Summary of the invention
The embodiment of the present application provides a kind of customer relationship network creating method, can promote the accurate of customer relationship net foundation
Property.
In a first aspect, the embodiment of the present application provides a kind of customer relationship network creating method, this method comprises:
Obtain the central user information of central user and the first user information of the first user;
Attribute information corresponding with preset attribute item in the central user information and the first user information is extracted respectively;
It is preset in the corresponding attribute information of the first preset attribute item of the central user and the first of first user
In the matched situation of the corresponding attribute information of attribute item, determine that first user is the association user of the central user;
The customer relationship net of the central user is established based on the central user and first user.
As an alternative embodiment, the attribute information includes high-quality attribute information and common property information;
The customer relationship net that the central user is established based on the central user and first user, comprising:
Corresponding first attribute information of the first preset attribute item described in first user information is high-quality attribute letter
In the case where breath, first user and the central user are associated by the first interrelational form;
Corresponding first attribute information of the first preset attribute item described in first user information is common property letter
In the case where breath, first user and the central user are associated by the second interrelational form.
As an alternative embodiment, in the association user that the determination first user is the central user
Later, the method also includes:
In the case where first user is non-abnormal user and first attribute information is common property information,
The second user information of second user is obtained, the second user is other than the central user and first user
Other users;
Extract attribute information corresponding with the preset attribute item in the second user information;
There are the corresponding attribute information matchings of the second preset attribute item between first user and the second user
In the case where, determine that the second user is the association user of first user;
It is described the customer relationship net of the central user is established based on the central user and first user after,
The method also includes:
Corresponding second attribute information of the second preset attribute item described in the second user information is high-quality attribute letter
In the case where breath, the second user and first user are associated by the first interrelational form;
Corresponding second attribute information of the second preset attribute item described in the second user information is common property letter
In the case where breath, the second user and first user are associated by the second interrelational form.
As an alternative embodiment, the method also includes: the customer relationship net based on the central user is raw
At the customer relationship figure of the central user, the node in the customer relationship figure indicates user, and different user types uses
Different joint forms indicates, is attached according to the interrelational form between node and node using corresponding connection type.
As an alternative embodiment, generating the center in the customer relationship net based on the central user
After the customer relationship figure of user, the method also includes:
Show the customer relationship figure;
The operational order to the customer relationship figure is received, the corresponding operation of the operational order, the operation are executed
Instruction includes at least one of operational order: showing that the operational order of designated user's information of designated user, display are different
Common family and the operation of the operational order, the risk class for calculating the central user of the shortest path of the central user refer to
It enables.
As an alternative embodiment, the method also includes:
Between number and abnormal user and the central user based on abnormal user in the customer relationship net away from
From calculating the risk class of the central user.
As an alternative embodiment, the method also includes:
Word segmentation processing is carried out to the attribute information of the central user and first user, obtains participle vector;
The feature vector of the central user and the attribute information of first user is determined based on the participle vector;
Calculate the distance between first user feature vector corresponding with the attribute information of the central user;
Distance between the corresponding feature vector of the first preset attribute item of first user and the central user
Less than threshold value, it is determined that there are the corresponding attribute informations of the first preset attribute item between the central user and first user
Matching.
Second aspect, the embodiment of the present application provide a kind of customer relationship net and establish device, which establishes dress
The unit including the method for executing above-mentioned first aspect is set, which establishes device and include:
Acquiring unit, for obtaining the central user information of central user and the first user information of the first user;
Extraction unit, it is corresponding with preset attribute item in the central user information and the first user information for extracting respectively
Attribute information;
First determination unit, for the corresponding attribute information of the first preset attribute item and described the in the central user
In the corresponding matched situation of attribute information of the first preset attribute item of one user, determine first user for center use
The association user at family;
Unit is established, for establishing the customer relationship of the central user based on the central user and first user
Net.
As an alternative embodiment, the attribute information includes high-quality attribute information or common property information;
It is described to establish unit, it is used for corresponding first attribute of the first preset attribute item described in first user information
In the case that information is high-quality attribute information, first user and the central user are closed by the first interrelational form
Connection;
Alternatively,
It is described to establish unit, it is used for corresponding first attribute of the first preset attribute item described in first user information
In the case that information is common property information, first user and the central user are closed by the second interrelational form
Connection.
As an alternative embodiment, the acquiring unit, is also used in first user be non-abnormal user,
And in the case that first attribute information is common property information, the second user information of second user is obtained, described second
User is the other users other than the central user and first user;
The extraction unit is also used to extract attribute letter corresponding with the preset attribute item in the second user information
Breath;
First determination unit is also used between first user and the second user default belong to there are second
Property the matched situation of the corresponding attribute information of item under, determine the second user be first user association user;
It is described to establish unit, it is also used to the second preset attribute item described in the second user information corresponding second and belongs to
Property information be high-quality attribute information in the case where, the second user and first user are carried out by the first interrelational form
Association;
Alternatively,
It is described to establish unit, it is also used to the second preset attribute item described in the second user information corresponding second and belongs to
Property information be common property information in the case where, the second user and first user are carried out by the second interrelational form
Association.
As an alternative embodiment, the method also includes:
Generation unit generates the customer relationship of the central user for the customer relationship net based on the central user
Scheme, the node in the customer relationship figure indicates user, and different user types is indicated using different joint forms, according to section
Point is attached with the interrelational form between node using corresponding connection type.
As an alternative embodiment, the method also includes:
Display unit, for showing the customer relationship figure;
Receiving unit, for receiving the operational order to the customer relationship figure;
Execution unit, for executing the corresponding operation of the operational order, the operational order includes operational order
At least one of: show operational order, display abnormal user and the central user of designated user's information of designated user
Shortest path operational order, calculate the central user risk class operational order.
As an alternative embodiment, the method also includes:
Computing unit, for based on abnormal user in the customer relationship net number and abnormal user and the center
The distance between user calculates the risk class of the central user.
As an alternative embodiment, the method also includes:
Processing unit carries out word segmentation processing for the attribute information to the central user and first user, obtains
Segment vector;
Second determination unit, for determining the attribute of the central user and first user based on the participle vector
The feature vector of information;
Computing unit, for calculate first user feature vector corresponding with the attribute information of the central user it
Between distance;
Second determination unit, it is right in the first preset attribute item of first user and the central user to be also used to
When the distance between feature vector answered is less than threshold value, it is determined that there are first between the central user and first user
The corresponding attribute information matching of preset attribute item.
The third aspect, the embodiment of the present application provide another customer relationship net and establish device, including processor, input are set
Standby, output equipment and memory, the processor, input equipment, output equipment and memory are connected with each other, wherein described to deposit
Reservoir, which is used to store, supports customer relationship net to establish the computer program that device executes the above method, and the computer program includes
Program instruction, the processor are configured for calling described program instruction, the method to execute above-mentioned first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, the computer storage medium
It is stored with computer program, the computer program includes program instruction, and described program instruction is when being executed by processor, to hold
The method of the above-mentioned first aspect of row.
The embodiment of the present application is by obtaining the central user information of central user and the first user information of the first user;It mentions
Take attribute information corresponding with preset attribute item in the central user information and the first user information;The central user with
There are in the corresponding matched situation of attribute information of the first preset attribute item between first user, first user is determined
For the association user of the central user;The user of the central user is established based on the central user and first user
Network of personal connections.It can accurate, various dimensions the customer relationship network for establishing user.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this present specification merely for the sake of description specific embodiment
And be not intended to limit the application.As present specification and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in present specification and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
As used in this specification and in the appended claims, term " if " can be according to context quilt
Be construed to " when ... " or " once " or " in response to determination " or " in response to detecting ".Similarly, phrase " if it is determined that " or
" if detecting [described condition or event] " can be interpreted to mean according to context " once it is determined that " or " in response to true
It is fixed " or " once detecting [described condition or event] " or " in response to detecting [described condition or event] ".
It is a kind of schematic flow diagram of customer relationship network creating method provided by the embodiments of the present application referring to Fig. 1, Fig. 1,
As shown, this method can include:
101: customer relationship net establishes device and obtains the central user information of central user and the first user of the first user
Information.
In the embodiment of the present application, it may include tablet computer, personal digital assistant that customer relationship net, which establishes device,
(Personal Digital Assistant, PDA), mobile internet device (Mobile Internet Device, MID) etc.
Various customer relationship nets establish device, and the embodiment of the present invention is not construed as limiting.
In the embodiment of the present application, above-mentioned central user refers to the user for needing to establish customer relationship net.It uses at above-mentioned center
Family information and the first user information can be stored in the information related with user in customer data base.Above-mentioned customer data base
It can be and creating in the local storage that above-mentioned customer relationship net establishes device.In this case, above-mentioned customer relationship net is built
Local storage can be read directly in vertical device, so that it may obtain the user information of above-mentioned central user and the first user;It is above-mentioned
Central user information and the first user information can also store in the user database server with peripheral hardware, in this case, on
State customer relationship net establish device can to the user database server send read requests, when database server receives this
Read requests then can establish device to above-mentioned customer relationship net and return to the user information of above-mentioned central user and the use of the first user
Family information.Wherein, above-mentioned central user and above-mentioned first user can be any user in above-mentioned customer data base.
In the embodiment of the present application, the user stored in customer data base can be the legitimate user of active typing, at this
In the case of, customer relationship net establishes the server that device is a certain application program, the client that user is installed by local terminal
Before logging in the server, it can become after needing the relevant information of typing to become legitimate user and correlation is initiated by client
Service request.The user is arrived in the user information storage that customer relationship net establishes each legitimate user that device can will acquire
In database.
Optionally, the user for including in customer data base can be to be acquired by the modes such as transaction channel or acquisition image
It arrives.For example, a certain user establishes the product of device by the customer relationship net that bank card purchase is under the jurisdiction of customer relationship net, at this
In the case of, customer relationship net, which establishes device, to issue user information acquisition request to the corresponding financial institution of bank card, then should
The user information can be returned to customer relationship net and establish device by the database of financial institution, to complete adopting for user information
Collection.
102: customer relationship net establishes device and extracts in above-mentioned center user information and the first user information and preset respectively
The corresponding attribute information of attribute item.
It in the embodiment of the present application, can be according to the corresponding business of customer relationship netting gear body or purposes to be established, in advance
Corresponding preset attribute item is set.After getting the user information of user, above-mentioned default category can be extracted from user information
The property corresponding attribute information of item.Such as above-mentioned preset attribute item may include: the essential information of user, inhabitation address, company
Location, Business Name, kinsfolk's information, social relationships etc..Wherein the essential information of above-mentioned user includes the name of user, property
Not, age, passport NO. etc..
Specifically, establishing the user information that device gets above-mentioned central user and the first user in above-mentioned customer relationship net
Afterwards, successively corresponding from each attribute item in above-mentioned preset attribute item is extracted in above-mentioned central user and the user information of the first user
Attribute information, the corresponding attribute information of each preset attribute item to compare above-mentioned central user and the first user comes true
Whether fixed above-mentioned central user and the first user are association user.
It is commented as an example it is assumed that carrying out risk class when above-mentioned customer relationship net is used to provide a loan to above-mentioned central user
Estimate;When for risk class assessment, may include and above-mentioned central user on the influential user of the risk assessment of central user
User at least one relationship therein such as Peer Relationships, kinship, classmate's relationship, neighborhood, friends.Cause
This in that case, above-mentioned preset attribute item may include: home address information, student status information, CompanyAddress's information, work
Information, household register information, social information, kinsfolk's information etc..
103: in the corresponding attribute information of the first preset attribute item and the first of above-mentioned first user of above-mentioned central user
In the matched situation of the corresponding attribute information of preset attribute item, customer relationship net establishes device and determines that above-mentioned first user is above-mentioned
The association user of central user.
In the embodiment of the present application, above-mentioned pre- when being extracted from above-mentioned central user and the user information of the first user
If after the corresponding attribute information of attribute item, successively judging the corresponding attribute information of the first preset attribute item of above-mentioned central user
Whether attribute information corresponding with the first preset attribute item of above-mentioned first user matches, if using in above-mentioned central user and first
Between family, there are the corresponding attribute informations of the first preset attribute item to be mutually matched, it is determined that above-mentioned central user and the first user
Interrelated, i.e., above-mentioned first user is the association user of above-mentioned central user.Wherein above-mentioned first preset attribute item is above-mentioned
Any one attribute item in preset attribute item.
As an alternative embodiment, being extracted from above-mentioned central user and the user information of the first user
After stating the corresponding attribute information of preset attribute item, the corresponding attribute of a attribute item of above-mentioned central user and the first user is believed
Breath carries out word segmentation processing, obtains the corresponding participle vector of respective attribute information;Then according to each of central user and the first user
From attribute information participle vector, obtain the corresponding feature vector of each attribute information.Then, calculate above-mentioned central user with
The distance between each corresponding feature vector between first user;When the distance between above-mentioned corresponding feature vector is small
In threshold value, it is determined that corresponding two attribute informations of above-mentioned corresponding feature vector are mutually matched.It is above-mentioned to further determine that
There are the corresponding attribute informations of above-mentioned first preset attribute item to be mutually matched between central user and the first user.Wherein, above-mentioned
Distance can be the COS distance between feature vector, the Euclidean distance being also possible between feature vector, the embodiment of the present application
This is not construed as limiting.
In a kind of implementation, above-mentioned attribute information can be segmented using the method based on string matching, it should
Method is also referred to as mechanical Chinese word segmentation method, according to the word sequence and a dictionary of certain tactful each sentence by attribute information
In entry matched, if found in dictionary attribute information some character or certain several character group at character string,
Successful match identifies a word.
For example, an above-mentioned attribute information is " Enterprises of Futian District safety mansion ", by mechanical Chinese word segmentation method to the sentence
After being segmented, the available sentence is corresponding to be respectively as follows: Shenzhen, Futian District, safety mansion.It is understood that
It is in above-mentioned implementation, to be segmented to obtain all participles to attribute information, it is meant that each word in attribute information wraps
It is contained in some participle.Certainly, the method segmented to attribute information is not limited to this.
As an alternative embodiment, determining the term vector of each participle, it can specifically include: passing through word2vec
Training obtains the term vector of each participle.
Word2vec is the efficient tool for word to be characterized as to real number term vector.Specifically, word2vec passes through CBoW
Word is mapped as a K dimensional vector by network or Skip-gram network, and K dimensional vector is generally high dimension vector, as K can be with value
400 or the biggish integer of other numeric ratios.CBoW model or Skip-gram model assume that word and surrounding several words have
Association, and word is contained in the term vector for not considering the ordinal relation of several words around, thus obtaining by word2vec training
Syntax and semantic feature.
As an alternative embodiment, obtaining the corresponding feature of attribute information according to the participle vector of attribute information
Vector can specifically include: the participle vector of above-mentioned attribute information being input to feature vector and is generated in model, above-mentioned category is exported
The property corresponding feature vector of information.Wherein features described above vector, which generates model, can be trained Recognition with Recurrent Neural Network.This is followed
Ring neural network can be what the mode training for using the attribute information training sample being mutually matched to pass through supervised learning obtained.
104: customer relationship net establishes device and establishes above-mentioned central user based on above-mentioned central user and above-mentioned first user
Customer relationship net.
In the embodiment of the present application, above-mentioned attribute information may include high-quality attribute information or common property information, when upper
When stating the type difference of the corresponding attribute information of the attribute information being mutually matched between central user and the first user, it can use
Above-mentioned first user and central user are associated by different interrelational forms.So that generating above-mentioned central user
Customer relationship network after, corresponding business can be carried out to above-mentioned central user by above-mentioned customer relationship net various dimensions
Processing.Such as it can be by being calculated in customer relationship net by the number of the associated user of the corresponding interrelational form of high-quality attribute
The credit grade of central user.
Wherein, above-mentioned high-quality attribute information indicates: when being because there is the high-quality attribute letter to match between two users
When ceasing and determining incidence relation, then when carrying out business processing (such as risk assessment or credit evaluation etc.), two users it
Between will not cause negative impact to other side mutually.Above-mentioned common property information indicates: when being because existing between two users
The common property information that matches and when determining incidence relation, then when carrying out business processing, (such as risk assessment or credit are commented
Estimate), negative impact may be caused to other side between two users.
Specifically, judging the first attribute item after determining above-mentioned first user is the association user of above-mentioned central user
Whether the attribute information of corresponding first user is high-quality attribute information, if the attribute of corresponding first user of the first attribute item is believed
Breath is high-quality attribute information, then is associated above-mentioned first user by the first interrelational form and above-mentioned central user, has given birth to
At the customer relationship network of central user;If the attribute information of corresponding first user of the first attribute item is common property information,
Then above-mentioned first user is associated by the second interrelational form and above-mentioned central user, the user for having generated central user is closed
It is network.
Wherein, above-mentioned first interrelational form refers to when matched attribute information is high-quality attribute between determining user and user
When information, two two users are indicated into two use plus the user identifier with two users using preset high-quality mark
Relevance between family.Such as assume the above-mentioned preset high-quality character string for being identified as " youzhi ", the user identifier of a user is
The user identifier of A, b user are B;Then a user and b user are associated by the first interrelational form can use (youzhi, A
And B) built-in value to indicating, key is the type of the match attribute information between two association users, is worth for two users'
User identifier.Above-mentioned second interrelational form is similar with above-mentioned first interrelational form, is not repeating.
In the embodiment of the present application, in order to which the type for distinguishing the match attribute that central user is associated between user is different
The category between the user and user in customer relationship net using different interrelational forms, to state central user in use
Property information type come when handling specific business, can directly by the interrelational form between central user and association user just
The type of the match attribute information between them can be quickly determined, to more effectively handle specific business.
It is understood that above-mentioned first user is any use other than central user in above-mentioned customer data base
Family.It therefore, can be by method identical with the first user by above-mentioned user after being associated with the first user with central user
The association user of other central users is associated with central user in database, is more completely used to obtain central user
Family relational network.
As can be seen that the embodiment of the present application is by obtaining the central user information of central user and the first use of the first user
Family information;Extract attribute information corresponding with preset attribute item in above-mentioned center user information and the first user information;Above-mentioned
There are in the corresponding matched situation of attribute information of the first preset attribute item between central user and above-mentioned first user, in determination
State the association user that the first user is above-mentioned central user;Above-mentioned center is established based on above-mentioned central user and above-mentioned first user
The customer relationship net of user.It can accurate, various dimensions the customer relationship network for establishing user.
Referring to fig. 2, Fig. 2 is the exemplary flow of another customer relationship network creating method provided by the embodiments of the present application
Figure, as shown, this method can include:
201: customer relationship net establishes device and obtains the central user information of central user and the first user of the first user
Information.
202: customer relationship net establishes device and extracts in above-mentioned center user information and the first user information and preset respectively
The corresponding attribute information of attribute item.
203: in the corresponding attribute information of the first preset attribute item and the first of above-mentioned first user of above-mentioned central user
In the matched situation of the corresponding attribute information of preset attribute item, customer relationship net establishes device and determines that above-mentioned first user is above-mentioned
The association user of central user.
204: customer relationship net establishes device and establishes above-mentioned central user based on above-mentioned central user and above-mentioned first user
Customer relationship net.
In the embodiment of the present application, above-mentioned steps 201-204 is similar with the step 101-104 in above-mentioned real-time example 1, therefore
Can be with reference to the step 101-104 in above-mentioned real-time example 1, details are not described herein again.
205: above-mentioned first user be non-abnormal user, and above-mentioned first attribute information be common property information the case where
Under, customer relationship net establish device obtain second user second user information, extract in above-mentioned second user information with it is above-mentioned
The corresponding attribute information of preset attribute item.
Wherein, above-mentioned second user is the other users other than above-mentioned central user and above-mentioned first user.
In real life, there may also be a kind of indirect incidence relation between user and user, i.e., two uncorrelated
User between can also pass through intermediate user and generate incidence relation, the intermediate user and above-mentioned two incoherent user
Association user each other.For example, it is assumed that being to be not directly relevant to join between the classmate and colleague of central user, but in some occasions
Under, between the colleague and classmate of user, incidence relation can be generated by the central user.For example, the classmate of central user to
Central user is borrowed money, and central user temporarily it is out of funds lend classmate, then borrow money to colleague, then lend the money borrowed to colleague
Classmate is then a kind of indirect debition between classmate and colleague at this time.
Therefore, in the embodiment of the present application, when by the association user of above-mentioned central user and above-mentioned center user-association it
Afterwards, the association user of the association user of above-mentioned central user can also be also associated in above-mentioned customer relationship network.
In addition, when carrying out business processing (such as risk assessment, credit evaluation etc.), to the center in customer relationship network
User is influential generally abnormal user (such as user that prestige is bad or risk class is high), therefore, is determining whether to
When the association user of association user is associated in above-mentioned customer relationship net, it can be determined that the association user of central user whether be
Abnormal user, if so, have determined that the association user can adversely affect central user, it also just need not be further
The association user of the association user of the exception is associated in above-mentioned customer relationship net;If non-abnormal user, then should determine
Whether central user can be influenced by the non-abnormal user with the non-associated abnormal user of abnormal user;If it exists,
Then explanation if it does not exist, then illustrates it is necessary to which the association user of the non-abnormal user to be associated in above-mentioned customer relationship network
It is not necessary to which the association user of the non-abnormal user is associated in above-mentioned customer relationship network.
As an alternative embodiment, when whether judge user is abnormal user, can by obtain one with
Then the blacklist at family judges whether the user is abnormal user by the blacklist.
Since the relevance between user and user is determined by the attribute information between user and user, that is,
It is that incidence relation is generated by the corresponding attribute of the attribute information being mutually matched between the two between user and user;Cause
This can be by between the non-abnormal user and central user when the association user of above-mentioned central user is non-abnormal user
The attribute information to match come determine be whether can be by the non-abnormal user with the non-associated abnormal user of abnormal user
To influence central user.I.e. when the attribute information to match between the non-abnormal user and central user is common property information
When, it is determined that central user can be influenced by the non-abnormal user with the non-abnormal user associated abnormal user;When
When the attribute information to match between the non-abnormal user and central user is high-quality attribute information, it is determined that with the non-abnormal use
The associated abnormal user in family cannot influence central user by the non-abnormal user.
To sum up, in the embodiment of the present application, it is established among the above above-mentioned based on above-mentioned central user and above-mentioned first user
After the customer relationship net of heart user, judge whether above-mentioned first user in above-mentioned customer relationship network is abnormal user, if
Above-mentioned first user is non-abnormal user, then judges that the attribute information being mutually matched between above-mentioned first user and central user is
It is no be common property information, if so, obtain second user second user information, extract in above-mentioned second user information with it is upper
The corresponding attribute information of preset attribute item is stated, if not then terminating.
206: there are the corresponding attribute informations of the second preset attribute item between above-mentioned first user and above-mentioned second user
In matched situation, customer relationship net establishes device and determines that above-mentioned second user is the association user of above-mentioned first user.
In the embodiment of the present application, right when extracting above-mentioned preset attribute item in the user information from above-mentioned second user
After the attribute information answered, successively judges that the above-mentioned preset attribute item between above-mentioned second user and above-mentioned first user is corresponding and belong to
Property information whether match, if there are the second preset attribute item corresponding attribute letters between above-mentioned second user and the first user
Breath is mutually matched, it is determined that above-mentioned second user and the first user are interrelated, i.e., above-mentioned second user is above-mentioned first user
Association user.Wherein above-mentioned second preset attribute item is any one attribute item in above-mentioned preset attribute item.
In the embodiment of the present application, the specific embodiment in the step can be with reference to the step in above-described embodiment 1
103, details are not described herein again.
207: customer relationship net establishes device and is associated second user and the first user.
It in the embodiment of the present application, will after it is the association user of above-mentioned first user that above-mentioned second user, which has been determined,
Second user is associated with the first user.
Specifically, corresponding second attribute information of above-mentioned second preset attribute item is high-quality in above-mentioned second user information
In the case where attribute information, above-mentioned second user and above-mentioned first user are associated by the first interrelational form.Above-mentioned
In the case that corresponding second attribute information of above-mentioned second preset attribute item is common property information in second user information, pass through
Above-mentioned second user and above-mentioned first user are associated by the second interrelational form.
As an alternative embodiment, by the non-abnormal association user in above-mentioned customer relationship net according to matched category
The type (high-quality attribute information, common property information) of property information is divided into high-quality association user, common association user.It is incited somebody to action above-mentioned
It, can also be further by the association of above-mentioned second user and association user later after second user and the first user-association
User-association into above-mentioned customer relationship network, until common association user all in above-mentioned customer relationship association user all
It is associated in above-mentioned customer relationship network to form complete detailed customer relationship network, specific correlating method and above-mentioned by the
Two user-associations are identical into above-mentioned customer relationship network.
208: customer relationship net establishes device and generates above-mentioned central user based on the customer relationship net of above-mentioned central user
Customer relationship figure.
In the embodiment of the present application, it after establishing the customer relationship net of above-mentioned central user, is used based on above-mentioned center
The customer relationship net at family generates the customer relationship figure of above-mentioned central user, and shows above-mentioned customer relationship figure.Wherein, above-mentioned user
Node in relational graph indicates user, and different user types is indicated using different joint forms, according to node and node it
Between interrelational form be attached using corresponding connection type;So as to make administrator quickly true by the customer relationship figure
The incidence relation to center between user and each association user, and quickly identify the type of each association user.
Specifically, according to the user type of above-mentioned customer relationship net (including central user, abnormal association user, high-quality pass
Be combined family, common association user), interrelational form generate customer relationship figure, the node in above-mentioned customer relationship figure indicates user, no
Same user type indicates that different interrelational forms is indicated with different lines with different symbols.As shown in figure 3, root node
For center user;Dotted line indicates the connection type of high-quality attribute information, i.e., above-mentioned first connection type;Solid line indicates common association
The connection type of attribute information, i.e., above-mentioned second connection type;The label of space rectangles frame expression common association user;Shade square
Shape indicates the label of abnormal association user;Circle indicates the label of high-quality association user.
209: customer relationship net establishes device and receives operational order to above-mentioned customer relationship figure, executes aforesaid operations and refers to
Enable corresponding operation.
In the embodiment of the present application, it after generating above-mentioned customer relationship figure, can receive for above-mentioned customer relationship figure
Operational order, be then responding to aforesaid operations instruction, triggering aforesaid operations instruct corresponding operation.Wherein, aforesaid operations instruct
Including at least one of operational order once: showing that the operational order of designated user's information of designated user, display are abnormal and use
The operational order at family and the operational order of the shortest path of above-mentioned central user, the risk class of the above-mentioned central user of calculating.
As an alternative embodiment, the operational order of designated user's information of above-mentioned display designated user specifically may be used
To be the user tag for receiving administrator and being clicked in above-mentioned customer relationship figure.Receiving the specified of above-mentioned display designated user
After the operational order of user information, determine the user identifier of the user tag being clicked, then by user identifier from
The user information that the user is obtained in the information bank of family is displayed next to the user got in the user tag in the form of dialog box
Information.
As an alternative embodiment, the operation of the shortest path of above-mentioned display abnormal user and above-mentioned central user
Instruction, which specifically can be, receives administrator in preset shortest path the Show Button of administration interface click of system, on receiving
After the operational order for stating the shortest path of display abnormal user and above-mentioned central user, obtain different in above-mentioned customer relationship net
Common family, then calculate the distance between abnormal user and central user in above-mentioned customer relationship figure, will finally be calculated
Shortest be highlighted in above-mentioned customer relationship figure between corresponding abnormal user and central user shows in above system
Show interface.
Wherein, abnormal association user is associated in above-mentioned customer relationship figure extremely with the distance between above-mentioned central user finger
The distance between user node and central user node;For example, if exception association user A is the association user of center user, i.e.,
It is directly connect with central user in customer relationship figure, then exception the distance between association user A and central user are 1, if different
Normal association user A is connect by intermediate user B with customer center user, then between exception association user A and central user away from
From being 2.
As an alternative embodiment, the operation in the risk class for receiving the above-mentioned central user of above-mentioned calculating refers to
After order, number, risk information and the abnormal user and above-mentioned center for counting the abnormal user in above-mentioned customer relationship figure are used
The distance between family.Then according to the number of the abnormal association user in above-mentioned customer relationship figure, risk information and abnormal pass
It is combined the risk class that the distance between family and above-mentioned central user calculate above-mentioned central user.
The specific calculation of the risk class of central user is as follows:
Wherein, P indicates the risk class of central user;I indicates i-th of abnormal association user;N indicates of abnormal user
Number;RiIndicate the risk class of i-th of abnormal association user;KiIndicate that i-th of abnormal association user is in customer relationship figure
The distance between heart user weight, when the more big then distance weighting of the distance between abnormal association user and central user more
It is small.
As can be seen that the embodiment of the present application is by obtaining the central user information of central user and the first use of the first user
Family information;Extract attribute information corresponding with preset attribute item in above-mentioned center user information and the first user information;Above-mentioned
There are in the corresponding matched situation of attribute information of the first preset attribute item between central user and above-mentioned first user, in determination
State the association user that the first user is above-mentioned central user;Above-mentioned center is established based on above-mentioned central user and above-mentioned first user
The customer relationship net of user.After establishing customer relationship net, according to customer relationship net generate customer relationship figure, then according to
The risk class of family relational graph calculating central user.It, can accurate, various dimensions the use for establishing user by the embodiment of the present application
Family relational network, and administrator can also be made quickly to identify abnormal user from customer relationship figure.
The embodiment of the present application also provides a kind of customer relationship net and establishes device, which establishes device for executing
The unit of any one of aforementioned method.Specifically, referring to fig. 4, Fig. 4 is that a kind of customer relationship net provided by the embodiments of the present application is built
The schematic block diagram of vertical device.It includes: acquiring unit 410, extraction unit 420, that the customer relationship net of the present embodiment, which establishes device,
One determination unit 430 establishes unit 440.
Acquiring unit 410, for obtaining the central user information of central user and the first user information of the first user;
Extraction unit 420, for extract respectively in above-mentioned center user information and the first user information with preset attribute item
Corresponding attribute information;
First determination unit 430, in above-mentioned central user the corresponding attribute information of the first preset attribute item with
In the corresponding matched situation of attribute information of the first preset attribute item for stating the first user, determine that above-mentioned first user is among the above
The association user of heart user;
Unit 440 is established, for establishing the user of above-mentioned central user based on above-mentioned central user and above-mentioned first user
Network of personal connections.
As an alternative embodiment, above-mentioned attribute information includes high-quality attribute information or common property information;
It is above-mentioned to establish unit 440, for the above-mentioned first preset attribute item corresponding first in above-mentioned first user information
In the case that attribute information is high-quality attribute information, by the first interrelational form by above-mentioned first user and above-mentioned central user into
Row association;
Alternatively,
It is above-mentioned to establish unit 440, for the above-mentioned first preset attribute item corresponding first in above-mentioned first user information
In the case that attribute information is common property information, by the second interrelational form by above-mentioned first user and above-mentioned central user into
Row association.
As an alternative embodiment, above-mentioned acquiring unit 410, is also used in above-mentioned first user be non-abnormal use
Family, and in the case that above-mentioned first attribute information is common property information, obtains the second user information of second user, and above-mentioned the
Two users are the other users other than above-mentioned central user and above-mentioned first user;
Said extracted unit 420 is also used to extract category corresponding with above-mentioned preset attribute item in above-mentioned second user information
Property information;
Above-mentioned first determination unit 430 is also used between above-mentioned first user and above-mentioned second user pre- there are second
If in the matched situation of the corresponding attribute information of attribute item, determining that above-mentioned second user is the association user of above-mentioned first user;
It is above-mentioned to establish unit 440, it is also used to the above-mentioned second preset attribute item in above-mentioned second user information corresponding
In the case that two attribute informations are high-quality attribute information, by the first interrelational form by above-mentioned second user and above-mentioned first user
It is associated;
Alternatively,
It is above-mentioned to establish unit 440, it is also used to the above-mentioned second preset attribute item in above-mentioned second user information corresponding
In the case that two attribute informations are common property information, by the second interrelational form by above-mentioned second user and above-mentioned first user
It is associated.
As an alternative embodiment, the above method further include:
Generation unit generates the customer relationship of above-mentioned central user for the customer relationship net based on above-mentioned central user
Scheme, the node in above-mentioned customer relationship figure indicates user, and different user types is indicated using different joint forms, according to section
Point is attached with the interrelational form between node using corresponding connection type.
As an alternative embodiment, the above method further include:
Display unit, for showing above-mentioned customer relationship figure;
Receiving unit, for receiving the operational order to above-mentioned customer relationship figure;
Execution unit instructs corresponding operation for executing aforesaid operations, and aforesaid operations instruction includes operational order
At least one of: show operational order, display abnormal user and the above-mentioned central user of designated user's information of designated user
Shortest path operational order, calculate above-mentioned central user risk class operational order.
As an alternative embodiment, in the above method further include:
Computing unit, for based on abnormal user in above-mentioned customer relationship net number and abnormal user and above-mentioned center
The distance between user calculates the risk class of above-mentioned central user.
As an alternative embodiment, the above method further include:
Processing unit carries out word segmentation processing for the attribute information to above-mentioned central user and above-mentioned first user, obtains
Segment vector;
Second determination unit, for determining the attribute of above-mentioned central user and above-mentioned first user based on above-mentioned participle vector
The feature vector of information;
Computing unit, for calculate above-mentioned first user feature vector corresponding with the attribute information of above-mentioned central user it
Between distance;
Above-mentioned second determination unit, it is right in the first preset attribute item of above-mentioned first user and above-mentioned central user to be also used to
The distance between feature vector answered is less than threshold value, it is determined that pre- there are first between above-mentioned central user and above-mentioned first user
If the corresponding attribute information matching of attribute item.
As can be seen that the embodiment of the present application is by obtaining the central user information of central user and the first use of the first user
Family information;Extract attribute information corresponding with preset attribute item in above-mentioned center user information and the first user information;Above-mentioned
There are in the corresponding matched situation of attribute information of the first preset attribute item between central user and above-mentioned first user, in determination
State the association user that the first user is above-mentioned central user;Above-mentioned center is established based on above-mentioned central user and above-mentioned first user
The customer relationship net of user.After establishing customer relationship net, according to customer relationship net generate customer relationship figure, then according to
The risk class of family relational graph calculating central user.It, can accurate, various dimensions the use for establishing user by the embodiment of the present application
Family relational network, and administrator can also be made quickly to identify abnormal user from customer relationship figure.
Referring to Fig. 5, Fig. 5 is the structural representation that a kind of customer relationship net provided by the embodiments of the present application establishes device 500
Figure, as shown in figure 5, sample generating means 500 include processor, memory, communication interface and one or more programs,
In, said one or multiple programs are different from said one or multiple application programs, and said one or multiple programs are stored
In above-mentioned memory, and it is configured to be executed by above-mentioned processor.Above procedure includes the instruction for executing following steps:
Obtain the central user information of central user and the first user information of the first user;Extract above-mentioned center user information and first
Attribute information corresponding with preset attribute item in user information;There are first between above-mentioned central user and above-mentioned first user
In the matched situation of the corresponding attribute information of preset attribute item, determine that the association that above-mentioned first user is above-mentioned central user is used
Family;The customer relationship net of above-mentioned central user is established based on above-mentioned central user and above-mentioned first user.
It should be appreciated that in the embodiment of the present application, alleged processor can be central processing unit (Central
Processing Unit, CPU), which can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic
Device, discrete gate or transistor logic, discrete hardware components etc..General processor can be microprocessor or this at
Reason device is also possible to any conventional processor etc..
A kind of computer readable storage medium, above-mentioned computer-readable storage medium are provided in another embodiment of the application
Matter is stored with computer program, realization when above-mentioned computer program is executed by processor: obtaining the central user letter of central user
First user information of breath and the first user;It is right with preset attribute item in above-mentioned center user information and the first user information to extract
The attribute information answered;There are the corresponding attribute informations of the first preset attribute item between above-mentioned central user and above-mentioned first user
In matched situation, determine that above-mentioned first user is the association user of above-mentioned central user;Based on above-mentioned central user and above-mentioned
First user establishes the customer relationship net of above-mentioned central user.
Above-mentioned computer readable storage medium can be the internal storage unit of the above-mentioned terminal of aforementioned any embodiment, example
Such as the hard disk or memory of terminal.Above-mentioned computer readable storage medium is also possible to the External memory equipment of above-mentioned terminal, such as
The plug-in type hard disk being equipped in above-mentioned terminal, intelligent memory card (Smart Media Card, SMC), secure digital (Secure
Digital, SD) card, flash card (Flash Card) etc..Further, above-mentioned computer readable storage medium can also be wrapped both
The internal storage unit for including above-mentioned terminal also includes External memory equipment.Above-mentioned computer readable storage medium is above-mentioned for storing
Other programs and data needed for computer program and above-mentioned terminal.Above-mentioned computer readable storage medium can be also used for temporarily
When store the data that has exported or will export.
In several embodiments provided herein, it should be understood that disclosed system, server and method, it can
To realize by another way.For example, sample generating means embodiment described above is only schematical, for example,
The division of said units, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple
Unit or assembly can be combined or can be integrated into another system, or some features can be ignored or not executed.In addition,
Shown or discussed mutual coupling, direct-coupling or communication connection can be through some interfaces, sample generate dress
It sets or the indirect coupling or communication connection of unit, is also possible to electricity, mechanical or other forms connections.
Above-mentioned unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.Some or all of unit therein can be selected to realize the embodiment of the present application scheme according to the actual needs
Purpose.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, is also possible to two or more units and is integrated in one unit.It is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.
If above-mentioned integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or the network equipment etc.) executes the complete of each embodiment above method of the application
Portion or part steps.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can store journey
The medium of sequence code.
The above, the only specific embodiment of the application, but the protection scope of the application is not limited thereto, it is any
Those familiar with the art within the technical scope of the present application, can readily occur in various equivalent modifications or replace
It changes, these modifications or substitutions should all cover within the scope of protection of this application.Therefore, the protection scope of the application should be with right
It is required that protection scope subject to.