CN111260257A

CN111260257A - Wind control model construction method, wind control auditing device and computer equipment

Info

Publication number: CN111260257A
Application number: CN202010120287.7A
Authority: CN
Inventors: 万忠伟; 甘丽婷
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2020-02-26
Filing date: 2020-02-26
Publication date: 2020-06-09
Also published as: WO2021169212A1

Abstract

The embodiment of the application provides a wind control model construction method, a wind control auditing device, computer equipment and a computer readable storage medium. The method belongs to the technical field of classification models, and comprises the steps of displaying a preset interface coding table, a preset query result coding table and a preset wind control result coding table through a list page when a preset operation for building a wind control model is received, receiving a selection instruction for determining a target interface code from the interface coding table, a target query result from the query result coding table and a target wind control result from the wind control result coding table through the list page to obtain a corresponding relation among the target interface code, the target query result and the target wind control result, respectively configuring the target interface code, the target query result and the target wind control result to nodes of a preset decision tree based on the corresponding relation, generating the wind control model based on the decision tree, improving the building efficiency of the wind control model, and improving the accuracy of wind control auditing based on the wind control model.

Description

Wind control model construction method, wind control auditing device and computer equipment

Technical Field

The present application relates to the field of classification model technology, and in particular, to a method for constructing a wind control model based on a decision tree, a method and an apparatus for auditing wind control based on a decision tree, a computer device, and a computer-readable storage medium.

Background

In the wind control service, one type of service can be handled only after a user performs wind control evaluation, a wind control model is generally used for the wind control evaluation of the user, and different wind control models are used for different services. For example, in a mobile phone staging service, a client can only handle the service after passing system wind control audit, and since different operators and different places and cities have different service development conditions, it is obviously infeasible to use the same set of wind control model, for example, in city a, there are many colleges and universities are many credit investigation blank households, and it is necessary to establish a set of wind control model suitable for university student groups different from ordinary salary groups. In general, different wind control models need to be correspondingly developed, when multiple services exist, multiple wind control models need to be developed, but the development of the multiple wind control models causes the problems of time consumption and labor consumption.

In order to support business development, the system needs to support configurable wind control model functions. In the conventional technology, a configurable wind control system exists, but various service scenes cannot be met, and a plurality of wind control models of specific service scenes still need to be developed and implemented by codes, so that great manpower is required for constructing or adjusting the wind control models each time, and the updating efficiency of the wind control models is reduced.

Disclosure of Invention

The embodiment of the application provides a wind control model construction method based on a decision tree, a wind control auditing method based on the decision tree, a device, computer equipment and a computer readable storage medium, and can solve the problem of updating efficiency of a wind control model in the prior art, so that accuracy of wind control auditing is improved.

In a first aspect, an embodiment of the present application provides a method for building a wind control model based on a decision tree, where the method includes: when receiving a preset operation of building a wind control model, displaying a preset interface coding table, a preset query result coding table and a preset wind control result coding table through a list page; the interface coding table comprises a plurality of interface codes, the query result coding table comprises a plurality of query results, and the wind control result coding table comprises a plurality of wind control results; receiving a selection instruction for determining a target interface code from the interface code table, a target query result from the query result code table and a target wind control result from the wind control result code table through the list page, and obtaining a corresponding relation among the target interface code, the target query result and the target wind control result; and respectively configuring the target interface code, the target query result and the target wind control result at nodes of a preset decision tree based on the corresponding relation to generate a wind control model based on the decision tree.

In a second aspect, an embodiment of the present application provides a wind control auditing method based on a decision tree, where the method includes: receiving user data of a user, wherein the user data comprises preset information used for determining the service type of the user; calling a wind control model based on a decision tree from a preset storage file according to the preset information; and performing wind control auditing according to the user data through the wind control model based on the decision tree.

In a third aspect, an embodiment of the present application further provides a wind control model building apparatus based on a decision tree, including: the display unit is used for displaying a preset interface coding table, a preset inquiry result coding table and a preset wind control result coding table through a list page when a preset operation of building a wind control model is received; the interface coding table comprises a plurality of interface codes, the query result coding table comprises a plurality of query results, and the wind control result coding table comprises a plurality of wind control results; the first receiving unit is used for receiving a selection instruction for determining a target interface code from the interface code table, a target query result from the query result code table and a target wind control result from the wind control result code table through the list page so as to obtain the corresponding relation among the target interface code, the target query result and the target wind control result; and the generating unit is used for respectively configuring the target interface code, the target query result and the target wind control result at nodes of a preset decision tree based on the corresponding relation to generate a wind control model based on the decision tree.

In a fourth aspect, an embodiment of the present application further provides a wind control auditing apparatus based on a decision tree, including: a second receiving unit, configured to receive a user profile of a user, where the user profile includes preset information for determining a service type of the user; the calling unit is used for calling the wind control model based on the decision tree from a preset storage file according to the preset information; and the auditing unit is used for carrying out wind control auditing according to the user data through the decision tree-based wind control model.

In a fifth aspect, an embodiment of the present application further provides a computer device, where the computer device includes a memory and a processor connected to the memory; the memory is used for storing a computer program; the processor is configured to run a computer program stored in the memory to perform the steps of the decision tree based wind control model building method or the steps of the decision tree based wind control auditing method.

In a sixth aspect, the present application further provides a computer-readable storage medium, where a computer program is stored, and when executed by a processor, the computer program causes the processor to implement the steps of the decision tree-based wind control model building method or the steps of the decision tree-based wind control auditing method.

The embodiment of the application provides a wind control model construction method based on a decision tree, a wind control auditing method based on the decision tree, a device, computer equipment and a computer readable storage medium. In the embodiment of the application, when the wind control model based on the decision tree is constructed, the preset three code tables are displayed through the list page, and the wind control model manager selects the matching relation corresponding to each node of the decision tree from the three code tables according to business requirements to generate the wind control model based on the decision tree, compared with the traditional technology for developing the wind control model by developing codes or the traditional technology for simply selecting and combining fixed wind control conditions, the method has the advantages that the three code tables are flexible and refined, so that when the wind control model is constructed based on the three code tables and the decision tree, the constructed wind control model also has the advantages of refinement and flexibility, and takes effect immediately after the wind control model is configured, and the timeliness of the wind control model configuration is improved, the construction efficiency of the wind control model is improved.

Furthermore, on the basis of the wind control model based on the decision tree, the construction and the updating of the wind control model can be performed according to the requirements of the actual business each time, so that the correspondence between the wind control model and the business requirements is improved, and the accuracy of wind control auditing is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic flowchart of a method for constructing a wind control model based on a decision tree according to an embodiment of the present application;

FIG. 2 is a schematic diagram illustrating a relationship between three code tables involved in a decision tree-based wind control model according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a decision tree architecture according to an embodiment of the present application;

fig. 4 is a schematic flow chart of a decision tree-based wind control auditing method according to an embodiment of the present application;

FIG. 5 is a schematic diagram of another decision tree architecture provided by an embodiment of the present application;

fig. 6 is a sub-flow diagram of a decision tree-based wind control auditing method according to an embodiment of the present application;

FIG. 7 is a schematic block diagram of a wind control model building apparatus based on a decision tree according to an embodiment of the present application;

FIG. 8 is a schematic block diagram of a wind-controlled auditing apparatus based on a decision tree according to an embodiment of the present application; and

fig. 9 is a schematic block diagram of a computer device provided in an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. 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 application.

It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

Please refer to fig. 1 to 3. Fig. 1 is a schematic flowchart of a method for constructing a wind control model based on a decision tree according to an embodiment of the present application, fig. 2 is a schematic diagram of a relationship between three code tables involved in the wind control model based on the decision tree according to the embodiment of the present application, and fig. 3 is a schematic diagram of a decision tree architecture according to the embodiment of the present application. As shown in fig. 1, the method comprises the following steps S101-S103:

s101, when a preset operation of building a wind control model is received, displaying a preset interface coding table, a preset query result coding table and a preset wind control result coding table through a list page; the interface coding table comprises a plurality of interface codes, the query result coding table comprises a plurality of query results, and the wind control result coding table comprises a plurality of wind control results.

Specifically, an interface coding table is preset, the interface coding table includes a plurality of interface codes, each interface code corresponds to one query result coding table, each query result coding table includes a plurality of query results, each query result corresponds to one wind control result coding table, and each wind control result coding table includes a plurality of wind control results. When the wind control model is required to be built, a wind control model manager starts to build the wind control model, the computer equipment receives the preset operation of the wind control model manager for building the wind control model, and when the preset operation of building the wind control model is received, the preset interface coding table, the preset query result coding table and the preset wind control result coding table are displayed through the list page. For example, the computer device receives an operation of constructing a wind control model, and sequentially displays a preset interface coding table, a query result coding table corresponding to each interface code included in the interface coding table, and a wind control result coding table corresponding to each query result included in each query result coding table according to the operation in a preset manner through a list page. Further, the display modes of the three code tables of the interface code table, the query result code table and the wind control result code table may include the following two modes:

1) and simultaneously displaying the preset interface code table, the query result code table corresponding to each interface code contained in the interface code table and the wind control result code table corresponding to each query result contained in the query result code table on a list page so as to enable a wind control model manager to select from the three code tables in sequence.

2) Displaying a preset interface code table, selecting a target interface code from the interface code table according to a wind control model manager, then displaying a query result code table corresponding to the target interface code, determining a target query result from the query result code table according to the wind control model manager, and then displaying a wind control result code table corresponding to the target query result, so that the wind control model manager can self-define the target wind control result corresponding to the target query result according to business needs.

It should be noted that, for the display modes of the three code tables, various specific implementation forms may be designed according to the pages of the list page, and the association relationship of the three code tables shown in fig. 2 is embodied regardless of the display order and the display mode of the three code tables, that is, the correspondence relationship between each interface code included in the three code tables, the query result code table corresponding to each interface code, and the wind control result corresponding to each query result.

S102, receiving a selection instruction for determining a target interface code from the interface code table, determining a target query result from the target query result code table and determining a target wind control result from the wind control result code table through the list page, and obtaining a corresponding relation among the target interface code, the target query result and the target wind control result.

Specifically, a wind control model manager selects a required interface code from an interface code table according to business requirements to obtain a target interface code, then selects a required target query result from a query result code table associated with each target interface code, and finally selects a target wind control result corresponding to each target query result from a wind control result code table corresponding to each target query result, and a computer device receives a selection instruction of the wind control model manager for sequentially determining the target interface code from the interface code table, determining the target query result corresponding to the target interface code from the query result code table, and determining the target wind control result corresponding to the target query result from the wind control result code table according to preset target interface codes, And obtaining the corresponding relation among the target interface code, the target query result and the target wind control result according to the incidence relation between the target query result and the target wind control result. Referring to fig. 2, the interface codes 2 corresponding to the decision tree nodes 2 shown in fig. 2 correspond to the query results 1 and the query results 2, respectively, and the respective query results, and the interface codes 2 may also be customized to correspond to the query results 3 and the wind control results thereof, so as to form a corresponding relationship between the target interface codes, each of the target query results, and the target wind control results corresponding to each of the target query results. The association relationship among the interface codes, the query results and the wind control results can be realized according to one-to-one, one-to-many and many-to-one mapping relationships in the design of the database table, for example, in an SQL database, a one-to-many mapping relationship realization method is generally to add a foreign key on the inside and outside of one of the more sides. The one-to-many mapping relation is realized in JAVA, and can be realized by defining a class combination array. In the embodiment of the present application, the association relationship between the interface code, the query result, and the wind control result may specifically include the following two ways:

1) the mapping relation between the interface coding and the query result is a one-to-many mapping relation.

2) The mapping relation between the query result and the wind control result can be a one-to-one mapping relation or a many-to-one mapping relation. For example, if the wind control results corresponding to all the query results are the same, each query result corresponds to one-to-one mapping relationship of one wind control result coding table, the number of the wind control result coding tables can be increased, so that the resource reuse of the database is increased, the query results and the wind control result coding tables can adopt many-to-one mapping relationships, namely, when each query result sets the wind control result corresponding to each query result, the same wind control result coding table is called, so that the resources of the wind control result coding tables are saved, and the use efficiency of the wind control result coding tables is improved.

S103, respectively configuring the target interface code, the target query result and the target wind control result at nodes of a preset decision tree based on the corresponding relation, and generating a wind control model based on the decision tree.

Specifically, each node of the decision tree corresponds to an interface code, each interface code is associated with one or more query results, each query result corresponds to a wind control result, the corresponding relationship corresponding to each interface code is preset to correspond to one node of the decision tree to generate a wind control model based on the decision tree, that is, the corresponding relationship among the target interface code, the target query result and the target wind control result is correspondingly associated with the node of the decision tree through the interface code, so that the wind control model based on the decision tree is generated.

The embodiment of the application is based on the design of an interface coding table, a query result coding table and a wind control result coding table, the three code tables of the interface coding table, the query result coding table and the wind control result coding table are pre-established, when the wind control model based on a decision tree is established, the preset operation of establishing the wind control model is received, when the preset operation of establishing the wind control model is received, the pre-set interface coding table, the query result coding table and the wind control result coding table are displayed through a list page, a target interface code is determined from the interface coding table, a target query result is determined from the target query result coding table through the list page, a selection instruction of the target wind control result is determined from the wind control result coding table, and the corresponding relation among the target interface code, the target query result and the target wind control result is obtained, and the corresponding relation corresponding to the interface codes is preset to correspond to nodes of a decision tree to generate a wind control model based on the decision tree, so that a wind control model manager customizes a target interface code corresponding to each node, a plurality of target query results corresponding to each target interface code and a target wind control result corresponding to each target query result in a three-code table according to service requirements corresponding to service types in the wind control model based on the decision tree to generate the wind control model based on the decision tree, the decision tree is customized, one decision tree corresponds to a final wind control model, the flexible configuration requirements of the wind control service on the wind control model are met, and personalized configuration of the wind control model under different scenes can be supported according to different service requirements. Compared with the configurable wind control system in the prior art, the configurable wind control system in the prior art has the advantages that a batch of fixed wind control conditions are defined in advance, and then simple selection and combination are performed, so that fine configuration cannot be realized, the configuration of the wind control model is not flexible enough, and the fine configuration of interface levels of the wind control model under various service scenes cannot be realized, so that the wind control models of a plurality of specific service scenes in the prior art still need to be developed with codes, great manpower is needed for each adjustment, the construction and updating of the wind control model based on the decision tree in the embodiment of the application have simplicity and high efficiency, and the construction and updating efficiency of the wind control model is improved, the timeliness of the construction and updating of the wind control model is improved.

In one embodiment, the step of receiving, through the list page, a selection instruction for determining a target interface code from the interface code table, a target query result from the target query result code table, and a target wind control result from the wind control result code table to obtain a corresponding relationship among the target interface code, the target query result, and the target wind control result includes:

receiving a selection instruction for determining a target interface code from the interface code table to obtain the target interface code;

displaying a query result code table associated with the target interface code through the list page;

receiving a selection instruction for determining a target query result from the query result coding table to obtain a target query result corresponding to the target interface code;

displaying a wind control result coding table associated with the target query result through the list page;

receiving a selection instruction for determining a target wind control result from the wind control result coding table to obtain a target wind control result corresponding to the target query result;

and associating the target interface code, the target query result and the target wind control result in a preset association mode to obtain a corresponding relation among the target interface code, the target query result and the target wind control result.

Specifically, a wind control model manager starts and configures a wind control model, computer equipment receives an operation of starting and configuring the wind control model, a preset interface coding table is displayed through a list page, a target interface code is selected from the interface coding table by the wind control model manager, the computer equipment receives selection of the interface code contained in the interface coding table to obtain the target interface code, after the target interface code selected by the wind control model manager is received, a query result coding table associated with each target interface code is displayed through the list page, the computer equipment receives selection of a query result contained in the query result coding table by the wind control model manager to obtain a target query result corresponding to the target interface code, and the query result is used for describing a preset classification corresponding to user data, for example, the age interface code corresponds to the division of the corresponding age group, the computer device further displays a wind control result code table associated with the target query result through the list page according to the target query result, the computer device receives the selection of the wind control result contained in the wind control result code table to obtain the target wind control result corresponding to the target query result, so as to obtain the target interface code selected by the wind control model manager, the target query result corresponding to the target interface code and the corresponding relationship between the wind control results corresponding to the target query result, and associates the target interface code, the target query result and the target wind control result in a preset association manner, for example, the interface code table and the query result are associated in a one-to-many association relationship, and the query result and the wind control result are associated in a one-to-one association relationship, and obtaining the corresponding relation among the target interface code, the target query result and the target wind control result. In the embodiment of the application, the interface coding table, each query result coding table corresponding to the target interface code and the wind control result coding table corresponding to each target query result are sequentially displayed according to the selection of a model manager in sequence, and the wind control model manager selects the target interface code, a plurality of target query results corresponding to each target interface code and target wind control results corresponding to each target query result from three code tables, so that the visual page design can be hierarchical, and reasonable page layout is constructed, thereby saving page resources and cache resources of computer equipment, improving the display efficiency of the computer equipment, and particularly improving the resource utilization rate of the computer equipment when the computer equipment runs in a multi-task mode.

In one embodiment, each query result contained in the query result encoding table is correspondingly set with a query result encoding; the step of receiving a selection instruction for determining a target wind control result from the wind control result coding table to obtain a target wind control result corresponding to the target query result comprises:

acquiring a target query result code corresponding to the target query result;

displaying a wind control result coding table associated with the target query result coding through the list page;

and receiving a selection instruction for determining a target wind control result from the wind control result coding table to obtain a target wind control result corresponding to the target query result code, so as to obtain a target wind control result corresponding to the target query result.

Specifically, a corresponding query result code is set in a query result code table according to each query result, and the established query result code table includes the query result, the query result code corresponding to the query result, and the query result judgment condition, wherein the query result is used for describing a corresponding classification category obtained by the data specified by the user in advance according to the preset classification condition satisfied by the data. The query result, the query result code and the query result judgment condition can be set respectively, so that the query result, the query result code and the query result judgment condition have flexibility of respective setting. For example, please refer to table 1, where table 1 is an example of a query result code table of an age control interface, the interface code return result of the age control interface is age, and the following query results shown in table 1 may be configured. Further, the query results in table 1 may be further subdivided according to the service requirements, for example, the query result judgment conditions are divided into five conditions of 0-17 years old, 18-30 years old, 31-50 years old, 50-65 years old and over 65 years old, and the corresponding query results and the query result codes are correspondingly adjusted into five types.

Table 1

Further, as can be seen from table 1, in the embodiment of the present application, since only different query result determination conditions need to be customized, the user condition control interface corresponding to one interface code can return various different corresponding query results according to the customized query result determination conditions, so that the same user condition control interface realizes customization of different conditions, and the more detailed the definition of the customized query result determination conditions, the more detailed the query result returned by the interface code, and the more detailed configuration of the wind control model can be realized. For example, the age control interface can return 4 query results shown in table 1, the age control interface can also return 5 query results according to business requirements, and the age control interface can also return 3 other query results according to business requirements, so that a wind control model manager can configure the wind control model finely in a background system through a visual wind control model configuration page, thereby improving the flexibility and accuracy of the interface codes for returning the query results, and realizing the accuracy, flexibility and fine configuration of the wind control model setting.

Further, please refer to table 2, where table 2 is an example of a wind control result encoding table. In table 2, two major categories of "pass" and "reject" wind control results are respectively established according to the wind control requirements of different service requirements, and each major category of results can support configuration of a plurality of specific minor categories of results. The wind control result can be set according to the business requirement, for example, a wind control result can be uniquely determined according to the business requirement by combining a custom credit line with a query result code, where the custom credit line refers to a requirement corresponding to a preset condition that the credit can be obtained only when the preset condition is met, for example, for an age condition, the wind control result corresponding to the age less than 18 years is rejected, or the wind control result corresponding to the age less than 22 years is rejected, where the credit line is self-defined according to the business requirement when the age less than 18 years or the age less than 22 years is rejected.

Table 2

With continued reference to table 2, if table 2 is for an organization that is a telecom (campus) card service, the service transaction requirements allow clients that are full of 18 to 70 years to be able to do so, and the result of the wind control is selectable: 1) the client type is "age 18 years (client _ class 002)", and the wind control result is "pass". 2) The client type is "age over 70 years (client _ class 004)", and the wind control result is "reject".

In the embodiment of the application, a corresponding query result code is set in the query result code table according to each query result, the wind control result corresponding to the query result is associated with the query result code corresponding to the query result, the computer device obtains the target query result code corresponding to the target query result according to the target query result after obtaining the target query result selected by the wind control model manager, then the wind control result code table associated with the target query result code is displayed through the list page, the computer device receives the selection of the wind control result contained in the wind control result code table by the wind control model manager to obtain the target wind control result corresponding to the target query result code, so as to obtain the target wind control result corresponding to the target query result, and aiming at a plurality of nodes of the decision tree, repeating the generation process of the corresponding relation corresponding to one node until a model manager completes the setting of the wind control auditing model according to business requirements so as to generate the wind control auditing model based on the decision tree. The query result and the wind control result are associated by arranging the query result code between the query result and the wind control result, and because the query result and the wind control result are not directly associated, when the query result or the wind control result is modified, the wind control result and the query result do not need to be directly modified in codes, so that the workload of model development is reduced, the configuration of the wind control model is simple and clear, the error probability of the configuration of the complex wind control model is reduced, in addition, the use threshold of a manager of the wind control model is reduced, the configuration operation of the wind control model is enabled to be simple and efficient as far as possible, the generation efficiency of the wind control model is improved, and the updating timeliness of the wind control model is improved.

Referring to fig. 4, fig. 4 is a schematic flowchart of a decision tree-based wind control auditing method according to an embodiment of the present application. As shown in fig. 4, the method comprises the following steps S401-S403:

s401, receiving user data of a user, wherein the user data comprises preset information used for determining the service type of the user.

The service type refers to the type of the service which is obtained by classifying the service according to the service target and takes different target groups as target objects. For example, in the wind control audit, one type of wind control audit business is for a college student group, and because the college student group and a salary group have different conditions in all aspects, the respective wind control audits for the college student group and the salary group are performed under different conditions, and the type of the wind control audit business for the college student group and the type of the wind control audit business for the salary group are correspondingly generated. The preset information comprises a user address, a user age, a service name and an identification number, and is mainly used for judging and identifying the service type handled by the user.

Specifically, when a user transacts a service which needs to be subjected to wind control auditing, the user is required to provide user data through computer equipment, the computer equipment receives the user data of the user, the user data comprises preset information used for determining the service type of the user, and the service type of the service transacted by the user is judged through the preset information. For example, when a user transacts a consumption staging service, the user profile to be provided includes personal data and a transacted package type, and the service type of the user is determined according to the information such as the personal data and the package type.

S402, calling a wind control model based on the decision tree from a preset storage file according to the preset information.

The Decision Tree is a Tree structure, wherein each internal node represents an attribute, each node represents a branch, each branch represents an attribute output, each node at least comprises a leaf node, each leaf node represents a wind control result, and the nodes of the Decision Tree support serial and parallel relations, and/or relations, multi-level structures and the like.

Specifically, in order to implement the situation that different wind control models need to be set in different service scenarios, for example, due to different cities and different package service types, the wind control model in the embodiment of the present application is described based on the decision tree, and the wind control model is constructed based on the decision tree-based wind control model construction method in each of the above embodiments. And when the wind control auditing is carried out on the user, a pre-constructed decision tree-based wind control model of the service type corresponding to the preset information is called from a preset storage file according to the preset information.

Further, the preset information includes a user address and a target service name. The step of calling the wind control model based on the decision tree from a preset storage file according to the preset information comprises the following steps: and calling a decision tree-based wind control model of the service type corresponding to the user address and the target service name in advance from a preset storage file according to the user address and the target service name.

Specifically, in the wind control service, the corresponding wind control models are set according to different groups in different regions, so that the wind control audit is performed according to the user address and the target service name of the user when the wind control audit is performed. If the preset information comprises a user address and a target service name, a pre-constructed decision tree-based wind control model of the service type corresponding to the user address and the target service name is called from a preset storage file according to the user address and the target service name. For example, in a wind control auditing service, because different service operators have different service development conditions in different cities and generally make corresponding service types according to the cities and target groups, a wind control model corresponding to the wind control auditing of a user can be determined through preset information such as a user address and a target service name, and the wind control model can be obtained only by configuring a visual wind control model configuration page in a system background in advance by a wind control model manager according to actual service requirements of the different cities, without code development of the wind control model, so that the wind control model is configured simply, flexibly and finely, and the accuracy and the efficiency of wind control auditing processing are improved.

And S403, performing wind control audit according to the user data through the wind control model based on the decision tree.

Specifically, since the classification of the target can be realized through the decision tree (also referred to as a classification tree), in the embodiment of the present application, the wind control audit can be performed on the wind control audit target through the decision tree, so as to obtain the result of the wind control audit according to the wind control model, for example, obtaining the audit results of two categories, that is, "audit passed" and "audit not passed". Furthermore, the wind control auditing is carried out according to the user data through the wind control model based on the decision tree, and the wind control auditing result of the user can be obtained according to the preset structure of the decision tree and the wind control result of each node in the decision tree. For example, according to the user data, a target query result corresponding to each interface code in the wind control model is obtained through each interface code, a target wind control result corresponding to the target query result is obtained according to the target query result, so as to obtain a target wind control result corresponding to the interface code, and thus a target wind control result corresponding to each node included in the wind control model is obtained, and thus a wind control auditing result is obtained according to the wind control model.

Furthermore, the structure of the decision tree and the relationship between the nodes may be set according to the service requirement, for example, the nodes of the decision tree may include an and relationship and an or relationship, the and relationship is used to describe that the wind control model needs to simultaneously satisfy that the wind control results of two nodes are both "pass", and the or relationship is used to describe that the wind control model needs to satisfy that at least one of the wind control results of two nodes is "pass". Taking the example that nodes included in a wind control model based on a decision tree include an and relationship and an or relationship, the step of obtaining a wind control auditing result according to the wind control model includes: judging whether the wind control results corresponding to the interface codes corresponding to the nodes with the and relation in the wind control model are all 'pass'; if the wind control results corresponding to the interface codes corresponding to the nodes with the and relation in the wind control model are all 'pass', judging that the wind control audit of the user is passed; and if the wind control results corresponding to the interface codes corresponding to the nodes with the and relation in the wind control model are not all 'pass', judging that the wind control audit of the user is not passed. For example, in the wind control model based on the decision tree, the decision tree includes a plurality of nodes, and a relationship between the plurality of nodes may be an and relationship or an or relationship, please continue to refer to fig. 3, as shown in fig. 3, the decision tree corresponding to the wind control model shown in fig. 3 includes nodes: A. a1, A2, A3, A11, A12, A31 and A32, wherein each node represents an interface code, the nodes can be in an AND or OR relationship, the AND relationship between the nodes represents that the conditions of two nodes need to be met simultaneously, the OR relationship between the nodes represents that the conditions of one of the two nodes are met, and the result of the decision tree can be obtained through the AND or OR relationship between the nodes and the wind control result corresponding to each node, so that the result of the wind control audit is obtained.

When the wind control auditing based on the decision tree is realized, the wind control model constructed by the wind control model construction method based on the decision tree in each embodiment can be subjected to fine user-defined configuration at an interface level, so that the construction and updating of the wind control model can meet the requirements of actual services each time, and the wind control model becomes effective immediately after being configured, so that the wind control model and the wind control auditing service can be subjected to fine efficient matching, and the efficiency and the accuracy of wind control auditing processing are improved.

In one embodiment, each query result contained in the query result code table is correspondingly provided with a query result code; the step of performing wind control auditing according to the user data through the wind control model based on the decision tree comprises the following steps:

according to the user data, acquiring a target query result corresponding to each interface code through the interface code corresponding to each node contained in the wind control model;

acquiring a target query result code corresponding to each target query result according to each target query result;

according to each target query result code, acquiring a target wind control result corresponding to each target query result code to obtain a wind control result corresponding to each node;

and performing wind control auditing on the user through the wind control model based on the decision tree according to the wind control result corresponding to each node.

Specifically, the computer device calls a wind control model of a service type corresponding to preset information according to the preset information in user data, matches the received user data with each node of the wind control model based on the decision tree, for example, the age information of a user is matched with an interface code through a node corresponding to an age interface code in the wind control model, the income information of the user is matched with an interface code through a node corresponding to an income interface code in the wind control model, and the like, obtains a target query result corresponding to each interface code in the wind control model through each interface code, obtains a target query result code corresponding to each target query result according to each target query result, and obtains a target wind control result corresponding to each target query result code according to each target query result code, and performing wind control examination on the user by combining the tree structure of the decision tree according to the wind control result corresponding to each node.

In an embodiment, before the step of obtaining the target wind control result corresponding to each target query result code, the method further includes: and pre-querying a wind control result corresponding to the node contained in the wind control model in a pre-query mode.

The pre-query means pre-querying a wind control result of the credit investigation wind control interface, and the pre-query mode comprises pre-query according to the interface type of the credit investigation wind control interface, pre-query according to the interface query time consumption of the credit investigation wind control interface and pre-query of the credit investigation wind control interface related to the wind control model by combining the two modes.

Specifically, by pre-querying the wind control result of the interface code corresponding to the node included in the wind control model, the response time of the wind control auditing system can be shortened, and the efficiency of processing the wind control auditing by the computer equipment can be improved.

Further, taking the pre-query according to the interface type of the credit investigation wind control interface as an example, in one embodiment, the interface codes include a plurality of interface codes, each interface code corresponds to one credit investigation wind control query interface, the decision tree includes a plurality of hierarchies, and the pre-query of the wind control result corresponding to the node included in the wind control model by the pre-query method includes:

when wind control auditing is initialized, concurrent inquiry is carried out on a first type of credit investigation wind control inquiry interface, and each inquiry result corresponding to the first type of credit investigation wind control inquiry interface is stored in a cache, wherein the first type of credit investigation wind control inquiry interface comprises a free credit investigation wind control inquiry interface and a credit investigation wind control inquiry interface during fee packet; according to the executed current level of the node of the decision tree, requesting the query result of a second type credit investigation wind control query interface corresponding to a child node contained in a first preset number of layers below the current level in advance, and storing the query result of the second type credit investigation wind control query interface in the cache for subsequent decision tree calling, wherein the second type credit investigation wind control query interface comprises a query interface for charging in each query.

Specifically, in the wind control audit, in order to identify the risk of the client more accurately, user data needs to be obtained from multiple credit data sources to establish a wind control model, such as a third-party identity check interface, a blacklist interface, a multi-head loan interface, a credit inquiry interface, and the like. In order to ensure the wind control auditing efficiency under the condition of multiple data sources, the wind control auditing data of the multiple data sources can be processed separately through the following steps:

1) when wind control auditing is initialized, concurrent inquiry is carried out on a first type of credit investigation wind control inquiry interface, and each inquiry result corresponding to the first type of credit investigation wind control inquiry interface is stored in a cache, wherein the first type of credit investigation wind control inquiry interface comprises a free credit investigation wind control inquiry interface and a credit investigation wind control inquiry interface during fee packet. 2) According to the current level to which the node of the executed decision tree belongs, the respective query results of second-type credit investigation wind control query interfaces corresponding to the sub-nodes with the first preset number of layers below the current level are requested in advance, the respective query results of the second-type credit investigation wind control query interfaces are stored in the cache for being called by the subsequent decision tree, and the second-type credit investigation wind control query interfaces comprise query interfaces for charging in each query.

Because the most occupied time in the operation of the wind control model is the waiting time of external data interface query, and the external data query is charged, all interfaces cannot be queried at the beginning, otherwise, the query is wasted for users who do not pass wind control audit. Therefore, the following two steps can be taken for separate query, for example, 1) when the user initializes the credit audit, all free interfaces and interfaces in the charge package, for example, interfaces in the charge package year, are concurrently queried and stored in a cache such as a Redis cache for the subsequent decision tree call. 2) For a charged interface, according to a hierarchy executed by a current decision tree, a first preset number of layers below the current hierarchy is requested in advance, for example, interface data of two layers of child nodes below the current hierarchy are stored in a cache such as a Redis cache for calling of a subsequent decision tree. Referring to fig. 5, fig. 5 is a schematic view of another decision tree architecture in the decision tree-based wind control auditing method according to the embodiment of the present application. As shown in fig. 5, if the determination a is currently performed, data of six interfaces, such as B1, B2, C1, C2, C3 and C4, may be queried in advance, and if the determination a can obtain the wind control result, it is not necessary to query data of eight interfaces, such as D1, D2, D3, D4, D5, D6, D7 and D8, especially when the interfaces D1-D8 include interfaces that need to be charged, it may avoid query waste, and shorten the response time of the credit auditing system; if B2 judgment is executed currently, data of six interfaces such as C3, C4, D5, D6, D7 and D8 need to be inquired in advance, if a wind control result can be obtained through B2 judgment, data of interfaces corresponding to nodes behind D5-D8 levels do not need to be inquired, and particularly when interfaces needing charging are contained in subsequent interfaces of D5-D8, inquiry waste can be avoided, and response time of a wind control auditing system can be shortened. In fig. 4, three logical or relationships between three levels of nodes are included in each of the nodes.

According to the embodiment of the application, through the pre-query mechanism of the credit investigation wind control interface in the wind control audit, the performance of processing credit audit by computer equipment is improved and the efficiency of credit audit is improved by shortening the response time of a credit audit system in the controllable range of credit investigation cost.

Further, for example, by performing pre-query according to the time consumption of the interface query of the credit investigation wind control interface, please refer to fig. 6, where fig. 6 is a sub-flow diagram of the decision tree-based wind control auditing method according to the embodiment of the present application. As shown in fig. 6, in the embodiment corresponding to the sub-process shown in fig. 6, the decision tree includes a plurality of levels, and the step of pre-querying the wind control result corresponding to the node included in the wind control model in a pre-query manner includes: s601, counting the time-consuming query data of each credit investigation wind control query interface in a preset time period before according to the time-consuming query historical data of each credit investigation wind control query interface; s602, sequencing the query time consumption data according to a preset sequence to obtain a preset number of credit investigation wind control query interfaces obtained according to the query time consumption in a sequence from top to bottom to form a credit investigation wind control query interface set; s603, judging whether the inquiry interfaces corresponding to the sub-nodes contained in the second preset number of layers below the current level of the decision tree execution node contain the credit investigation wind control inquiry interface in the credit investigation wind control inquiry interface set or not; s604, if the inquiry interfaces corresponding to the sub-nodes contained in the second preset number of layers below the current level to which the decision tree execution node belongs contain the credit investigation wind control inquiry interfaces in the credit investigation wind control inquiry interface set, calling the credit investigation wind control inquiry interfaces in the credit investigation wind control inquiry interface set, and storing inquiry results corresponding to the inquiry interfaces in the credit investigation wind control inquiry interface set in a cache for calling the follow-up decision tree; s605, if the inquiry interfaces corresponding to the child nodes included in the second preset number of layers below the current level to which the decision tree executing node belongs do not include the credit investigation wind control inquiry interface in the credit investigation wind control inquiry interface set, not calling the credit investigation wind control inquiry interface in the credit investigation wind control inquiry interface set.

Specifically, for the situation that user data needs to be acquired from multiple credit investigation data sources to establish a wind control model in wind control audit, time-consuming inquiry historical data of each credit investigation wind control inquiry interface can be counted according to time-consuming inquiry history data of each credit investigation wind control inquiry interface in a preset time period, inquiry time-consuming data are sorted according to a preset sequence to acquire a preset number of credit investigation wind control inquiry interfaces obtained according to the inquiry time-consuming sequence from top to bottom to form a credit investigation wind control inquiry interface set, whether a credit investigation wind control inquiry interface in the credit investigation wind control inquiry interface set is included in inquiry interfaces corresponding to sub-nodes included in a second preset number of layers below a current level to which a decision tree execution node belongs is judged, and if the credit investigation wind control inquiry interface corresponding to the sub-node included in the second preset number of layers below the current level to which the decision tree execution node belongs includes the credit investigation interface set, a decision tree execution node belongs to the current level And if the inquiry interface corresponding to the child node included in the second preset number of layers below the current level to which the decision tree execution node belongs does not include the credit investigation wind control inquiry interface in the credit investigation wind control inquiry interface set, the credit investigation wind control inquiry interface in the credit investigation wind control inquiry interface set is not called. For example, time-consuming monitoring is inquired according to each interface in the previous hour of history, the most time-consuming interface is counted, if the interface appears in the next five layers of child nodes, the interface is called in advance and stored in cache such as Redis cache and the like for calling of a subsequent decision tree, so that the inquiry efficiency is improved, the response time of a credit auditing system can be shortened, the performance of processing credit auditing by computer equipment is improved, and the efficiency of credit auditing is improved.

Furthermore, in one embodiment, the pre-query according to the interface type of the credit investigation wind control interface and the pre-query according to the time consumption of the interface query of the credit investigation wind control interface are combined to pre-query the credit investigation wind control interface involved in the wind control model.

Specifically, the pre-query may be performed according to the interface type of the credit investigation wind control interface, and then the pre-query may be performed according to the interface query time consumption of the credit investigation wind control interface, or the pre-query may be performed according to the interface query time consumption of the credit investigation wind control interface, and then the pre-query may be performed according to the interface type of the credit investigation wind control interface. Please continue to refer to fig. 5, the pre-query may be performed according to the interface type of the credit investigation wind control interface, that is, when the judgment a is currently performed, the data of six interfaces, i.e., B1, B2, C1, C2, C3 and C4, are queried, and then when the data of the six interfaces are queried, if the query time consumption is the longest through the statistics of C2, the pre-query is performed according to the interface query time consumption of the credit investigation wind control interface, the query is performed on C2, and then the data of five interfaces, i.e., B1, B2, C1, C3 and C4, are queried, so as to combine the above two manners. Or if the statistical C2 shows that the query time is the longest, the C2 can be queried in advance according to the interface query time consumption of the credit investigation wind control interface, then the pre-query is performed according to the interface type of the credit investigation wind control interface, namely, the judgment A is performed at present, and then the data of the five interfaces B1, B2, C1, C3 and C4 are queried in advance, so that the two modes are combined.

It should be noted that, in the wind control model building method based on the decision tree and the wind control auditing method based on the decision tree described in the above embodiments, technical features included in different embodiments may be recombined as needed to obtain a combined implementation, but all of them are within the protection scope claimed in the present application.

Referring to fig. 7, fig. 7 is a schematic block diagram of a decision tree-based wind control model building apparatus according to an embodiment of the present application. Corresponding to the wind control model construction method based on the decision tree, the embodiment of the application also provides a wind control model construction device based on the decision tree. As shown in fig. 7, the decision tree-based wind control model building apparatus includes a unit for executing the above decision tree-based wind control model building method, and the apparatus may be configured in a computer device such as a server. Specifically, referring to fig. 7, the apparatus 700 for constructing a wind control model based on a decision tree includes a display unit 701, a first receiving unit 702, and a generating unit 703.

The display unit 701 is configured to display a preset interface coding table, a preset query result coding table and a preset wind control result coding table through a list page when a preset operation for constructing a wind control model is received; the interface coding table comprises a plurality of interface codes, the query result coding table comprises a plurality of query results, and the wind control result coding table comprises a plurality of wind control results; a first receiving unit 702, configured to receive, through the list page, a selection instruction for determining a target interface code from the interface code table, a target query result from the query result code table, and a target wind control result from the wind control result code table, so as to obtain a corresponding relationship between the target interface code, the target query result, and the target wind control result; a generating unit 703, configured to configure the target interface code, the target query result, and the target wind control result to nodes of a preset decision tree respectively based on the correspondence, and generate a wind control model based on the decision tree.

In one embodiment, the first receiving unit 702 includes: the first receiving subunit is used for receiving a selection instruction for determining a target interface code from the interface code table to obtain the target interface code; the first display subunit is used for displaying the query result coding table associated with the target interface coding through the list page; the second receiving subunit is configured to receive a selection instruction for determining a target query result from the query result coding table, so as to obtain a target query result corresponding to the target interface code; the second display subunit is used for displaying the wind control result coding table associated with the target query result through the list page; the third receiving subunit is configured to receive a selection instruction for determining a target wind control result from the wind control result coding table, so as to obtain a target wind control result corresponding to the target query result; and the association subunit is used for associating the target interface code, the target query result and the target wind control result in a preset association mode so as to obtain a corresponding relation among the target interface code, the target query result and the target wind control result.

In one embodiment, each query result contained in the query result encoding table is correspondingly set with a query result encoding; the third receiving subunit includes: the acquisition subunit is used for acquiring a target query result code corresponding to the target query result; the third display subunit is used for displaying the wind control result coding table associated with the target query result coding through the list page; and the fourth receiving subunit is configured to receive a selection instruction for determining a target wind control result from the wind control result coding table, so as to obtain a target wind control result corresponding to the target query result code, and thus obtain a target wind control result corresponding to the target query result.

Referring to fig. 8, fig. 8 is a schematic block diagram of a decision tree-based wind control auditing apparatus according to an embodiment of the present application. Corresponding to the wind control auditing method based on the decision tree, the embodiment of the application also provides a wind control auditing device based on the decision tree. As shown in fig. 8, the decision tree-based wind control auditing apparatus includes a unit for executing the above decision tree-based wind control auditing method, and the apparatus may be configured in a computer device such as a terminal. Specifically, referring to fig. 8, the decision tree-based wind control auditing apparatus 800 includes a second receiving unit 801, a retrieving unit 802, and an auditing unit 803.

The second receiving unit 801 is configured to receive a user profile of a user, where the user profile includes preset information for determining a service type of the user; the calling unit 802 is configured to call a decision tree-based wind control model from a preset storage file according to the preset information; and the auditing unit 803 is configured to perform wind control auditing according to the user data through the decision tree-based wind control model.

In one embodiment, each query result contained in the query result code table is correspondingly provided with a query result code; the auditing unit 803 includes: the first obtaining subunit is configured to obtain, according to the user data, a target query result corresponding to each interface code through the interface code corresponding to each node included in the wind control model; the second obtaining subunit is configured to obtain, according to each target query result, a target query result code corresponding to each target query result; and the auditing subunit is used for carrying out wind control auditing on the user through the decision tree-based wind control model according to the respective wind control result corresponding to each node.

In one embodiment, the decision tree based wind control auditing apparatus 800 further includes: and the pre-query unit is used for pre-querying the wind control result corresponding to the node contained in the wind control model in a pre-query mode.

It should be noted that, as will be clear to those skilled in the art, the specific implementation process of the wind control model building device based on the decision tree and each unit thereof, and the specific implementation process of the wind control auditing device based on the decision tree and each unit thereof may refer to the corresponding description in the foregoing method embodiments, and are not described herein again for convenience and brevity of description.

Meanwhile, the division and connection modes of each unit in the wind control model building device based on the decision tree and the wind control auditing device based on the decision tree are only used for illustration, in other embodiments, the wind control model building device based on the decision tree and the wind control auditing device based on the decision tree can be divided into different units according to needs, and each unit in the wind control model building device based on the decision tree and the wind control auditing device based on the decision tree can also adopt different connection sequences and modes to respectively complete all or part of functions of the wind control model building device based on the decision tree and the wind control auditing device based on the decision tree.

The decision tree-based wind control model building device and the decision tree-based wind control auditing device can be respectively realized in the form of a computer program, and the computer program can be respectively run on a computer device as shown in fig. 9.

Referring to fig. 9, fig. 9 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 900 may be a computer device such as a desktop computer or a server, or may be a component or part of another device.

Referring to fig. 9, the computer device 900 includes a processor 902, memory, and a network interface 905 connected by a system bus 901, where the memory may include a non-volatile storage medium 903 and an internal memory 904.

The non-volatile storage medium 903 may store an operating system 9031 and a computer program 9032. The computer program 9032, when executed, may cause the processor 902 to perform one of the above-described decision tree-based wind control model building methods, or may cause the processor 902 to perform one of the above-described decision tree-based wind control auditing methods.

The processor 902 is used to provide computing and control capabilities to support the operation of the overall computer device 900.

The internal memory 904 provides an environment for running a computer program 9032 in the non-volatile storage medium 903, and when the computer program 9032 is executed by the processor 902, the processor 902 may be enabled to execute a method for constructing a wind control model based on a decision tree as described above, or the processor 902 may be enabled to execute a method for auditing wind control based on a decision tree as described above.

The network interface 905 is used for network communication with other devices. Those skilled in the art will appreciate that the configuration shown in fig. 9 is a block diagram of only a portion of the configuration associated with the present application and does not constitute a limitation of the computer device 900 to which the present application is applied, and that a particular computer device 900 may include more or less components than those shown, or combine certain components, or have a different arrangement of components. For example, in some embodiments, the computer device may only include a memory and a processor, and in such embodiments, the structures and functions of the memory and the processor are consistent with those of the embodiment shown in fig. 9, and are not described herein again.

Taking the processor 902 described above as an example to execute one of the above-described wind control model building methods based on the decision tree, the processor 902 is configured to run a computer program 9032 stored in the memory, so as to implement the following steps: when receiving a preset operation of building a wind control model, displaying a preset interface coding table, a preset query result coding table and a preset wind control result coding table through a list page; the interface coding table comprises a plurality of interface codes, the query result coding table comprises a plurality of query results, and the wind control result coding table comprises a plurality of wind control results; receiving a selection instruction for determining a target interface code from the interface code table, a target query result from the query result code table and a target wind control result from the wind control result code table through the list page, and obtaining a corresponding relation among the target interface code, the target query result and the target wind control result; and respectively configuring the target interface code, the target query result and the target wind control result at nodes of a preset decision tree based on the corresponding relation to generate a wind control model based on the decision tree.

In an embodiment, when the processor 902 implements the steps of receiving, through the list page, a selection instruction for determining a target interface code from the interface code table, a target query result from the query result code table, and a target wind control result from the wind control result code table, and obtaining a corresponding relationship between the target interface code, the target query result, and the target wind control result, the following steps are specifically implemented: receiving a selection instruction for determining a target interface code from the interface code table to obtain the target interface code; displaying a query result code table associated with the target interface code through the list page; receiving a selection instruction for determining a target query result from the query result coding table to obtain a target query result corresponding to the target interface code; displaying a wind control result coding table associated with the target query result through the list page; receiving a selection instruction for determining a target wind control result from the wind control result coding table to obtain a target wind control result corresponding to the target query result; and associating the target interface code, the target query result and the target wind control result in a preset association mode to obtain a corresponding relation among the target interface code, the target query result and the target wind control result.

In one embodiment, each query result contained in the query result code table is set with a query result code; when the step of receiving the selection instruction for determining the target wind control result from the wind control result coding table to obtain the target wind control result corresponding to the target query result is implemented, the processor 902 specifically implements the following steps: acquiring a target query result code corresponding to the target query result; displaying a wind control result coding table associated with the target query result coding through the list page; and receiving a selection instruction for determining a target wind control result from the wind control result coding table to obtain a target wind control result corresponding to the target query result code, so as to obtain a target wind control result corresponding to the target query result.

Taking the processor 902 described above as an example for executing one of the above wind control auditing methods based on decision trees, the processor 902 is configured to run a computer program 9032 stored in a memory, so as to implement the following steps: receiving user data of a user, wherein the user data comprises preset information used for determining the service type of the user; calling a wind control model based on a decision tree from a preset storage file according to the preset information; and performing wind control auditing according to the user data through the wind control model based on the decision tree.

In one embodiment, each query result contained in the query result code table is correspondingly set with a query result code; when the processor 902 implements the step of performing the wind control audit according to the user data through the decision tree-based wind control model, the following steps are specifically implemented: according to the user data, acquiring a target query result corresponding to each interface code through the interface code corresponding to each node contained in the wind control model; acquiring a target query result code corresponding to each target query result according to each target query result; according to each target query result code, acquiring a target wind control result corresponding to each target query result code to obtain a wind control result corresponding to each node; and performing wind control auditing on the user through the wind control model based on the decision tree according to the wind control result corresponding to each node.

In an embodiment, before the step of obtaining the target query result code corresponding to each target query result code is implemented, the processor 902 further implements the following steps: and pre-querying a wind control result corresponding to the node contained in the wind control model in a pre-query mode.

It should be understood that, in the embodiment of the present Application, the Processor 902 may be a Central Processing Unit (CPU), and the Processor 902 may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable gate arrays (FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

It will be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiments may be implemented by a computer program, and the computer program may be stored in a computer readable storage medium. The computer program is executed by at least one processor in the computer system to implement the flow steps of the embodiments of the method described above.

Accordingly, the present application also provides a computer-readable storage medium. The computer readable storage medium may be a non-volatile computer readable storage medium, the computer readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of:

a computer program product which, when run on a computer, causes the computer to perform the steps of the decision tree based wind control model building method described in the embodiments above, or causes the computer to perform the steps of the decision tree based wind control auditing method described in the embodiments above.

The computer readable storage medium may be an internal storage unit of the aforementioned device, such as a hard disk or a memory of the device. The computer readable storage medium may also be an external storage device of the device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. provided on the device. Further, the computer-readable storage medium may also include both an internal storage unit and an external storage device of the apparatus.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses, devices and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The computer readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk or an optical disk, and various computer readable storage media capable of storing program codes.

Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the 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 application.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, various elements or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented.

The steps in the method of the embodiment of the application can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the application can be combined, divided and deleted according to actual needs. In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing an electronic device (which may be a personal computer, a terminal, or a network device) to perform all or part of the steps of the method according to the embodiments of the present application.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A wind control model construction method based on a decision tree is characterized by comprising the following steps:

when receiving a preset operation of building a wind control model, displaying a preset interface coding table, a preset query result coding table and a preset wind control result coding table through a list page; the interface coding table comprises a plurality of interface codes, the query result coding table comprises a plurality of query results, and the wind control result coding table comprises a plurality of wind control results;

receiving a selection instruction for determining a target interface code from the interface code table, a target query result from the query result code table and a target wind control result from the wind control result code table through the list page, and obtaining a corresponding relation among the target interface code, the target query result and the target wind control result;

and respectively configuring the target interface code, the target query result and the target wind control result at nodes of a preset decision tree based on the corresponding relation to generate a wind control model based on the decision tree.

2. The method as claimed in claim 1, wherein the step of receiving, through the list page, a selection instruction for determining a target interface code from the interface code table, a target query result from the query result code table, and a target wind control result from the wind control result code table to obtain a corresponding relationship between the target interface code, the target query result, and the target wind control result includes:

3. The method for constructing a wind control model based on a decision tree according to claim 2, wherein each query result contained in the query result code table is correspondingly provided with a query result code;

the step of receiving a selection instruction for determining a target wind control result from the wind control result coding table to obtain a target wind control result corresponding to the target query result comprises:

acquiring a target query result code corresponding to the target query result;

4. A wind control auditing method based on a decision tree is characterized by comprising the following steps:

receiving user data of a user, wherein the user data comprises preset information used for determining the service type of the user;

calling a wind control model based on a decision tree from a preset storage file according to the preset information;

and performing wind control auditing according to the user data through the wind control model based on the decision tree.

5. The wind control auditing method based on decision tree according to claim 4, characterized in that each query result contained in the query result code table is correspondingly set with a query result code;

the step of performing wind control auditing according to the user data through the wind control model based on the decision tree comprises the following steps:

6. The decision tree-based wind control auditing method according to claim 5, where before the step of obtaining a target wind control result corresponding to each target query result code, the method comprises:

and pre-querying a wind control result corresponding to the node contained in the wind control model in a pre-query mode.

7. A wind control model building device based on a decision tree is characterized by comprising the following components:

the display unit is used for displaying a preset interface coding table, a preset inquiry result coding table and a preset wind control result coding table through a list page when a preset operation of building a wind control model is received; the interface coding table comprises a plurality of interface codes, the query result coding table comprises a plurality of query results, and the wind control result coding table comprises a plurality of wind control results;

the first receiving unit is used for receiving a selection instruction for determining a target interface code from the interface code table, a target query result from the query result code table and a target wind control result from the wind control result code table through the list page so as to obtain the corresponding relation among the target interface code, the target query result and the target wind control result;

and the generating unit is used for respectively configuring the target interface code, the target query result and the target wind control result at nodes of a preset decision tree based on the corresponding relation to generate a wind control model based on the decision tree.

8. A wind control auditing device based on a decision tree is characterized by comprising:

a second receiving unit, configured to receive a user profile of a user, where the user profile includes preset information for determining a service type of the user;

the calling unit is used for calling the wind control model based on the decision tree from a preset storage file according to the preset information;

and the auditing unit is used for carrying out wind control auditing according to the user data through the decision tree-based wind control model.

9. A computer device, comprising a memory and a processor coupled to the memory; the memory is used for storing a computer program; the processor is adapted to run a computer program stored in the memory to perform the steps of the method according to any of the claims 1-3 or to perform the steps of the method according to any of the claims 4-6.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, carries out the steps of the method according to any one of claims 1-3, or carries out the steps of the method according to any one of claims 4-6.