Specific implementation mode
In order to make those skilled in the art better understand the technical solutions in the application, below in conjunction with the application reality
The attached drawing in example is applied, technical solutions in the embodiments of the present application is clearly and completely described, it is clear that described implementation
Example is merely a part but not all of the embodiments of the present application.Based on the embodiment in the application, this field is common
The every other embodiment that technical staff is obtained without creative efforts should all belong to the application protection
Range.
For the risk data in identification network, the embodiment of the present application provides a kind of risk data and determines method and device,
Wherein, risk data determines that method can be executed by the server on backstage, which can be server cluster, can also be
Cloud Server etc..
Fig. 1 is the flow diagram that the risk data that one embodiment of the application provides determines method, as shown in Figure 1, the party
Method includes the following steps:
Step S102 obtains the corresponding risk data list of current business scene;Wherein, risk data list includes risk
User information list and/or Risk Content data list, risk data list are generated based on incidence relation network, the incidence relation
Network is used to indicate the incidence relation between user information and the content-data used by user's distributing content data;
Step S104 determines the corresponding risk data of current business scene according to risk data list.
In the embodiment of the present application, the corresponding risk data list of current business scene is obtained first, then according to the risk
Data list determines the corresponding risk data of current business scene, wherein risk data list includes risk subscribers information list
And/or Risk Content data list, risk data list are generated based on incidence relation network, the incidence relation network is for indicating
Incidence relation between user information used by user's distributing content data and the content-data of user's publication.As it can be seen that passing through
The embodiment of the present application can determine the corresponding wind of current business scene according to the corresponding risk data list of current business scene
Dangerous data, to achieve the purpose that identify the risk data in network.
In the embodiment of the present application, business scenario can be scene of game, financial scenario, social scene etc., different business field
Scape corresponds to different risk data lists, and certainly, different business scene can also correspond to identical risk data list, pass through figure
Flow in 1 can acquire the corresponding risk data list of current business scene, and determination obtains current business scene pair
The risk data answered, the risk data include risk subscribers information and/or Risk Content data.
In the embodiment of the present application, risk data is properly termed as junk data again, and junk data can be information promulgating platform
The rubbish contents data for being not intended to user to issue, or the often junk user account of publication rubbish contents data, these rubbish
Data can be as the risk data in the application example.Rubbish contents data can be exemplified as " arbitrage being spent to add V
123sdf”。
In above-mentioned steps S102, the corresponding risk of current business scene can be obtained according to the mark of current business scene
Data list.Since the corresponding risk data list of current business scene is generated based on incidence relation network, wind is being generated
Before dangerous data list, it is also necessary to build incidence relation network.Method in the embodiment of the present application is further comprising the steps of:
(a1) user information node is generated according to user information used by user's distributing content data, according to the content number
According to generation content-data node;
(a2) according to the incidence relation between user information and content-data, user information node and content-data section are determined
Connection relation between point;
(a3) user information node and content-data node are connected according to the connection relation, generates incidence relation network.
In the embodiment of the present application, incidence relation network includes that user information used by user's distributing content data is corresponding
User information node content-data node corresponding with the content-data, when building incidence relation network, first according to user
User information used by distributing content data generates user information node, wherein user information includes but not limited to user's account
Number, customer equipment identification etc., therefore the corresponding user information node of user information includes but not limited to user account node, user
Device identification node etc..Also, content-data node is generated according to the content-data of user's publication, content-data node is used for table
Show the content-data of user's publication, the content-data of user's publication includes but not limited to contact method etc., which includes
But be not limited to cell-phone number, QQ number, WeChat ID and mailbox etc., therefore content-data node includes but not limited to contact method node.
In the embodiment of the present application, the content-data of user's publication can be obtained according to following manner:It obtains in user's generation
Hold (User Generated Content, UGC), data cleansing is carried out to user-generated content, to be removed from it designated symbols,
Such as ", " "." ", " "/" etc., then the content after data cleansing is converted, for example word figure is converted into Arab
Number, English digital is converted into Arabic numerals, the complex form of Chinese characters is converted to simplified Chinese character, emoji expressions are converted to it is corresponding
Character etc. extracts from the content after data cleansing in turn and obtains contact method, contact method includes cell-phone number, QQ number, wechat
Number and mailbox etc., the content-data that the contact method that extraction obtains is issued as user.Wherein, before extracting contact method,
It can be that corresponding recognition rule is arranged in each contact method, when extracting contact method, be identified and corresponded to according to the recognition rule
Contact method and extraction, for example be that corresponding recognition rule is arranged be 11 bit digitals that " 1 " starts to cell-phone number, to extract hand
Machine number.
After generating user information node and content-data node, then by above-mentioned action (a2), according to user's user information
Incidence relation between content-data determines the connection relation between user information node and content-data node.For example, certain
A user account has issued certain contact method, then the corresponding user information node of the user account is corresponding with this contact method
Content-data node between, publication relationship is there is, that is, there are connection relations.Finally, according to determining connection relation,
User information node and content-data node are connected, incidence relation network is generated.
Fig. 2 a are the schematic diagram for the incidence relation network that one embodiment of the application provides, which is to use with user information node
Family account node, content-data node is illustrate for contact method node, as shown in Fig. 2, user A issues WeChat ID
" 123abc " and WeChat ID " 456def ", WeChat ID " 123abc " also also issue WeChat ID by user B and user's C publications, user D
" 456def " and WeChat ID " mnj789 ".
Fig. 2 b are the schematic diagram for the incidence relation network that another embodiment of the application provides, and the figure is with user information node packet
User account node and customer equipment identification node, content-data node are included to be illustrated for contact method node, is such as schemed
Shown in 2b, user A issues WeChat ID " 123abc " and WeChat ID " 456def " by equipment a, and user B is issued micro- by equipment b
Signal " 123abc ", user C issue WeChat ID " 123abc " by equipment d, and user D issues WeChat ID by equipment c
" 456def " and WeChat ID " mnj789 ".
Further include following action in the embodiment of the present application, according to the incidence relation network built, to generate risk data
List:
(b1) it determines in incidence relation network, the feature of the feature and content-data node of user information node;
(b2) according to the feature of user information node, the corresponding risk subscribers information list of current business scene is generated;
(b3) according to the feature of content-data node, the corresponding Risk Content data list of current business scene is generated;
(b4) it is risk data list by risk subscribers information list and/or Risk Content data name nonoculture.
In above-mentioned action (b1), the feature of user information node in incidence relation network is determined, including:
According to current business scene, chooses at least one following manner (b11) to (b14) and execute:
(b11) data statistics is carried out based on the connection relation that user information node has in incidence relation network, obtained
First statistical nature.
For example, the number of nodes being directly connected in incidence relation network to each user information node counts, it will
A part of the quantity that statistics obtains as the first statistical nature of the user information node, and, to each user information section
The number of nodes that point is indirectly connected in incidence relation network is counted, and the quantity that statistics is obtained is as the user information section
A part for first statistical nature of point.Therefore, the first statistical nature may include user information node in incidence relation network
In the number of nodes that is directly connected to and the number of nodes being indirectly connected with, wherein the node being indirectly connected with can be straight by one
The node that the node connect in succession is connected can also be the node connected by n node, be directly connected to also known as once connecting
Connect, be indirectly connected with also known as n degree connection, n be equal to formed required for this is indirectly connected with by the quantity of node add 1.For example, section
Point A is connect by node B with node C, and node A is exactly two degree of connecting nodes of node C, node A by node B, node C with and
Node D connections, node A are exactly three degree of connecting nodes of node D
In one specific embodiment, number of nodes that each user information node was once being connected in incidence relation network
Amount is counted, and the first quantity is obtained, and, to the node of each user information node two degree of connections in incidence relation network
Quantity is counted, and the second quantity is obtained, using the first quantity and the second quantity as the first statistical nature of user information node.
(b12) it is based on the corresponding user information of user information node and carries out data statistics, obtain content publication relevant the
Two statistical natures.
The corresponding user information of user information node includes user account or user equipment.In the method, the second statistics is special
Sign can be the corresponding user account of user information node or user equipment, the number of distributing content data and the content number of publication
According to the number (namely number of publication Risk Content data) for being identified as Risk Content data, wherein can be by manually assert
Whether the content-data of publication is Risk Content data, for example whether the artificial contact method for assert publication is swindle correspondent party
Formula.
It should be noted that carry out that data statistics can obtain based on the corresponding user information of user information node with it is interior
Hold relevant second statistical nature of publication to will not enumerate here all within the scope of the present embodiment.
(b13) first weight of the user information node in incidence relation network is determined according to PageRank algorithms.
PageRank algorithms arise from the searching order of webpage, Google using the link structure of webpage calculate each webpage etc.
Grade ranking, PageRank algorithm basic ideas are:If a webpage is directed toward by other multiple webpages, this illustrates that the webpage compares
Important or quality is higher.
In the method, based on the graph topological structure of incidence relation network, user's letter is each determined by PageRank algorithms
First weight of the node in incidence relation network is ceased, using the first weight as the feature of the user information node.First weight
Indicate significance level of the user information node in the corresponding network structure of incidence relation network, significance level is higher, the first power
Again bigger, for example, the number of nodes being connect with user information node is more, the significance level of the user information node is higher,
First weight is bigger.
(b14) user information node is determined according to preset risk node in label propagation algorithm and incidence relation network
Second weight.
Label propagation clustering is the semi-supervised learning method based on figure, and basic ideas are that the label of node relies on its neighbour
The label information of node, influence degree are determined by node similarity, and reach stable by propagation iterative update.
In the method, there is preset risk node, which includes risk subscribers information in incidence relation network
Node and/or Risk Content back end, the risk node can be set manually.For example, manually empirically determined have
The user information of risk, such as frequent releasing advertisements user account, and by incidence relation network with the risky user of the tool
The corresponding user information node of information is set as risk subscribers information node, and for another example, artificial empirically determined tool is risky
Content-data, such as by online friend labeled as swindle cell-phone number, and by incidence relation network with the risky content-data of the tool
Corresponding content-data node is set as Risk Content back end.In the present embodiment, risk node includes risk subscribers information
At least one of node and Risk Content back end.
Since label propagation algorithm is the Risk rated ratio for calculating other nodes according to the risk node of setting, artificial
After setting risk node in incidence relation network, according to the risk section set in label propagation algorithm and incidence relation network
Point, it will be able to determine that the second weight of user information node, the second weight indicate that user information node has risky possibility
Size, the second weight is bigger, and user information node more may be risk subscribers information node, i.e. user information node is corresponding
User information more may be the risky risk subscribers information of tool.Wherein, when calculating the second weight, preset wind can be set
The weight of dangerous node is 1.
It in the present embodiment, according to current business scene, determines and executes at least one above (b11) to (b14), with determining
To the feature of user information node in incidence relation network.Under different business scene, it can be chosen not at (b11) to (b14)
With mode execute, to determine the feature of user information node.In one specific embodiment, above (b11) is executed extremely
(b14), the feature of user information node includes:Number of nodes that user information node was once connecting, two degree of connections number of nodes
Amount, the corresponding user account of user information node or user equipment, the number of distributing content data and the content-data quilt of publication
The number for regarding as Risk Content data, the user information node determined according to PageRank algorithms are in incidence relation network
The of first weight, the user information node determined according to preset risk node in label propagation algorithm and incidence relation network
Two weights.
Further, in above-mentioned action (b1), the feature of content-data node in incidence relation network is determined, including:
According to current business scene, chooses at least one following manner (b15) to (b19) and execute:
(b15) data statistics is carried out based on the connection relation that content-data node has in incidence relation network, obtained
Third statistical nature.
Number of nodes similar with mode (b11), that each content-data node is directly connected in incidence relation network
It is counted, obtained quantity will be counted as a part for the third statistical nature of the content-data node, and, to each
The number of nodes that content-data node is indirectly connected in incidence relation network is counted, and the quantity that statistics is obtained is as this
A part for the third statistical nature of content-data node.Therefore, third statistical nature may include that content-data node is closing
The number of nodes being directly connected to and the number of nodes being indirectly connected in connection relational network.It can be with about being directly connected to and being indirectly connected with
The explanation of reference mode (b11).
In one specific embodiment, number of nodes that each content-data node was once being connected in incidence relation network
Amount is counted, and the first quantity is obtained, and, to the node of each content-data node two degree of connections in incidence relation network
Quantity is counted, and the second quantity is obtained, using the first quantity and the second quantity as the third statistical nature of content-data node.
(b16) it is based on the corresponding content-data of content-data node and carries out data statistics, obtain content publication relevant the
Four statistical natures.
In the method, the 4th statistical nature can be the publication number of the corresponding content-data of content-data node, content
The publication number etc. of the corresponding content-data of back end.Such as to " contact method " node, statistics " contact method " is sent out
The number of cloth, publication number of users of duplicate removal etc..
It should be noted that carry out that data statistics can obtain based on the corresponding content-data of content-data node with it is interior
Hold relevant 4th statistical nature of publication to will not enumerate here all within the scope of the present embodiment.
(b17) according to the attribute of the corresponding content-data of content-data node, the corresponding content of content-data node is determined
The attributive character of data.
In the method, according to the attribute of the corresponding content-data of content-data node, determine that content-data node is corresponding
The attributive character of content-data, the attributive character can be that the corresponding content-data of content-data node is cell-phone number, is wechat
Number, the context of the corresponding content-data of content-data node include specific induction word (such as wechat induction word), content-data
The mutation degree etc. of the corresponding content-data of node.Wherein, mutation degree can be the switching time of Chinese English in content-data
The switching times etc. of number, capitalization and lowercase.If the content-data had capitalization number during above-mentioned data cleansing
Word is converted to Arabic numerals or English digital is converted to the process of Arabic numerals, then the mutation degree further includes corresponding turn
Change number.
In one specific embodiment, content-data (such as contact method) is being extracted from the content after data cleansing
Afterwards, the content-data obtained to extraction labels, which includes " content-data is cell-phone number ", " content-data is cardinar number
Word ", " context of content-data includes that wechat induces word " etc., which is the attributive character of content-data.If certain content
Data do not have label, then the content-data can consider no attributive character.Determining the corresponding content number of content-data node
According to attributive character when, using the label of the content-data as its attributive character.
It is and interior it should be noted that the attributive character of the corresponding content-data of content-data node is not limited to example from above
The related feature of attribute for holding data, all can serve as the attributive character of the corresponding content-data of content-data node.
(b18) first weight of the content-data node in incidence relation network is determined according to PageRank algorithms.
In the method, based on the graph topological structure of incidence relation network, content number is each determined by PageRank algorithms
According to first weight of the node in incidence relation network, using the first weight as the feature of the content-data node.First weight
Indicate significance level of the content-data node in the corresponding network structure of incidence relation network, significance level is higher, the first power
Again bigger, for example, the number of nodes being connect with content-data node is more, the significance level of the content-data node is higher,
First weight is bigger.
(b19) content-data node is determined according to preset risk node in label propagation algorithm and incidence relation network
Second weight.
Explanation about preset risk node in label propagation algorithm and incidence relation network can refer to aforementioned activities
(b14) description.
Since label propagation algorithm is the Risk rated ratio for calculating other nodes according to the risk node of setting, artificial
After setting risk node in incidence relation network, according to the risk section set in label propagation algorithm and incidence relation network
Point, it will be able to determine that the second weight of content-data node, the second weight indicate that content-data node has risky possibility
Size, the second weight is bigger, and content-data node more may be Risk Content back end, i.e. content-data node is corresponding
Content-data more may be the risky Risk Content data of tool.Wherein, when calculating the second weight, preset wind can be set
The weight of dangerous node is 1.
It in the present embodiment, according to current business scene, determines and executes at least one above (b15) to (b19), with determining
To the feature of content-data node in incidence relation network.Under different business scene, it can be chosen not at (b15) to (b19)
With mode execute, to determine the feature of content-data node.In one specific embodiment, above (b15) is executed extremely
(b19), the feature of content-data node includes:Number of nodes that content-data node was once connecting, two degree of connections number of nodes
Amount, the number of the corresponding content-data of content-data node being published, the publication number of users of duplicate removal, content-data node correspond to
Content-data attributive character, according to PageRank algorithms determine content-data node in incidence relation network first
Weight, the second power according to the content-data node that preset risk node determines in label propagation algorithm and incidence relation network
Weight.
In the present embodiment, after the feature of the feature and content-data node that determine user information node, above-mentioned action
(b2), according to the feature of user information node, the corresponding risk subscribers information list of current business scene is determined, specially:It will
In incidence relation network, corresponding feature meets the user information node of preset first risk decision rule, is determined as target
User information node;According to the corresponding user information of target user's information node, the corresponding risk of structure current business scene is used
Family information list.Wherein, the first risk decision rule is determined according to current business scene.
Specifically, it according to current business scene, determines the first risk decision rule, is corresponded under different business scene different
First risk decision rule.First risk decision rule is the rule differentiated to the feature of user information node, due to
When determining the feature of user information node, it is determined based on current business scene, and, the first risk decision rule also root
Determine that therefore the first risk decision rule is corresponding with the feature of user information node according to current business scene, it can be using the
One risk decision rule differentiates the feature of user information node.
In one embodiment, the first risk decision rule can be:The number of nodes that user information node was once connecting is super
Cross the corresponding setting value of current business scenario, the number of nodes of two degree of connections is more than the corresponding setting value of current business scene, use
The corresponding user account of family information node or user equipment, the number of distributing content data and the content-data of publication are identified as
The number of Risk Content data is more than the corresponding setting value of current business scene, user information node respectively in incidence relation network
In the first weight be more than the second weight of the corresponding setting value of current business scene and user information node also greater than setting value
The corresponding setting value of current business scene.
In the present embodiment, by incidence relation network, corresponding feature meets the use of preset first risk decision rule
Family information node is determined as target user's information node, then, according to the corresponding user information of target user's information node, structure
Build the corresponding risk subscribers information list of current business scene, wherein risk subscribers information list includes multiple risk subscribers letters
Breath, the corresponding user information of target user's information node, the risk subscribers information for as including in risk subscribers information list.
In the present embodiment, after the feature of the feature and content-data node that determine user information node, above-mentioned action
(b3) according to the feature of content-data node, the corresponding Risk Content data list of current business scene is determined, specially:It will close
Join in relational network, corresponding feature meets the content-data node of preset second risk decision rule, is determined as in target
Hold back end;According to the corresponding content-data of object content back end, the corresponding Risk Content of structure current business scene
Data list.Wherein, the second risk decision rule is determined according to current business scene.
Specifically, it according to current business scene, determines the second risk decision rule, is corresponded under different business scene different
Second risk decision rule.Second risk decision rule is the rule differentiated to the feature of content back end, due to
When determining the feature of content-data node, it is determined based on current business scene, and, the second risk decision rule also root
Determine that therefore the second risk decision rule is corresponding with the feature of content-data node according to current business scene, it can be using the
Two risk decision rules differentiate the feature of content back end.
In one embodiment, the second risk decision rule can be:The number of nodes that content-data node was once connecting is super
Cross the corresponding setting value of current business scenario, the number of nodes of two degree of connections is more than the corresponding setting value of current business scene, interior
The number being published for holding the corresponding content-data of back end is more than the corresponding setting value of current business scene, content-data section
The publication number of users of the duplicate removal of the corresponding content-data of point is more than the corresponding setting value of current business scene, content-data node pair
The attributive character for the content-data answered is attributive character, the first weight of content-data node and that current business scene is specified
Two weights are all higher than the corresponding setting value of current business scene.
In the present embodiment, by incidence relation network, corresponding feature meets the interior of preset second risk decision rule
Hold back end, is determined as object content back end, then, according to the corresponding content-data of object content back end, structure
Build the corresponding Risk Content data list of current business scene, wherein Risk Content data list includes multiple Risk Content numbers
According to, the corresponding content-data of object content back end, the Risk Content data for as including in Risk Content data list.
As can be observed from the foregoing, include risk subscribers information in risk subscribers information list, wrapped in Risk Content data list
Data containing Risk Content, in one embodiment, the risk subscribers information for including in risk subscribers information list includes:Risk subscribers
Account and/or risk subscribers device identification, the Risk Content data for including in Risk Content data list include:Risk correspondent party
Formula.
In above-mentioned steps S104, according to risk data list, the corresponding risk data of current business scene is determined, specifically
For:
Risk data list includes risk subscribers information list;By in current business scene, with risk subscribers information list
In include the consistent user information of risk subscribers information, be determined as the corresponding risk subscribers information of current business scene;It will work as
In preceding business scenario, based on the content-data for the risk subscribers information publication for including in risk subscribers information list, it is determined as working as
The corresponding Risk Content data of preceding business scenario;
And/or
Risk data list includes Risk Content data list;By in current business scene, with Risk Content data list
In include Risk Content data between similarity meet preset similarity require content-data, be determined as current business field
The corresponding Risk Content data of scape;By in current business scene, the Risk Content number for including in Risk Content data list is issued
According to used user information, it is determined as the corresponding risk subscribers information of current business scene.
For example, by current business scene, the use consistent with the risk subscribers account for including in risk subscribers information list
Family account is determined as the corresponding risk subscribers account of current business scene, will be based on the wind for including in risk subscribers information list
The content-data of dangerous user account publication, is determined as the corresponding Risk Content data of current business scene.
For another example, by current business scene, with include in Risk Content data list risk contact method between phase
Meet the contact method preset similarity and required like degree, is determined as the corresponding risk contact method of current business scene;It will be current
In business scenario, the user account that the risk contact method for including in Risk Content data list is based on is issued, is determined as working as
The corresponding risk subscribers account of preceding business scenario.
Wherein it is possible to pass through the phase between two content-datas of similarity of character string algorithm comparison (such as two contact methods)
Like degree.
It, can will be consistent with the risk subscribers account for including in risk subscribers information list in one specific embodiment
User account, the blacklist account being determined as under current business scene will issue the risk for including in Risk Content data list
The user account that contact method is based on, the gray list account being determined as under current business scene, to be realized to user account
Graduate monitoring.
Similarity between the risk contact method for including in Risk Content data list is met default similarity to want
The contact method asked is determined as the corresponding risk contact method of current business scene, can reach similarity absolutely
Contact method, be determined as the corresponding risk contact method of current business scene, can be that similarity is reached into certain threshold value
Contact method is determined as the corresponding risk contact method of current business scene.
Set certain similarity threshold, it is ensured that when user replaces similar contact method publication risk data, energy
Contact method after enough user is replaced identifies, additionally it is possible to ensure extracting contact method from the content after data cleansing
When, if there is the situation of extraction mistake, can be matched by certain similarity threshold come correct risk contact method, than
Such as, WeChat ID " 1234ryt " has been extracted into " 123ryt ", then it, can will be correct by setting certain similarity threshold
Risk contact method " 1234ryt " is identified as the corresponding risk contact method of current business scene.
To sum up, it by the embodiment of the present application, can identify in risk subscribers information and/or the risk under current business scene
Hold data, also, also has the advantages that:
(1) in the embodiment of the present application, the process that risk data list is semi-supervised or unsupervised is established, for example, working as basis
When business scenario determines the feature of user information node, the data of artificial mark are if desired relied on (such as according to artificial mark knot
Fruit determines that the content-data of the corresponding user account publication of user information node is identified as the number of Risk Content data), then
For semi-supervised process, if needing not rely on the data of artificial mark, for unsupervised process.Semi-supervised or unsupervised process tool
There is reality convenient, not exclusively rely on the advantage of artificial treatment, efficiency is established so as to improve risk data list.
(2) Risk Content data are set to risk contact method (when such as cell-phone number, QQ number), due to contact method
Mutation situation is fixed against the update of input method, therefore the mutation situation of contact method is controllable, therefore contact method is arranged
For the object of risk identification, it can achieve the effect that better resistance is different.
(3) when establishing risk data list, the feature of the feature and content-data node of user information node is relied on, by
It is less in the used time of the feature of the feature and content-data node that determine user information node, it is only necessary to reserved data statistics,
The used time of PageRank algorithms, label propagation algorithm, and data statistics, PageRank algorithms, label propagation algorithm are equal
For unsupervised process, therefore risk data list, such as each hour or every day can be regularly updated according to business demand
Update is primary, to improve the iteration efficiency of risk data list, improves the recognition efficiency of risk data.
(4) when establishing risk data list, mainly according to the spy of the feature of user information node and content-data node
Sign, does not depend on the context relation of content-data, therefore to the semantic dependency of content itself in the identification process that can reduce risks,
And risk data is identified by the incidence relation between user-content, to improve risk data under risk data migration situation
Recognition efficiency, wherein risk data migration refers to be after some user account is sealed off, and replacing user account, to continue publication same
After the Risk Content data of sample or some Risk Content data are sealed off, other risks are issued by the same user account
Content-data.
To sum up, by the embodiment of the present application, incidence relation network can be built according to the incidence relation of user-content, into
And generate risk data list, risk data is identified according to risk data list, reach iteration quickly, it is resistance kind, high-precision
Risk data recognition effect.
Fig. 3 is the flow diagram that the risk data that the another embodiment of the application provides determines method, as shown in figure 3, should
Method includes following below scheme:
Step S302, used by building for indicating user's distributing content data between user information and the content-data
Incidence relation incidence relation network;
Step S304 is based on the incidence relation network, generates the corresponding risk data list of current business scene;Wherein,
Risk data list includes risk subscribers information list and/or Risk Content data list;
Step S306 determines the corresponding risk data of current business scene according to risk data list.
In the embodiment of the present application, incidence relation network is built first, then according to incidence relation network, generates current business
The corresponding risk data list of scene determines the corresponding risk data of current business scene finally according to risk data list.It can
See, by the embodiment of the present application, can determine current business scene pair according to the corresponding risk data list of current business scene
The risk data answered, to achieve the purpose that identify the risk data in network.
In above-mentioned steps S302, user information and the content number used by building for indicating user's distributing content data
The incidence relation network of incidence relation between, specifically includes:
(c1) user information node is generated according to user information, content-data node is generated according to content-data;
(c2) according to the incidence relation between user information and content-data, the user information node and described interior is determined
Hold the connection relation between back end;
(c3) the user information node and the content-data node are connected according to the connection relation, generates the pass
Join relational network.
In the present embodiment, incidence relation network includes the content of the corresponding user information node of user information and user's publication
The corresponding content-data node of data;
In above-mentioned steps S304, it is based on the incidence relation network, generates the corresponding risk data list of current business scene,
Specially:
(d1) it determines in incidence relation network, the feature of the feature and content-data node of user information node;
(d2) according to the feature of user information node, the corresponding risk subscribers information list of current business scene is generated;
(d3) according to the feature of content-data node, the corresponding Risk Content data list of current business scene is generated;
(d4) it is risk data list by risk subscribers information list and/or Risk Content data name nonoculture.
It is understood that partial content is similar with previous embodiment in the embodiment of the present application, therefore no longer repeated here
It explains, the detailed process of the embodiment of the present application can refer to the description of previous embodiment.
The case where in view of sharing a risk data list under different business scene, Fig. 4 are another embodiment of the application
The risk data of offer determines the flow diagram of method, as shown in figure 4, this method includes below scheme:
Step S402 obtains the risk data list of risk data for identification;Wherein, risk data list includes risk
User information list and/or Risk Content data list, risk data list are generated based on incidence relation network, incidence relation net
Network is used to indicate the incidence relation between user information and the content-data used by user's distributing content data;
Step S404 identifies risk data according to risk data list.
By the embodiment of the present application, risk data list can be obtained, and risk data is identified according to risk data list,
To achieve the purpose that identify the risk data in network.
The flow in flow and Fig. 1 in Fig. 4 the difference is that, the risk data list involved in Fig. 4 can be each
The general risk data list of business scenario.
Method in the embodiment of the present application further includes:
(e1) user information node is generated according to user information used by user's distributing content data, according to the content number
According to generation content-data node;
(e2) according to the incidence relation between user information and content-data, user information node and content-data section are determined
Connection relation between point;
(e3) user information node and content-data node are connected according to connection relation, generates incidence relation network.
The process is consistent with aforementioned process, is not repeated herein.
In Fig. 4, incidence relation network includes the corresponding user information of user information used by user's distributing content data
Node content-data node corresponding with the content-data;Method in the embodiment of the present application further includes:
(f1) it determines in incidence relation network, the feature of the feature and content-data node of user information node;
During being somebody's turn to do, at least one can be chosen in aforementioned activities (b11) to (b14) according to the first configuration information of acquiescence
Execute, to determine the feature of user information node, and according to the second configuration information of acquiescence aforementioned activities (b15) extremely
(b19) it chooses at least one in execute, to determine the feature of content-data node.The first or second configuration information of the acquiescence can
To be the general configuration information of each business scenario, as chosen in whole actions and (b15) to (b19) in (b11) to (b14)
Whole actions.
(f2) by incidence relation network, corresponding feature meets the user information section of preset third risk decision rule
Point is determined as target user's information node, according to the corresponding user information of target user's information node, builds risk subscribers information
List;
(f3) by the incidence relation network, corresponding feature meets the described interior of preset 4th risk decision rule
Hold back end, be determined as object content back end, according to the corresponding content-data of the object content back end, structure
Risk Content data list;
In process (f2) and (f3), third risk decision rule and the 4th risk decision rule are also that each business scenario is logical
Rule, it is to be understood that third risk decision rule it is corresponding with above-mentioned first configuration information (the two determine characteristic type and
The characteristic type of differentiation is consistent), the 4th risk decision rule (characteristic type that the two determines corresponding with above-mentioned second configuration information
It is consistent with the characteristic type of differentiation), to determine target user's information node by third risk decision rule, pass through the 4th wind
Dangerous decision rule determines object content back end.It, can be by target user's information node in the corresponding embodiment of Fig. 1 to Fig. 4
Corresponding user information, group become risk subscribers information list, and by the corresponding content-data of object content back end, group becomes
Risk Content data list.
(f4) it is risk data list by risk subscribers information list and/or Risk Content data name nonoculture.
In the present embodiment, according to risk data list, risk data is identified, including:
Risk data list includes risk subscribers information list;By with the risk subscribers that include in risk subscribers information list
The consistent user information of information is determined as the risk subscribers information that identification obtains;Will be based on risk subscribers information list in include
The publication of risk subscribers information content-data, be determined as the obtained Risk Content data of identification;
And/or
Risk data list includes Risk Content data list;By with the Risk Content that includes in Risk Content data list
Similarity between data, which meets, presets the content-data that similarity requires, and is determined as the Risk Content data that identification obtains;It will
User information used by the Risk Content data for including in publication Risk Content data list is determined as the risk that identification obtains
User information.
For example, by the user account consistent with the risk subscribers account for including in risk subscribers information list, it is determined as knowing
The risk subscribers account not obtained, by the content number based on the risk subscribers account publication for including in risk subscribers information list
According to being determined as the obtained Risk Content data of identification.
For another example, the similarity between the risk contact method for including in Risk Content data list is met default similar
Desired contact method is spent, the risk contact method that identification obtains is determined as;To include in publication Risk Content data list
The user account that risk contact method is based on is determined as the risk subscribers account that identification obtains.
Wherein it is possible to pass through the phase between two content-datas of similarity of character string algorithm comparison (such as two contact methods)
Like degree.
It, can will be consistent with the risk subscribers account for including in risk subscribers information list in one specific embodiment
User account is determined as the blacklist account that identification obtains, and will issue the risk correspondent party for including in Risk Content data list
The user account that formula is based on is determined as the gray list account that identification obtains, to realize graduate monitoring to user account.
Similarity between the risk contact method for including in Risk Content data list is met default similarity to want
The contact method asked is determined as the risk contact method that identification obtains, can be that similarity is reached absolutely correspondent party
Formula is determined as the risk contact method that identification obtains, can be the contact method that similarity is reached to certain threshold value, be determined as knowing
The risk contact method not obtained.
Set certain similarity threshold, it is ensured that when user replaces similar contact method publication risk data, energy
Contact method after enough user is replaced identifies, additionally it is possible to ensure extracting contact method from the content after data cleansing
When, if there is the situation of extraction mistake, can be matched by certain similarity threshold come correct risk contact method, than
Such as, WeChat ID " 1234ryt " has been extracted into " 123ryt ", then it, can will be correct by setting certain similarity threshold
Risk contact method " 1234ryt " is identified as the risk contact method that identification obtains.
It is understood that partial content is similar with previous embodiment in the embodiment of the present application, therefore no longer repeated here
It explains, the detailed process of the embodiment of the present application can refer to the description of previous embodiment.
Fig. 5 is the module composition schematic diagram for the risk data determining device that one embodiment of the application provides, the device and Fig. 1
In method correspond to, as shown in figure 5, the device includes:
First list acquisition module 51, for obtaining the corresponding risk data list of current business scene;Wherein, the wind
Dangerous data list includes risk subscribers information list and/or Risk Content data list, and the risk data list is based on association
Relational network generates, and the incidence relation network is for indicating user information used by user's distributing content data and the content
Incidence relation between data;
First data determining module 52, for according to the risk data list, determining that the current business scene corresponds to
Risk data.
Optionally, further include network struction module, be used for:
User information node is generated according to the user information, content-data node is generated according to the content-data;
According to the incidence relation between the user information and the content-data, the user information node and institute are determined
State the connection relation between content-data node;
The user information node and the content-data node are connected according to the connection relation, the association is generated and closes
It is network.
Optionally, the incidence relation network includes the corresponding user information node of the user information and the content number
According to corresponding content-data node;
Further include list generation module, is used for:
It determines in the incidence relation network, the spy of the feature of the user information node and the content-data node
Sign;
According to the feature of the user information node, the corresponding risk subscribers information name of the current business scene is generated
It is single;
According to the feature of the content-data node, the corresponding Risk Content data name of the current business scene is generated
It is single;
It is the risk data list by the risk subscribers information list and/or the Risk Content data name nonoculture.
Optionally, the list generation module is specifically used for:
According to the current business scene, chooses at least one following manner and execute, with the determination incidence relation network
Described in user information node feature:
Data statistics is carried out based on the connection relation that the user information node has in the incidence relation network, is obtained
To the first statistical nature;
Data statistics is carried out based on the corresponding user information of the user information node, obtains content publication relevant second
Statistical nature;
First weight of the user information node in the incidence relation network is determined according to PageRank algorithms;
The user information section is determined according to preset risk node in label propagation algorithm and the incidence relation network
Second weight of point;
Wherein, preset risk node includes in the incidence relation network:In risk subscribers information node and/or risk
Hold back end.
Optionally, the list generation module is specifically used for:
According to the current business scene, chooses at least one following manner and execute, with the determination incidence relation network
Described in content-data node feature:
Data statistics is carried out based on the connection relation that the content-data node has in the incidence relation network, is obtained
To third statistical nature;
Data statistics is carried out based on the corresponding content-data of the content-data node, obtains content publication the relevant 4th
Statistical nature;
According to the attribute of the corresponding content-data of the content-data node, determine that the content-data node is corresponding interior
Hold the attributive character of data;
First weight of the content-data node in the incidence relation network is determined according to PageRank algorithms;
The content-data section is determined according to preset risk node in label propagation algorithm and the incidence relation network
Second weight of point;
Wherein, preset risk node includes in the incidence relation network:In risk subscribers information node and/or risk
Hold back end.
Optionally, the list generation module is specifically used for:
By in the incidence relation network, corresponding feature meets the user letter of preset first risk decision rule
Node is ceased, target user's information node is determined as;
According to the corresponding user information of target user's information node, the corresponding risk of the current business scene is built
User information list;
Wherein, the first risk decision rule is determined according to the current business scene.
Optionally, the list generation module is specifically used for:
By in the incidence relation network, corresponding feature meets the content number of preset second risk decision rule
According to node, it is determined as object content back end;
According to the corresponding content-data of the object content back end, the corresponding risk of the current business scene is built
Content-data list;
Wherein, the second risk decision rule is determined according to the current business scene.
Optionally, first data determining module 52 is specifically used for:
The risk data list includes risk subscribers information list;By in the current business scene, with the risk
The consistent user information of the risk subscribers information that includes in user information list, is determined as the corresponding wind of the current business scene
Dangerous user information;By in the current business scene, based on the risk subscribers information for including in the risk subscribers information list
The content-data of publication is determined as the corresponding Risk Content data of the current business scene;
And/or
The risk data list includes Risk Content data list;By in the current business scene, with the risk
Similarity between the Risk Content data for including in content-data list, which meets, presets the content-data that similarity requires, and determines
For the corresponding Risk Content data of the current business scene;By in the current business scene, the Risk Content number is issued
According to user information used by the Risk Content data for including in list, it is determined as the corresponding risk of the current business scene and uses
Family information.
Optionally, the risk subscribers information for including in the risk subscribers information list includes:Risk subscribers account and/or
Risk subscribers device identification;The Risk Content data for including in the Risk Content data list include:Risk contact method.
By the embodiment of the present application, current business can be determined according to the corresponding risk data list of current business scene
The corresponding risk data of scene, to achieve the purpose that identify the risk data in network.
Fig. 6 is the module composition schematic diagram of risk data determining device that another embodiment of the application provides, the device with
Method in Fig. 3 corresponds to, as shown in fig. 6, the device includes:
Network struction module 61, for building for indicating user's distributing content data used by user information and described
The incidence relation network of incidence relation between content-data;
List generation module 62 generates the corresponding risk number of current business scene for being based on the incidence relation network
According to list;Wherein, the risk data list includes risk subscribers information list and/or Risk Content data list;
Second data determining module 63, for according to the risk data list, determining that the current business scene corresponds to
Risk data.
Optionally, the network struction module 61 is specifically used for:
User information node is generated according to the user information, content-data node is generated according to the content-data;
According to the incidence relation between the user information and the content-data, the user information node and institute are determined
State the connection relation between content-data node;
The user information node and the content-data node are connected according to the connection relation, the association is generated and closes
It is network.
Optionally, the incidence relation network includes the corresponding user information node of the user information and the content number
According to corresponding content-data node;
The list generation module 62 is specifically used for:
It determines in the incidence relation network, the spy of the feature of the user information node and the content-data node
Sign;
According to the feature of the user information node, the corresponding risk subscribers information name of the current business scene is generated
It is single;
According to the feature of the content-data node, the corresponding Risk Content data name of the current business scene is generated
It is single;
It is the risk data list by the risk subscribers information list and/or the Risk Content data name nonoculture.
By the embodiment of the present application, current business can be determined according to the corresponding risk data list of current business scene
The corresponding risk data of scene, to achieve the purpose that identify the risk data in network.
Fig. 7 is the module composition schematic diagram of risk data determining device that another embodiment of the application provides, the device with
Method in Fig. 4 corresponds to, as shown in fig. 7, the device includes:
Second list acquisition module 71, the risk data list for obtaining risk data for identification;Wherein, the wind
Dangerous data list includes risk subscribers information list and/or Risk Content data list, and the risk data list is based on association
Relational network generates, and the incidence relation network is for indicating user information used by user's distributing content data and described interior
Hold the incidence relation between data;
Data identification module 72, for according to the risk data list, identifying risk data.
Optionally, further include network struction module, be used for:
User information node is generated according to the user information, content-data node is generated according to the content-data;
According to the incidence relation between the user information and the content-data, the user information node and institute are determined
State the connection relation between content-data node;
The user information node and the content-data node are connected according to the connection relation, the association is generated and closes
It is network.
Optionally, the incidence relation network includes the corresponding user information node of the user information and the content number
According to corresponding content-data node;
Further include list generation module, is used for:
It determines in the incidence relation network, the spy of the feature of the user information node and the content-data node
Sign;
By in the incidence relation network, corresponding feature meets the user letter of preset third risk decision rule
Node is ceased, target user's information node is determined as, according to the corresponding user information of target user's information node, builds risk
User information list;
By in the incidence relation network, corresponding feature meets the content number of preset 4th risk decision rule
According to node, it is determined as object content back end, according to the corresponding content-data of the object content back end, builds risk
Content-data list;
It is the risk data list by the risk subscribers information list and/or the Risk Content data name nonoculture.
Optionally, the data identification module 72 is specifically used for:
The risk data list includes risk subscribers information list;To include with the risk subscribers information list
The consistent user information of risk subscribers information is determined as the risk subscribers information that identification obtains;The risk subscribers will be based on to believe
The content-data for the risk subscribers information publication for including in breath list is determined as the Risk Content data that identification obtains;
And/or
The risk data list includes Risk Content data list;To include with the Risk Content data list
Similarity between Risk Content data, which meets, presets the content-data that similarity requires, and is determined as the Risk Content that identification obtains
Data;By issue include in the Risk Content data list Risk Content data used by user information, be determined as knowing
The risk subscribers information not obtained.
By the embodiment of the present application, risk data list can be obtained, and risk data is identified according to risk data list,
To achieve the purpose that identify the risk data in network.
It should be noted that the device in Fig. 5, Fig. 6, Fig. 7 is corresponding with the method in Fig. 1, Fig. 3, Fig. 4 respectively, therefore energy
It enough realizes the detailed process of preceding method, and there is corresponding advantageous effect, be not repeated herein.
Further, the embodiment of the present application also provides a kind of risk datas to determine that equipment, Fig. 8 are one embodiment of the application
The risk data of offer determines the structural schematic diagram of equipment, as shown in Figure 8.Risk data determine equipment can because configuration or performance not
With and generate bigger difference, may include one or more processor 901 and memory 902, in memory 902
One or more storage application programs or data can be stored with.Wherein, memory 902 can be of short duration storage or lasting
Storage.The application program for being stored in memory 902 may include one or more modules (diagram is not shown), each module
It may include the series of computation machine executable instruction determined to risk data in equipment.Further, processor 901 can be with
It is set as communicating with memory 902, determines that the series of computation machine in executing memory 902 in equipment is executable in risk data
Instruction.Risk data determines that equipment can also include one or more power supplys 903, one or more are wired or wireless
Network interface 904, one or more input/output interfaces 905, one or more keyboards 906 etc..
In a specific embodiment, risk data determine equipment include memory and one or more
Program, either more than one program is stored in memory and one or more than one program may include for one of them
One or more modules, and each module may include determining that the series of computation machine in equipment is executable to risk data
Instruction, and it is configured to by one that either more than one processor executes this or more than one program includes for carrying out
Following computer executable instructions:
Obtain the corresponding risk data list of current business scene;Wherein, the risk data list includes risk subscribers
Information list and/or Risk Content data list, the risk data list are generated based on incidence relation network, and the association is closed
It is that network is used to indicate the incidence relation between user information and the content-data used by user's distributing content data;
According to the risk data list, the corresponding risk data of the current business scene is determined.
Optionally, computer executable instructions when executed, further include:
User information node is generated according to the user information, content-data node is generated according to the content-data;
According to the incidence relation between the user information and the content-data, the user information node and institute are determined
State the connection relation between content-data node;
The user information node and the content-data node are connected according to the connection relation, the association is generated and closes
It is network.
Optionally, when executed, the incidence relation network includes the user information pair to computer executable instructions
The corresponding content-data node of user information node and the content-data answered;Further include:
It determines in the incidence relation network, the spy of the feature of the user information node and the content-data node
Sign;
According to the feature of the user information node, the corresponding risk subscribers information name of the current business scene is generated
It is single;
According to the feature of the content-data node, the corresponding Risk Content data name of the current business scene is generated
It is single;
It is the risk data list by the risk subscribers information list and/or the Risk Content data name nonoculture.
Optionally, computer executable instructions when executed, determine user information described in the incidence relation network
The feature of node, including:According to the current business scene, chooses at least one following manner and execute:
Data statistics is carried out based on the connection relation that the user information node has in the incidence relation network, is obtained
To the first statistical nature;
Data statistics is carried out based on the corresponding user information of the user information node, obtains content publication relevant second
Statistical nature;
First weight of the user information node in the incidence relation network is determined according to PageRank algorithms;
The user information section is determined according to preset risk node in label propagation algorithm and the incidence relation network
Second weight of point;
Wherein, preset risk node includes in the incidence relation network:In risk subscribers information node and/or risk
Hold back end.
Optionally, computer executable instructions when executed, determine content-data described in the incidence relation network
The feature of node, including:According to the current business scene, chooses at least one following manner and execute:
Data statistics is carried out based on the connection relation that the content-data node has in the incidence relation network, is obtained
To third statistical nature;
Data statistics is carried out based on the corresponding content-data of the content-data node, obtains content publication the relevant 4th
Statistical nature;
According to the attribute of the corresponding content-data of the content-data node, determine that the content-data node is corresponding interior
Hold the attributive character of data;
First weight of the content-data node in the incidence relation network is determined according to PageRank algorithms;
The content-data section is determined according to preset risk node in label propagation algorithm and the incidence relation network
Second weight of point;
Wherein, preset risk node includes in the incidence relation network:In risk subscribers information node and/or risk
Hold back end.
Optionally, computer executable instructions when executed, according to the feature of the user information node, described in generation
The corresponding risk subscribers information list of current business scene, including:
By in the incidence relation network, corresponding feature meets the user letter of preset first risk decision rule
Node is ceased, target user's information node is determined as;
According to the corresponding user information of target user's information node, the corresponding risk of the current business scene is built
User information list;
Wherein, the first risk decision rule is determined according to the current business scene.
Optionally, computer executable instructions when executed, according to the feature of the content-data node, described in generation
The corresponding Risk Content data list of current business scene, including:
By in the incidence relation network, corresponding feature meets the content number of preset second risk decision rule
According to node, it is determined as object content back end;
According to the corresponding content-data of the object content back end, the corresponding risk of the current business scene is built
Content-data list;
Wherein, the second risk decision rule is determined according to the current business scene.
Optionally, computer executable instructions when executed, according to the risk data list, determine the current industry
The corresponding risk data of scene of being engaged in, including:
The risk data list includes risk subscribers information list;By in the current business scene, with the risk
The consistent user information of the risk subscribers information that includes in user information list, is determined as the corresponding wind of the current business scene
Dangerous user information;By in the current business scene, based on the risk subscribers information for including in the risk subscribers information list
The content-data of publication is determined as the corresponding Risk Content data of the current business scene;
And/or
The risk data list includes Risk Content data list;By in the current business scene, with the risk
Similarity between the Risk Content data for including in content-data list, which meets, presets the content-data that similarity requires, and determines
For the corresponding Risk Content data of the current business scene;By in the current business scene, the Risk Content number is issued
According to user information used by the Risk Content data for including in list, it is determined as the corresponding risk of the current business scene and uses
Family information.
Optionally, computer executable instructions when executed, use by the risk for including in the risk subscribers information list
Family information includes:Risk subscribers account and/or risk subscribers device identification;The risk for including in the Risk Content data list
Content-data includes:Risk contact method.
By the embodiment of the present application, current business can be determined according to the corresponding risk data list of current business scene
The corresponding risk data of scene, to achieve the purpose that identify the risk data in network.
In a specific embodiment, risk data determine equipment include memory and one or more
Program, either more than one program is stored in memory and one or more than one program may include for one of them
One or more modules, and each module may include determining that the series of computation machine in equipment is executable to risk data
Instruction, and it is configured to by one that either more than one processor executes this or more than one program includes for carrying out
Following computer executable instructions:
Association used by building for indicating user's distributing content data between user information and the content-data
The incidence relation network of relationship;
Based on the incidence relation network, the corresponding risk data list of current business scene is generated;Wherein, the risk
Data list includes risk subscribers information list and/or Risk Content data list;
According to the risk data list, the corresponding risk data of the current business scene is determined.
Optionally, computer executable instructions when executed, are built for indicating that user's distributing content data is used
User information and the content-data between incidence relation incidence relation network, including:
User information node is generated according to the user information, content-data node is generated according to the content-data;
According to the incidence relation between the user information and the content-data, the user information node and institute are determined
State the connection relation between content-data node;
The user information node and the content-data node are connected according to the connection relation, the association is generated and closes
It is network.
Optionally, when executed, the incidence relation network includes the user information pair to computer executable instructions
The user information node and the content-data node answered;
Based on the incidence relation network, the corresponding risk data list of current business scene is generated, including:
It determines in the incidence relation network, the spy of the feature of the user information node and the content-data node
Sign;
According to the feature of the user information node, the corresponding risk subscribers information name of the current business scene is generated
It is single;
According to the feature of the content-data node, the corresponding Risk Content data name of the current business scene is generated
It is single;
It is the risk data list by the risk subscribers information list and/or the Risk Content data name nonoculture.
By the embodiment of the present application, current business can be determined according to the corresponding risk data list of current business scene
The corresponding risk data of scene, to achieve the purpose that identify the risk data in network.
In a specific embodiment, risk data determine equipment include memory and one or more
Program, either more than one program is stored in memory and one or more than one program may include for one of them
One or more modules, and each module may include determining that the series of computation machine in equipment is executable to risk data
Instruction, and it is configured to by one that either more than one processor executes this or more than one program includes for carrying out
Following computer executable instructions:
Obtain the risk data list of risk data for identification;Wherein, the risk data list includes risk subscribers
Information list and/or Risk Content data list, the risk data list are generated based on incidence relation network, and the association is closed
It is that network is used to indicate the incidence relation between user information and the content-data used by user's distributing content data;
According to the risk data list, risk data is identified.
Optionally, computer executable instructions when executed, further include:
User information node is generated according to the user information, content-data node is generated according to the content-data;
According to the incidence relation between the user information and the content-data, the user information node and institute are determined
State the connection relation between content-data node;
The user information node and the content-data node are connected according to the connection relation, the association is generated and closes
It is network.
Optionally, when executed, the incidence relation network includes the user information pair to computer executable instructions
The corresponding content-data node of user information node and the content-data answered;Further include:
It determines in the incidence relation network, the spy of the feature of the user information node and the content-data node
Sign;
By in the incidence relation network, corresponding feature meets the user letter of preset third risk decision rule
Node is ceased, target user's information node is determined as, according to the corresponding user information of target user's information node, builds risk
User information list;
By in the incidence relation network, corresponding feature meets the content number of preset 4th risk decision rule
According to node, it is determined as object content back end, according to the corresponding content-data of the object content back end, builds risk
Content-data list;
It is the risk data list by the risk subscribers information list and/or the Risk Content data name nonoculture.
Optionally, computer executable instructions when executed, according to the risk data list, identify risk data,
Including:
The risk data list includes risk subscribers information list;To include with the risk subscribers information list
The consistent user information of risk subscribers information is determined as the risk subscribers information that identification obtains;The risk subscribers will be based on to believe
The content-data for the risk subscribers information publication for including in breath list is determined as the Risk Content data that identification obtains;
And/or
The risk data list includes Risk Content data list;To include with the Risk Content data list
Similarity between Risk Content data, which meets, presets the content-data that similarity requires, and is determined as the Risk Content that identification obtains
Data;By issue include in the Risk Content data list Risk Content data used by user information, be determined as knowing
The risk subscribers information not obtained.
By the embodiment of the present application, risk data list can be obtained, and risk data is identified according to risk data list,
To achieve the purpose that identify the risk data in network.
It should be noted that the risk data in the present embodiment determine equipment respectively with the method pair in Fig. 1, Fig. 3, Fig. 4
It answers, therefore can realize the detailed process of preceding method, and there is corresponding advantageous effect, be not repeated herein.
Further, the embodiment of the present application also provides a kind of storage medium, for storing computer executable instructions, one
In kind specific embodiment, which can be USB flash disk, CD, hard disk etc., and the computer of storage medium storage is executable
Instruction can realize following below scheme when being executed by processor:
Obtain the corresponding risk data list of current business scene;Wherein, the risk data list includes risk subscribers
Information list and/or Risk Content data list, the risk data list are generated based on incidence relation network, and the association is closed
It is that network is used to indicate the incidence relation between user information and the content-data used by user's distributing content data;
According to the risk data list, the corresponding risk data of the current business scene is determined.
Optionally, the computer executable instructions of storage medium storage further include when being executed by processor:
User information node is generated according to the user information, content-data node is generated according to the content-data;
According to the incidence relation between the user information and the content-data, the user information node and institute are determined
State the connection relation between content-data node;
The user information node and the content-data node are connected according to the connection relation, the association is generated and closes
It is network.
Optionally, the computer executable instructions of storage medium storage are when being executed by processor, the incidence relation
Network includes the corresponding user information node of the user information and the corresponding content-data node of the content-data;
Further include:
It determines in the incidence relation network, the spy of the feature of the user information node and the content-data node
Sign;
According to the feature of the user information node, the corresponding risk subscribers information name of the current business scene is generated
It is single;
According to the feature of the content-data node, the corresponding Risk Content data name of the current business scene is generated
It is single;
It is the risk data list by the risk subscribers information list and/or the Risk Content data name nonoculture.
Optionally, the computer executable instructions of storage medium storage determine the association when being executed by processor
The feature of user information node described in relational network, including:According to the current business scene, choose following manner at least it
One executes:
Data statistics is carried out based on the connection relation that the user information node has in the incidence relation network, is obtained
To the first statistical nature;
Data statistics is carried out based on the corresponding user information of the user information node, obtains content publication relevant second
Statistical nature;
First weight of the user information node in the incidence relation network is determined according to PageRank algorithms;
The user information section is determined according to preset risk node in label propagation algorithm and the incidence relation network
Second weight of point;
Wherein, preset risk node includes in the incidence relation network:In risk subscribers information node and/or risk
Hold back end.
Optionally, the computer executable instructions of storage medium storage determine the association when being executed by processor
The feature of content-data node described in relational network, including:According to the current business scene, choose following manner at least it
One executes:
Data statistics is carried out based on the connection relation that the content-data node has in the incidence relation network, is obtained
To third statistical nature;
Data statistics is carried out based on the corresponding content-data of the content-data node, obtains content publication the relevant 4th
Statistical nature;
According to the attribute of the corresponding content-data of the content-data node, determine that the content-data node is corresponding interior
Hold the attributive character of data;
First weight of the content-data node in the incidence relation network is determined according to PageRank algorithms;
The content-data section is determined according to preset risk node in label propagation algorithm and the incidence relation network
Second weight of point;
Wherein, preset risk node includes in the incidence relation network:In risk subscribers information node and/or risk
Hold back end.
Optionally, the computer executable instructions of storage medium storage are when being executed by processor, according to the user
The feature of information node generates the corresponding risk subscribers information list of the current business scene, including:
By in the incidence relation network, corresponding feature meets the user letter of preset first risk decision rule
Node is ceased, target user's information node is determined as;
According to the corresponding user information of target user's information node, the corresponding risk of the current business scene is built
User information list;
Wherein, the first risk decision rule is determined according to the current business scene.
Optionally, the computer executable instructions of storage medium storage are when being executed by processor, according to the content
The feature of back end generates the corresponding Risk Content data list of the current business scene, including:
By in the incidence relation network, corresponding feature meets the content number of preset second risk decision rule
According to node, it is determined as object content back end;
According to the corresponding content-data of the object content back end, the corresponding risk of the current business scene is built
Content-data list;
Wherein, the second risk decision rule is determined according to the current business scene.
Optionally, the computer executable instructions of storage medium storage are when being executed by processor, according to the risk
Data list determines the corresponding risk data of the current business scene, including:
The risk data list includes risk subscribers information list;By in the current business scene, with the risk
The consistent user information of the risk subscribers information that includes in user information list, is determined as the corresponding wind of the current business scene
Dangerous user information;By in the current business scene, based on the risk subscribers information for including in the risk subscribers information list
The content-data of publication is determined as the corresponding Risk Content data of the current business scene;
And/or
The risk data list includes Risk Content data list;By in the current business scene, with the risk
Similarity between the Risk Content data for including in content-data list, which meets, presets the content-data that similarity requires, and determines
For the corresponding Risk Content data of the current business scene;By in the current business scene, the Risk Content number is issued
According to user information used by the Risk Content data for including in list, it is determined as the corresponding risk of the current business scene and uses
Family information.
Optionally, the computer executable instructions of storage medium storage are when being executed by processor, the risk subscribers
The risk subscribers information for including in information list includes:Risk subscribers account and/or risk subscribers device identification;In the risk
Holding the Risk Content data for including in data list includes:Risk contact method.
By the embodiment of the present application, current business can be determined according to the corresponding risk data list of current business scene
The corresponding risk data of scene, to achieve the purpose that identify the risk data in network.
Further, the embodiment of the present application also provides a kind of storage medium, for storing computer executable instructions, one
In kind specific embodiment, which can be USB flash disk, CD, hard disk etc., and the computer of storage medium storage is executable
Instruction can realize following below scheme when being executed by processor:
Association used by building for indicating user's distributing content data between user information and the content-data
The incidence relation network of relationship;
Based on the incidence relation network, the corresponding risk data list of current business scene is generated;Wherein, the risk
Data list includes risk subscribers information list and/or Risk Content data list;
According to the risk data list, the corresponding risk data of the current business scene is determined.
Optionally, the computer executable instructions of storage medium storage are built when being executed by processor for indicating
The incidence relation network of incidence relation between user information and the content-data used by user's distributing content data, packet
It includes:
User information node is generated according to the user information, content-data node is generated according to the content-data;
According to the incidence relation between the user information and the content-data, the user information node and institute are determined
State the connection relation between content-data node;
The user information node and the content-data node are connected according to the connection relation, the association is generated and closes
It is network.
Optionally, the computer executable instructions of storage medium storage are when being executed by processor, the incidence relation
Network includes the corresponding user information node of the user information and the corresponding content-data node of the content-data;
Based on the incidence relation network, the corresponding risk data list of current business scene is generated, including:
It determines in the incidence relation network, the spy of the feature of the user information node and the content-data node
Sign;
According to the feature of the user information node, the corresponding risk subscribers information name of the current business scene is generated
It is single;
According to the feature of the content-data node, the corresponding Risk Content data name of the current business scene is generated
It is single;
It is the risk data list by the risk subscribers information list and/or the Risk Content data name nonoculture.
By the embodiment of the present application, current business can be determined according to the corresponding risk data list of current business scene
The corresponding risk data of scene, to achieve the purpose that identify the risk data in network.
Further, the embodiment of the present application also provides a kind of storage medium, for storing computer executable instructions, one
In kind specific embodiment, which can be USB flash disk, CD, hard disk etc., and the computer of storage medium storage is executable
Instruction can realize following below scheme when being executed by processor:
Obtain the risk data list of risk data for identification;Wherein, the risk data list includes risk subscribers
Information list and/or Risk Content data list, the risk data list are generated based on incidence relation network, and the association is closed
It is that network is used to indicate the incidence relation between user information and the content-data used by user's distributing content data;
According to the risk data list, risk data is identified.
Optionally, the computer executable instructions of storage medium storage further include when being executed by processor:
User information node is generated according to the user information, content-data node is generated according to the content-data;
According to the incidence relation between the user information and the content-data, the user information node and institute are determined
State the connection relation between content-data node;
The user information node and the content-data node are connected according to the connection relation, the association is generated and closes
It is network.
Optionally, the computer executable instructions of storage medium storage are when being executed by processor, the incidence relation
Network includes the corresponding user information node of the user information and the corresponding content-data node of the content-data;
Further include:
It determines in the incidence relation network, the spy of the feature of the user information node and the content-data node
Sign;
By in the incidence relation network, corresponding feature meets the user letter of preset third risk decision rule
Node is ceased, target user's information node is determined as, according to the corresponding user information of target user's information node, builds risk
User information list;
By in the incidence relation network, corresponding feature meets the content number of preset 4th risk decision rule
According to node, it is determined as object content back end, according to the corresponding content-data of the object content back end, builds risk
Content-data list;
It is the risk data list by the risk subscribers information list and/or the Risk Content data name nonoculture.
Optionally, the computer executable instructions of storage medium storage are when being executed by processor, according to the risk
Data list identifies risk data, including:
The risk data list includes risk subscribers information list;To include with the risk subscribers information list
The consistent user information of risk subscribers information is determined as the risk subscribers information that identification obtains;The risk subscribers will be based on to believe
The content-data for the risk subscribers information publication for including in breath list is determined as the Risk Content data that identification obtains;
And/or
The risk data list includes Risk Content data list;To include with the Risk Content data list
Similarity between Risk Content data, which meets, presets the content-data that similarity requires, and is determined as the Risk Content that identification obtains
Data;By issue include in the Risk Content data list Risk Content data used by user information, be determined as knowing
The risk subscribers information not obtained.
By the embodiment of the present application, risk data list can be obtained, and risk data is identified according to risk data list,
To achieve the purpose that identify the risk data in network.
It should be noted that the storage medium in the present embodiment is corresponding with the method in Fig. 1, Fig. 3, Fig. 4 respectively, therefore energy
It enough realizes the detailed process of preceding method, and there is corresponding advantageous effect, be not repeated herein.
In the 1990s, the improvement of a technology can be distinguished clearly be on hardware improvement (for example,
Improvement to circuit structures such as diode, transistor, switches) or software on improvement (improvement for method flow).So
And with the development of technology, the improvement of current many method flows can be considered as directly improving for hardware circuit.
Designer nearly all obtains corresponding hardware circuit by the way that improved method flow to be programmed into hardware circuit.Cause
This, it cannot be said that the improvement of a method flow cannot be realized with hardware entities module.For example, programmable logic device
(Programmable Logic Device, PLD) (such as field programmable gate array (Field Programmable Gate
Array, FPGA)) it is exactly such a integrated circuit, logic function determines device programming by user.By designer
Voluntarily programming comes a digital display circuit " integrated " on a piece of PLD, designs and makes without asking chip maker
Dedicated IC chip.Moreover, nowadays, substitution manually makes IC chip, this programming is also used instead mostly " patrols
Volume compiler (logic compiler) " software realizes that software compiler used is similar when it writes with program development,
And the source code before compiling also write by handy specific programming language, this is referred to as hardware description language
(Hardware Description Language, HDL), and HDL is also not only a kind of, but there are many kind, such as ABEL
(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description
Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL
(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby
Hardware Description Language) etc., VHDL (Very-High-Speed are most generally used at present
Integrated Circuit Hardware Description Language) and Verilog.Those skilled in the art also answer
This understands, it is only necessary to method flow slightly programming in logic and is programmed into integrated circuit with above-mentioned several hardware description languages,
The hardware circuit for realizing the logical method flow can be readily available.
Controller can be implemented in any suitable manner, for example, controller can take such as microprocessor or processing
The computer for the computer readable program code (such as software or firmware) that device and storage can be executed by (micro-) processor can
Read medium, logic gate, switch, application-specific integrated circuit (Application Specific Integrated Circuit,
ASIC), the form of programmable logic controller (PLC) and embedded microcontroller, the example of controller includes but not limited to following microcontroller
Device:ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320, are deposited
Memory controller is also implemented as a part for the control logic of memory.It is also known in the art that in addition to
Pure computer readable program code mode is realized other than controller, can be made completely by the way that method and step is carried out programming in logic
Controller is obtained in the form of logic gate, switch, application-specific integrated circuit, programmable logic controller (PLC) and embedded microcontroller etc. to come in fact
Existing identical function.Therefore this controller is considered a kind of hardware component, and to including for realizing various in it
The device of function can also be considered as the structure in hardware component.Or even, it can will be regarded for realizing the device of various functions
For either the software module of implementation method can be the structure in hardware component again.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,
Or it is realized by the product with certain function.It is a kind of typically to realize that equipment is computer.Specifically, computer for example may be used
Think personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media play
It is any in device, navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or these equipment
The combination of equipment.
For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each unit is realized can in the same or multiple software and or hardware when application.
It should be understood by those skilled in the art that, embodiments herein can be provided as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, the application can be used in one or more wherein include computer usable program code computer
The computer program production implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The application is with reference to method, the flow of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that can be realized by computer program instructions every first-class in flowchart and/or the block diagram
The combination of flow and/or box in journey and/or box and flowchart and/or the block diagram.These computer programs can be provided
Instruct the processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine so that the instruction executed by computer or the processor of other programmable data processing devices is generated for real
The device for the function of being specified in present one flow of flow chart or one box of multiple flows and/or block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that instruction generation stored in the computer readable memory includes referring to
Enable the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device so that count
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, in computer or
The instruction executed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, computing device includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology realizes information storage.Information can be computer-readable instruction, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic tape cassette, tape magnetic disk storage or other magnetic storage apparatus
Or any other non-transmission medium, it can be used for storage and can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
Including so that process, method, commodity or equipment including a series of elements include not only those elements, but also wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that wanted including described
There is also other identical elements in the process of element, method, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can be provided as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The application can describe in the general context of computer-executable instructions executed by a computer, such as program
Module.Usually, program module includes routines performing specific tasks or implementing specific abstract data types, program, object, group
Part, data structure etc..The application can also be put into practice in a distributed computing environment, in these distributed computing environments, by
Task is executed by the connected remote processing devices of communication network.In a distributed computing environment, program module can be with
In the local and remote computer storage media including storage device.
Each embodiment in this specification is described in a progressive manner, identical similar portion between each embodiment
Point just to refer each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality
For applying example, since it is substantially similar to the method embodiment, so description is fairly simple, related place is referring to embodiment of the method
Part explanation.
Above is only an example of the present application, it is not intended to limit this application.For those skilled in the art
For, the application can have various modifications and variations.It is all within spirit herein and principle made by any modification, equivalent
Replace, improve etc., it should be included within the scope of claims hereof.