Disclosure of Invention
In view of this, the embodiment of the invention provides a method for associating user information, which can simply and conveniently obtain the association between user information.
The embodiment of the invention also provides a system for associating the user information, which can simply and conveniently acquire the association between the user information.
The invention is implemented for legal use.
The embodiment of the invention is realized as follows:
a method of user information association, the method comprising:
establishing a user information association model, wherein the model is provided with behavior attribute categories of a plurality of user information, and the behavior attribute categories of the user information are associated with each other;
classifying and storing the user information of each user based on the behavior attribute category of the user information in the established user information association model;
after receiving the association request for inquiring the user information, calling a user information association model, and obtaining other user information associated with the requested user information according to the behavior attribute type of the user information.
The behavior attribute categories of the plurality of user information include: the user's address, user's IP address, user's virtual order, user's physical order, user's mobile phone number, user's International Mobile Equipment Identity (IMEI), user's mobile equipment identity, user's personal identification Password (PIN), user's money borrowing information and user's bank card information.
The establishment of the user information association model and the classification and storage of the user information of each user based on the behavior attribute category of the user information are completed under the control of a relational data association system;
the behavior attribute category based on the user information classifies the user information of each user respectively and is completed by adopting the data processing modes of extraction, interactive conversion and ETL loading;
the establishment of the user information association model is completed by a set graph calculation engine;
the established user information association model is stored in a distributed storage system HBase.
The association request for inquiring the user information is as follows: basic information inquiry, intelligent analysis, layout mode and labeling of other user information related to the obtained requested user information.
The intelligent analysis includes: cluster analysis, co-neighbor analysis, blood-edge analysis, path analysis, or/and automatic blackout search is performed on other user information obtained that is associated with the requested user information.
The layout modes are force guidance, left-right layout tree mode and uplink layout tree mode.
The labeling includes: after the obtained other user information associated with the requested user information is labeled, the obtained other user information is stored in the set multidimensional high risk database, so that the set graph calculation engine is called after a user information association model is established, and the labeled user information is highlighted.
A system for user information correlation, the system comprising: the system comprises a model building unit, a user information processing unit and a request processing unit, wherein,
the model building unit is used for building a user information association model, wherein the model is provided with behavior attribute categories of a plurality of user information, and the behavior attribute categories of the user information are associated with each other;
the user information processing unit is used for classifying and storing the user information of each user based on the behavior attribute category of the user information in the established user information association model;
and the request processing unit is used for calling the user information association model after receiving the association request for inquiring the user information, and obtaining other user information associated with the requested user information according to the behavior attribute type of the user information.
An apparatus for associating user information, comprising:
a memory; and a processor coupled to the memory, the processor configured to perform the method of user information association of any of the above based on instructions stored in the memory.
A computer readable storage medium having stored thereon a computer program, characterized in that the program, when executed by a processor, implements the method of user information correlation according to any of the preceding claims.
As can be seen from the foregoing, in the embodiment of the present invention, a user information association model is established, where the model is provided with a plurality of behavior attribute categories of user information, and the behavior attribute categories of user information of two users are associated with each other, the user information of each user is respectively classified and stored based on the behavior attribute category of the user information, after receiving an association request for querying the user information, the user information association model is invoked, and other user information associated with the requested user information is obtained according to the behavior attribute category of the user information. Thus, the embodiment of the invention can simply and conveniently acquire the association between the user information.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below by referring to the accompanying drawings and examples.
The invention is implemented for legal use.
In order to simply and conveniently acquire the association between the user information without carrying out manual association between the user information after inquiring the user information, the embodiment of the invention establishes a user information association model, wherein the model is provided with a plurality of behavior attribute categories of the user information, the behavior attribute categories of the user information are mutually associated, the user information of each user is respectively classified and stored based on the behavior attribute categories of the user information, after receiving an association request for inquiring the user information, the user information association model is called, and other user information associated with the requested user information is acquired according to the behavior attribute categories of the user information.
Fig. 1 is a flowchart of a method for associating user information, which includes the following specific steps:
step 101, establishing a user information association model, wherein the model is provided with behavior attribute categories of a plurality of user information, and the behavior attribute categories of the user information are associated with each other;
step 102, classifying and storing the user information of each user based on the behavior attribute category of the user information in the established user information association model;
step 103, after receiving the association request for inquiring the user information, calling a user information association model, and obtaining other user information associated with the requested user information according to the behavior attribute type of the user information.
When the user information association model is established, the embodiment of the invention analyzes the behavior relation of the user information based on the behavior generated by the user in the electronic commerce process, realizes the visual display of the platform relation network, supports the relation exploration of the behavior attribute category, improves the efficiency and assists the association inquiry among various user information.
FIG. 2 is a diagram of a modeling process of a user information association model according to an embodiment of the present invention, as shown in the following:
step one, setting a user information association model;
step two, extracting the data object, namely user information;
and thirdly, forming service data, namely respectively classifying and storing the user information of each user based on the behavior attribute category of the user information in the established user information association model.
In the embodiment of the invention, the behavior attribute categories of the plurality of user information in the established user information association model comprise: user address, user Internet Protocol (IP) address, user virtual order, user physical order, user cell phone number, user International Mobile Equipment Identification (IMEI), user mobile equipment identification, user Personal Identification Number (PIN), user money borrowing information, and user bank card information. Here, there are ten behavior attribute categories, where the association of two by two completes modeling of the user information association model, and a relational network display may be used during storage, where each vertex may represent user information that has been classified.
In the embodiment of the present invention, the processes of step 101 and step 102 are performed under the control of a relational data management system (Mysql).
In the embodiment of the present invention, the process of classifying the user information of each user based on the behavior attribute category of the user information in step 102 is completed by adopting a data processing mode of extraction, interactive conversion and loading (ETL). The emerging patterns are accomplished using a set-up graph computation engine.
In the embodiment of the present invention, the step 102 of storing in the established user information association model is stored in a distributed storage system (HBase)
Fig. 3 is a schematic diagram of a specific example of a method for associating user information provided in an embodiment of the present invention, where the user information is processed by ETL data and stored in HBase under the control of Mysql as shown in the figure. And processing the association request for querying the user information by the graph computation engine, and transmitting the obtained other user information associated with the requested user information through a world wide web (web) layer, that is, a user operation layer.
In the association request for inquiring the user information, the request can be basic information inquiry, intelligent analysis, layout or labeling, and the like, as shown in f 1-f 4 in fig. 3, wherein when labeling, the labeled user information can be stored in a set multidimensional high risk database. The multidimensional high-risk database is a MySqL database and mainly stores high-risk data comprising intermediary equipment, stealing equipment, abnormal IP, small mobile phone numbers, cashing addresses, identity card blacklists and the like.
In the figure, a data flow A carries out ETL data processing according to a user information association model to process a data table of behavior attribute categories of 10 kinds of user information and a relation table between every two;
the data flow B, the ETL finishes data processing and is stored in the HBase;
the data flow C queries the user information in the HBase according to the condition transmitted by the web layer and converts the user information into a relation map form;
the data flow D, the graph calculation engine obtains high risk data and marks the high risk data in the user information association model;
the data flow E, the graph calculation engine transmits the processed data to a web layer, and the web layer is displayed in a form of a relational network;
and the data flow G, wherein the user can label other user information related to the obtained user information in the analysis process and store the information in a multidimensional high-risk database for subsequent analysis and reference.
Thus, based on the user information association model provided by the embodiment of the invention, a relationship network based on user address, user IP address, user virtual order, user physical order, user mobile phone number, user IMEI, user mobile equipment identification, user PIN, user money information and user information association of user bank card information can be obtained, and sent to related personnel, and the related personnel can make the following requests according to the relationship network.
1) Basic information query
The user information association model may provide basic information queries. For example: and inquiring basic information and ordering condition of an address, and judging whether the address has abnormal behaviors, such as a high ordering amount for a period of time, and the like.
Fig. 4 is a schematic diagram of basic information query provided by an embodiment of the present invention, where in fig. 4, for searching for a node with an address and a node with a difference, the address is ordered up to 461 orders in one day, and can be basically identified as a problem vertex.
2) Intelligent analysis
a) Cluster analysis, cluster analysis can be implemented. For example, the association network lines among a plurality of devices are queried, and whether the devices have strong association relationship or not is judged, so that the association network lines are used for group crime screening and the like.
Fig. 5 is a schematic diagram of cluster analysis provided in the embodiment of the present invention, in which user information of four user mobile device identifiers is respectively set as data vertices, and relationships between two vertices, including direct relationships and indirect relationships, can be analyzed, so as to analyze aggregation and cluster analysis of the four user mobile device identifiers. When the four user mobile equipment identifiers are found to be associated with the same address, the user mobile equipment corresponding to the user mobile equipment identifier can be identified to have a strong association relationship.
b) And (3) carrying out common neighbor analysis to find out other user information commonly associated with the plurality of user information, namely, finding out nodes commonly associated with the plurality of nodes. The embodiment of the invention supports the selection of two or more nodes and obtains the common neighbors between the two nodes. For example, if a common neighbor of two or more problem pins is queried, then the resulting common neighbor may also be a problem vertex, which may provide basis for subsequent analysis investigation.
Fig. 6 is a schematic diagram of a common neighbor analysis provided in an embodiment of the present invention, where a common neighbor between an address vertex and three mobile phone number vertices is analyzed, and one or more orders between the address and the other three mobile phone numbers are found to be used as the common neighbors, i.e. related.
c) Blood margin analysis
Specific blood relationship analysis may be performed based on the user information correlation model. For example: if one address is considered as the cashing address, inquiring the blood relationship of the address, inquiring all orders related to the address, and inquiring information such as pins, mobile phone numbers and the like related to the orders, so that an analyst can judge that cashing behaviors exist on the pins and the mobile phone numbers.
Fig. 7 is a schematic diagram of a blood-edge analysis provided by an embodiment of the present invention, in which a 2-level quilt blood-edge relationship map is queried based on a certain address vertex. The address has 5 physical orders in a certain time range, and the physical orders are associated with orders such as pin, user mobile equipment identification, mobile phone number, IMEI and the like.
d) Path analysis
The association path analysis of two target objects can be realized based on the user information association model, which has great auxiliary effect on the analysis of the group cases.
Fig. 8 is a schematic diagram of association analysis provided in the embodiment of the present invention, in which a path between certain mobile phone numbers is queried, and association analysis is performed between the two mobile phone numbers, so that it can be obviously seen that two mobile phone numbers have a strong association relationship with one address, and the relationship can be used as a reference for case investigation.
e) Automatic black-related exploration
The automatic blackout exploration based on certain or certain user information vertexes can be realized based on the user information association model, the appointed exploration hierarchy and the exploration data vertex types are supported, and if certain data vertexes are blackout in the obtained result, the highlight display is correspondingly highlighted. This feature enables the sharing person to quickly determine whether a certain user information vertex is suspicious. For example: when an analyst suspects that an address is suspicious, automatic black-related search can be performed, if a black-related vertex exists in the searched association relation diagram of the user information, the analyst can analyze the address with emphasis, otherwise, if the black-related vertex is not found, the suspicious performance of the address is reduced, and even the address can be judged as a normal address.
Fig. 9 is a schematic diagram of automatic black search provided in an embodiment of the present invention, where 3-level automatic black search is performed according to a certain address vertex, so that it can be seen that a plurality of black vertices exist in an association network of user information detected by the address, and then the address may be a problem address.
3) Layout mode
The layout of the view area is mainly three, namely: force guidance, left and right layout tree forms and up and down layout tree forms are respectively shown in fig. 10 a-10 c, and different layout modes are convenient for an analyst to perform relationship analysis.
4) Labeling
Personalized labeling operation can be performed on the user information vertex based on the user information association model, so that user labeling and case analysis are facilitated, as shown in fig. 11, and fig. 11 is a labeling schematic diagram provided by the embodiment of the invention. When an analyst confirms that a certain vertex is a problem vertex, the label can be marked, and the label information is displayed as the attribute of the vertex without changing with time, so that the subsequent analysis and investigation are facilitated.
Fig. 12 is a system for associating user information according to an embodiment of the present invention, where the system includes: the system comprises a model building unit, a user information processing unit and a request processing unit, wherein,
the model building unit is used for building a user information association model, wherein the model is provided with behavior attribute categories of a plurality of user information, and the behavior attribute categories of the user information are associated with each other;
the user information processing unit is used for classifying and storing the user information of each user based on the behavior attribute category of the user information in the established user information association model;
and the request processing unit is used for calling the user information association model after receiving the association request for inquiring the user information, and obtaining other user information associated with the requested user information according to the behavior attribute type of the user information.
The embodiment of the invention also provides a device for associating the user information, which comprises the following steps:
a memory; and a processor coupled to the memory, the processor configured to perform the method of user information association described in the above embodiments based on instructions stored in the memory.
The embodiment of the present invention also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the method for associating user information according to any one of the above embodiments.
It can be seen that the embodiment of the invention can provide visual display based on user behavior based on the user information association model, thereby completing intelligent inquiry and association relation exploration between user information, greatly improving user information analysis efficiency of analysts in a business system, and greatly improving discrimination efficiency of team criminal investigation and providing reliable basis because of realizing functions of community analysis, path analysis and the like.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather to enable any modification, equivalent replacement, improvement or the like to be made within the spirit and principles of the invention.