CN109495378A - Detect method, apparatus, server and the storage medium of abnormal account number - Google Patents
Detect method, apparatus, server and the storage medium of abnormal account number Download PDFInfo
- Publication number
- CN109495378A CN109495378A CN201811626326.XA CN201811626326A CN109495378A CN 109495378 A CN109495378 A CN 109495378A CN 201811626326 A CN201811626326 A CN 201811626326A CN 109495378 A CN109495378 A CN 109495378A
- Authority
- CN
- China
- Prior art keywords
- account number
- users
- characteristic data
- behavioural characteristic
- user
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/21—Monitoring or handling of messages
- H04L51/212—Monitoring or handling of messages using filtering or selective blocking
-
- 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
Abstract
This application discloses a kind of method, apparatus, server and storage mediums for detecting abnormal account number, are related to network communication technology field.This method comprises: obtaining behavioural characteristic data of the account number to be detected in object time section, what account number to be detected described in the behavioural characteristic data characterization was initiated in the object time section, the feature of incidence relation behavior is established with other users, the behavioural characteristic data include that account number to be detected requests to establish the number of users of incidence relation in object time section；Judge whether the behavioural characteristic data meet goal condition；If it is determined that the behavioural characteristic data meet the goal condition, determine that the account number to be detected is abnormal account number.This programme passes in and out the behavioural characteristic data of user by obtaining direct broadcasting room, configures the judgement of goal condition strategy by backstage and screens out abnormal account number, the account number that quickly notes abnormalities may be implemented, effectively prevent user from frequently being harassed, improve user friendly.
Description
Technical field
This application involves network communication technology field, more particularly, to a kind of method, apparatus for detecting abnormal account number,
Server and storage medium.
Background technique
With the fast development of network technology, user can be chatted by instant messaging application or social networks with good friend
It is to promote the emotion between good friend.Instant messaging is the business of instant exchange message Internet-based, can give user
The communication mode of multi-person interactive is provided, the public chats such as different channel space can establish by instant messaging tools, for example, net
Platform is broadcast live in network.It generally may include multiple direct broadcasting rooms on network direct broadcasting platform, include main broadcaster and user, user in direct broadcasting room
It can be interacted by network direct broadcasting platform with main broadcaster, can also add other users is good friend.But there are more and more
Malefactor frequently add good friend using any special measures, and then propagate junk information, inevitably other people constituted and is disturbed
It disturbs.
Summary of the invention
In view of the above problems, present applicant proposes a kind of method, apparatus for detecting abnormal account number, server and storages to be situated between
Matter, to improve the above problem.
In a first aspect, the embodiment of the present application provides a kind of method for detecting abnormal account number, this method comprises: obtaining to be checked
Behavioural characteristic data of the account number in object time section are surveyed, behavioural characteristic data characterization account number to be detected is in object time section
Interior initiation, the feature of incidence relation behavior is established with other users, behavioural characteristic data include account number to be detected in target
Between in section request establish the number of users of incidence relation；Judge whether behavioural characteristic data meet goal condition；If it is determined that row
It is characterized data and meets goal condition, determine account number to be detected for abnormal account number.
Second aspect, the embodiment of the present application provide a kind of device for detecting abnormal account number, which includes: acquisition mould
Block, for obtaining behavioural characteristic data of the account number to be detected in object time section, behavioural characteristic data characterization account to be detected
Number initiated in object time section, establish the feature of incidence relation behavior with other users, behavioural characteristic data include to
Detection account number requests to establish the number of users of incidence relation in object time section；Judgment module, for judging behavioural characteristic
Whether data meet goal condition；Processing module, for determining account to be detected if it is determined that behavioural characteristic data meet goal condition
Number for abnormal account number.
The third aspect, the embodiment of the present application provide a kind of server, including memory and one or more processors；
One or more programs are stored in memory and are configured as being executed by one or more of processors, one or more
Program is configured to carry out method described in above-mentioned first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, computer readable storage medium
In be stored with program code, wherein method described in above-mentioned first aspect is executed when program code is run as processor.
A kind of method, apparatus, server and storage medium detecting abnormal account number provided by the embodiments of the present application, this method
It is to be checked described in the behavioural characteristic data characterization by behavioural characteristic data of the acquisition account number to be detected in object time section
It surveys what account number was initiated in the object time section, the feature of incidence relation behavior is established with other users, the behavior is special
Levying data includes that account number to be detected requests to establish the number of users of incidence relation in object time section；Judge that the behavior is special
Whether sign data meet goal condition；If it is determined that the behavioural characteristic data meet the goal condition, determine described to be detected
Account number is abnormal account number.This method passes in and out the correlation behavior data of user by obtaining direct broadcasting room, configures target item by backstage
The judgement of part strategy screens out abnormal account number, and the account number that quickly notes abnormalities may be implemented, effectively prevent user from frequently being harassed, mention
High user friendly.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the drawings in the following description are only some examples of the present application, for
For those skilled in the art, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 shows a kind of application environment schematic diagram provided by the embodiments of the present application.
Fig. 2 shows the flow charts for the method for detecting abnormal account number that one embodiment of the application provides.
Fig. 3 shows the flow chart of the method for the abnormal account number of detection that another embodiment of the application provides.
Fig. 4 shows the flow chart of the method for the step S220 in Fig. 3.
Fig. 5 shows the flow chart of the method for the abnormal account number of detection that the another embodiment of the application provides.
Fig. 6 shows the flow chart of the method for the abnormal account number of detection of the application another embodiment offer.
Fig. 7 shows the flow chart of the method for the abnormal account number of detection of the application another embodiment offer.
Fig. 8 shows the structural block diagram of the device provided by the embodiments of the present application for detecting abnormal account number.
Fig. 9 shows a kind of structural block diagram of server provided by the embodiments of the present application.
Figure 10 shows the different according to the detection of the embodiment of the present application for saving or carrying realization of the embodiment of the present application
The storage unit of the program code of the method for normal account number.
Specific embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described.
Instant messaging (Instant Messenger, abbreviation IM) is a kind of industry of instant exchange message Internet-based
Business, With the fast development of internet, instant messaging is also rapidly developed, and instant messaging not only may be implemented two people's
Exchange in time, in order to realize the timely exchange between more people, instant messaging is also proposed more people's chat communication services, such as chats
Room, group or network direct broadcasting platform etc., more and more users carry out frequently by instant messaging application or social networks and good friend
Chat is to promote the emotion between good friend.But more and more malefactors are using side plug-in or using the protocol software
Formula enters instant messaging application or social network-i i-platform and sends fallacious message to user, or frequent addition user is preferably
Friend, such as enter certain live streaming platform batch addition good friend etc. by plug-in, different degrees of harassing and wrecking are produced to user, are reduced
User experience.
In view of the above-mentioned problems, inventor has found by long-term research and proposes a kind of inspection provided by the embodiments of the present application
Method, apparatus, server and the storage medium for surveying abnormal account number, the behavioural characteristic data of user are passed in and out by obtaining direct broadcasting room,
The judgement of goal condition strategy is configured by backstage and screens out abnormal account number, and the account number that quickly notes abnormalities may be implemented, it is effective anti-
Only user is frequently harassed, and improves user friendly.
For the ease of application scheme is described in detail, ring first is applied to one of the embodiment of the present application in conjunction with attached drawing below
Border is introduced.
Referring to Fig. 1, for a kind of application environment schematic diagram for the method for detecting abnormal account number provided by the embodiments of the present application,
As shown in Figure 1, the application environment can be understood as a kind of network system 10 of the offer of the embodiment of the present application, the network system 10
It include: server 11 and user terminal 12.Wherein, server 11 can be a server (network access server),
It can be the server cluster (Cloud Server) consisted of several servers, or can be a cloud computing center (data
Library server).User terminal 12 can be any equipment for having communication and store function, including but not limited to PC
(Personal Computer, personal computer), PDA (tablet computer), smart television, smart phone, intelligent wearable device
Or other intelligent communication devices with network connecting function.
It should be noted that the method in the embodiment of the present application is applied to network direct broadcasting platform, as a kind of mode, network
Live streaming platform can be run in a server 11 as shown in Figure 1, be also possible to run on several servers 11 (in figure only
Show one) composition server cluster in.
Optionally, the client of instant messaging application or social networking application, the client are mounted in user terminal 12
End can be application client (the video playing application program in such as cell phone application), be also possible to webpage client (such as
Network direct broadcasting platform), it is not limited thereto.Wherein, server 11 can be established by network and user terminal 12 and be communicated to connect,
As a kind of mode, which can be wireless network, is also possible to cable network.The user account number of registration can be used in user
Client or internet in login user terminal 12, the client can have information input interface, and user is at the interface
Interior input text information, and text information is shown in the chat interface of client.
Present embodiments are specifically described below in conjunction with attached drawing.
Referring to Fig. 2, a kind of flow chart of the method for detection exception account number of one embodiment of the application offer is provided, this
Embodiment provides a kind of method for detecting abnormal account number, can be applied to network direct broadcasting platform, this method comprises:
Step S110: behavioural characteristic data of the account number to be detected in object time section, the behavioural characteristic are obtained
What account number to be detected described in data characterization was initiated in the object time section, incidence relation behavior is established with other users
Feature, the behavioural characteristic data include that account number to be detected requests to establish the number of users of incidence relation in object time section
Amount.
In the present embodiment, the behavior that the user of network direct broadcasting platform frequently adds good friend, which can be constituted other users, is harassed,
In order to overcome the problems, such as this, network direct broadcasting platform can pass in and out network direct broadcasting platform to the account number to be detected in object time section
The behavioural characteristic data of direct broadcasting room monitored.Wherein, object time section can be any time period, can be set by machine
It is fixed, different object time sections can also can be set as the case may be by artificial customized.Behavioural characteristic characterization is to be checked
It surveys account number and other users establishes the behavior of incidence relation, such as establish friend relation；Behavioural characteristic data include account to be detected
The number of users of incidence relation is established in request number in object time section, such as can be account number to be detected in object time area
The interior number of users that friend relation is established with other users request that is entering direct broadcasting room.
In a specific application scenarios, network direct broadcasting platform can add good friend's behavior to the malice of operating room's account number
Characteristic is monitored.It should be noted that operating room's account number in the present embodiment characterizes improper user account number (this implementation
Can be understood as abnormal account number in example), it can it is that the plug-in or protocol software of single or multiple uses (has cracked network direct broadcasting
The Malware of the background protocol of platform) it logs in live streaming platform and is added the user account number of good friend's behavior.For example, if it exists
Operating room's account number has monitored the behavior that user passes in and out channel by the plug-in or protocol software, is broadcast live when there is normal users one to enter
Between when, one or more operating room's account numbers can by search addition normal users be good friend, then network direct broadcasting platform can be right
One or more operating room's account number addition normal users are that the behavioural characteristic data of good friend are monitored, such as are just being commonly used to addition
Family is the frequency of good friend, and solicited message, text message or time of addition etc. are monitored, different so as to quickly find
Normal account number avoids abnormal account number malice addition good friend.
Optionally, when user enters the direct broadcasting room of the network platform, the background management system of the network platform can give the user
A channel information, the direct broadcasting room number that the user is currently located for identification are configured, then can take in the account data of user
Channel information (for example, channel ID) with the direct broadcasting room, when user exits direct broadcasting room or not in direct broadcasting room, then the account of user
The channel information of the direct broadcasting room is not carried in data.It is understood, therefore, that the account number to be detected so in the present embodiment can
It can not also include channel information to include channel information.That is, establishing incidence relation row with other users when detecting
For account number channel information be have channel state when, can be using account as account number to be detected；When detect and other use
It, can be using account as account number to be detected when the channel information of the account number of incidence relation behavior is established as no channel state in family.
In one implementation, the background management system of network direct broadcasting platform can monitoring users account number in real time channel
Information can be using the user account number as account to be detected when detecting the channel information of certain user account number for no channel state
Number.
As an implementation, when account number to be detected includes channel information, account number to be detected can be straight in network
Broadcast the account number that the user in the direct broadcasting room of platform in the same direct broadcasting room of addition is good friend, in this case, account number to be detected with
The user account number of its be added to good friend has identical channel information；Account number to be detected is also possible in network direct broadcasting platform
User in direct broadcasting room in the different direct broadcasting rooms of addition is the account number of good friend, and in such cases, account number to be detected is added to it
The user account number of good friend has different channel informations.
As another embodiment, when account number to be detected does not include channel information, account number to be detected, which can be, not to exist
User in the direct broadcasting room of the network platform in the direct broadcasting room of the addition network platform is the account number of good friend, in such cases, to be detected
For account number without channel information, the user account number that account number to be detected is added to good friend has channel information.
Step S120: judge whether the behavioural characteristic data meet goal condition.
Wherein, goal condition can be network direct broadcasting platform according to the preset critical condition of behavioural characteristic data,
It can be the critical condition that the background management system of network direct broadcasting platform configures in real time, can also be from preset multiple critical items
The critical condition selected in part can refer to subsequent implementation as goal condition, the set-up mode of specific goal condition
Example.Wherein, the threshold range that can be used for limiting behavioural characteristic data of critical condition characterization setting.
Step S130: if it is determined that the behavioural characteristic data meet the goal condition, determine that the account number to be detected is
Abnormal account number.
As a kind of mode, if behavioural characteristic data meet goal condition, it is possible to determine that account number to be detected is abnormal account number.
Optionally, if behavioural characteristic data are unsatisfactory for goal condition, can be determined that account number to be detected not is abnormal account number.
Optionally, if behavioural characteristic data are unsatisfactory for goal condition, terminate the judgement to current behavior characteristic.
The method provided by the embodiments of the present application for detecting abnormal account number, by obtaining account number to be detected in object time section
Interior behavioural characteristic data；Then judge whether behavioural characteristic data meet goal condition；If it is determined that behavioural characteristic data meet
Goal condition determines that account number to be detected for abnormal account number, so as to quickly identify abnormal account number, promotes user experience.
Referring to Fig. 3, a kind of flow chart of the method for detection exception account number that another embodiment of the application provides is shown,
The present embodiment provides a kind of methods for detecting abnormal account number, can be applied to network direct broadcasting platform, this method comprises:
Step S210: it obtains account number to be detected and requests establish the user of incidence relation first to use in object time section
Amount amount.
Optionally, the account number to be detected in the present embodiment can be the main broadcaster in network direct broadcasting platform and (refer to that logging in network is straight
Broadcast platform and the user of network direct broadcasting can be carried out in the network direct broadcasting platform) account number, it is also possible to network direct broadcasting platform
Non- main broadcaster (refers to logging in network live streaming platform but cannot carry out the user of network direct broadcasting in network direct broadcasting platform) account number, usual feelings
Under condition, can mutually it be paid close attention between the user of logging in network live streaming platform, then, if account number to be detected is main broadcaster's account number,
In a kind of implementation, account number to be detected can be in order to draw numerous beans vermicelli, or enhances the reputation and frequently add good friend,
If account number to be detected is non-main broadcaster's account number, in one implementation, account number to be detected can seek to reach certain business
It sells purpose and frequently adds good friend, but frequently addition good friend inevitably constitutes harassing and wrecking to other users, destroys
The friendly of network direct broadcasting platform.
Wherein, the available account number to be detected of network direct broadcasting platform requests to establish incidence relation in object time section
Number of users set, as a kind of mode, number of users set can be asked with what account number to be detected in object time section was initiated
The user for the user that incidence relation is established in the request for asking the request set for establishing incidence relation and account number to be detected to issue gathers it
Between the mode of mapping indicate.For example, it is assumed that set " A { A1, A2, A3,...,An" indicate to be detected in object time section
The request set of incidence relation is established in the request that account number is initiated, and gathers " B { B1,B2,B3,...,Bm" indicate object time section
User's set of the user of incidence relation is established in the request that interior account number to be detected issues, then A { A1, A2, A3,...,An}→B
{B1,B2,B3,...,BmIt can indicate number of users set in object time section.Wherein, object time section can be
The a period of time of current time stamp (i.e. the time of network direct broadcasting backstage management of platform system start recording) forward, such as one point
Clock, 10 minutes or 30 minutes etc., objectives time interval can be by the background management system of network direct broadcasting platform according to reality
It needs and is selected, is not limited thereto.
As a kind of mode, calculating can be iterated to each of number of users set number of users, until using
Each of amount duration set number of users is all calculated and is completed.It should be noted that for number of users set A { A1, A2,
A3,...,An}→B{B1,B2,B3,...,Bm, set A { A1, A2, A3,...,AnIn certain two or more element can phase
Together, the request there are two characterizing or more is intended for the same user；As a kind of mode, set B { B1,B2,B3,...,Bm}
In each element can be different, such as set A { A1, A2, A3,...,AnIn same or different request
It is respectively issued to set B { B1,B2,B3,...,BmIn each user；Alternatively, set B { B1,B2,B3,...,Bm}
In also may include two or more identical elements, for example, set A { A1, A2, A3,...,AnIn elements A1Respectively to
Set B { B1,B2,B3,...,BmIn element B1、B2Have sent request, that is, set B { B1,B2,B3,...,BmIn two
A or multiple and different elements, which can receive, comes from set A { A1, A2, A3,...,AnIn identity element send request.
Optionally, more accurate judging result in order to obtain, can be in the set A to the subscriber data set got
Request element is removed reprocessing, specifically, the multiple request for issuing same subscriber in set A can be merged
Processing obtains not including because the target user repeatedly requested is same user, and to the first of same user's repeat count
Number of users.For example, it is assumed that it is good friend that user A, which will add user B, addition good friend request three times is had sent to user B, because this
The sending object of good friend's request is same user three times, so need to remove the extra repetitive requests twice sent to user B,
It can be to avoid computing repeatedly, so that judging result is more acurrate.Therefore the first number of users is to account number to be detected in the object time
The user that incidence relation is established in request in section carries out the quantity obtained after duplicate removal processing.
Step S220: it obtains the account number to be detected and requests have same channel information in the user for establishing incidence relation
The second user quantity of user.
Optionally, it for obtained the first number of users by duplicate removal processing, needs to judge wherein with the presence or absence of identical
Channel information user, and if it exists, obtain and count the quantity for having the user of same channel information, obtain second user number
Amount is specifically, as follows to the description reference for obtaining second user quantity:
Optionally, as shown in figure 4, step S220 may include:
Step S221: it obtains the account number to be detected and requests have same channel information in the user for establishing incidence relation
User.
Wherein, channel information may include channel number, it is understood that and it is the ID number in the live streaming room of network direct broadcasting platform,
Network direct broadcasting platform includes multiple live streaming rooms, and the room ID number in identical live streaming room is identical, and different live streaming rooms have
Different room ID numbers, i.e. channel ID.As a kind of mode, network direct broadcasting platform can monitor account number request to be detected and establish pass
The behavioral data of connection relationship, and then can identify that account number to be detected requests to have same channel in the user for establishing incidence relation
The user of information.
In one implementation, for example, if account number to be detected request with other users establish friend relation, then when to
It, can be by clicking the live streaming room when one or more users in a certain live streaming room of the desired addition of detection account number are good friend
Online spectators' list, triggering need to be added to good friend user user's head portrait, enter the corresponding personal information of user (or
User information, account etc.) interface can send corresponding carryings and room is broadcast live by triggering " addition good friend " function button
Between the addition good friend of room ID request to server, network direct broadcasting platform is in the addition good friend request being stored in server
Data (including addition good friend's time, addition good friend request text, or addition good friend's frequency etc.) audit, can identify
The room ID in the live streaming room where good friend added by account number to be detected, and then identify in good friend added by account number to be detected
The number of users for having same channel information.
Optionally, the user for having same channel information in the user of incidence relation is established in account number to be detected request, can be with
It is the user for having same channel information in a direct broadcasting room, is also possible to have same channel information in multiple direct broadcasting rooms respectively
User.
In a specific application scenarios, for example, account number A is account number to be detected, if account number A request addition is from same
Direct broadcasting room (direct broadcasting room number are as follows: 875632, it is intended merely to be illustrated the example enumerated, the position of specific direct broadcasting room number here
Number, form and direct broadcasting room number can correspond in different according to the permission and respective level of the account number of network direct broadcasting platform
Hold, be not limited thereto) 100 users be good friend, then account number A request establishes in the user of incidence relation and has same frequency
The user of road information is 100 person-times.If account number A request add different direct broadcasting rooms (direct broadcasting room number is respectively as follows: 7814,7022,
44935, it is good friend that 3451,2082) quantity, which is respectively the user of (10,20,1,8,2), is closed then association is established in account number A request
The user for having same channel information in the user of system is respectively 10 person-times, 20 person-times, 1 person-time, 8 person-times, 2 person-times.
Step S222: using the user with same channel information as a groups of users, if having same channel letter
The number of the groups of users of breath is greater than or equal to two, using the corresponding number of users of the most groups of users of number of users as the
Two numbers of users.
In one implementation, it is assumed that it is good friend that user A, which is added to 10 users from same direct broadcasting room, due to coming
It is identical from the channel information of the user of same direct broadcasting room, therefore the channel information of this 10 users is identical, then can by this 10
A user with same channel information is as a groups of users.And if user A is added in the same time from difference
The user of direct broadcasting room is good friend, for example, 10 users for being added to direct broadcasting room 1 are good friend, is added to 15 users of direct broadcasting room 2
For good friend, 52 users for being added to direct broadcasting room 8 are good friend, in such cases, addition can be come from different live streamings respectively
Between user as a groups of users, then at this time with same channel information groups of users number be more than or equal to two
It is a, it, can be using the corresponding number of users of the most groups of users of number of users as second user in order to improve accuracy in computation
Quantity, i.e., 52 from direct broadcasting room 8 user added user A is as second user quantity.
As a kind of mode, when the good friend of account number to be detected addition is multiple, and good friend added by account number to be detected
From same live streaming room, then the channel information of these added good friends is identical, this in this case, can will have
There is the user of same channel information as a groups of users, and then can be using the corresponding number of users of the groups of users as
Two numbers of users.
Alternatively, when the good friend of account number to be detected addition is multiple, and it is good added by account number to be detected
Friend is from different live streaming rooms, it is understood that there may be multiple groups of users for having same channel information respectively, optionally, if
The number for having the groups of users of same channel information is greater than or equal to two, then user group that can be most by number of users
The corresponding number of users of group is as second user quantity.
Step S230: using first number of users and the second user quantity as behavioural characteristic data.
Optionally, the first number of users and second user quantity can be combined as behavioural characteristic data, to
Network direct broadcasting platform accurately controls the behavior of account number to be detected, and note abnormalities account number in time.
Step S240: judge whether the behavioural characteristic data meet goal condition.
Optionally, the background management system of network direct broadcasting platform can be according to the historical behavior characteristic of account number to be detected
Reliable goal condition is preset, for judging whether behavioural characteristic data meet goal condition.It, can be with as a kind of mode
Configure to the first threshold that is compared with the first number of users, with the ratio of second user quantity and the first number of users into
The second threshold that row compares, and the third threshold value being compared with second user quantity.Therefore, if goal condition may include
First number of users is greater than first threshold, and the ratio of second user quantity and the first number of users is greater than second threshold；Or packet
If including the first number of users less than or equal to first threshold (third threshold value), and second user quantity is greater than the 4th threshold value.It needs
It is bright, due to object time section be it is uncertain, thus correspond to different object time sections, same threshold (such as
First threshold and third threshold value) threshold range in different target time interval can be different.
In one embodiment, if first threshold, second threshold, third threshold value are present in different mesh from the 4th threshold value
It marks in time interval, then judging whether behavioural characteristic data meet goal condition may include: to judge that the first number of users is
Whether the no ratio greater than first threshold and second user quantity and the first number of users is greater than second threshold.If first uses
Amount amount is greater than first threshold, and the ratio of second user quantity and the first number of users is greater than second threshold, then can sentence
Determine behavioural characteristic data and meets goal condition.
Optionally, judging whether behavioural characteristic data meet goal condition can also include: to judge that the first number of users is
It is no whether to be greater than the 4th threshold value no more than third threshold value and second user quantity, wherein third threshold value is greater than the 4th threshold value.
If the first number of users is not more than third threshold value, and second user quantity is greater than the 4th threshold value, then can be determined that behavioural characteristic
Data meet goal condition.
In another embodiment, if first threshold, second threshold and third threshold value are present in the identical object time
In section, then judging whether behavioural characteristic data meet goal condition may include: to judge whether the first number of users is greater than
Whether the ratio of first threshold and second user quantity and the first number of users is greater than second threshold.As a kind of mode, if
First number of users is greater than first threshold, and the ratio of second user quantity and the first number of users is greater than second threshold, then
It can be determined that behavioural characteristic data meet goal condition.Alternatively, if the first number of users is not more than first threshold,
And second user quantity is greater than the 4th threshold value, then can be determined that behavioural characteristic data meet goal condition, wherein first threshold
Greater than the 4th threshold value.
In a specific application scenarios, for example, it is assumed that account number to be detected is A, network direct broadcasting platform has intercepted one point
The number of requests of account number A addition good friend in clock, in 10 minutes, due to being the data in different object time sections, because
This first threshold can be unequal with third threshold value.Optionally, the first number of users and second user quantity can be respectively 30
With 20, first threshold, second threshold, third threshold value, the 4th threshold value can be respectively 20,0.5,32,15.So for target plan
Slightly " judge the first number of users whether be greater than first threshold and second user quantity and the first number of users ratio whether
Greater than second threshold ", since the first number of users 30 is greater than first threshold 20, and second user quantity 20 and the first number of users
30 ratio2/3Greater than second threshold 0.5, therefore it can be determined that behavioural characteristic data meet goal condition；For target strategy
" judging whether the first number of users is not more than third threshold value and whether second user quantity is greater than the 4th threshold value ", due to
One number of users 30 is less than (being not more than) third threshold value 32, and second user quantity 20 is greater than the 4th threshold value 15, therefore can sentence
Determine behavioural characteristic data and meets goal condition.It should be noted that any one satisfaction of the target strategy in this application scene,
It can determine that behavioural characteristic data meet goal condition.
In another specific application scenarios, for example, it is assumed that account number to be detected is A, network direct broadcasting platform has intercepted 30
The number of requests of account number A addition good friend in minute, due to being the data in identical object time section, the first threshold
Value can be equal with third threshold value.Optionally, the first user data and second user data can be respectively 100 and 70, and first
Threshold value, second threshold, third threshold value and the 4th threshold value can be respectively 90,0.6,90 and 88.So for target strategy " judgement
Whether the first number of users is greater than first threshold and second user quantity and whether the ratio of the first number of users is greater than second
Threshold value ", since the first number of users 100 is greater than first threshold 90, and the ratio 0.7 of second user quantity and the first number of users
Greater than second threshold, therefore it can be determined that behavioural characteristic data meet goal condition；It should be noted that for above-mentioned target plan
It slightly, is antagonistic relations since the first number of users is greater than first threshold and the first number of users no more than first threshold, it is right
Data in the same target time interval of interception, two kinds of goal conditions cannot be set up simultaneously, in fact, the arbitrary target time
Data in section, above-mentioned two situations are also mutually contradictory, that is to say, that for the number in arbitrary target time interval
According to a kind of mode that need to only meet above-mentioned strategy can determine that behavioural characteristic data meet goal condition.
It should be noted that first threshold above-mentioned in the present embodiment, second threshold, third threshold value and the 4th threshold value
Each threshold value is adjusted according to the configuration of historical experience value by the background management system of network direct broadcasting platform, so as to quickly send out
Now abnormal account number, effectively prevent user frequently to be harassed.
Step S250: if it is determined that the behavioural characteristic data meet the goal condition, determine that the account number to be detected is
Abnormal account number.
It is understood that if it is determined that obtaining behavioural characteristic data meets goal condition, then then can be determined that be detected
Account number is abnormal account number.
Optionally, if behavioural characteristic data are unsatisfactory for goal condition, terminate the judgement to current behavior characteristic.
The method of the abnormal account number of the detection that the embodiment of the present application proposes, by obtaining account number to be detected in object time section
The first number of users of the interior user for requesting to establish incidence relation；Account number request to be detected is obtained to establish in the user of incidence relation
The second user quantity for having the user of same channel information；Using the first number of users and second user quantity as behavior spy
Levy data；Judge whether behavioural characteristic data meet goal condition；If it is determined that behavioural characteristic data meet goal condition, determine to
Detecting account number is abnormal account number.The behavioural characteristic data that user is passed in and out by obtaining direct broadcasting room configure goal condition by backstage
Strategy judgement screens out abnormal account number, and the account number that quickly notes abnormalities may be implemented, effectively prevent user from frequently being harassed.
Referring to Fig. 5, a kind of flow chart of the method for detection exception account number that the another embodiment of the application provides is shown,
The present embodiment provides a kind of methods for detecting abnormal account number, can be applied to network direct broadcasting platform, this method comprises:
Step S310: behavioural characteristic data of the account number to be detected in object time section, the behavioural characteristic number are obtained
According to characterizing what the account number to be detected was initiated in the object time section, the spy of incidence relation behavior is established with other users
Sign, the behavioural characteristic data include that account number to be detected requests to establish the number of users of incidence relation in object time section.
It should be noted that the present embodiment is suitable for, account number to be detected is there are channel information and there is no the feelings of channel information
Condition.
Optionally, the object time section in the present embodiment characterizes the different time cycles.As a kind of implementation, mesh
Marking time interval can be 1 minute, 10 minutes, 30 minutes, 1 hour, 24 hours etc., then the period can be understood as in the time
It, every 1 minute can be with behavior of poll with behavioural characteristic data of poll, every 10 minutes in one day 24 hours time
Characteristic, every 30 minutes, 1 hour, 24 hours difference can be with behavioural characteristic data of poll, therefore can be according to different need
Ask setting the different time period poll behavioural characteristic data, for example, can network direct broadcasting platform background management system it is pre-
It first sets every 30 minutes and a poll is carried out to all behavioural characteristic data for establishing incidence relation in platform, check whether to deposit
In abnormal account number.It should be noted that 10 minutes durations here are greater than 1 minute, 30 minutes durations were greater than 10 minutes, i.e.,
10 minutes include 1 minute, and 30 minutes include 10 minutes, and so on, network direct broadcasting platform can in this way obtained more accurate
Behavioural characteristic monitored data.
Optionally, behavioural characteristic data may include that account number to be detected requests to establish incidence relation in object time section
Number of users, then, for account number to be detected initiate it is all establish incidence relations request, network direct broadcasting platform backstage pipe
Reason system can obtain the number of users set that incidence relation is established in account number to be detected request in different cycles time interval.Make
For a kind of mode, the mapping relations " A between set can be used1→B{B1,B2,B3,...,Bm" indicate account number to be detected in target
The request total amount of incidence relation is established in the request initiated in time interval.
Step S320: the account number to be detected is requested to establish the request of the user of incidence relation in object time section
Quantity, interval threshold corresponding with the object time section are compared, wherein different object time section institutes is right
The interval threshold answered is different, and the more long corresponding interval threshold in object time section is bigger.
As a kind of mode, the background management system of network direct broadcasting platform can be pre-configured with different target time interval
The number of requests for the user that incidence relation is established in account number to be detected request is compared threshold value with corresponding interval threshold, can
Choosing, the corresponding interval threshold of different time intervals is different, and the more long corresponding interval threshold in object time section is bigger.
In a specific application scenarios, " 1 minute threshold value is δ ", " 10 minutes threshold values are ε ", " 30 minutes can be configured
Threshold value is", " 1 hour threshold value is γ " and " 24 hours threshold values are η ", wherein δ, ε,γ, η characterize the representative symbol of specific value
Number, specific value can configure adjustment by the background management system of network direct broadcasting platform according to the actual situation, optionally,
Step S330: if the number of requests is greater than the corresponding interval threshold in the object time section, determine the row
It is characterized data and meets the goal condition.
Optionally, if number of requests is greater than the corresponding interval threshold in object time section, then can be determined that behavioural characteristic
Data meet goal condition.In one implementation, referring to the description in above-mentioned steps S320, if number of requests is greater than 1 point
Clock threshold value, or it is greater than 10 minutes threshold values, or be greater than 30 minutes threshold values, or be greater than 1 hour threshold value, or be greater than 1 hour threshold value, then
It can be determined that behavioural characteristic data meet goal condition.It should be noted that different target time interval is corresponding in performance
Interval threshold can adjust according to the actual situation, also can be set more or fewer interval thresholds come with number of users into
Row compares.
Step S340: determine that the account number to be detected is abnormal account number.
The method of the abnormal account number of the detection that the present embodiment proposes, by obtaining account number to be detected in object time section
Account number to be detected is requested the number of users for establishing incidence relation, when with target by behavioural characteristic data in object time section
Between the corresponding interval threshold in section be compared, if number of users be greater than the corresponding interval threshold in object time section, determine row
It is characterized data and meets goal condition, determine account number to be detected for abnormal account number, by account number to be detected in object time section
Behavioural characteristic data be compared with the interval threshold in the pre-set object time, can quickly identify malice add
The abnormal account number of plusing good friend.
Referring to Fig. 6, a kind of flow chart of the method for detection exception account number of the application another embodiment offer is provided,
The present embodiment provides a kind of methods for detecting abnormal account number, can be applied to network direct broadcasting platform, this method comprises:
Step S410: behavioural characteristic data of the account number to be detected in object time section, the behavioural characteristic number are obtained
According to characterizing what the account number to be detected was initiated in the object time section, the spy of incidence relation behavior is established with other users
Sign, the behavioural characteristic data include that account number to be detected requests to establish the number of users of incidence relation in object time section.
Step S420: judge whether the behavioural characteristic data meet goal condition.
Step S430: if it is determined that the behavioural characteristic data meet the goal condition, determine that the account number to be detected is
Abnormal account number.
Optionally, if behavioural characteristic data are unsatisfactory for goal condition, terminate the judgement to current behavior characteristic.
Step S440: blacklist is added in the abnormal account number.
Optionally, after determining account number to be detected for abnormal account number, abnormal account number can be punished, as a kind of side
Blacklist can be added in abnormal account number by formula.The abnormal account number that blacklist is added, which cannot execute, establishes incidence relation behavior, to
Incidence relation is established with other users again, needs to carry out authentication.
The method of the abnormal account number of the detection that the present embodiment proposes, by obtaining account number to be detected in object time section
Behavioural characteristic data, then judge whether behavioural characteristic data meet goal condition, if it is determined that behavioural characteristic data meet target
Condition determines account number to be detected for abnormal account number, blacklist is added in abnormal account number, by the behavioural characteristic data of account number to be detected
It is compared with pre-set goal condition, can quickly note abnormalities account number, and blacklist is added in abnormal account number, can be with
Effectively prevent user from frequently being harassed.
Referring to Fig. 7, a kind of flow chart of the method for detection exception account number of the application another embodiment offer is provided,
The present embodiment provides a kind of methods for detecting abnormal account number, can be applied to network direct broadcasting platform, this method comprises:
Step S510: behavioural characteristic data of the account number to be detected in object time section, the behavioural characteristic number are obtained
According to characterizing what the account number to be detected was initiated in the object time section, the spy of incidence relation behavior is established with other users
Sign, the behavioural characteristic data include that account number to be detected requests to establish the number of users of incidence relation in object time section.
Step S520: judge whether the behavioural characteristic data meet goal condition.
Step S530: if it is determined that the behavioural characteristic data meet the goal condition, determine that the account number to be detected is
Abnormal account number.
Optionally, if behavioural characteristic data are unsatisfactory for goal condition, terminate the judgement to current behavior characteristic.
Step S540: when detecting that the abnormal account number establishes incidence relation behavior with other users again, judgement is
It is no that there are the association binding informations of the abnormal account number.
Optionally, when identifying account number to be detected is abnormal account number, if abnormal account number establishes incidence relation behavior again
When, when abnormal account number is initiated to establish the request of incidence relation behavior with other users, the back-stage management system of network direct broadcasting platform
System can intercept the request, detect abnormal account number corresponding to the request and (such as tie up with the presence or absence of association binding information
Determine cell-phone number, mailbox, wechat, QQ etc.), as a kind of mode, it is associated with binding information and is also possible to other association binding informations, example
Such as other instant messaging account numbers.
Step S550: if it exists, indicate that the abnormal account number carries out identifying code verifying.
Optionally, it is associated with binding information if it exists, can identify and by bullet of the user terminal pop-up comprising verification information
Window indicates that abnormal account number is verified.As a kind of mode, it can indicate that abnormal account number carries out identifying code verifying, network direct broadcasting
Application where the background management system of platform can send identifying code to the association binding information of abnormal account number indicates abnormal account number
Corresponding user carries out authentication according to the identifying code received.Optionally, if being verified, then abnormal account number can be again
It is secondary to establish good friend's incidence relation behavior.
Step S560: if it does not exist, indicate that the abnormal account number carries out identity binding.
Optionally, it is associated with binding information if it does not exist, then the background management system of network direct broadcasting platform will indicate exception
Account number carries out identity binding.As a kind of mode, it can indicate that abnormal account number carries out handset binding or mailbox binding etc. and carries out body
Part verifying.
The method of the abnormal account number of the detection that the embodiment of the present application proposes, by obtaining account number to be detected in object time section
Interior behavioural characteristic data, judge whether behavioural characteristic data meet goal condition, if it is determined that behavioural characteristic data meet target
Condition determines account number to be detected for abnormal account number, when detecting that abnormal account number establishes incidence relation behavior with other users again
When, judge whether there is the association binding information of abnormal account number, and if it exists, indicate that abnormal account number carries out identifying code verifying, if not
In the presence of the abnormal account number of instruction carries out identity binding.Can quickly be noted abnormalities account number, be implemented to the behavioural characteristic of abnormal account number
It monitors, can effectively prevent abnormal account number and frequently go harassing and wrecking other users, promote security performance.
Referring to Fig. 8, for a kind of structural block diagram for the device for detecting abnormal account number provided by the embodiments of the present application, this implementation
Example provides a kind of device 600 for detecting abnormal account number, and described device 600 includes: to obtain module 610, judgment module 620 and place
Manage module 630:
Module 610 is obtained, for obtaining behavioural characteristic data of the account number to be detected in object time section, the behavior
Characteristic characterizes what the account number to be detected was initiated in the object time section, establishes incidence relation row with other users
For feature, the behavioural characteristic data include that account number to be detected requests to establish the user of incidence relation in object time section
Quantity.
Wherein, obtaining module 610 may include: first acquisition unit, for obtaining account number to be detected in object time area
The first number of users of the interior user for requesting to establish incidence relation；Second acquisition unit, for obtaining account number request to be detected
It establishes in the user of incidence relation and has the second user quantity of the user of same channel information；Processing unit is used for first
Number of users and second user quantity are as behavioural characteristic data.Wherein, it should be noted that the first number of users is to treat
Detection account number requests the user for establishing incidence relation to carry out the quantity obtained after duplicate removal processing in object time section.
Optionally, second acquisition unit can be used for obtaining account number to be detected and request to have in the user for establishing incidence relation
The user of same channel information；Using the user with same channel information as a groups of users, if having same channel
The number of the groups of users of information be greater than or equal to two, using the corresponding number of users of the most groups of users of number of users as
Second user quantity.
As a kind of mode, acquisition module 610, which can be used for detect, establishes incidence relation behavior with other users
When the channel information of account number is no channel state, using account as account number to be detected；Account number to be detected is obtained in the object time
Behavioural characteristic data in section.
Judgment module 620, for judging whether the behavioural characteristic data meet goal condition.
Optionally, in a kind of specific implement scene, as a kind of mode, judgment module 620 can be used for judging
Whether one number of users is greater than first threshold and second user quantity and whether the ratio of the first number of users is greater than the second threshold
Value；If the first number of users is greater than first threshold, and the ratio of second user quantity and the first number of users is greater than second threshold,
Determine that behavioural characteristic data meet goal condition.
Alternatively, judgment module 620 can be used for judging whether the first number of users is not more than third threshold value,
And whether second user quantity is greater than the 4th threshold value, wherein third threshold value is greater than the 4th threshold value；If the first number of users is little
In third threshold value, and second user quantity is greater than the 4th threshold value, determines that behavioural characteristic data meet goal condition.
As another mode, judgment module 620 can be used for judging whether the first number of users is greater than first threshold, with
And whether second user quantity and the ratio of the first number of users are greater than second threshold；If the first number of users is greater than the first threshold
Value, and the ratio of second user quantity and the first number of users is greater than second threshold, determines that behavioural characteristic data meet target item
Part；If the first number of users is not more than first threshold, and second user quantity is greater than the 4th threshold value, determines that behavioural characteristic data are full
Foot-eye condition, wherein first threshold is greater than the 4th threshold value.
Optionally, in another specific implement scene, judgment module 620 can be used for account number to be detected in target
The number of requests of the user of incidence relation is established in request in time interval, and interval threshold corresponding with object time section is compared
It is right, wherein interval threshold corresponding to different object time sections is different, the more long corresponding interval threshold in object time section
It is bigger；If number of requests is greater than the corresponding interval threshold in object time section, it is possible to determine that behavioural characteristic data meet target item
Part.
Processing module 630, for if it is determined that the behavioural characteristic data meet the goal condition, judgement to be described to be detected
Account number is abnormal account number.
Optionally, processing module 630 further includes processing unit: for blacklist to be added in abnormal account number.
Optionally, processing module 630, which can be used for working as, detects that abnormal account number establishes incidence relation with other users again
When behavior, the association binding information of abnormal account number is judged whether there is, wherein the use that association binding information characterization user has bound
In the communication information of verifying identity；If it exists, indicate that abnormal account number carries out identifying code verifying；If it does not exist, abnormal account number is indicated
Carry out identity binding.
It is apparent to those skilled in the art that for convenience and simplicity of description, foregoing description device and
The specific work process of module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, the mutual coupling of shown or discussed module or direct coupling
It closes or communication connection can be through some interfaces, the indirect coupling or communication connection of device or module can be electrical property, mechanical
Or other forms.
It, can also be in addition, can integrate in a processing module in each functional module in each embodiment of the application
It is that modules physically exist alone, can also be integrated in two or more modules in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.
Referring to Fig. 9, the method and device based on the above-mentioned abnormal account number of detection, the embodiment of the present application also provides one kind
The server 11 of the aforementioned method for detecting abnormal account number can be executed.Server 11 includes memory 112 and intercouples
One or more (one is only shown in figure) processors 114, communication line connects between memory 112 and processor 114.It deposits
The program that can execute content in previous embodiment is stored in reservoir 112, and processor 114 can execute in memory 112
The program of storage.
Wherein, processor 114 may include one or more processing core.Processor 114 utilizes various interfaces and route
The various pieces in entire server 11 are connected, by running or executing the instruction being stored in memory 112, program, code
Collection or instruction set, and the data being stored in memory 112 are called, the various functions and processing data of execute server 11.
Optionally, processor 114 can be compiled using Digital Signal Processing (Digital Signal Processing, DSP), scene
Journey gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable
Logic Array, PLA) at least one of example, in hardware realize.Processor 114 can integrating central processor (Central
Processing Unit, CPU), in image processor (Graphics Processing Unit, GPU) and modem etc.
One or more of combinations.Wherein, the main processing operation system of CPU, user interface and application program etc.；GPU is for being responsible for
Show the rendering and drafting of content；Modem is for handling wireless communication.It is understood that above-mentioned modem
It can not be integrated into processor 114, be realized separately through one piece of communication chip.
Memory 112 may include random access memory (Random Access Memory, RAM), also may include read-only
Memory (Read-Only Memory).Memory 112 can be used for store instruction, program, code, code set or instruction set.It deposits
Reservoir 112 may include storing program area and storage data area, wherein the finger that storing program area can store for realizing operating system
Enable, for realizing at least one function instruction (such as touch function, sound-playing function, image player function etc.), be used for
Realize the instruction etc. of foregoing individual embodiments.The data that storage data area can be created in use with storage server 11
(such as phone directory, audio, video data, chat record data) etc..
Referring to FIG. 10, it illustrates a kind of structural frames of computer readable storage medium provided by the embodiments of the present application
Figure.Program code is stored in the computer readable storage medium 700, said program code can call execution above-mentioned by processor
Method described in embodiment of the method.
Computer readable storage medium 700 can be such as flash memory, EEPROM (electrically erasable programmable read-only memory),
The electronic memory of EPROM, hard disk or ROM etc.Optionally, computer readable storage medium 700 includes non-transient meter
Calculation machine readable medium (non-transitory computer-readable storage medium).Computer-readable storage
Medium 700 has the memory space for the program code 710 for executing any method and step in the above method.These program codes can
With from reading or be written in one or more computer program product in this one or more computer program product.
Program code 710 can for example be compressed in a suitable form.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is contained at least one embodiment or example of the application.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It can be combined in any suitable manner in one or more embodiment or examples.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the feature of different embodiments or examples described in this specification and different embodiments or examples
It closes and combines.
Finally, it should be noted that above embodiments are only to illustrate the technical solution of the application, rather than its limitations；Although
The application is described in detail with reference to the foregoing embodiments, those skilled in the art are when understanding: it still can be with
It modifies the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；And
These are modified or replaceed, do not drive corresponding technical solution essence be detached from each embodiment technical solution of the application spirit and
Range.
Claims (12)
1. a kind of method for detecting abnormal account number, which is characterized in that the described method includes:
Obtain behavioural characteristic data of the account number to be detected in object time section, it is to be checked described in the behavioural characteristic data characterization
It surveys what account number was initiated in the object time section, the feature of incidence relation behavior is established with other users, the behavior is special
Levying data includes that account number to be detected requests to establish the number of users of incidence relation in object time section；
Judge whether the behavioural characteristic data meet goal condition；
If it is determined that the behavioural characteristic data meet the goal condition, determine that the account number to be detected is abnormal account number.
2. the method as described in claim 1, which is characterized in that the row for obtaining account number to be detected in object time section
The step of being characterized data include:
Account number to be detected is obtained to request to establish the first number of users of the user of incidence relation in object time section；
Obtaining the account number to be detected requests have the user of same channel information in the user for establishing incidence relation second to use
Amount amount；
Using first number of users and the second user quantity as behavioural characteristic data.
3. method according to claim 2, which is characterized in that incidence relation is established in the acquisition account number request to be detected
User in have same channel information user second user quantity the step of include:
It obtains the account number to be detected and requests the user for having same channel information in the user for establishing incidence relation；
Using the user with same channel information as a groups of users, if the groups of users with same channel information
Number is greater than or equal to two, using the corresponding number of users of the most groups of users of number of users as second user quantity.
4. method as claimed in claim 2 or claim 3, which is characterized in that described to judge whether the behavioural characteristic data meet mesh
The step of mark condition includes:
Judge whether first number of users is greater than first threshold and the second user quantity and first number of users
Whether the ratio of amount is greater than second threshold；
If first number of users is greater than first threshold, and the ratio of the second user quantity and first number of users
Greater than second threshold, determine that the behavioural characteristic data meet the goal condition.
5. method as claimed in claim 2 or claim 3, which is characterized in that described to judge whether the behavioural characteristic data meet mesh
The step of mark condition includes:
Judge whether first number of users is not more than third threshold value and whether the second user quantity is greater than the 4th threshold
Value, the third threshold value are greater than the 4th threshold value；
If first number of users is not more than third threshold value, and the second user quantity is greater than the 4th threshold value, described in judgement
Behavioural characteristic data meet the goal condition.
6. method according to claim 2, which is characterized in that described to judge whether the behavioural characteristic data meet target item
The step of part includes:
Judge whether first number of users is greater than first threshold and the second user quantity and first number of users
Whether the ratio of amount is greater than second threshold；
If first number of users is greater than first threshold, and the ratio of the second user quantity and first number of users
Greater than second threshold, determine that the behavioural characteristic data meet the goal condition；
If first number of users is not more than first threshold, and the second user quantity is greater than the 4th threshold value, described in judgement
Behavioural characteristic data meet the goal condition, and the first threshold is greater than the 4th threshold value.
7. method according to claim 2, which is characterized in that first number of users be to account number to be detected in target
Between incidence relation is established in request in section user carry out the quantity obtained after duplicate removal processing.
8. the method as described in claim 2 to 7 any one, which is characterized in that described to obtain account number to be detected in target
Between behavioural characteristic data in section the step of include:
When detect with other users establish incidence relation behavior account number channel information for no channel state when, by the account
Number be used as account number to be detected；
Obtain behavioural characteristic data of the account number to be detected in the object time section.
9. the method as described in claim 1, which is characterized in that the behavioural characteristic data include account number to be detected in target
Between in section request establish incidence relation user number of requests, it is described to judge whether the behavioural characteristic data meet target
The step of condition includes:
The number of requests that the account number to be detected is requested to establish in object time section the user of incidence relation, with the mesh
The corresponding interval threshold of mark time interval is compared, wherein interval threshold corresponding to the different object time sections
Difference, the more long corresponding interval threshold in object time section are bigger；
If the number of requests is greater than the corresponding interval threshold in the object time section, determine that the behavioural characteristic data meet
The goal condition.
10. a kind of device for detecting abnormal account number, which is characterized in that described device includes:
Module is obtained, for obtaining behavioural characteristic data of the account number to be detected in object time section, the behavioural characteristic number
According to characterizing what the account number to be detected was initiated in the object time section, the spy of incidence relation behavior is established with other users
Sign, the behavioural characteristic data include that account number to be detected requests to establish the number of users of incidence relation in object time section；
Judgment module, for judging whether the behavioural characteristic data meet goal condition；
Processing module, for if it is determined that the behavioural characteristic data meet the goal condition, the judgement account number to be detected to be
Abnormal account number.
11. a kind of server, which is characterized in that including memory；
One or more processors；
One or more programs are stored in the memory and are configured as being executed by one or more of processors, institute
It states one or more programs and is configured to carry out any method of claim 1-9.
12. a kind of computer readable storage medium, which is characterized in that be stored with program generation in the computer readable storage medium
Code, wherein perform claim requires any method of 1-9 when said program code is run by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811626326.XA CN109495378B (en) | 2018-12-28 | 2018-12-28 | Method, device, server and storage medium for detecting abnormal account |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811626326.XA CN109495378B (en) | 2018-12-28 | 2018-12-28 | Method, device, server and storage medium for detecting abnormal account |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109495378A true CN109495378A (en) | 2019-03-19 |
| CN109495378B CN109495378B (en) | 2021-03-12 |
Family
ID=65713115
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811626326.XA Active CN109495378B (en) | 2018-12-28 | 2018-12-28 | Method, device, server and storage medium for detecting abnormal account |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109495378B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110232473A (en) * | 2019-05-22 | 2019-09-13 | 重庆邮电大学 | A kind of black production user in predicting method based on big data finance |
| CN110418173A (en) * | 2019-07-18 | 2019-11-05 | 北京达佳互联信息技术有限公司 | Determine method, apparatus, server and the storage medium of exception account |
| CN111339436A (en) * | 2020-02-11 | 2020-06-26 | 腾讯科技（深圳）有限公司 | Data identification method, device, equipment and readable storage medium |
| CN113938455A (en) * | 2021-10-13 | 2022-01-14 | 平安银行股份有限公司 | User monitoring method and device of group chat system, electronic equipment and storage medium |
| CN115987579A (en) * | 2022-12-07 | 2023-04-18 | 南京鼎山信息科技有限公司 | Data processing method and data processing system based on big data and Internet of things communication |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101212419A (en) * | 2006-12-25 | 2008-07-02 | 阿里巴巴公司 | Junk message handling method in instant messaging system |
| US20100169970A1 (en) * | 2001-08-16 | 2010-07-01 | Stolfo Salvatore J | System and methods for detecting malicious email transmission |
| CN201985891U (en) * | 2010-12-03 | 2011-09-21 | 北京开心人信息技术有限公司 | System for preventing harassment of strangers in social network |
| US20150052138A1 (en) * | 2013-08-16 | 2015-02-19 | Nexgate, Inc. | Classifying social entities and applying unique policies on social entities based on crowd-sourced data |
| CN104636453A (en) * | 2015-01-29 | 2015-05-20 | 小米科技有限责任公司 | Illegal user data identification method and device |
| CN105592008A (en) * | 2014-10-23 | 2016-05-18 | 腾讯科技（深圳）有限公司 | Method and device for processing user network behavior |
| CN106549974A (en) * | 2016-12-06 | 2017-03-29 | 北京知道创宇信息技术有限公司 | Prediction the social network account whether equipment of malice, method and system |
| CN108280346A (en) * | 2017-01-05 | 2018-07-13 | 腾讯科技（深圳）有限公司 | A kind of application protecting, monitoring method, apparatus and system |
| CN108718271A (en) * | 2018-04-20 | 2018-10-30 | Oppo广东移动通信有限公司 | Processing method, device, storage medium and the terminal of good friend's request |
-
2018
- 2018-12-28 CN CN201811626326.XA patent/CN109495378B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100169970A1 (en) * | 2001-08-16 | 2010-07-01 | Stolfo Salvatore J | System and methods for detecting malicious email transmission |
| CN101212419A (en) * | 2006-12-25 | 2008-07-02 | 阿里巴巴公司 | Junk message handling method in instant messaging system |
| CN201985891U (en) * | 2010-12-03 | 2011-09-21 | 北京开心人信息技术有限公司 | System for preventing harassment of strangers in social network |
| US20150052138A1 (en) * | 2013-08-16 | 2015-02-19 | Nexgate, Inc. | Classifying social entities and applying unique policies on social entities based on crowd-sourced data |
| CN105592008A (en) * | 2014-10-23 | 2016-05-18 | 腾讯科技（深圳）有限公司 | Method and device for processing user network behavior |
| CN104636453A (en) * | 2015-01-29 | 2015-05-20 | 小米科技有限责任公司 | Illegal user data identification method and device |
| CN106549974A (en) * | 2016-12-06 | 2017-03-29 | 北京知道创宇信息技术有限公司 | Prediction the social network account whether equipment of malice, method and system |
| CN108280346A (en) * | 2017-01-05 | 2018-07-13 | 腾讯科技（深圳）有限公司 | A kind of application protecting, monitoring method, apparatus and system |
| CN108718271A (en) * | 2018-04-20 | 2018-10-30 | Oppo广东移动通信有限公司 | Processing method, device, storage medium and the terminal of good friend's request |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110232473A (en) * | 2019-05-22 | 2019-09-13 | 重庆邮电大学 | A kind of black production user in predicting method based on big data finance |
| CN110232473B (en) * | 2019-05-22 | 2022-12-27 | 重庆邮电大学 | Black product user prediction method based on big data finance |
| CN110418173A (en) * | 2019-07-18 | 2019-11-05 | 北京达佳互联信息技术有限公司 | Determine method, apparatus, server and the storage medium of exception account |
| CN110418173B (en) * | 2019-07-18 | 2021-10-08 | 北京达佳互联信息技术有限公司 | Method, device, server and storage medium for determining abnormal account |
| CN111339436A (en) * | 2020-02-11 | 2020-06-26 | 腾讯科技（深圳）有限公司 | Data identification method, device, equipment and readable storage medium |
| CN113938455A (en) * | 2021-10-13 | 2022-01-14 | 平安银行股份有限公司 | User monitoring method and device of group chat system, electronic equipment and storage medium |
| CN115987579A (en) * | 2022-12-07 | 2023-04-18 | 南京鼎山信息科技有限公司 | Data processing method and data processing system based on big data and Internet of things communication |
| CN115987579B (en) * | 2022-12-07 | 2023-09-15 | 南京鼎山信息科技有限公司 | Data processing method and data processing system based on big data and Internet of things communication |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109495378B (en) | 2021-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109495378A (en) | Detect method, apparatus, server and the storage medium of abnormal account number | |
| CN110365996A (en) | Management method, live streaming management platform, electronic equipment and storage medium is broadcast live | |
| CN105808070B (en) | A kind of method and apparatus of setting comment bandwagon effect | |
| CN110442712B (en) | Risk determination method, risk determination device, server and text examination system | |
| US20140344286A1 (en) | Method and apparatus for displaying webcast roomss | |
| CN107979525A (en) | A kind of red packet distribution method, equipment and medium | |
| US20060235932A1 (en) | Chat server mute capability | |
| CN104579912B (en) | Data pushing method and device | |
| WO2014183427A1 (en) | Method and apparatus for displaying webcast rooms | |
| CN106134134B (en) | Product and method for Transit time flow meter | |
| CN109450771A (en) | Add method, apparatus, computer equipment and the storage medium of good friend | |
| CN101562581A (en) | Method and system for achieving web page game | |
| CN104283769B (en) | The user oriented instant message service based on project interested | |
| CN113412607B (en) | Content pushing method and device, mobile terminal and storage medium | |
| CN106105110A (en) | Instant message transmission | |
| CN108377396A (en) | A kind of live streaming method for recording, device and equipment | |
| CN107682328A (en) | A kind of data verification method and client | |
| CN112770129A (en) | Live broadcast-based group chat establishing method, related device, equipment and medium | |
| CN106685800A (en) | Information prompting method and device | |
| CN104967603B (en) | Using account number safety verification method and device | |
| CN104917631A (en) | Prediction initiation, participation and information processing methods, device and system | |
| CN106533923A (en) | Information processing method and device based on instant messaging software | |
| CN113127723A (en) | User portrait processing method, device, server and storage medium | |
| CN106354725B (en) | Event anti-brushing method, device, server and system | |
| CN109729303A (en) | Meeting provides the connection terminal variation in device and described device |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20190319 Assignee: GUANGZHOU CUBESILI INFORMATION TECHNOLOGY Co.,Ltd. Assignor: GUANGZHOU HUADUO NETWORK TECHNOLOGY Co.,Ltd. Contract record no.: X2021440000032 Denomination of invention: Method, device, server and storage medium for detecting abnormal account number License type: Common License Record date: 20210125 |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |