the interaction data between getting multiple accounts
Interactive information is side, establishes the Internet of multiple account interactions, and the Internet is carried out connectivity division, obtains multiple companies
Logical figure, and obtain the Centroid of each connected graph, wherein the corresponding account of Centroid is crucial account.
By taking game as an example, using the ID of each game role as node, transaction each time generates transaction net as side
Network.There are two types of the recording modes on side：(1) transaction forms independent side every time.That is it merchandises between role A and role B, every time
Transaction all forms " A->B " and " B->The attribute on two sides A ", side is the corresponding game money paid；(2) add up Transaction Information
Side.It is accumulative to merchandise between role A and role B, only form " A->B " and " B->The attribute on two sides A ", side is accumulative transaction
Number and the accumulative game money paid.
It should be noted that when carrying out connectivity division to the Internet, strong continune division can be carried out, also may be used
To carry out weak connectedness division, optionally, the application carries out weak connectedness division to trade network, that is, does not differentiate between the direction on side.
It optionally, can be with base as an alternative embodiment, when obtaining the Centroid of each connected graph
The Centroid of each connected graph is determined in following at least one nodal community of each connected graph：The accumulative interaction of each node
Amount, each node are to the degree of dependence of other nodes, the propagation effect degree of each node.
By taking game as an example, in the transaction net for obtaining multiple game accounts according to the interaction data between multiple game accounts
Network, and by traversing after trade network obtains multiple connected graphs, for each connected graph, the Centroid of connected graph is calculated, i.e.,
Important game role can use several ways：
(1) game money assembles center.Cluster set is defined as follows：
The summation of all in-degrees of cluster set=node game money in game money summation-all out-degree
The cluster set of each node is calculated, the maximum N number of account of cluster set, i.e., the most N number of angle of accumulative game money are obtained
Color.
(2) neighbouring centrad (Closeness Centrality).Connected graph is considered as non-directed graph, some node is calculated and arrives
The sum of the shortest path of other all nodes, each edge weighted weight are 1.Acquisition approach and minimum N number of node, i.e., in transaction
The minimum N number of role of dependence to other roles.
(3) intermediary's centrad (Shortest-path Betweenness Centrality).Connected graph is considered as undirected
Figure, calculates number of some node on the shortest path between all nodes.Obtaining influences entire trade network transaction propagation
Maximum N number of role.
Based on above-described embodiment, in a kind of optional embodiment, as shown in figure 3, the Internet is divided into multiple companies
Logical figure, may include steps of：
Step S302 traverses each node in the Internet, obtains all connected graphs；
Step S304 filters out the multiple connected graphs for meeting preset condition based on the number of nodes that each connected graph includes.
Specifically, after traversing node all in trade network, multiple sizes of connected graph is formd.Due to section
Too small connected graph of counting can not accumulate enough interaction datas (for example, game money in game transaction)；Number of nodes is excessive
Connected graph information is too mixed and disorderly, is not suitable for further analysis.Thus, it is based on above-described embodiment, in each of traversal Internet
Node, after obtaining all connected graphs, the number of nodes that can include based on each connected graph filters out and meets the more of preset condition
A connected graph.
Optionally, it as an alternative embodiment, as shown in figure 4, based on the number of nodes that each connected graph includes, sieves
The multiple connected graphs for meeting preset condition are selected, may include as follows：
Step S402, deletion of node number are less than the connected graph of first threshold；
Step S404, the connected graph for being more than second threshold to number of nodes based on modularity algorithm carries out cutting, until each
The number of nodes of connected graph, which is respectively less than, is equal to second threshold；
Step S406, the connected graph using number of nodes more than or equal to first threshold and less than or equal to second threshold are pre- as meeting
If multiple connected graphs of condition.
Specifically, in above-described embodiment, first threshold can be the lower limiting value (k_min) of connected graph interior joint number, second
Threshold value (k_max) can be the upper limit value of connected graph interior joint number.Multiple connections are obtained carrying out connection division to trade network
After figure, the connected graph that number of nodes can be less than to lower limiting value (first threshold) filters out, and is more than upper limit value (second for number of nodes
Threshold value) connected graph can further carry out cutting.
For example, carrying out weakly connected graph division to trade network, after obtaining all weakly connected graphs, it is possible to specify number of nodes
Lower limit k_min, connected graph of the number of nodes less than k_min will can be filtered；Specified number of nodes upper limit k_max, number of nodes are more than
The connected graph of k_max carries out the operation of above-mentioned steps S404, if number of nodes in the section [k_min, k_max], then to connection
The Centroid of figure calculates.
Wherein, very big calculating can be consumed when determining the node of crucial account for number of nodes connected graph bigger than normal
Resource.Since abnormal interactive account is usually to merchandise to benefit larger node, therefore, it is possible to keeping base center characteristic constant
Under the premise of entire connected graph is divided into multiple small-scale bargaining colonies of the mutual income compared with balance, to greatly reduce meter
Calculate complexity.
Still by taking game as an example, Fig. 5 is a kind of showing for optional number of nodes connected graph bigger than normal according to the ... of the embodiment of the present invention
Be intended to, as shown in figure 5, number of nodes it is excessive connected graph information it is too mixed and disorderly, need to consume a large amount of meter when determining Centroid
Resource is calculated, thus, after carrying out cutting based on the modularity algorithm connected graph bigger than normal to number of nodes, it can obtain as shown in FIG. 6
Number of nodes connected graph less than normal, when determining the Centroid in being connected to, connected graph shown in fig. 6 is than connected graph shown in fig. 5
Computation amount.Optionally, it is that a kind of optional independent communication diagram according to the ... of the embodiment of the present invention is intended to shown in Fig. 7,
As shown in fig. 7, abnormal player characteristic is clearly.
As can be seen that connected graph is carried out cutting using the algorithm based on modularity, determining connected graph can be greatly reduced
Centroid when calculation amount.Algorithm comparison based on modularity is exactly typically Louvain algorithms.Using Louvain
When algorithm carries out connected graph division, the weights of Appointed edges are needed, to calculate the modularity (modularity) of community, with
For game, weights herein can be using absolute value of the difference of merchandising between game account, for example, game role A and game angle
The transaction absolute value of the difference of the accumulative game money of color B：
Weight (A, B)=| the game money that the game money that ∑ A is exported to B-∑ B is exported to A |
After determining the middle crucial account of trade network, it is based on any one of the above optional embodiment, it can as one kind
The embodiment of choosing may include as shown in figure 8, determining the interaction group that at least one of Internet includes key user：
Step S802, is traversed according to predetermined depth, and it includes crucial account to obtain at least one of Internet
Interaction group, wherein size of the predetermined depth for determining interaction group.
Specifically, as an alternative embodiment, can be made with designated depth Depth using key user as starting point
Breadth first traversal can obtain the trade network for having center small one by one.The centrality of node is generally between 3 to 6
Depth is just than more significant.If in the range of designated depth Depth, other Centroids are enumerated, then take multiple centers
The network intersection of node.
After the crucial account determined in based on trade network determines at least one interactive group, in conjunction with interaction group network
In each node Role Information, judge whether the interaction group is abnormal interactive group.Specifically, as a kind of optional reality
Example is applied, as shown in figure 9, the characteristic information based on interaction group, determines whether interaction group is extremely interactive group, including：
Step S902 analyzes the characteristic information of each interactive group according to the sequence of pre-set priority；
Step S904 determines whether each interaction group is extremely interactive group according to analysis result.
Specifically, the characteristic information of above-mentioned each interactive group includes but not limited at least one following：In interaction group
Each account pair in Internet protocol IP information, interaction group used in account in similarity, interaction group between account
Interactive information in the Role Information answered, interaction group between the corresponding account of other nodes account corresponding with Centroid.
By taking game as an example, common characteristic information includes but not limited at least one following：(1) game money aggregate-value has
Obvious building-up effect, i.e., multiple roles convey game credits to center role in group；(2) in group, the account of player
Number mailbox name similarity is higher；(3) the IP registrations in group are higher, i.e. IP quantity/role's quantity is usually less than normal；(4) group
Character profession distribution characteristics in body, such as multiple inferior grades and be that be easy the to form a team role of brush money occupation corresponds to a high-grade angle
Color.
As an alternative embodiment, can be to the priority of each interactive population analysis：First priority is
A variety of centrads calculate the intersection of the Centroid obtained；Second priority is that game money gathers the corresponding node of center calculation
Three priority are neighbouring centrad and the corresponding nodes of intermediary's centrad.In practical application scene, priority processing is most suspicious
Node ensures that the corresponding Centroid of the first priority can be screened in time within the time limit of demand；Latter two priority is corresponding
Centroid is handled successively as one sees fit according to time and processing capacity.
Based on any one of the above optional embodiment, in a kind of optional embodiment, obtain between multiple accounts
Interaction data may include：
Step 1 obtains the daily record data of multiple accounts；
Step 2 extracts the interaction data between multiple accounts based on the daily record data of multiple accounts, wherein interaction number
According to including at least one following：Each interaction time between the account information of account, the attribute information of each account, account,
Interaction content between account.
Still by taking game as an example, after getting log data, original log can be cleaned, extracted, be converted.
For example, extraction transaction log (including but not limited to ID, exchange hour, the transaction amount etc. of both parties' game role)；Extraction
Role basic information (include but not limited to game role ID, role's account, role hierarchy, character profession, supplement with money situation,
Line duration, game money quantity etc.).Optionally, if game in can mainly merchandise stage property can by recent transaction record into
Row approximate evaluation, the then transaction record for counting recent obtain the reference price of stage property, will be in the transaction of " game money-stage property " type
Stage property be converted to game money valuation；If being unable to approximate evaluation (such as identical stage property, attribute is different, and price difference is especially big), then
All Activity only retains the unidirectional information of game money transaction, ignores the flow direction of stage property.
Embodiment as one preferred, Figure 10 are to determine exception in a kind of preferred game according to the ... of the embodiment of the present invention
The method flow diagram of player, includes the following steps：
(1) original log cleaned, extracted, converted, obtain the transaction data between game role and each trip
The essential information of play player (role)；
(2) based on the transaction data between game role, the trade network between multiple game roles is generated；
(3) weakly connected graph division is carried out to trade network, forms multiple connected subgraphs.The direction on side is not differentiated between, institute is obtained
Some weakly connected graphs.
(4) it is directed to number of nodes connected graph bigger than normal, it is slightly smaller to be cut to multiple scales using the algorithm based on modularity
Subgraph.
(5) it is directed to each connected graph, calculates the Centroid of connected graph, i.e., important game role.
(6) using critical game role as starting point, the trade network of designated depth is obtained, obtains abnormal player's microcommunity.
(7) basic information of economic circulation situation and each player based on the small trade network for having center, judging should
Whether group is abnormal bargaining colony.
By scheme disclosed in the above embodiments of the present application, using the mode tissue Transaction Information of figure, to whole network
Centrality analysis is carried out, exceptional value is looked for from relative priority, avoids analyzing the uncertainty that transaction encounters merely.Using based on mould
The bigger connected graph of the algorithm cutting of lumpiness can greatly reduce in the case where keeping bargaining colony central characteristics constant
The calculation amount of central point is obtained in 5th step.From the player role interactive information in game, according to mutual interaction
Degree divides multiple independent microcommunities.For each group, the Central Player in each group, emphasis role's emphasis point are positioned
Analysis.The emphasis data that the method obtains numerous types can be extended, for example add up with game credits, for side, doubtful work can be obtained
The abnormal player of disadvantage；Using chat message as side, the more high active player etc. of chatting in game can be obtained.
According to embodiments of the present invention, a kind of device of the method for realizing above-mentioned determining abnormal interactive account is additionally provided
Embodiment, Figure 11 are a kind of schematic devices of determining interactive account of exception according to the ... of the embodiment of the present invention, as shown in figure 11, should
Device includes：Acquiring unit 111, the first determination unit 113, the second determination unit 115 and third determination unit 117.
Wherein, acquiring unit 111, for obtaining the interaction data between multiple accounts；
First determination unit 113 is used for based on interaction data, in the Internet and the Internet that determine multiple accounts
At least one crucial account；
Second determination unit 115, for determining that at least one of Internet includes the interaction group of crucial account；
Third determination unit 117 determines whether interaction group is abnormal interactive for the characteristic information based on interaction group
Group, wherein include abnormal interactive account in extremely interactive group.
Herein it should be noted that above-mentioned acquiring unit 111, the first determination unit 113, the second determination unit 115 and
Three determination units 117 correspond to the step S102 to S108 in embodiment of the method, and above-mentioned module is realized with corresponding step
Example is identical with application scenarios, but is not limited to above method embodiment disclosure of that.It should be noted that above-mentioned module is made
A part of for device can execute in the computer system of such as a group of computer-executable instructions.
From the foregoing, it will be observed that in the above embodiments of the present application, multiple accounts to be analyzed are being got by acquiring unit 111
Between interaction data after, by the first determination unit 113 according to the interaction data between multiple accounts build multiple accounts it
Between the Internet, and analyzed by the interaction data between account, determine that one or more of trade network closes
Key account, then by the second determination unit 115 centered on each crucial account node, determine at least one in the Internet
It is a to include the interaction group of crucial account, and the characteristic information of each interactive group is divided by third determination unit 117
Analysis determines whether each interaction group is that extremely interactive group has reached to determine abnormal interactive account according to group
Interaction characteristic determines the purpose of abnormal interactive account, to realize positioning abnormal interactive account accuracy technology effect
Fruit, and then solve the prior art only in accordance with the quantity of interaction content between account to determine that there is extremely interactive account causes
The relatively low technical problem of result precision.
In a kind of optional embodiment, above-mentioned first determination unit may include：Generation module, for based on interaction number
According to using each account as node, and using the interactive information between account as side, generating the Internet of multiple accounts；Divide mould
Block, for the Internet to be divided into multiple connected graphs；First acquisition module, the Centroid for obtaining each connected graph,
Wherein, the corresponding account of Centroid is crucial account.
In a kind of optional embodiment, above-mentioned division module may include：Spider module, for traversing in the Internet
Each node, obtain all connected graphs；Screening module, the number of nodes for including based on each connected graph filter out symbol
Close multiple connected graphs of preset condition.
In a kind of optional embodiment, above-mentioned screening module includes：Removing module is less than first for deletion of node number
The connected graph of threshold value；First processing module, the connected graph for being more than second threshold to number of nodes based on modularity algorithm are carried out
Cutting is equal to second threshold until the number of nodes of each connected graph is respectively less than；Second processing module, be used to number of nodes being more than etc.
In first threshold and less than or equal to second threshold connected graph as the multiple connected graphs for meeting preset condition.
In a kind of optional embodiment, above-mentioned acquisition module includes：First determining module, for being based on each connected graph
Following at least one nodal community, determine the Centroid of each connected graph：Accumulative interactive quantity, each node of each node
To the propagation effect degree of the degrees of dependence of other nodes, each node.
In a kind of optional embodiment, above-mentioned second determination unit includes：Third processing module, for according to default depth
Degree is traversed, and obtains the interaction group that at least one of Internet includes crucial account, wherein predetermined depth is for true
Surely the size of interactive group.
In a kind of optional embodiment, above-mentioned third determination unit includes：Analysis module, for according to pre-set priority
Sequence, the characteristic information of each interactive group is analyzed；Second determining module, for according to analysis result, determining every
Whether a interactive group is extremely interactive group.
In a kind of optional embodiment, features described above information includes at least one following：In interaction group between account
Similarity, Internet protocol IP information used in account, the corresponding role of each account in interaction group in interaction group
Interactive information in information, interaction group between the corresponding account of other nodes account corresponding with Centroid.
In a kind of optional embodiment, above-mentioned acquiring unit includes：Second acquisition module, for obtaining multiple accounts
Daily record data；Extraction module is used for the daily record data based on multiple accounts, extracts the interaction data between multiple accounts, wherein
Interaction data includes at least one following：Each interaction between the account information of account, the attribute information of each account, account
Interaction content between time, account.
According to embodiments of the present invention, a kind of storage medium is additionally provided, storage medium includes the program of storage, wherein
Any one of equipment execution above method embodiment is optional or preferred where control storage medium when program is run determines
The method of abnormal interactive account.
According to embodiments of the present invention, a kind of processor is additionally provided, processor is for running program, wherein program is run
The method that any one of Shi Zhihang above method embodiments optionally or preferably determine abnormal interactive account.
According to embodiments of the present invention, a kind of terminal is additionally provided, including：One or more processors, memory, display dress
Set and one or more program, wherein one or more programs are stored in memory, and be configured as by one or
Multiple processors execute, and one or more programs include optional or preferred for executing any one of above method embodiment
The method for determining abnormal interactive account.
Above-mentioned device may include processor and memory, and said units can be stored in storage as program unit
In device, above procedure unit stored in memory is executed by processor to realize corresponding function.
Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, if read-only memory (ROM) or flash memory (flash RAM), memory include at least one deposit
Store up chip.
The sequence of above-mentioned the embodiment of the present application can not represent the quality of embodiment.
In above-described embodiment of the application, all emphasizes particularly on different fields to the description of each embodiment, do not have in some embodiment
The part of detailed description may refer to the associated description of other embodiment.In several embodiments provided herein, it should be appreciated that
It arrives, disclosed technology contents can be realized by another way.
Wherein, the apparatus embodiments described above are merely exemplary, for example, the unit division, can be one
Kind of division of logic function, formula that in actual implementation, there may be another division manner, such as multiple units or component can combine or
It is desirably integrated into another system, or some features can be ignored or not executed.Another point, it is shown or discussed it is mutual it
Between coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some interfaces, unit or module
It connects, can be electrical or other forms.
In addition, each functional unit in each embodiment of the application can be integrated in a processing unit, it can also
It is that each unit physically exists alone, it can also be during two or more units be integrated in one unit.Above-mentioned integrated list
The form that hardware had both may be used in member is realized, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can be stored in a computer read/write memory medium.Based on this understanding, the technical solution of the application is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or network equipment etc.) execute each embodiment the method for the application whole or
Part steps.And storage medium above-mentioned includes：USB flash disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic disc or CD etc. are various can to store program code
Medium.
The above is only the preferred embodiment of the application, it is noted that for the ordinary skill people of the art
For member, under the premise of not departing from the application principle, several improvements and modifications can also be made, these improvements and modifications are also answered
It is considered as the protection domain of the application.
Claims (13)
1. a kind of method of the interactive account of determining exception, which is characterized in that including：
Obtain the interaction data between multiple accounts；
Based on the interaction data, determine that at least one of the Internet of the multiple account and described Internet close
Key account；
Determine that at least one of described Internet includes the interaction group of the crucial account；
Based on the characteristic information of the interactive group, determine whether the interactive group is extremely interactive group, wherein described
Extremely include abnormal interactive account in interactive group.
2. according to the method described in claim 1, it is characterized in that, based on the interaction data, the multiple account is determined
At least one of the Internet and the Internet key account, including：
Based on the interaction data, using each account as node, and using the interactive information between account as side, generate the multiple
The Internet of account；
The Internet is divided into multiple connected graphs；
Obtain the Centroid of each connected graph, wherein the corresponding account of the Centroid is crucial account.
3. according to the method described in claim 2, it is characterized in that, the Internet is divided into multiple connected graphs, including：
Each node in the Internet is traversed, all connected graphs are obtained；
Based on the number of nodes that each connected graph includes, the multiple connected graphs for meeting preset condition are filtered out.
4. according to the method described in claim 3, it is characterized in that, based on the number of nodes that each connected graph includes, symbol is filtered out
Multiple connected graphs of preset condition are closed, including：
Deletion of node number is less than the connected graph of first threshold；
The connected graph for being more than second threshold to number of nodes based on modularity algorithm carries out cutting, until the number of nodes of each connected graph
Respectively less than it is equal to the second threshold；
Connected graph using number of nodes more than or equal to the first threshold and less than or equal to the second threshold is described pre- as meeting
If multiple connected graphs of condition.
5. according to the method described in claim 2, it is characterized in that, obtain the Centroid of each connected graph, including：
Following at least one nodal community based on each connected graph, determines the Centroid of each connected graph：Each section
The accumulative interactive quantity of point, each node is to the degree of dependence of other nodes, the propagation effect degree of each node.
6. method according to claim 1 or 2, which is characterized in that determine that at least one of described Internet includes
The interaction group of the key account, including：
It is traversed according to predetermined depth, obtains the interaction group that at least one of described Internet includes the crucial account
Body, wherein the predetermined depth is used to determine the size of the interactive group.
7. according to the method described in claim 1, it is characterized in that, the characteristic information based on the interactive group, determine described in
Whether interaction group is extremely interactive group, including：
According to the sequence of pre-set priority, the characteristic information of each interactive group is analyzed；
According to analysis result, determine whether each interactive group is extremely interactive group.
8. according to the method described in claim 1, it is characterized in that, the characteristic information includes at least one following：The friendship
Internet protocol IP information, the interaction used in account in similarity, the interactive group in mutual group between account
The corresponding account of other nodes is corresponding with Centroid in the corresponding Role Information of each account, the interactive group in group
Interactive information between account.
9. according to the method described in claim 1, it is characterized in that, obtain the interaction data between multiple accounts, including：
Obtain the daily record data of the multiple account；
Based on the daily record data of the multiple account, the interaction data between the multiple account is extracted, wherein the interactive number
According to including at least one following：Each interaction time between the account information of account, the attribute information of each account, account,
Interaction content between account.
10. a kind of device of the interactive account of determining exception, which is characterized in that including：
Acquiring unit, for obtaining the interaction data between multiple accounts；
First determination unit determines the Internet of the multiple account and the interaction for being based on the interaction data
At least one of network key account；
Second determination unit, for determining that at least one of described Internet includes the interaction group of the crucial account；
Third determination unit is used for the characteristic information based on the interactive group, determines whether the interactive group is abnormal friendship
Mutual group, wherein include abnormal interactive account in the extremely interactive group.
11. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein run in described program
When control the storage medium where equipment perform claim require the side for determining abnormal interactive account described in 1 to 9 any one
Method.
12. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Profit requires the method for determining abnormal interactive account described in any one of 1 to 9.
13. a kind of terminal, which is characterized in that including：
One or more processors, memory, display device and one or more programs, wherein one or more of journeys
Sequence is stored in the memory, and is configured as being executed by one or more of processors, one or more of
Program includes the method for determining abnormal interactive account required for perform claim described in any one of 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810182329.2A CN108295476B (en) | 2018-03-06 | 2018-03-06 | Method and device for determining abnormal interaction account |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810182329.2A CN108295476B (en) | 2018-03-06 | 2018-03-06 | Method and device for determining abnormal interaction account |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108295476A true CN108295476A (en) | 2018-07-20 |
| CN108295476B CN108295476B (en) | 2021-12-28 |
Family
ID=62849112
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810182329.2A Active CN108295476B (en) | 2018-03-06 | 2018-03-06 | Method and device for determining abnormal interaction account |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108295476B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108905210A (en) * | 2018-07-24 | 2018-11-30 | 合肥爱玩动漫有限公司 | A kind of method of quick detection game studios |
| CN109091871A (en) * | 2018-09-17 | 2018-12-28 | 网易（杭州）网络有限公司 | The plug-in player's detection method of game and device |
| CN109146638A (en) * | 2018-08-29 | 2019-01-04 | 阿里巴巴集团控股有限公司 | The recognition methods of abnormal financial transaction group and device |
| CN109460930A (en) * | 2018-11-15 | 2019-03-12 | 武汉斗鱼网络科技有限公司 | A kind of method and relevant device of determining adventure account |
| CN109615521A (en) * | 2018-12-26 | 2019-04-12 | 天翼电子商务有限公司 | Anti- arbitrage recognition methods, system and server based on anti-arbitrage model of marketing |
| CN110264326A (en) * | 2019-05-24 | 2019-09-20 | 阿里巴巴集团控股有限公司 | Identify the method, device and equipment of abnormal account aggregation and adventure account set |
| CN111292090A (en) * | 2020-02-19 | 2020-06-16 | 京东数字科技控股有限公司 | Method and device for detecting abnormal account |
| CN111400570A (en) * | 2020-04-17 | 2020-07-10 | 支付宝(杭州)信息技术有限公司 | User group auditing processing method and device |
| CN111461756A (en) * | 2019-01-19 | 2020-07-28 | 游戏橘子数位科技股份有限公司 | Game account valuation method and system |
| CN111539811A (en) * | 2020-05-27 | 2020-08-14 | 支付宝(杭州)信息技术有限公司 | Risk account identification method and device |
| CN112184267A (en) * | 2020-10-27 | 2021-01-05 | 北京嘀嘀无限科技发展有限公司 | Method, apparatus, device and medium for discovering user group in service application |
| CN112245930A (en) * | 2020-09-11 | 2021-01-22 | 杭州浮云网络科技有限公司 | Risk behavior identification method and device and computer equipment |
| CN112308565A (en) * | 2020-08-14 | 2021-02-02 | 中国工商银行股份有限公司 | Many-to-many cross-border fund wind control method and system based on knowledge graph |
| CN112435126A (en) * | 2021-01-26 | 2021-03-02 | 深圳华锐金融技术股份有限公司 | Account identification method and device, computer equipment and storage medium |
| WO2021082020A1 (en) * | 2019-11-02 | 2021-05-06 | 游戏橘子数位科技股份有限公司 | Game account valuation method and system |
| CN112948673A (en) * | 2021-02-22 | 2021-06-11 | 网易（杭州）网络有限公司 | Game content pushing method and device, electronic equipment and storage medium |
| CN113904943A (en) * | 2021-09-26 | 2022-01-07 | 北京百度网讯科技有限公司 | Account detection method and device, electronic equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2439435A1 (en) * | 2001-02-26 | 2002-09-06 | Paypal, Inc. | System and method for depicting on-line transactions |
| CN103927307A (en) * | 2013-01-11 | 2014-07-16 | 阿里巴巴集团控股有限公司 | Website user identification method and device |
| CN104025094A (en) * | 2011-10-13 | 2014-09-03 | 新人类有限公司 | Apparatus And Method For Detecting Abnormal Account |
| CN104025143A (en) * | 2011-10-13 | 2014-09-03 | 新人类有限公司 | Apparatus and method for detecting abnormal account |
| CN106301978A (en) * | 2015-05-26 | 2017-01-04 | 阿里巴巴集团控股有限公司 | The recognition methods of gang member account, device and equipment |
| CN106355405A (en) * | 2015-07-14 | 2017-01-25 | 阿里巴巴集团控股有限公司 | Method and device for identifying risks and system for preventing and controlling same |
| US20170132636A1 (en) * | 2015-11-11 | 2017-05-11 | Idm Global, Inc. | Systems and methods for detecting relations between unknown merchants and merchants with a known connection to fraud |
| CN106709800A (en) * | 2016-12-06 | 2017-05-24 | 中国银联股份有限公司 | Community partitioning method and device based on characteristic matching network |
| CN107093076A (en) * | 2016-02-18 | 2017-08-25 | 卡巴斯基实验室股份制公司 | The system and method for detecting fraudulent user transaction |
| CN107730262A (en) * | 2017-10-23 | 2018-02-23 | 阿里巴巴集团控股有限公司 | One kind fraud recognition methods and device |
-
2018
- 2018-03-06 CN CN201810182329.2A patent/CN108295476B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2439435A1 (en) * | 2001-02-26 | 2002-09-06 | Paypal, Inc. | System and method for depicting on-line transactions |
| CN104025094A (en) * | 2011-10-13 | 2014-09-03 | 新人类有限公司 | Apparatus And Method For Detecting Abnormal Account |
| CN104025143A (en) * | 2011-10-13 | 2014-09-03 | 新人类有限公司 | Apparatus and method for detecting abnormal account |
| CN103927307A (en) * | 2013-01-11 | 2014-07-16 | 阿里巴巴集团控股有限公司 | Website user identification method and device |
| CN106301978A (en) * | 2015-05-26 | 2017-01-04 | 阿里巴巴集团控股有限公司 | The recognition methods of gang member account, device and equipment |
| CN106355405A (en) * | 2015-07-14 | 2017-01-25 | 阿里巴巴集团控股有限公司 | Method and device for identifying risks and system for preventing and controlling same |
| US20170132636A1 (en) * | 2015-11-11 | 2017-05-11 | Idm Global, Inc. | Systems and methods for detecting relations between unknown merchants and merchants with a known connection to fraud |
| CN107093076A (en) * | 2016-02-18 | 2017-08-25 | 卡巴斯基实验室股份制公司 | The system and method for detecting fraudulent user transaction |
| CN106709800A (en) * | 2016-12-06 | 2017-05-24 | 中国银联股份有限公司 | Community partitioning method and device based on characteristic matching network |
| CN107730262A (en) * | 2017-10-23 | 2018-02-23 | 阿里巴巴集团控股有限公司 | One kind fraud recognition methods and device |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108905210A (en) * | 2018-07-24 | 2018-11-30 | 合肥爱玩动漫有限公司 | A kind of method of quick detection game studios |
| CN109146638A (en) * | 2018-08-29 | 2019-01-04 | 阿里巴巴集团控股有限公司 | The recognition methods of abnormal financial transaction group and device |
| CN109146638B (en) * | 2018-08-29 | 2021-11-30 | 创新先进技术有限公司 | Method and device for identifying abnormal financial transaction group |
| CN109091871A (en) * | 2018-09-17 | 2018-12-28 | 网易（杭州）网络有限公司 | The plug-in player's detection method of game and device |
| CN109460930A (en) * | 2018-11-15 | 2019-03-12 | 武汉斗鱼网络科技有限公司 | A kind of method and relevant device of determining adventure account |
| CN109460930B (en) * | 2018-11-15 | 2021-11-26 | 武汉斗鱼网络科技有限公司 | Method for determining risk account and related equipment |
| CN109615521A (en) * | 2018-12-26 | 2019-04-12 | 天翼电子商务有限公司 | Anti- arbitrage recognition methods, system and server based on anti-arbitrage model of marketing |
| CN111461756A (en) * | 2019-01-19 | 2020-07-28 | 游戏橘子数位科技股份有限公司 | Game account valuation method and system |
| CN111461756B (en) * | 2019-01-19 | 2023-03-24 | 游戏橘子数位科技股份有限公司 | Game account valuation method and system |
| CN110264326A (en) * | 2019-05-24 | 2019-09-20 | 阿里巴巴集团控股有限公司 | Identify the method, device and equipment of abnormal account aggregation and adventure account set |
| CN110264326B (en) * | 2019-05-24 | 2023-03-24 | 创新先进技术有限公司 | Method, device and equipment for identifying abnormal account set and risk account set |
| WO2021082020A1 (en) * | 2019-11-02 | 2021-05-06 | 游戏橘子数位科技股份有限公司 | Game account valuation method and system |
| CN111292090A (en) * | 2020-02-19 | 2020-06-16 | 京东数字科技控股有限公司 | Method and device for detecting abnormal account |
| CN111400570A (en) * | 2020-04-17 | 2020-07-10 | 支付宝(杭州)信息技术有限公司 | User group auditing processing method and device |
| CN111400570B (en) * | 2020-04-17 | 2023-05-23 | 支付宝(杭州)信息技术有限公司 | User group auditing processing method and device |
| CN111539811B (en) * | 2020-05-27 | 2022-06-14 | 支付宝(杭州)信息技术有限公司 | Risk account identification method and device |
| CN111539811A (en) * | 2020-05-27 | 2020-08-14 | 支付宝(杭州)信息技术有限公司 | Risk account identification method and device |
| CN112308565A (en) * | 2020-08-14 | 2021-02-02 | 中国工商银行股份有限公司 | Many-to-many cross-border fund wind control method and system based on knowledge graph |
| CN112245930A (en) * | 2020-09-11 | 2021-01-22 | 杭州浮云网络科技有限公司 | Risk behavior identification method and device and computer equipment |
| CN112184267A (en) * | 2020-10-27 | 2021-01-05 | 北京嘀嘀无限科技发展有限公司 | Method, apparatus, device and medium for discovering user group in service application |
| CN112435126A (en) * | 2021-01-26 | 2021-03-02 | 深圳华锐金融技术股份有限公司 | Account identification method and device, computer equipment and storage medium |
| CN112435126B (en) * | 2021-01-26 | 2021-06-18 | 深圳华锐金融技术股份有限公司 | Account identification method and device, computer equipment and storage medium |
| CN112948673A (en) * | 2021-02-22 | 2021-06-11 | 网易（杭州）网络有限公司 | Game content pushing method and device, electronic equipment and storage medium |
| CN113904943A (en) * | 2021-09-26 | 2022-01-07 | 北京百度网讯科技有限公司 | Account detection method and device, electronic equipment and storage medium |
| CN113904943B (en) * | 2021-09-26 | 2024-04-05 | 北京百度网讯科技有限公司 | Account detection method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108295476B (en) | 2021-12-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108295476A (en) | The method and apparatus for determining abnormal interactive account | |
| Jourdan et al. | Characterizing entities in the bitcoin blockchain | |
| CN103198161B (en) | Microblog water army recognition methods and equipment | |
| CN109063966A (en) | The recognition methods of adventure account and device | |
| Cortes et al. | Communities of interest | |
| CN106453357A (en) | Network ticket buying abnormal behavior recognition method and system and equipment | |
| CN107767055A (en) | A kind of mass-rent result assemblage method and device based on collusion detection | |
| Blackburn et al. | Branded with a scarlet" C" cheaters in a gaming social network | |
| CN103353920B (en) | Method and device for recommending games based on SNS | |
| CN107679856B (en) | Transaction-based service control method and device | |
| CN109598509A (en) | The recognition methods of risk clique and device | |
| CN109615524B (en) | Money laundering crime group partner identification method, money laundering crime group partner identification device, computer equipment and storage medium | |
| Drachen et al. | To be or not to be... social: Incorporating simple social features in mobile game customer lifetime value predictions | |
| CN106548343A (en) | A kind of illegal transaction detection method and device | |
| CN108540431A (en) | The recognition methods of account type, device and system | |
| CN109816323A (en) | Transaction auditing method, calculating equipment, storage medium for block chain network | |
| CN110009365B (en) | User group detection method, device and equipment for abnormally transferring electronic assets | |
| CN110225104A (en) | Data capture method, device and terminal device | |
| CN107294974A (en) | The method and apparatus for recognizing target clique | |
| CN110060052A (en) | Interactive approach and device, electronic equipment based on electronic certificate | |
| CN110175299A (en) | A kind of method and server that recommendation information is determining | |
| CN105516192B (en) | A kind of mail address is safe to identify control method and device | |
| CN110033302A (en) | The recognition methods of malice account and device | |
| CN110390585A (en) | A kind of method and device identifying exception object | |
| CN107330718A (en) | A kind of anti-cheat method of media and device, storage medium, terminal |
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 |