CN110177094A - A kind of user community recognition methods, device, electronic equipment and storage medium - Google Patents
A kind of user community recognition methods, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN110177094A CN110177094A CN201910431373.7A CN201910431373A CN110177094A CN 110177094 A CN110177094 A CN 110177094A CN 201910431373 A CN201910431373 A CN 201910431373A CN 110177094 A CN110177094 A CN 110177094A
- Authority
- CN
- China
- Prior art keywords
- user
- behavior
- vertex
- customer relationship
- similarity
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/10—Active monitoring, e.g. heartbeat, ping or trace-route
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/16—Threshold monitoring
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1441—Countermeasures against malicious traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/535—Tracking the activity of the user
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Cardiology (AREA)
- General Health & Medical Sciences (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the invention discloses a kind of user community recognition methods, device, electronic equipment and storage mediums, which comprises constructs customer relationship figure according to the specific internet behavior of user；The number that specific internet behavior occurs in the set time period based on user calculates the behavior similarity in the customer relationship figure between every two user；The customer relationship figure is cut according to the behavior similarity, with deleting act similarity lower than the incidence relation between the user of given threshold；Used terminal device quantity and internet protocol address quantity, identify target user group based on the customer relationship figure after cutting when according to user's progress internet behavior.By using above-mentioned technical proposal, the accuracy of identification of target user group is improved.
Description
Technical field
The present embodiments relate to computer field more particularly to a kind of user community recognition methods, device, electronic equipment
And storage medium.
Background technique
In webcast website, in order to acquire an advantage, in the prevalence of the cheating row of the brushes popularities such as some brush barrages, brush concern
For.Cheating based on platform (such as webcast website) has clique's property mostly, and above-mentioned cheating also will cause net
The problems such as Platform Server pressure is excessive is broadcast live in network blocking, causes strong influence to the live streaming ecological environment of platform.Therefore
It is negatively affected to reduce above-mentioned cheating bring, the user community for having cheating suspicion is found using reasonable method, and
Take appropriate measure to stop significant the user community.
A kind of cheating group recognition methods generallyd use at present are as follows: user is established based on the incidence relation between user and is closed
System's figure, and calculated by figure to determine cheating group, this method is completely dependent on the topological relation between user, therefore once exists
Noise data is then easy to cause to misidentify, such as has 10 normal users to log in one day by same computer of Internet bar
10 normal users may be then identified as cheating group by the above method by webcast website.Another kind cheating group knows
Other method are as follows: Behavior-based control consistency identifies that this method cannot exclude accidental one between normal users to cheating group
The influence of sexual behaviour is caused, therefore recognition accuracy is not high.
Summary of the invention
The present invention provides a kind of user community recognition methods, device, electronic equipment and storage medium, to improve target user
The recognition accuracy of group.
In a first aspect, the embodiment of the invention provides a kind of user community recognition methods, which comprises
Customer relationship figure is constructed according to the specific internet behavior of user；
The number that specific internet behavior is occurred in the set time period based on user is calculated every two in the customer relationship figure
Behavior similarity between a user；
The customer relationship figure is cut according to the behavior similarity, with deleting act similarity lower than setting threshold
Incidence relation between the user of value；
Used terminal device quantity and IP when carrying out internet behavior according to user (Internet Protocol, mutually
Networking protocol) number of addresses, target user group is identified based on the customer relationship figure after cutting.
Second aspect, the embodiment of the invention provides a kind of user community identification device, described device includes:
Module is constructed, for constructing customer relationship figure according to the specific internet behavior of user；
Computing module calculates the use for the number of specific internet behavior to occur in the set time period based on user
Behavior similarity in the relational graph of family between every two user；
Module is cut, for cutting according to the behavior similarity to the customer relationship figure, with deleting act phase
Like degree lower than the incidence relation between the user of given threshold；
Identification module, used terminal device quantity and Internet protocol when for according to user's progress internet behavior
IP address quantity identifies target user group based on the customer relationship figure after cutting.
The third aspect the embodiment of the invention provides a kind of electronic equipment, including first memory, first processor and is deposited
The computer program that can be run on a memory and on first processor is stored up, the first processor executes the computer journey
The user community recognition methods as described in above-mentioned first aspect is realized when sequence.
Fourth aspect, the embodiment of the invention provides a kind of storage medium comprising computer executable instructions, the meters
Calculation machine executable instruction realizes the user community recognition methods as described in above-mentioned first aspect when being executed as computer processor.
A kind of user community recognition methods provided in an embodiment of the present invention, by being constructed according to the specific internet behavior of user
The number of specific internet behavior occurs in the set time period based on user for customer relationship figure, calculates in the customer relationship figure
Behavior similarity between every two user, and the behavior similarity cuts the customer relationship figure, last basis
User carries out used terminal device quantity and internet protocol address quantity when internet behavior, based on the use after cutting
The technological means that family relational graph identifies target user group is realized to the target user with outburst Sexual behavior features
Group accurately identifies, and when carrying out internet behavior by synthetic user used terminal device situation, IP address situation with
And the tight type of user community to be identified, effectively prevent the influence of noise data and to accidental behavior congruence feature
The misrecognition of user community improves the accuracy of identification of target user group.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, institute in being described below to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without creative efforts, can also implement according to the present invention
The content of example and these attached drawings obtain other attached drawings.
Fig. 1 is a kind of user community recognition methods flow diagram that the embodiment of the present invention one provides；
Fig. 2 is a kind of customer relationship schematic diagram that the embodiment of the present invention one provides；
Fig. 3 is a kind of user community recognition methods flow diagram provided by Embodiment 2 of the present invention；
Fig. 4 is a kind of user community identification device structural schematic diagram that the embodiment of the present invention three provides；
Fig. 5 is the structural schematic diagram for a kind of electronic equipment that the embodiment of the present invention four provides.
Specific embodiment
To keep the technical problems solved, the adopted technical scheme and the technical effect achieved by the invention clearer, below
It will the technical scheme of the embodiment of the invention will be described in further detail in conjunction with attached drawing, it is clear that described embodiment is only
It is a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those skilled in the art exist
Every other embodiment obtained under the premise of creative work is not made, shall fall within the protection scope of the present invention.
Embodiment one
Fig. 1 is a kind of user community recognition methods flow diagram that the embodiment of the present invention one provides.The present embodiment discloses
User community recognition methods be applicable to identify the user community for being engaged in online cheating, such as in direct broadcasting room
The user community for carrying out the online cheatings such as brush barrage, brush concern is identified, can be held by user community identification device
Row, wherein the device can be implemented by software and/or hardware, and be typically integrated in terminal, such as smart phone or computer etc..
Referring specifically to shown in Fig. 1, this method comprises the following steps:
Step 110 constructs customer relationship figure according to the specific internet behavior of user.
Wherein, the specific internet behavior specifically can be the behavior of positive worth promotion, such as online contribution, may be used also
To be behavior that passive needs resist, such as identical main broadcaster is directed to by live streaming platform and carries out the behavior of brush barrage or passes through
Live streaming platform carries out brush concern behavior for identical main broadcaster.The behavior that usually passive needs resist often brings some negative
Face is rung, as escribed above to carry out the behavior of brush barrage for identical main broadcaster by live streaming platform or be directed to by the way that platform is broadcast live
Identical main broadcaster carries out brush concern behavior, it will usually cause network blockage, the problems such as Platform Server pressure is excessive is broadcast live.Therefore
It is engaged in order to reduce negative effect brought by the behavior of brush barrage or brush concern behavior or in order to actively advocate beneficial to behavior,
A kind of user community recognition methods disclosed in the present embodiment goes out to be engaged in the work of the behavior of brush barrage or brush concern behavior for identification
Disadvantage group, with alerted perhaps take other measures prevented or identified be engaged in contribution etc. public goods behavior group,
To commend, healthy tendency in society etc. is built.The present embodiment is engaged in the behavior of brush barrage or brush concern behavior etc. to identify
Online cheating group for be illustrated.
The customer relationship figure is the figure for embodying incidence relation between user.Such as regard each user as one solely
Vertical vertex will connect a line if there is friend relation each other between two users between the corresponding vertex of two users,
If the line between active user and other users is more, then it represents that with active user there are the user of friend relation mostly etc.,
Certainly it can also be the incidence relation established between user from other dimensions.
It is illustratively, described that customer relationship figure is constructed according to the specific internet behavior of user, comprising:
Determine all users for carrying out specific internet behavior in the set time period；
Using each user in all users as a vertex；
The specific internet behavior will be carried out based on same terminal equipment and/or identical IP address in the set time period
The corresponding vertex of user is attached by sideline, generates undirected customer relationship figure.
Wherein, the set period of time can be specific some day, a certain week or some moon.In the ad hoc networks
Behavior for example can be the account for logining or registering with live streaming platform, and all users refer specifically to occur in the set time period
The account crossed, including logging in the account of live streaming platform and the account of registration live streaming platform.Specifically, will in the set time period
The corresponding vertex of user for logining or registering with same live streaming platform based on same terminal equipment is attached by sideline, is generated
Undirected customer relationship figure；Or same live streaming platform will be logined or registered with based on identical IP address in the set time period
The corresponding vertex of user is attached by sideline, generates undirected customer relationship figure；Or it will be based in the set time period
Same terminal equipment, and pass through sideline using the corresponding vertex of user that identical IP address logins or registers with same live streaming platform
It is attached, generates undirected customer relationship figure.
For being based on same equipment in the set time period and carry out brush concern behavior, a kind of user shown in Figure 2
Relation schematic diagram, it is assumed that user 1 and user 2 have carried out brush concern behavior based on terminal device A in the set period of time, use
Family 1 and user 8 have carried out brush concern behavior, therefore the corresponding vertex of user 1 based on terminal device B in the set period of time
1 vertex 2 corresponding with user 2, user 8 are attached between corresponding vertex 8 by sideline respectively；Assuming that user 2 and user 3
Brush concern behavior is carried out based on terminal device C in the set period of time, therefore the corresponding vertex 2 of user 2 and user 3 are right
It is attached between the vertex 3 answered by sideline, user 2 and user 5 are carried out in the set period of time based on terminal device D
Brush concern behavior, therefore be attached by sideline between the vertex 5 corresponding with user 5 of the corresponding vertex 2 of user 2；With this
Analogize, has obtained non-directed graph shown in Fig. 2.In non-directed graph shown in Fig. 2, in the set time period due to user 1 and user 2
It has used identical terminal device A to carry out identical internet behavior (brush concern), therefore the user with above-mentioned relation has been claimed
For neighbor user.
Illustratively, the determination carries out all users of specific internet behavior in the set time period and includes:
Behavior-based control gets acquisition User action log ready, to determine the use for carrying out specific internet behavior in the set time period
Family；
The network environment information that user uses is obtained for the user for carrying out specific internet behavior, with the determination use
The IP address at family；And/or
The terminal device information that user uses is obtained for the user for carrying out specific internet behavior, with the determination use
The device id that family uses.
It is that event, the page (are such as clicked in the place for needing to bury in engineering for counting user behavior a little that the behavior, which is got ready,
Jump) it is inserted into and buries point code, the internet behavior of user will be recorded in User action log later, passed through and acquired user behavior
Log simultaneously inquires user behavior and can determine the user for carrying out specific internet behavior, described specific to surf the net as which is for example specially
A little users have sent barrage information for main broadcaster A.User is also recorded in User action log simultaneously and carries out internet behavior institute
The network environment information and used terminal device information used.The User action log is in mobile terminal (such as intelligent hand
Machine) it can directly be obtained by data acquisition interface.
By combining user to carry out equipment situation and IP address situation used in specific internet behavior, realize to
The preliminary excavation of family group.The user for generally falling into same group is concentrated in carrying out specific internet behavior together, therefore passes through phase
The user for carrying out specific internet behavior with terminal device and/or identical IP address may belong to same group.
Step 120, the number that specific internet behavior occurs in the set time period based on user, calculate the customer relationship
Behavior similarity in figure between every two user.
Specifically, if two users' number that specific internet behavior occurs in the set time period is higher, and relatively,
Indicate the behavior of two users consistency with higher, then a possibility that two users progress group's cheating is bigger.For example, with
Family a sends out barrage 100 between 2:00 AM-yesterday 3:00 AM yesterday, user b yesterday 2:00 AM-yesterday 3:00 AM it
Between send out barrage 110, then a possibility that user a and user b belongs to group's brush barrage, is larger.
Further, in order to sufficiently excavate the synchronization sexual behaviour between user, the set period of time can further be drawn
It is divided into equidistant multiple smaller periods, to fully demonstrate the synchronization sexual behaviour of explosion type of the user within certain period.
Step 130 cuts the customer relationship figure according to the behavior similarity, low with deleting act similarity
Incidence relation between the user of given threshold.
It can effectively avoid noise data to knowledge by cut to the customer relationship figure according to the behavior similarity
Not Zuo Bi group influence, and due to the consistent sexual behaviour being incidentally present of between user cause practise fraud group misrecognition.Example
Such as, the similarity being incidentally present of between the user of consistent sexual behaviour can be made lower by the way that specific similarity algorithm is arranged, such as
This can delete the incidence relation between the lower user of behavior similarity from the customer relationship figure.
Illustratively, the customer relationship figure is cut according to the behavior similarity, with deleting act similarity
Lower than the incidence relation between the user of given threshold, comprising:
Behavior similarity is deleted lower than the sideline between the corresponding vertex of two users of given threshold；The given threshold
Recognition methods provided in this embodiment can be based on according to the internet behavior of known cheating group to be back-calculated to obtain.
Step 140, used terminal device quantity and Internet protocol IP are carried out when internet behavior according to user
Location quantity identifies target user group based on the customer relationship figure after cutting.
Specifically, all connected subgraphs in figure are found out based on the customer relationship figure after cutting, by each connected subgraph institute
Including the user of vertex correspondence be determined as a user community to be identified, in conjunction with all users in each user community to be identified
It carries out used terminal device quantity and IP address quantity when internet behavior and calculates each user community to be identified to be cheating
The confidence level of group further determines whether user community to be identified is cheating user community according to confidence level.
A kind of user community recognition methods provided in this embodiment, it is specific by being occurred in the set time period based on user
The number of internet behavior calculates the behavior similarity in customer relationship figure between every two user, realizes to explosion type
The embodiment of consistent sexual behaviour user, by being cut according to the behavior similarity to the customer relationship figure, avoid by
Influence of the consistent sexual behaviour being incidentally present of between user to the identification of cheating group, and the terminal of comprehensive user community to be identified
Equipment service condition, IP address service condition and group's scale are the confidence level of target user group to user community to be identified
It is calculated, identification angle changing rate is comprehensive, to improve the accuracy of identification of cheating group；And it can be adopted according to different confidence levels
Different degrees of measure to stop is taken, to will not cause to take lighter measure to stop to the cheating higher group of risk, is led
Cause the result of " leakage is killed "；And heavier measure to stop is taken for the cheating lower user community of risk, to cause " accidentally
Kill " result.
Embodiment two
Fig. 3 is a kind of flow diagram of user community recognition methods provided by Embodiment 2 of the present invention, in above-mentioned implementation
On the basis of example, the present embodiment " is occurred the number of specific internet behavior in the set time period based on user, counted to step 120
Calculate the behavior similarity in the customer relationship figure between every two user " and step " according to user carry out internet behavior when
Used terminal device quantity and internet protocol address quantity calculate separately each user community to be identified as target use
The confidence level of family group " gives specific implementation, shown in Figure 3, which comprises
Step 310 constructs customer relationship figure according to the specific internet behavior of user.
Step 320, the number that specific internet behavior occurs in the set time period based on user, calculate the customer relationship
Behavior similarity in figure between every two user.
Specifically, calculating the behavior similarity between the every two user according to following formula:
Wherein, sim (u, v) indicates the behavior similarity between user u and user v, uiIndicate user u in period TiIt is interior
The number of specific internet behavior, v occursiIndicate user i in period TiThe interior number that specific internet behavior occurs, n indicate setting
The period T that period T includesiNumber, for example, set period of time T be one day, i.e., 24 hours, period TiIt is 2 hours, then
One day time was divided into 0. -2 point, 2. -4 points, 4. -6 points, 6. -8 points, 8. -10 points, 10. -12 points, 12. -14
Point, 14. -16 points, 16. -18 points, 18. -20 points, 20. -22 points and 22. -24 points, totally 12 period period Ti。
Step 330 cuts the customer relationship figure according to the behavior similarity, low with deleting act similarity
Incidence relation between the user of given threshold.
Step 340 based on the customer relationship figure after the cutting obtains each use to be identified in such a way that connected graph clusters
Family group.
Specifically, assuming that customer relationship schematic diagram shown in Fig. 2 is the customer relationship schematic diagram after a kind of cutting, with Fig. 2
For illustrate above-mentioned " based on the customer relationship figure after the cutting to obtain each user group to be identified in such a way that connected graph clusters
The process of body ": in order to which based on the incidence relation between the non-neighbor user of relation excavation between neighbor user, the present embodiment passes through
It is excavated based on depth-first search DFS algorithm, obtains multiple connected subgraphs, all vertex correspondences in each connected subgraph
User be a user community to be identified, whether each user community to be identified is target user group, it is also necessary to each
User community to be identified carries out confidence calculations.
Specifically, the working principle of the DFS algorithm are as follows: from some vertex of non-directed graph, access and the vertex phase
Some adjacent abutment points, some abutment points ... for then accessing this abutment points are so deeply gone down, certain is reached up to
A vertex finds that the abutment points around the vertex were visited, and at this time toward a vertex is return back to, accesses the vertex
Not visited mistake abutment points ... until all vertex are all accessed, all node structures for being accessed in current search
At a connected subgraph.The search process of above-mentioned DFS algorithm is introduced by taking Fig. 2 as an example:
(1) vertex 1 is put into stack, and vertex 1 is labeled as having traversed；
(2) vertex 1 that stack top is accessed from the stack, finds out the vertex adjacent with vertex 1, there is vertex 2 and 8 two, vertex
Vertex, may be selected it is therein any one, select rule that can be set, it is assumed that according to vertex correspondence number from small to large
Sequence is selected, this chooses vertex 2, vertex 2 is labeled as having traversed, and vertex 2 is put into the stack；
(3) vertex 2 that stack top is accessed from the stack, finds out the vertex adjacent with vertex 2, there is vertex 1, vertex 3 and top
5 three vertex of point, vertex 1 is traversed, therefore vertex 1 is excluded, and according to above-mentioned selection rule, vertex 3 is chosen, by vertex
3 are labeled as having traversed, and vertex 3 is put into the stack；
(4) vertex 3 that stack top is accessed from the stack, finds out the vertex adjacent with vertex 3, there is vertex 2 and 4 two, vertex
Vertex, vertex 2 is traversed, therefore vertex 2 is excluded, and chooses vertex 4, vertex 4 is labeled as having traversed, and vertex 4 is put
Enter in the stack；
(5) vertex 4 that stack top is accessed from the stack, finds out the vertex adjacent with vertex 4, there is vertex 3, vertex 5 and top
6 three vertex of point, vertex 3 is traversed, therefore vertex 3 is excluded, and according to above-mentioned selection rule, vertex 5 is chosen, by vertex
5 are labeled as having traversed, and vertex 5 is put into the stack；
(6) vertex 5 that stack top is accessed from the stack, finds out the vertex adjacent with vertex 5, there is vertex 2 and 4 two, vertex
Vertex, vertex 2 and vertex 4 are traversed, therefore the abutment points that vertex 5 does not traverse not yet, abandon the visit to opposite vertexes 5
It asks, vertex 5 is removed from the stack, indicate that vertex 5 is not accessed at this time；
(7) vertex 4 that stack top is accessed from the stack, finds out the vertex adjacent with vertex 4, there is vertex 3, vertex 5 and top
6 three vertex of point, vertex 3 and vertex 5 are traversed, therefore, choose vertex 6, by vertex 6 labeled as having traversed, and by vertex 6
It is put into the stack；
(8) vertex 6 that stack top is accessed from the stack, finds out the vertex adjacent with vertex 6, there is vertex 4, vertex 7 and top
8 three vertex of point, vertex 4 is traversed, according to above-mentioned selection rule, chooses vertex 7, vertex 7 is labeled as having traversed, and will
Vertex 7 is put into the stack；
(9) vertex 7 that stack top is accessed from the stack, finds out the vertex adjacent with vertex 7, only vertex 6, and vertex 6
Traversed, therefore, the abutment points that vertex 7 does not traverse not yet abandon the access to opposite vertexes 7, by vertex 7 from the stack
It removes, indicates that vertex 7 is not accessed at this time；
(10) vertex 6 that stack top is accessed from the stack, finds out the vertex adjacent with vertex 6, there is vertex 4, vertex 7 and top
8 three vertex of point, vertex 4 and vertex 7 are traversed, choose vertex 8, vertex 8 are labeled as having traversed, and vertex 8 is put into
In the stack；
(11) vertex 8 that stack top is accessed from the stack, finds out the vertex adjacent with vertex 8, there is vertex 1, vertex 6 and top
9 three vertex of point, vertex 1 and vertex 6 are traversed, choose vertex 9, vertex 9 are labeled as having traversed, and vertex 9 is put into
In the stack；
(12) vertex 9 that stack top is accessed from the stack, finds out the vertex adjacent with vertex 9, only vertex 8 and vertex 8
Traversed, therefore, the abutment points that vertex 9 does not traverse not yet abandon the access to opposite vertexes 9, by vertex 9 from the stack
It removes, indicates that vertex 9 is not accessed at this time, so far, all vertex have been traversed, and the vertex in stack is without not yet
The abutment points of traversal will all be removed from stack, and last stack is sky, indicate that all vertex have been traversed, current traversal search
During the vertex 1, vertex 2, vertex 3, vertex 4, vertex 6 and the vertex 8 that are accessed to constitute a connected subgraph；The connection
User 1, user 2, user 3, user 4, user 6 and the user 8 of all vertex correspondences in subgraph form a user to be identified
Group.
Then from the non-directed graph, there are no arbitrarily select a work in the searched vertex as known connected subgraph
For next time search starting point, by multiple traversal search (connected subgraph can be obtained in each traversal search), until described
There are no be searched as the vertex of known connected subgraph being the isolated vertex not being connected with other vertex in non-directed graph.
Step 350, used terminal device quantity and Internet protocol IP are carried out when internet behavior according to user
Location quantity calculates separately the confidence level that each user community to be identified is target user group.
Specifically, calculating the confidence level that user community to be identified is target user group according to following formula:
Wherein, F (G) indicates that user community G to be identified is the confidence level of target user group, | G | indicate user to be identified
User's number of members that group G includes, IP (G) indicate that all user members send out in the set time period in user community G to be identified
Used IP address sum, Device (G) indicate all user members in user community G to be identified when raw specific internet behavior
Used terminal device sum, Edge (G) when specific internet behavior occur in the set time period indicates user group to be identified
The quantity on the side that body G is formed in the customer relationship figure after the cutting, w1、w2、w3It is weight coefficient, and w1+w2+w3=1, root
Think according to business experience, compared to IP address situation used by a user and group's scale, terminal device used by a user
Situation can more illustrate whether active user group is cheating group, therefore, usual w2>w3>w1；The specific internet behavior includes
It logs in, register, sending out barrage or concern.
Step 360, the user community to be identified that confidence level is reached to threshold value are determined as target user group.
Wherein, the threshold value can according to it is known cheating group internet behavior be based on recognition methods provided in this embodiment into
Row is back-calculated to obtain.
For example, it is assumed that current user community to be identified includes 10 user members, in user between 10 user members
20 sides are formd in relational graph, used altogether when specific internet behavior occurring in the set time period 5 different IP address,
2 different terminal devices, weight coefficient w1、w2、w3Respectively 0.2,0.5,0.3, threshold value 0.5, then current user to be identified
Group is the confidence level of cheating group are as follows:
Since 0.51 is greater than 0.5, current user community to be identified is cheating group.
It, can be according to different confidence levels to corresponding after obtaining the confidence level that user community to be identified is cheating user community
User community take different measures to stop, such as blacklist is added in the higher user community of confidence level, to limit thereafter
Continuous cheating；Using the lower user community of confidence level as suspicion cheating group, it is continued to pay close attention to, and be based on it
Subsequent internet behavior carries out the calculating of confidence level using recognition methods provided in an embodiment of the present invention again, should with final determination
Whether suspicion cheating group is group of really practising fraud.
A kind of user community recognition methods provided in this embodiment, is made by the terminal device of synthesis user community to be identified
The confidence level that user community to be identified is target user group is counted with situation, IP address service condition and group's scale
It calculates, identification angle changing rate is comprehensive, to improve the accuracy of identification of cheating group；And difference can be taken according to different confidence levels
The measure to stop of degree leads to " leakage to will not cause to take lighter measure to stop to the cheating higher group of risk
Kill " result；And heavier measure to stop is taken for the cheating lower user community of risk, to cause " manslaughtering "
As a result.
Embodiment three
Fig. 4 is a kind of user community identification device structural schematic diagram that the embodiment of the present invention three provides.It is shown in Figure 4,
Described device includes: building module 410, computing module 420, cuts module 430 and identification module 440；
Wherein, module 410 is constructed, for constructing customer relationship figure according to the specific internet behavior of user；Computing module
420, for the number of specific internet behavior to occur in the set time period based on user, calculate every two in the customer relationship figure
Behavior similarity between a user；Module 430 is cut, for carrying out according to the behavior similarity to the customer relationship figure
It cuts, with deleting act similarity lower than the incidence relation between the user of given threshold；Identification module 440, for according to
Family carries out used terminal device quantity and internet protocol address quantity when internet behavior, based on the user after cutting
Relational graph identifies target user group.
Further, building module 410 includes:
Determination unit carries out all users of specific internet behavior for determining in the set time period, and by the institute
There is each user in user as a vertex；
Connection unit, for that will be based in the set time period described in same terminal equipment and/or the progress of identical IP address
The corresponding vertex of the user of specific internet behavior is attached by sideline, generates undirected customer relationship figure.
Further, module 430 is cut to be specifically used for:
Behavior similarity is deleted lower than the sideline between the corresponding vertex of two users of given threshold.
Further, computing module 420 is specifically used for:
The behavior similarity between the every two user is calculated according to following formula:
Wherein, sim (u, v) indicates the behavior similarity between user u and user v, uiIndicate user u in period TiIt is interior
The number of specific internet behavior, v occursiIndicate user i in period TiThe interior number that specific internet behavior occurs, n indicate setting
The period T that period T includesiNumber.
Further, identification module 440 includes:
Searching unit, for being obtained respectively based on the customer relationship figure after the cutting wait know in such a way that connected graph clusters
Other user community；
Computing unit, used terminal device quantity and Internet protocol when for according to user's progress internet behavior
IP address quantity calculates separately the confidence level that each user community to be identified is target user group；
Determination unit, the user community to be identified for confidence level to be reached threshold value are determined as target user group.
Further, computing unit is specifically used for:
The confidence level that user community to be identified is target user group is calculated according to following formula:
Wherein, F (G) indicates that user community G to be identified is the confidence level of target user group, | G | indicate user to be identified
User's number of members that group G includes, IP (G) indicate that all user members send out in the set time period in user community G to be identified
Used IP address sum, Device (G) indicate all user members in user community G to be identified when raw specific internet behavior
Used terminal device sum, Edge (G) when specific internet behavior occur in the set time period indicates user group to be identified
The quantity on the side that body G is formed in the customer relationship figure after the cutting, w1、w2、w3It is weight coefficient, and w1+w2+w3=1.
Further, the specific internet behavior includes logging in, registering, sending out barrage or concern.
User community identification device provided in this embodiment, by being occurred in ad hoc networks in the set time period based on user
The number of behavior calculates the behavior similarity in customer relationship figure between every two user, realizes to consistent with explosion type
The embodiment of sexual behaviour user, by being cut according to the behavior similarity to the customer relationship figure, avoid due to
Influence of the consistent sexual behaviour being incidentally present of between family to the identification of cheating group, and the terminal device of comprehensive user community to be identified
Service condition, IP address service condition and group's scale carry out the confidence level that user community to be identified is target user group
It calculates, identification angle changing rate is comprehensive, to improve the accuracy of identification of cheating group；And it can be taken not according to different confidence levels
With the measure to stop of degree, to will not cause to take lighter measure to stop to the cheating higher group of risk, lead to " leakage
Kill " result；And heavier measure to stop is taken for the cheating lower user community of risk, to cause " manslaughtering "
As a result.
Example IV
Fig. 5 is the structural schematic diagram for a kind of electronic equipment that the embodiment of the present invention five provides.Fig. 5, which is shown, to be suitable for being used in fact
The block diagram of the example devices 12 of existing embodiment of the present invention.The equipment 12 that Fig. 5 is shown is only an example, should not be to this hair
The function and use scope of bright embodiment bring any restrictions.
As shown in figure 5, equipment 12 is showed in the form of universal computing device.The component of equipment 12 may include but unlimited
In one or more processor or processing unit 16, system storage 28, connecting different system components, (including system is deposited
Reservoir 28 and processing unit 16) bus 18.
Bus 18 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Equipment 12 typically comprises a variety of computer system readable media.These media can be it is any can be by equipment 12
The usable medium of access, including volatile and non-volatile media, moveable and immovable medium.
System storage 28 may include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 30 and/or cache memory 32.Equipment 12 may further include it is other it is removable/nonremovable,
Volatile/non-volatile computer system storage medium.Only as an example, storage system 34 can be used for reading and writing irremovable
, non-volatile magnetic media (Fig. 5 do not show, commonly referred to as " hard disk drive ").Although being not shown in Fig. 5, use can be provided
In the disc driver read and write to removable non-volatile magnetic disk (such as " floppy disk "), and to removable anonvolatile optical disk
The CD drive of (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driver can
To be connected by one or more data media interfaces with bus 18.Memory 28 may include at least one program product,
There is the program product one group (such as building module 410 in user community identification device, computing module 420, to cut module
430 and identification module 440) program module, these program modules are configured to perform the function of various embodiments of the present invention.
(such as building module 410 in user community identification device, computing module 420, module 430 is cut with one group
With identification module 440) program/utility 40 of program module 42, it can store in such as memory 28, such program
Module 42 including but not limited to operating system, one or more application program, other program modules and program data, these
It may include the realization of network environment in each of example or certain combination.Program module 42 usually executes the present invention and is retouched
The function and/or method in embodiment stated.
Equipment 12 can also be communicated with one or more external equipments 14 (such as keyboard, sensing equipment, display 24 etc.),
Can also be enabled a user to one or more equipment interacted with the equipment 12 communication, and/or with enable the equipment 12 with
One or more of the other any equipment (such as network interface card, modem etc.) communication for calculating equipment and being communicated.It is this logical
Letter can be carried out by input/output (I/O) interface 22.Also, equipment 12 can also by network adapter 20 and one or
The multiple networks of person (such as local area network (LAN), wide area network (WAN) and/or public network, such as internet) communication.As shown,
Network adapter 20 is communicated by bus 18 with other modules of equipment 12.It should be understood that although not shown in the drawings, can combine
Equipment 12 use other hardware and/or software module, including but not limited to: microcode, device driver, redundant processing unit,
External disk drive array, RAID system, tape drive and data backup storage system etc..
Processing unit 16 by the program that is stored in system storage 28 of operation, thereby executing various function application and
Data processing, such as realize user community recognition methods provided by the embodiment of the present invention.
Embodiment five
The embodiment of the present invention five also provides a kind of storage medium comprising computer executable instructions, and the computer can be held
Row instruction is used to execute a kind of user community recognition methods when being executed by computer processor, this method comprises:
Customer relationship figure is constructed according to the specific internet behavior of user；
The number that specific internet behavior is occurred in the set time period based on user is calculated every two in the customer relationship figure
Behavior similarity between a user；
The customer relationship figure is cut according to the behavior similarity, with deleting act similarity lower than setting threshold
Incidence relation between the user of value；
Used terminal device quantity and internet protocol address quantity, base when according to user's progress internet behavior
Customer relationship figure after cutting identifies target user group.
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present invention
The method operation that executable instruction is not limited to the described above, can also be performed user community provided by any embodiment of the invention
Identify relevant operation.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but in many cases, the former is more
Good embodiment.Based on this understanding, technical solution of the present invention substantially in other words contributes to the prior art
Part can be embodied in the form of software products, which can store in computer readable storage medium
In, floppy disk, read-only memory (Read-Only Memory, ROM), random access memory (Random such as computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are with so that a computer is set
Standby (can be personal computer, storage medium or the network equipment etc.) executes described in each embodiment of the present invention.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of user community recognition methods characterized by comprising
Customer relationship figure is constructed according to the specific internet behavior of user；
The number that specific internet behavior is occurred in the set time period based on user is calculated every two in the customer relationship figure and used
Behavior similarity between family；
The customer relationship figure is cut according to the behavior similarity, with deleting act similarity lower than given threshold
Incidence relation between user；
Used terminal device quantity and internet protocol address quantity when according to user's progress internet behavior, based on sanction
Customer relationship figure after cutting identifies target user group.
2. the method according to claim 1, wherein described construct user pass according to the specific internet behavior of user
System's figure, comprising:
Determine all users for carrying out specific internet behavior in the set time period；
Using each user in all users as a vertex；
The user of the specific internet behavior will be carried out based on same terminal equipment and/or identical IP address in the set time period
Corresponding vertex is attached by sideline, generates undirected customer relationship figure.
3. according to the method described in claim 2, it is characterized in that, according to the behavior similarity to the customer relationship figure into
Row is cut, with deleting act similarity lower than the incidence relation between the user of given threshold, comprising:
Behavior similarity is deleted lower than the sideline between the corresponding vertex of two users of given threshold.
4. the method according to claim 1, wherein specific surf the net occurs in the set time period based on user
For number calculate the behavior similarity in the customer relationship figure between every two user, comprising:
The behavior similarity between the every two user is calculated according to following formula:
Wherein, sim (u, v) indicates the behavior similarity between user u and user v, uiIndicate user u in period TiInterior generation
The number of specific internet behavior, viIndicate user i in period TiThe interior number that specific internet behavior occurs, n indicate setting time
The period T that section T includesiNumber.
5. method according to claim 1-4, which is characterized in that used when carrying out internet behavior according to user
Terminal device quantity and internet protocol address quantity based on the customer relationship figure after cutting to target user group into
Row identification, comprising:
Each user community to be identified is obtained based on the customer relationship figure after the cutting in such a way that connected graph clusters；
Used terminal device quantity and internet protocol address quantity are counted respectively when carrying out internet behavior according to user
Calculate the confidence level that each user community to be identified is target user group；
The user community to be identified that confidence level reaches threshold value is determined as target user group.
6. according to the method described in claim 5, it is characterized in that, used terminal is set when carrying out internet behavior according to user
Standby quantity and internet protocol address quantity calculate separately the confidence level that each user community to be identified is target user group,
Include:
The confidence level that user community to be identified is target user group is calculated according to following formula:
Wherein, F (G) indicates that user community G to be identified is the confidence level of target user group, | G | indicate user community G to be identified
Including user's number of members, IP (G) indicates that all user members occur specific in the set time period in user community G to be identified
Used IP address sum, Device (G) indicate that all user members are setting in user community G to be identified when internet behavior
Used terminal device sum, Edge (G) when specific internet behavior occur in period indicates user community G to be identified in institute
State the quantity on the side formed in the customer relationship figure after cutting, w1、w2、w3It is weight coefficient, and w1+w2+w3=1.
7. method according to claim 1-4, which is characterized in that the specific internet behavior includes logging in, signing
It arrives, send out barrage or concern.
8. a kind of user community identification device, which is characterized in that described device includes:
Module is constructed, for constructing customer relationship figure according to the specific internet behavior of user；
Computing module is calculated the user and closed for the number of specific internet behavior to be occurred in the set time period based on user
It is the behavior similarity in figure between every two user；
Module is cut, for cutting according to the behavior similarity to the customer relationship figure, with deleting act similarity
Lower than the incidence relation between the user of given threshold；
Identification module, used terminal device quantity and Internet protocol IP when for carrying out internet behavior according to user
Location quantity identifies target user group based on the customer relationship figure after cutting.
9. a kind of electronic equipment, including first memory, first processor and storage are on a memory and can be in first processor
The computer program of upper operation, which is characterized in that realized when the first processor executes the computer program as right is wanted
Ask user community recognition methods described in any one of 1-7.
10. a kind of storage medium comprising computer executable instructions, the computer executable instructions are by computer disposal
Such as user community recognition methods of any of claims 1-7 is realized when device executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910431373.7A CN110177094B (en) | 2019-05-22 | 2019-05-22 | User group identification method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910431373.7A CN110177094B (en) | 2019-05-22 | 2019-05-22 | User group identification method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110177094A true CN110177094A (en) | 2019-08-27 |
| CN110177094B CN110177094B (en) | 2021-11-09 |
Family
ID=67691871
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910431373.7A Active CN110177094B (en) | 2019-05-22 | 2019-05-22 | User group identification method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110177094B (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852761A (en) * | 2019-10-11 | 2020-02-28 | 支付宝(杭州)信息技术有限公司 | Method and device for formulating anti-cheating strategy and electronic equipment |
| CN110929105A (en) * | 2019-11-28 | 2020-03-27 | 杭州云徙科技有限公司 | User ID (identity) association method based on big data technology |
| CN111401959A (en) * | 2020-03-18 | 2020-07-10 | 多点(深圳)数字科技有限公司 | Risk group prediction method and device, computer equipment and storage medium |
| CN111489190A (en) * | 2020-03-16 | 2020-08-04 | 上海趣蕴网络科技有限公司 | Anti-cheating method and system based on user relationship |
| CN112616074A (en) * | 2021-03-08 | 2021-04-06 | 武汉斗鱼鱼乐网络科技有限公司 | Target group identification method and electronic equipment |
| CN112651764A (en) * | 2019-10-12 | 2021-04-13 | 武汉斗鱼网络科技有限公司 | Target user identification method, device, equipment and storage medium |
| CN112788351A (en) * | 2019-11-01 | 2021-05-11 | 武汉斗鱼鱼乐网络科技有限公司 | Target live broadcast room identification method, device, equipment and storage medium |
| CN112800286A (en) * | 2021-04-08 | 2021-05-14 | 北京轻松筹信息技术有限公司 | User relationship chain construction method and device and electronic equipment |
| CN112839027A (en) * | 2020-12-16 | 2021-05-25 | 贝壳技术有限公司 | User group identification method and device, electronic equipment and storage medium |
| CN112995283A (en) * | 2021-02-03 | 2021-06-18 | 杭州海康威视系统技术有限公司 | Object association method and device and electronic equipment |
| CN113117338A (en) * | 2021-05-08 | 2021-07-16 | 上海益世界信息技术集团有限公司广州分公司 | Game cheating user identification method and device |
| CN113205129A (en) * | 2021-04-28 | 2021-08-03 | 五八有限公司 | Cheating group identification method and device, electronic equipment and storage medium |
| CN113283908A (en) * | 2021-06-09 | 2021-08-20 | 武汉斗鱼鱼乐网络科技有限公司 | Target group identification method and device |
| CN113365113A (en) * | 2021-05-31 | 2021-09-07 | 武汉斗鱼鱼乐网络科技有限公司 | Target node identification method and device |
| CN113554308A (en) * | 2021-07-23 | 2021-10-26 | 中信银行股份有限公司 | User community division and risk user identification method and device and electronic equipment |
| CN113553498A (en) * | 2021-06-18 | 2021-10-26 | 北京旷视科技有限公司 | Community updating method, apparatus, electronic device and computer readable medium |
| CN113810341A (en) * | 2020-06-12 | 2021-12-17 | 武汉斗鱼鱼乐网络科技有限公司 | Method, system, storage medium and equipment for identifying target network group |
| CN113807862A (en) * | 2021-01-29 | 2021-12-17 | 北京沃东天骏信息技术有限公司 | Access security control method, device, equipment and storage medium |
| CN114071196A (en) * | 2020-08-03 | 2022-02-18 | 武汉斗鱼鱼乐网络科技有限公司 | Method, system, medium and equipment for identifying target live broadcast room |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102571485A (en) * | 2011-12-14 | 2012-07-11 | 上海交通大学 | Method for identifying robot user on micro-blog platform |
| CN108898505A (en) * | 2018-05-28 | 2018-11-27 | 武汉斗鱼网络科技有限公司 | Recognition methods, corresponding medium and the electronic equipment of cheating clique |
| CN109255632A (en) * | 2018-09-03 | 2019-01-22 | 武汉斗鱼网络科技有限公司 | A kind of user community recognition methods, device, equipment and medium |
-
2019
- 2019-05-22 CN CN201910431373.7A patent/CN110177094B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102571485A (en) * | 2011-12-14 | 2012-07-11 | 上海交通大学 | Method for identifying robot user on micro-blog platform |
| CN108898505A (en) * | 2018-05-28 | 2018-11-27 | 武汉斗鱼网络科技有限公司 | Recognition methods, corresponding medium and the electronic equipment of cheating clique |
| CN109255632A (en) * | 2018-09-03 | 2019-01-22 | 武汉斗鱼网络科技有限公司 | A kind of user community recognition methods, device, equipment and medium |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852761A (en) * | 2019-10-11 | 2020-02-28 | 支付宝(杭州)信息技术有限公司 | Method and device for formulating anti-cheating strategy and electronic equipment |
| CN112651764A (en) * | 2019-10-12 | 2021-04-13 | 武汉斗鱼网络科技有限公司 | Target user identification method, device, equipment and storage medium |
| CN112651764B (en) * | 2019-10-12 | 2023-03-31 | 武汉斗鱼网络科技有限公司 | Target user identification method, device, equipment and storage medium |
| CN112788351A (en) * | 2019-11-01 | 2021-05-11 | 武汉斗鱼鱼乐网络科技有限公司 | Target live broadcast room identification method, device, equipment and storage medium |
| CN112788351B (en) * | 2019-11-01 | 2022-08-05 | 武汉斗鱼鱼乐网络科技有限公司 | Target live broadcast room identification method, device, equipment and storage medium |
| CN110929105B (en) * | 2019-11-28 | 2022-11-29 | 广东云徙智能科技有限公司 | User ID (identity) association method based on big data technology |
| CN110929105A (en) * | 2019-11-28 | 2020-03-27 | 杭州云徙科技有限公司 | User ID (identity) association method based on big data technology |
| CN111489190A (en) * | 2020-03-16 | 2020-08-04 | 上海趣蕴网络科技有限公司 | Anti-cheating method and system based on user relationship |
| CN111401959B (en) * | 2020-03-18 | 2023-09-29 | 多点(深圳)数字科技有限公司 | Risk group prediction method, apparatus, computer device and storage medium |
| CN111401959A (en) * | 2020-03-18 | 2020-07-10 | 多点(深圳)数字科技有限公司 | Risk group prediction method and device, computer equipment and storage medium |
| CN113810341A (en) * | 2020-06-12 | 2021-12-17 | 武汉斗鱼鱼乐网络科技有限公司 | Method, system, storage medium and equipment for identifying target network group |
| CN113810341B (en) * | 2020-06-12 | 2023-08-22 | 武汉斗鱼鱼乐网络科技有限公司 | Method and system for identifying target network group, storage medium and equipment |
| CN114071196A (en) * | 2020-08-03 | 2022-02-18 | 武汉斗鱼鱼乐网络科技有限公司 | Method, system, medium and equipment for identifying target live broadcast room |
| CN112839027A (en) * | 2020-12-16 | 2021-05-25 | 贝壳技术有限公司 | User group identification method and device, electronic equipment and storage medium |
| CN113807862A (en) * | 2021-01-29 | 2021-12-17 | 北京沃东天骏信息技术有限公司 | Access security control method, device, equipment and storage medium |
| CN112995283A (en) * | 2021-02-03 | 2021-06-18 | 杭州海康威视系统技术有限公司 | Object association method and device and electronic equipment |
| CN112616074B (en) * | 2021-03-08 | 2021-05-28 | 武汉斗鱼鱼乐网络科技有限公司 | Target group identification method and electronic equipment |
| CN112616074A (en) * | 2021-03-08 | 2021-04-06 | 武汉斗鱼鱼乐网络科技有限公司 | Target group identification method and electronic equipment |
| CN112800286A (en) * | 2021-04-08 | 2021-05-14 | 北京轻松筹信息技术有限公司 | User relationship chain construction method and device and electronic equipment |
| CN113205129A (en) * | 2021-04-28 | 2021-08-03 | 五八有限公司 | Cheating group identification method and device, electronic equipment and storage medium |
| CN113117338A (en) * | 2021-05-08 | 2021-07-16 | 上海益世界信息技术集团有限公司广州分公司 | Game cheating user identification method and device |
| CN113365113A (en) * | 2021-05-31 | 2021-09-07 | 武汉斗鱼鱼乐网络科技有限公司 | Target node identification method and device |
| CN113365113B (en) * | 2021-05-31 | 2022-09-09 | 武汉斗鱼鱼乐网络科技有限公司 | Target node identification method and device |
| CN113283908A (en) * | 2021-06-09 | 2021-08-20 | 武汉斗鱼鱼乐网络科技有限公司 | Target group identification method and device |
| CN113553498A (en) * | 2021-06-18 | 2021-10-26 | 北京旷视科技有限公司 | Community updating method, apparatus, electronic device and computer readable medium |
| CN113554308A (en) * | 2021-07-23 | 2021-10-26 | 中信银行股份有限公司 | User community division and risk user identification method and device and electronic equipment |
| CN113554308B (en) * | 2021-07-23 | 2024-05-28 | 中信银行股份有限公司 | User community division and risk user identification method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110177094B (en) | 2021-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110177094A (en) | A kind of user community recognition methods, device, electronic equipment and storage medium | |
| US11710131B2 (en) | Method and apparatus of identifying a transaction risk | |
| US10120956B2 (en) | Methods and systems for distributed computation of graph data | |
| US20120299925A1 (en) | Determining affinity in social networks | |
| US20140304180A1 (en) | Method, system and computer-readable storage medium for dividing a user's social network relationship circle | |
| CN109255632A (en) | A kind of user community recognition methods, device, equipment and medium | |
| WO2016145993A1 (en) | Method and system for user device identification | |
| CN110287688A (en) | Associated account number analysis method, device and computer readable storage medium | |
| CN105391594B (en) | The method and device of identification feature account | |
| CN110555172B (en) | User relationship mining method and device, electronic equipment and storage medium | |
| CN107294974A (en) | The method and apparatus for recognizing target clique | |
| CN110224859B (en) | Method and system for identifying a group | |
| CN113849702B (en) | Method and device for determining target data, electronic equipment and storage medium | |
| CN110674247A (en) | Barrage information intercepting method and device, storage medium and equipment | |
| CN104182422B (en) | Unified address list information processing method and system | |
| CN114841374A (en) | Method for optimizing transverse federated gradient spanning tree based on stochastic greedy algorithm | |
| CN105069290A (en) | Parallelization critical node discovery method for postal delivery data | |
| CN114124484B (en) | Network attack identification method, system, device, terminal equipment and storage medium | |
| CN114880522A (en) | Method and device for realizing ID Mapping based on graph database | |
| CN110309154A (en) | Substance feature selection method, device, equipment and storage medium based on map | |
| CN112667869B (en) | Data processing method, device, system and storage medium | |
| CN110457600B (en) | Method, device, storage medium and computer equipment for searching target group | |
| CN112819056A (en) | Group control account mining method, device, equipment and storage medium | |
| CN107194280A (en) | Method for establishing model and device | |
| CN114547476B (en) | Community searching method and device based on bipartite graph and processing equipment |
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 |