CN111291234A

CN111291234A - Account risk probability assessment method, device and system and storage medium

Info

Publication number: CN111291234A
Application number: CN202010247921.3A
Authority: CN
Inventors: 周亮; 钱勇; 张国庆
Original assignee: JD Digital Technology Holdings Co Ltd
Current assignee: JD Digital Technology Holdings Co Ltd
Priority date: 2020-03-31
Filing date: 2020-03-31
Publication date: 2020-06-16

Abstract

The embodiment of the invention relates to an account risk probability assessment method, device, system and storage medium, comprising the following steps: acquiring service data; carrying out abstract coding on the data; updating the existing relational network graph according to the abstract codes or constructing a new relational network graph; acquiring a first account vertex to be queried currently in a relationship network diagram, and determining an account identifier of the first account vertex; determining a first account risk probability according to the account identification of the first account vertex; when the risk probability of the first account is determined to be lower than a preset threshold value according to the account identification of the vertex of the first account, querying a second account vertex which has an association relation with the first account vertex in a relation network diagram according to a preset rule; and determining the risk probability of the first account according to the risk probability of the vertex of the second account. By the method, the user risk probability is determined by fully utilizing the relationship network diagram which is updated in real time and has an incidence relationship with the user account, so that the real-time performance is better, and the accuracy rate of the risk probability evaluation is high.

Description

Account risk probability assessment method, device and system and storage medium

Technical Field

The embodiment of the invention relates to the technical field of computers, in particular to an account risk probability assessment method, device and system and a storage medium.

Background

In order to reduce the economic loss of a company in an e-commerce wind control scene, an important means is to perform risk assessment on a user to obtain a risk index, and then take corresponding measures according to the risk index when the user transacts related financial services. The current risk assessment method for users is based on relational database keyword matching: establishing a risk account information base by utilizing a relational database, carrying out keyword comparison query in a black-involved database according to key attributes aiming at a user to be identified, and giving a risk index of the user according to the weight of the attributes if the identified user is the same as the information of the existing black-involved user on some attributes.

However, this method has certain drawbacks. For example: first, the keyword matching method based on the relational database can only identify users who are directly matched with existing black-involved users on the key attributes, the risk index of the matched users is very high, and otherwise, no risk exists. This approach ignores certain possibilities that users that do not directly match on key attributes may actually be at some high risk. In one example, if there is no direct relationship between a user and a risky account, but an account closer to the user in the relationship network diagram of the user has an association relationship with the risky account, the user should be considered to have a certain risk. The risk assessment method in the prior art has insufficient risk assessment precision for users, and usually omits the possibility in the examples, so that the risk assessment is not accurate enough; secondly, the relational data need to calculate the relational network of the user due to the characteristics of the relational data, so a large amount of time-consuming join operations need to be performed, and the join operations cannot be completed at all under a large data volume or when the relational network needing to be calculated exceeds a 3-degree relation; third, there is a lack of real-time.

Disclosure of Invention

In view of this, embodiments of the present invention provide an account risk probability assessment method, apparatus, system and storage medium to solve the above technical problems in the prior art.

In a first aspect, an embodiment of the present invention provides an account risk probability assessment method, where the method includes:

acquiring service data;

abstract coding is carried out on the service data;

updating the existing relational network graph according to the abstract codes or constructing a new relational network graph;

acquiring a first account vertex to be queried currently in a relationship network diagram, and determining an account identifier of the first account vertex;

determining a first account risk probability according to the account identification of the first account vertex;

when the risk probability of the first account is determined to be lower than a preset threshold value according to the account identification of the vertex of the first account, querying a second account vertex which has an association relation with the first account vertex in a relation network diagram according to a preset rule; and determining the risk probability of the first account according to the risk probability of the vertex of the second account.

In one possible embodiment, after querying a second account vertex having an association relationship with a first account vertex in the relationship network graph according to a preset rule, the method further includes:

and when the risk probability of the second account vertex is lower than a preset threshold value or the second account vertex is not inquired, determining the risk probability of the first account vertex according to the account information of the vertex within n degrees of the first account vertex, wherein n is a positive integer greater than or equal to 2.

In one possible embodiment, the service data composition format includes: a source vertex \ t source vertex type \ t destination vertex type \ t account identification; the abstract coding of the service data specifically includes:

generating coding numbers respectively corresponding to the source vertex and the target vertex;

establishing a first mapping relation among a source vertex, a source vertex type and a source vertex coding number;

and establishing a second mapping relation among the destination vertex, the destination vertex type and the destination vertex code number, wherein the source vertex is a first account vertex, and the account identifier in the service data is the account identifier corresponding to the first account vertex.

In a possible embodiment, updating an existing relational network graph according to the abstract code, or constructing a new relational network graph specifically includes:

and updating the existing relationship network graph or constructing a new relationship network graph according to the first mapping relationship, the second mapping relationship, the incidence relationship between the source vertex and the destination vertex and the account identification corresponding to the first account vertex.

In a possible embodiment, after abstractly encoding the service data, the method further includes:

and storing the first mapping relation and the second mapping relation in a pre-constructed database.

In one possible embodiment, after storing the first mapping relationship and the second mapping relationship in the pre-constructed database, the method further includes:

and matching the source vertex in the acquired service data with the first mapping relation in the database after the service data is received again, and/or matching the target vertex in the acquired service data with the second mapping relation so as to perform abstract coding on the acquired service data according to the final matching result.

In a possible implementation manner, determining the risk probability of the vertex of the first account according to the account information of the vertex within n degrees of the vertex of the first account specifically includes:

according to the account information of the vertexes within n degrees of the vertex of the first account, counting a first number belonging to the risk account in the vertex within n degrees of the vertex of the first account and the total number of the vertex of the account, and taking the ratio of the first number to the total number of the vertex of the account as the risk probability of the vertex of the first account.

In a possible implementation manner, determining the first account risk probability according to the account id of the vertex of the first account specifically includes:

when the account number identification corresponding to the first account number vertex is 1, determining that the risk probability of the first account number is a preset threshold value; or when the account number identification of the vertex of the first account number is 0, determining that the risk probability of the first account number is lower than a preset threshold value.

In one possible embodiment, the acquired service data is transmitted in the form of a message queue.

In a possible implementation manner, after determining the user risk probability corresponding to the first account, the method further includes:

and establishing an updated relationship network diagram or a new relationship network diagram, and storing the association relationship between the user risk probability corresponding to the first account and a pre-constructed database.

In one possible embodiment, the destination vertex includes, but is not limited to, one of the following: a device number, a mailbox, a mobile phone number, a WiFi number, a mobile phone number, or an identification number.

In a second aspect, an embodiment of the present invention provides an account risk probability assessment apparatus, where the apparatus includes:

an obtaining unit, configured to obtain service data;

the coding unit is used for carrying out abstract coding on the service data;

the processing unit is used for updating the existing relational network graph according to the abstract codes or constructing a new relational network graph;

the obtaining unit is further configured to obtain a first account vertex to be queried currently in the relationship network graph;

the processing unit is further used for determining account identification of the first account vertex;

In a third aspect, an embodiment of the present invention provides an account risk probability assessment system, where the system includes: at least one processor and memory;

the processor is configured to execute an account risk probability assessment program stored in the memory to implement the account risk probability assessment method as described in any one of the embodiments of the first aspect.

In a fourth aspect, an embodiment of the present invention provides a computer storage medium, where one or more programs are stored, and the one or more programs may be executed by the account risk probability evaluation system described in the third aspect, so as to implement the account risk probability evaluation method described in any of the embodiments of the first aspect.

According to the account risk probability evaluation method provided by the embodiment of the invention, even if the first account risk probability is determined to be very low according to the account identification of the vertex of the first account, the extreme condition is avoided, and the account is directly judged to have no risk. But rather look at other accounts with which there is an associative relationship and determine the risk probabilities of the other accounts. And finally, further determining the risk probability of the first account according to the risk probabilities of other accounts. That is, the online service data is added to the relational network graph in real time for calculation. The user risk probability is determined by fully utilizing the relationship network diagram which is updated in real time and has an incidence relationship with the user account, so that the real-time performance is better, and the accuracy of evaluating the user risk probability is better. In addition, the method also avoids the defects that a large amount of time-consuming join operations are needed for calculating the relationship network of the user due to the characteristics of the relationship type data, and the join operations cannot be completed when the relationship network exceeds 3-degree relationship, and greatly improves the risk assessment efficiency.

Drawings

Fig. 1 is a schematic flow chart of an account risk probability assessment method according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a user risk assessment provided by the present invention;

FIG. 3 is a schematic view of another user risk assessment provided by the present invention;

FIG. 4 is a block diagram of an overall process for assessing user risk according to the present invention;

fig. 5 is a schematic structural diagram of an account risk probability assessment apparatus according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram of an account risk probability evaluation system according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

For the convenience of understanding of the embodiments of the present invention, the following description will be further explained with reference to specific embodiments, which are not to be construed as limiting the embodiments of the present invention.

Fig. 1 is a schematic flow chart of an account risk probability assessment method provided in an embodiment of the present invention, and as shown in fig. 1, the method includes:

step 110, acquiring service data.

Specifically, the online service system monitors the operation data of the user in real time. And once one piece of data is monitored to be business data influencing the change of the user relationship network, the business data is transmitted to the account risk probability evaluation system. Optionally, in order to ensure real-time data transmission, the service data is transmitted to the account risk probability evaluation system in the form of a message queue.

And step 120, abstract coding is carried out on the service data.

Specifically, the service data composition format includes: and the source vertex \ t source vertex type \ t destination vertex type \ t account identification.

The abstract coding of the service data may include the following ways:

and establishing a second mapping relation among the destination vertex, the type of the destination vertex and the code number of the destination vertex, wherein the source vertex is a first account vertex, namely the first account vertex is an account vertex corresponding to the service data. And the account identification in the service data is the account identification corresponding to the vertex of the first account.

In a specific example, the acquired service data is, for example: zhang III \ t1\ tzhangsan @163.com \ t3\ t 0. Wherein, Zhang three is a source vertex, 1 is a source vertex type, zhangsan @163.com is a destination vertex, 3 is a destination vertex type, and 0 is an account identifier.

See in particular tables 1 and 2. Table 1 shows some vertex types and vertex type numbers corresponding to the vertex types, for example, the vertex types include an account number, a device number, a mailbox, a mobile phone number, an identity card number, a WiFi account number, and the like. In an alternative example, the destination vertex includes, but is not limited to, one of the following: a device number, a mailbox, a mobile phone number, a WiFi number, a mobile phone number, or an identification number.

Table 2 shows the account id and the account type. In one specific example, the account id corresponding to the risky account is labeled as 1, and the account id that is not the risky account (white account) is labeled as 0. See in particular table 2.

Account number	1
		Equipment number	2
Mailbox	3
		Mobile phone number	4
Identity card number	5
		WiFi number	6

TABLE 2

Account type	Account identification
		Risk account number	1
White account number	0

And generating code numbers respectively corresponding to a source vertex (Zhang III) and a destination vertex (mailbox zhangsan @163.com), wherein the specific code number is a preset code number corresponding to a vertex type. For example, the code number corresponding to Zhang III is 0, and the code number corresponding to mailbox zhangsan @163.com is 1. The first mapping relation is 1_ three to 0; the second mapping relation is as follows: 3_ zhangsan @163. com-1. The source vertex "Zhang three" is also the account vertex. The account id 1 is an account id corresponding to the top point of the account. Whether an account is a risk account or a white account can be determined by the prior art, which is not described herein.

And step 130, updating the existing relational network graph according to the abstract codes, or constructing a new relational network graph.

Specifically, based on the above steps, an existing relationship network graph may be updated according to the first mapping relationship, the second mapping relationship, the association relationship between the source vertex and the destination vertex, and the account id corresponding to the first account vertex, or a new relationship network graph may be constructed.

For example, the most basic relationship network diagram is shown in FIG. 2. The network graph comprises a plurality of vertexes, the target vertex having a mapping relation with one account vertex forms a relation network graph by surrounding the account vertex through an abstract edge, and the abstract edge is an abstraction of the mapping relation. The account number vertex shown in fig. 2 establishes a relationship network diagram with a mailbox, a device number, a WiFi number, a mobile phone number, an identity card number, and the like. Each vertex includes, in addition to the account number vertex, a vertex type number corresponding thereto.

The relationship network graph is expanded through the abstract edges in the way that the target vertex and other account vertices have direct or indirect incidence relationship. As shown in fig. 3, fig. 3 is a relationship network diagram corresponding to zhang san in a specific example. The figure also includes the relation network of Li four, Wang five and Zhao six, etc. The figure is a 4-degree internal relation diagram of Zhangthree.

Step 140, obtaining a first account vertex to be queried currently in the relationship network diagram, and determining an account identifier of the first account vertex.

And 150, determining the risk probability of the first account according to the account identification of the vertex of the first account.

Step 160, when it is determined that the risk probability of the first account is lower than the preset threshold according to the account identifier of the vertex of the first account, querying a second account vertex having an association relationship with the vertex of the first account in the relationship network graph according to a preset rule.

Step 170, determining the risk probability of the first account according to the risk probability of the vertex of the second account.

Specifically, as introduced in step 130, the nodes corresponding to the account vertices in the relational network graph include not only the account nodes but also the account ids. Therefore, the vertex of the first account to be queried in the relationship network graph can be directly acquired, and then the account identifier corresponding to the vertex of the first account is determined. For example, as shown in fig. 3, if the vertex of the account to be queried is Zhang III, the account id is 0 as can be seen in the figure. In an optional manner, as shown in table 2 specifically, when the account identifier corresponding to the vertex of the first account is 1, it is determined that the first account is a risky account, and the risk probability corresponding to the first account is a preset threshold, for example, the preset threshold is 1; or when the account id of the vertex of the first account is 0, determining that the first account is not a risk account, and the risk probability of the first account is lower than a preset threshold. However, at this time, it cannot be directly determined that the first account is not at risk. But needs to be further verified.

If the account id corresponding to zhang-three in fig. 3 is 0, the vertex of the second account having an association relationship with the vertex of the first account may be queried in the relationship network graph according to a preset rule. And searching according to a preset rule, wherein the searching can be according to a destination vertex related to the source vertex. For example, the destination vertex related to the source vertex Zhang III includes a mobile phone number, an identification number and the like. And inquiring whether a second account with an association relation exists or not through the destination vertex. Such as lie four in fig. 3.

As can be seen from fig. 3, the account id corresponding to liqi is also 0, so that subsequent operations need to be performed continuously. Otherwise, if the account id corresponding to liqi is 1, it may be directly determined that the risk probability of the account id of zhang san is the preset threshold. That is, when the second account is determined to be a risk account according to the account identifier corresponding to the vertex of the second account, the risk probability of the vertex of the second account is a preset threshold. Correspondingly, the user risk probability corresponding to the first account can also be determined to be a preset threshold.

However, the account id corresponding to liqi in fig. 3 is 0, that is, the risk probability of the vertex of the second account is lower than the preset threshold, so the following steps need to be executed:

and determining the risk probability of the vertex of the first account according to the account information of the vertex within n degrees of the vertex of the first account, wherein n is a positive integer greater than or equal to 2.

In another case, if the vertex of the second account is not queried, as shown in fig. 3, the associated account is not queried according to the third identity card number. Then, the risk probability of the vertex of the first account is also determined according to the account information of the vertex within n degrees of the vertex of the first account.

As shown in fig. 3, a relationship network diagram with a 4-degree relationship exists, and then the risk probability of the vertex of the first account needs to be determined according to the account information of all vertices in the 4-degree relationship network diagram.

When specifically executed, the method comprises: according to the account information of the vertexes within n degrees of the vertex of the first account, counting a first number belonging to the risk account in the vertex within n degrees of the vertex of the first account and the total number of the vertex of the account, and taking the ratio of the first number to the total number of the vertex of the account as the risk probability of the vertex of the first account.

According to the account information of the vertex within n degrees of the vertex of the first account, when counting the first number of risk accounts in the vertex within n degrees of the vertex of the first account, whether the vertex of the account is a risk account can be determined according to the identification of each vertex of the account. And then counting the number of all risk account number vertexes in the relationship network graph.

And finally, counting the total number of the account vertexes, and taking the ratio of the first number to the total number of the account vertexes as the user risk probability corresponding to the first account.

For example, in fig. 3, the total number of vertices of the account is 4, the number of vertices of the risk account is 1, and the user risk probability corresponding to Zhang III account is:

wherein, M is the number of the risk accounts, S is the total number of the peaks of the accounts, and R is the risk probability of the peak of the first account.

Further optionally, after performing step 120, the method may further include: and storing the first mapping relation and the second mapping relation in a pre-constructed database. The method aims to match a source vertex in the service data obtained again with a first mapping relation in a database after the service data is received again, and/or match a target vertex in the service data obtained again with a second mapping relation so as to carry out abstract coding on the service data obtained again according to a final matching result.

That is, if the account vertices, destination vertices, and the like of some service data have been abstractly encoded before, the abstractly encoded result obtained at the previous time may be directly used at this time. Without the need to perform this act of abstract coding again.

Further optionally, after obtaining the user risk probability corresponding to the first account, the method may further include:

and establishing a mapping relation between the updated relationship network diagram or the constructed new relationship network diagram and the user risk probability corresponding to the first account, and storing the mapping relation in a pre-constructed database.

If the first mapping relation or the second mapping relation is obtained from the database in the service data obtained again, the relationship network graph corresponding to the first mapping relation or the second mapping relation can be directly inquired from the pre-constructed database, and then the user risk probability is directly obtained.

Fig. 4 is a block diagram of an overall process of risk assessment for a user according to the present invention, and is specifically shown in fig. 4.

And the online service system monitors the operation data of the user in real time. And once one piece of data is monitored to be business data influencing the change of the user relationship network, the business data is transmitted to the account risk probability evaluation system. Specifically, as shown in fig. 4, after the online service system detects the service data, the service data is transmitted to the account risk probability evaluation system in the form of a message queue. And an access coding service module in the account risk probability evaluation system can carry out abstract coding on the service data. Specifically, the method comprises the steps of generating abstract edges and establishing mapping relations between business values and abstract vertexes. The traffic values include the source vertices and destination vertices described above. The process of specifically generating the abstract edge and establishing the mapping relationship has been described in detail in step 120 above, and will not be described in detail here. In this manner, an incremental snapshot is constructed. If the abstract graph has been constructed before, the incremental abstract graph is updated to the existing abstract graph. If the abstract diagram is not constructed before, the incremental abstract diagram is taken as the basic abstract diagram, and when new service data exists later, the incremental abstract diagram is continuously generated and updated to the current basic abstract diagram. The abstract diagram, i.e. the relational network diagram introduced above, is referred to above in step 130.

Then, enter the calculation query service module, as shown in fig. 4, to perform the query service. Firstly, acquiring a full amount of abstract edges in a relational network graph, inputting the abstract edges into a graph calculation engine, and evaluating risk probability by using a risk evaluation algorithm. See step 140 and step 170 for a specific implementation. It should be noted that the algorithm performs calculation in a loop, each calculation reads the latest full amount of abstract edge data, and a new graph calculation result set is generated after each calculation is completed. The graph calculation result set stores the risk value of each account. The query service module in the calculation query service provides the function of querying the latest result set externally. In addition, the user can also query according to the business value of the account, and the query service can firstly obtain the abstract vertex corresponding to the account value from the K/V storage and then query the risk value of the vertex in the result according to the abstract vertex.

The reason for this is that the K/V storage module, i.e. the pre-constructed database as described above. And storing the mapping relation between the business value and the abstract vertex, and providing mapping conversion for the query service. The K/V storage service employs a Redis database.

Specifically, the K/V storage module stores a first mapping relationship and a second mapping relationship. And matching the source vertex in the acquired service data with the first mapping relation in the database after the service data is received again, and/or matching the target vertex in the acquired service data with the second mapping relation so as to perform abstract coding on the acquired service data according to the final matching result.

And the updated relationship network graph or the constructed new relationship network graph establishes a mapping relationship with the user risk probability corresponding to the first account, and is also stored in a pre-constructed database.

If the first mapping relation or the second mapping relation is obtained from the database in the service data obtained again, the relationship network diagram corresponding to the first mapping relation or the second mapping relation can be directly inquired from the K/V storage module, and then the user risk probability is directly obtained.

Of course, if the query in the K/V storage module is not available, the query is carried out through the calculation query service module. The reason why the old result set and the new result set are included in fig. 4 is that when the user requests for query, the calculation query service module does not obtain the incremental abstract map, or the calculation of the loop is not finished, and then the old result set is provided. If the query service module acquires the incremental abstract graph and updates the query result according to the incremental abstract graph when the user queries, a new result set is provided.

Fig. 5 is an account risk probability assessment device provided in an embodiment of the present invention, where the account risk probability assessment device includes: an acquisition unit 501, an encoding unit 502 and a processing unit 503.

An obtaining unit 501, configured to obtain service data;

an encoding unit 502, configured to perform abstract encoding on service data;

a processing unit 503, configured to update an existing relationship network graph according to the abstract code, or construct a new relationship network graph;

the obtaining unit 501 is further configured to obtain a first account vertex to be queried currently in the relationship network graph;

the processing unit 503 is further configured to determine an account id of the first account vertex;

Optionally, the processing unit 503 is specifically configured to, when it is determined that the risk probability of the vertex of the second account is lower than a preset threshold or the vertex of the second account is not queried, determine the risk probability of the vertex of the first account according to account information of a vertex within n degrees of the vertex of the first account, where n is a positive integer greater than or equal to 2.

Optionally, the service data composition format includes: a source vertex \ t source vertex type \ t destination vertex type \ t account identification; the encoding unit 502 is specifically configured to generate encoding numbers corresponding to the source vertex and the destination vertex, respectively;

Optionally, the processing unit 503 is specifically configured to update an existing relationship network graph according to the first mapping relationship, the second mapping relationship, the association relationship between the source vertex and the destination vertex, and the account id corresponding to the first account vertex, or construct a new relationship network graph.

Optionally, the processing unit 503 is further configured to store the first mapping relationship and the second mapping relationship in a pre-constructed database.

Optionally, the encoding unit 502 is further configured to, after the service data is received again, match a source vertex in the service data obtained again with the first mapping relationship in the database, and/or match a destination vertex in the service data obtained again with the second mapping relationship, so as to perform abstract encoding on the service data obtained again according to a final matching result.

Optionally, the processing unit 503 is specifically configured to, according to the account information of the vertex within n degrees of the vertex of the first account, count a first number belonging to the risk account in the vertex within n degrees of the vertex of the first account and a total number of the vertex of the account, and use a ratio between the first number and the total number of the vertex of the account as the risk probability of the vertex of the first account.

Optionally, the processing unit 503 is specifically configured to determine that the risk probability of the first account is a preset threshold when the account identifier corresponding to the vertex of the first account is 1; or when the account number identification of the vertex of the first account number is 0, determining that the risk probability of the first account number is lower than a preset threshold value.

Optionally, the acquired service data is transmitted in a message queue.

Optionally, the processing unit 503 is further configured to establish an updated relationship network graph or a new relationship network graph, and store an association relationship between the user risk probability corresponding to the first account and the updated relationship network graph and the user risk probability in a pre-constructed database.

Optionally, the destination vertex includes, but is not limited to, one of the following: a device number, a mailbox, a mobile phone number, a WiFi number, a mobile phone number, or an identification number.

The functions executed by each functional component in the account risk probability assessment apparatus provided in this embodiment have been described in detail in the embodiment corresponding to fig. 1, and therefore are not described herein again.

According to the account risk probability evaluation device provided by the embodiment of the invention, even if the first account risk probability is determined to be very low according to the account identification of the vertex of the first account, the extreme condition is avoided, and the account is directly judged to have no risk. But rather look at other accounts with which there is an associative relationship and determine the risk probabilities of the other accounts. And finally, further determining the risk probability of the first account according to the risk probabilities of other accounts. That is, the online service data is added to the relational network graph in real time for calculation. The user risk probability is determined by fully utilizing the relationship network diagram which is updated in real time and has an incidence relationship with the user account, so that the real-time performance is better, and the accuracy of evaluating the user risk probability is better. In addition, the method also avoids the defects that a large amount of time-consuming join operations are needed for calculating the relationship network of the user due to the characteristics of the relationship type data, and the join operations cannot be completed when the relationship network exceeds 3-degree relationship, and greatly improves the risk assessment efficiency.

Fig. 6 is a schematic structural diagram of an account risk probability evaluation system according to an embodiment of the present invention, where the account risk probability evaluation system 600 shown in fig. 6 includes: at least one processor 601, memory 602, at least one network interface 603, and other user interfaces 604. Account Risk probability assessment the various components of the account risk probability assessment system 600 are coupled together by a bus system 605. It is understood that the bus system 605 is used to enable communications among the components. The bus system 605 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 605 in fig. 6.

The user interface 604 may include, among other things, a display, a keyboard, or a pointing device (e.g., a mouse, trackball, touch pad, or touch screen, among others.

It will be appreciated that the memory 602 in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of illustration and not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), Double Data rate Synchronous Dynamic random access memory (ddr SDRAM), Enhanced Synchronous SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and direct memory bus RAM (DRRAM). The memory 602 described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

In some embodiments, memory 602 stores the following elements, executable units or data structures, or a subset thereof, or an expanded set thereof: an operating system 6021 and application programs 6022.

The operating system 6021 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, and is used for implementing various basic services and processing hardware-based tasks. The application program 6022 includes various application programs such as a Media Player (Media Player), a Browser (Browser), and the like, and is used to implement various application services. A program implementing the method of an embodiment of the invention can be included in the application program 6022.

In the embodiment of the present invention, by calling a program or an instruction stored in the memory 602, specifically, a program or an instruction stored in the application program 6022, the processor 601 is configured to execute the method steps provided by the method embodiments, for example, including:

acquiring service data;

abstract coding is carried out on the service data;

Optionally, when it is determined that the risk probability of the vertex of the second account is lower than a preset threshold or the vertex of the second account cannot be queried, determining the risk probability of the vertex of the first account according to account information of the vertex within n degrees of the vertex of the first account, where n is a positive integer greater than or equal to 2.

Optionally, generating coding numbers corresponding to the source vertex and the destination vertex respectively;

Optionally, an existing relationship network graph is updated according to the first mapping relationship, the second mapping relationship, the association relationship between the source vertex and the destination vertex, and the account id corresponding to the first account vertex, or a new relationship network graph is constructed.

Optionally, the first mapping relationship and the second mapping relationship are stored in a pre-constructed database.

Optionally, after the service data is received again, the source vertex in the service data acquired again is matched with the first mapping relationship in the database, and/or the destination vertex in the service data acquired again is matched with the second mapping relationship, so that the service data acquired again is subjected to abstract coding according to the final matching result.

Optionally, according to the account information of the vertices within the n degrees of the vertices of the first account, the first number of the risk accounts in the vertices within the n degrees of the vertices of the first account and the total number of the vertices of the account are counted, and a ratio between the first number and the total number of the vertices of the account is used as the risk probability of the vertices of the first account.

Optionally, when the account identifier corresponding to the vertex of the first account is 1, determining that the risk probability of the first account is a preset threshold; or when the account number identification of the vertex of the first account number is 0, determining that the risk probability of the first account number is lower than a preset threshold value.

Optionally, the acquired service data is transmitted in a message queue.

Optionally, an updated relationship network graph or a new relationship network graph is established, and the association relationship between the user risk probabilities corresponding to the first account is stored in a pre-constructed database.

The method disclosed by the above-mentioned embodiment of the present invention can be applied to the processor 601, or implemented by the processor 601. The processor 601 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 601. The Processor 601 may be a general-purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable Gate Array (FPGA) or other programmable logic device, discrete Gate or transistor logic device, or discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software elements in the decoding processor. The software elements may be located in ram, flash, rom, prom, or eprom, registers, among other storage media that are well known in the art. The storage medium is located in the memory 602, and the processor 601 reads the information in the memory 602 and completes the steps of the method in combination with the hardware thereof.

It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or any combination thereof. For a hardware implementation, the Processing units may be implemented in one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units configured to perform the functions of the present application, or a combination thereof.

For a software implementation, the techniques herein may be implemented by means of units performing the functions herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.

The account risk probability evaluation system provided in this embodiment may be the account risk probability evaluation system shown in fig. 6, and may execute all the steps of the account risk probability evaluation method shown in fig. 1, so as to achieve the technical effect of the account risk probability evaluation method shown in fig. 1.

The embodiment of the invention also provides a storage medium (computer readable storage medium). The storage medium herein stores one or more programs. Among others, the storage medium may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, a hard disk, or a solid state disk; the memory may also comprise a combination of memories of the kind described above.

When the one or more programs in the storage medium are executable by the one or more processors, the account risk probability assessment method executed on the account risk probability assessment system side is implemented.

The processor is used for executing the account risk probability evaluation program stored in the memory so as to realize the following steps of the account risk probability evaluation method executed on the account risk probability evaluation system side:

acquiring service data;

abstract coding is carried out on the service data;

Optionally, the acquired service data is transmitted in a message queue.

Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, a software module executed by a processor, or a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

The above embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, it should be understood that the above embodiments are merely exemplary embodiments of the present invention and are not intended to limit the scope of the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims

1. An account risk probability assessment method is characterized by comprising the following steps:

acquiring service data;

abstract coding is carried out on the service data;

acquiring a first account vertex to be queried currently in the relationship network diagram, and determining an account identifier of the first account vertex;

determining the risk probability of the first account according to the account identification of the vertex of the first account;

when the first account risk probability is determined to be lower than a preset threshold value according to the account identification of the first account vertex, querying a second account vertex which has an association relation with the first account vertex in the relation network graph according to a preset rule;

and determining the risk probability of the first account according to the risk probability of the vertex of the second account.

2. The method according to claim 1, wherein after querying a second account vertex in the relationship network graph according to a preset rule, the second account vertex having an association relationship with the first account vertex, the method further comprises:

and when the risk probability of the second account vertex is lower than the preset threshold or the second account vertex is not inquired, determining the risk probability of the first account vertex according to the account information of the vertex within n degrees of the first account vertex, wherein n is a positive integer greater than or equal to 2.

3. The method of claim 1, wherein the service data composition format comprises: a source vertex \ t source vertex type \ t destination vertex type \ t account identification; the abstract coding of the service data specifically includes:

establishing a first mapping relation among the source vertex, the type of the source vertex and the code number of the source vertex;

and establishing a second mapping relation among the destination vertex, the destination vertex type and the destination vertex code number, wherein the source vertex is the first account vertex, and the account identifier in the service data is the account identifier corresponding to the first account vertex.

4. The method according to claim 3, wherein the updating an existing relationship network graph according to the abstract code or constructing a new relationship network graph specifically comprises:

and updating an existing relationship network graph or constructing a new relationship network graph according to the first mapping relationship, the second mapping relationship, the incidence relationship between the source vertex and the destination vertex, and the account identification corresponding to the first account vertex.

5. The method of claim 3, wherein after abstractly encoding the traffic data, the method further comprises:

storing the first mapping relation and the second mapping relation in a pre-constructed database.

6. The method of claim 5, wherein after storing the first mapping relationship and the second mapping relationship in a pre-built database, the method further comprises:

and after the service data is received again, matching a source vertex in the service data obtained again with the first mapping relation in the database, and/or matching a target vertex in the service data obtained again with the second mapping relation, so as to carry out abstract coding on the service data obtained again according to a final matching result.

7. The method according to claim 2, wherein the determining the risk probability of the vertex of the first account according to the account information of the vertex within n degrees of the vertex of the first account specifically includes:

according to the account information of the vertexes within the n degrees of the first account vertex, counting a first number belonging to the risk accounts in the vertexes within the n degrees of the first account vertex and the total number of the account vertexes, and taking the ratio of the first number to the total number of the account vertexes as the risk probability of the first account vertex.

8. The method according to any one of claims 1 to 7, wherein the determining the first account risk probability according to the account id of the first account vertex specifically includes:

when the account number identification corresponding to the first account number vertex is 1, determining that the first account number risk probability is a preset threshold value; or when the account number identification of the vertex of the first account number is 0, determining that the risk probability of the first account number is lower than the preset threshold value.

9. The method according to any of claims 1-7, wherein the acquired traffic data is transmitted in the form of a message queue.

10. The method according to any one of claims 1 to 7, wherein after determining the user risk probability corresponding to the first account according to the account id of the vertex of the first account, the method further comprises:

11. The method according to any one of claims 3-6, wherein the destination vertex includes, but is not limited to, one of: a device number, a mailbox, a mobile phone number, a WiFi number, a mobile phone number, or an identification number.

12. An account risk probability assessment device, the device comprising:

an obtaining unit, configured to obtain service data;

the coding unit is used for carrying out abstract coding on the service data;

the processing unit is further configured to determine account id of the first account vertex;

when the first account risk probability is determined to be lower than a preset threshold value according to the account identification of the first account vertex, querying a second account vertex which has an association relation with the first account vertex in the relation network graph according to a preset rule; and determining the risk probability of the first account according to the risk probability of the vertex of the second account.

13. An account risk probability assessment system, the system comprising: at least one processor and memory;

the processor is used for executing an account risk probability assessment program stored in the memory to realize the account risk probability assessment method according to any one of claims 1 to 11.

14. A computer storage medium storing one or more programs executable by the account risk probability assessment system according to claim 13 to implement the account risk probability assessment method according to any one of claims 1 to 11.