CN113888181A

CN113888181A - Business processing and risk detection strategy system construction method, device and equipment

Info

Publication number: CN113888181A
Application number: CN202111243667.0A
Authority: CN
Inventors: 黄莹
Original assignee: Alipay Hangzhou Information Technology Co Ltd; Ant Blockchain Technology Shanghai Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd; Ant Blockchain Technology Shanghai Co Ltd
Priority date: 2021-10-25
Filing date: 2021-10-25
Publication date: 2022-01-04

Abstract

The embodiment of the specification provides a method, a device and equipment for constructing a business processing and risk detection strategy system, wherein the business processing method comprises the following steps: acquiring service data of a target service to be subjected to risk detection processing; performing risk detection processing on the service data based on a multi-layer risk detection strategy system which is constructed in advance to obtain risk detection result information; performing corresponding service processing on the target service according to the risk detection result information; the risk detection system comprises a risk detection strategy system and a risk detection strategy system, wherein the risk detection strategy system is provided with a plurality of strategy containers, the strategy containers comprise at least one risk detection strategy which accords with risk constraint conditions of the strategy containers, and the risk constraint conditions of the strategy containers are determined by dividing information of a plurality of dimensions related to business; the strategy container is deployed in a risk detection strategy system according to the hierarchy of the strategy container and risk constraint conditions; the hierarchy of policy containers characterizes the priority of the risk detection process.

Description

Business processing and risk detection strategy system construction method, device and equipment

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, and a device for constructing a business processing and risk detection policy system.

Background

In recent years, fraud cases have been transacted. Transaction fraud can be divided into active fraud and passive fraud according to passive party attributes. In active fraud, the collection account for the transaction is a bad account and the fraudulent party uses its own account or rents a running account to cheat the victim into collecting fraudulent funds. In passive fraud, the collection account for the transaction is a good account, and often some large merchant account, and only the fraudulent party finds a hole in the payment link, so that the good collection account is used to collect fraud.

In order to avoid the occurrence of transaction fraud, people are beginning to break through from the technical aspect to effectively identify the fraudulent transaction through technical means. For example, for active fraud, characteristics such as transaction time, transaction amount, transaction level and the like can be characterized for each collection account based on a big data processing technology, so that bad accounts are determined based on the characterized characteristics, and operations such as right limit setting and the like are performed on the bad accounts to realize risk control, thereby avoiding transaction fraud. However, since the payment account in the passive fraud is a good account of the merchant, the right limit setting of the payment account will reduce the business level of the merchant, and bring much inconvenience to the merchant. Therefore, how to accurately and effectively identify the passive fraud is a technical problem which needs to be solved urgently at present.

Disclosure of Invention

One or more embodiments of the present specification provide a service processing method. The method comprises the step of obtaining service data of a target service to be subjected to risk detection processing. And carrying out risk detection processing on the service data based on a multi-layer risk detection strategy system which is constructed in advance to obtain risk detection result information. Wherein a plurality of policy containers are deployed in the risk detection policy system. The policy container includes at least one risk detection policy that complies with its risk constraints. The risk constraint of the policy container is determined by partitioning information of multiple dimensions related to the business. The policy container is deployed in the risk detection policy hierarchy according to a hierarchy of policy containers and risk constraints. The hierarchy of the policy container characterizes the priority of the risk detection process. And performing corresponding service processing on the target service according to the risk detection result information.

One or more embodiments of the present specification provide a method for constructing a risk detection policy system. The method includes obtaining historical service data for a plurality of services. A plurality of policy containers corresponding to predetermined risk constraints are generated based on the historical business data. Wherein the policy container comprises at least one risk detection policy meeting the risk constraint condition. The risk constraint of the policy container is determined by partitioning information of multiple dimensions related to the business. And deploying the multiple policy containers according to the determined hierarchy of the policy containers and risk constraint conditions to form a risk detection policy system. The risk detection strategy system is used for carrying out risk detection processing on the service data of the target service to be subjected to the risk detection processing. The hierarchy of the policy container characterizes the priority of the risk detection process.

One or more embodiments of the present specification provide a service processing apparatus. The device comprises an acquisition module for acquiring the service data of the target service to be subjected to risk detection processing. The device also comprises a detection module, and based on a multi-layer risk detection strategy system which is constructed in advance, the detection module carries out risk detection processing on the service data to obtain risk detection result information. Wherein a plurality of policy containers are deployed in the risk detection policy system. The policy container includes at least one risk detection policy that complies with its risk constraints. The risk constraint of the policy container is determined by partitioning information of multiple dimensions related to the business. The policy container is deployed in the risk detection policy hierarchy according to a hierarchy of policy containers and risk constraints. The hierarchy of the policy container characterizes the priority of the risk detection process. The device also comprises a processing module which is used for carrying out corresponding service processing on the target service according to the risk detection result information.

One or more embodiments of the present specification provide a device for constructing a risk detection policy system. The device comprises an acquisition module for acquiring historical service data of a plurality of services. The apparatus also includes a generation module that generates a plurality of policy containers corresponding to predetermined risk constraints based on the historical business data. Wherein the policy container comprises at least one risk detection policy meeting the risk constraint condition. The risk constraint of the policy container is determined by partitioning information of multiple dimensions related to the business. The device also comprises a construction module, and the construction module deploys the plurality of strategy containers according to the determined hierarchy of the strategy containers and the risk constraint conditions to form a risk detection strategy system. The risk detection strategy system is used for carrying out risk detection processing on the service data of the target service to be subjected to the risk detection processing. The hierarchy of the policy container characterizes the priority of the risk detection process.

One or more embodiments of the present specification provide a service processing device. The apparatus includes a processor. The apparatus also comprises a memory arranged to store computer executable instructions. The computer executable instructions, when executed, cause the processor to obtain business data of a target business to be risk-detected. And carrying out risk detection processing on the service data based on a multi-layer risk detection strategy system which is constructed in advance to obtain risk detection result information. Wherein a plurality of policy containers are deployed in the risk detection policy system. The policy container includes at least one risk detection policy that complies with its risk constraints. The risk constraint of the policy container is determined by partitioning information of multiple dimensions related to the business. The policy container is deployed in the risk detection policy hierarchy according to a hierarchy of policy containers and risk constraints. The hierarchy of the policy container characterizes the priority of the risk detection process. And performing corresponding service processing on the target service according to the risk detection result information.

One or more embodiments of the present specification provide a device for constructing a risk detection policy system. The apparatus includes a processor. The apparatus also comprises a memory arranged to store computer executable instructions. The computer executable instructions, when executed, cause the processor to obtain historical business data for a plurality of businesses. A plurality of policy containers corresponding to predetermined risk constraints are generated based on the historical business data. Wherein the policy container comprises at least one risk detection policy meeting the risk constraint condition. The risk constraint of the policy container is determined by partitioning information of multiple dimensions related to the business. And deploying the multiple policy containers according to the determined hierarchy of the policy containers and risk constraint conditions to form a risk detection policy system. The risk detection strategy system is used for carrying out risk detection processing on the service data of the target service to be subjected to the risk detection processing. The hierarchy of the policy container characterizes the priority of the risk detection process.

One or more embodiments of the present specification provide a storage medium. The storage medium is used to store computer-executable instructions. The computer executable instruction, when executed by the processor, obtains business data of a target business to be subjected to risk detection processing. And carrying out risk detection processing on the service data based on a multi-layer risk detection strategy system which is constructed in advance to obtain risk detection result information. Wherein a plurality of policy containers are deployed in the risk detection policy system. The policy container includes at least one risk detection policy that complies with its risk constraints. The risk constraint of the policy container is determined by partitioning information of multiple dimensions related to the business. The policy container is deployed in the risk detection policy hierarchy according to a hierarchy of policy containers and risk constraints. The hierarchy of the policy container characterizes the priority of the risk detection process. And performing corresponding service processing on the target service according to the risk detection result information.

One or more embodiments of the present specification provide a storage medium. The storage medium is used to store computer-executable instructions. The computer-executable instructions, when executed by a processor, obtain historical business data for a plurality of businesses. A plurality of policy containers corresponding to predetermined risk constraints are generated based on the historical business data. Wherein the policy container comprises at least one risk detection policy meeting the risk constraint condition. The risk constraint of the policy container is determined by partitioning information of multiple dimensions related to the business. And deploying the multiple policy containers according to the determined hierarchy of the policy containers and risk constraint conditions to form a risk detection policy system. The risk detection strategy system is used for carrying out risk detection processing on the service data of the target service to be subjected to the risk detection processing. The hierarchy of the policy container characterizes the priority of the risk detection process.

Drawings

In order to more clearly illustrate one or more embodiments or prior art solutions of the present specification, the drawings that are needed in the description of the embodiments or prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and that other drawings can be obtained by those skilled in the art without inventive exercise.

Fig. 1 is a first flowchart of a service processing method according to one or more embodiments of the present disclosure;

fig. 2 is a second flowchart of a service processing method according to one or more embodiments of the present disclosure;

fig. 3 is a third schematic flow chart of a service processing method according to one or more embodiments of the present disclosure;

fig. 4 is a fourth flowchart illustrating a service processing method according to one or more embodiments of the present disclosure;

FIG. 5 is a schematic view of a planar chessboard provided by one or more embodiments of the present disclosure;

FIG. 6 is a schematic diagram of a risk detection policy framework building process provided by one or more embodiments of the present disclosure;

FIG. 7 is a flowchart illustrating a method for constructing a risk detection policy system according to one or more embodiments of the present disclosure;

fig. 8 is a schematic block diagram of a service processing apparatus according to one or more embodiments of the present disclosure;

fig. 9 is a schematic block diagram illustrating a risk detection policy system building apparatus according to one or more embodiments of the present disclosure;

fig. 10 is a schematic structural diagram of a service processing device according to one or more embodiments of the present disclosure;

fig. 11 is a schematic structural diagram of a risk detection policy framework building device according to one or more embodiments of the present disclosure.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in one or more embodiments of the present disclosure, the technical solutions in one or more embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in one or more embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all embodiments. All other embodiments that can be derived by a person skilled in the art from one or more of the embodiments described herein without making any inventive step shall fall within the scope of protection of this document.

Fig. 1 is a schematic flowchart of a service processing method according to one or more embodiments of the present disclosure, and as shown in fig. 1, the method includes the following steps:

step S102, acquiring service data of a target service to be subjected to risk detection processing;

the service processing method provided by the embodiments of the present description may be executed by a service processing apparatus. Optionally, a client Application of the target service is installed in the terminal device of the user handling the target service, and the client Application may be an independent Application program (App for short) or an applet set in another Application program; the service processing device is arranged in the client application or is separated from the client application and independently arranged in the terminal equipment of the user; when a user operates a client application of a target service to submit service data of the target service, the service processing device acquires the service data submitted by the user. Or, the service processing device is arranged in a server corresponding to the client application of the target service, and when the client application acquires the service data of the target service submitted by the user, the service processing device in the server transmits the service data to the corresponding server, and the service processing device in the server acquires the service data. Or, the service processing device is separated from and exists independently of a service end corresponding to the client application of the target service, and when the service end receives service data of the target service sent by the client application, the service data is sent to the service processing device, and the service processing device receives the service data sent by the service end. The existence form of the service processing device is not particularly limited in this specification, and may be set by itself as needed in practical application.

Wherein, the target business can be a transaction, such as resource transfer transaction of funds, points, virtual currency and the like; the target service may also be a service acquisition service, such as an account opening service, a credit service, etc. Accordingly, the service data may be different according to the target service, for example, the target service is a fund transfer transaction, and the service data may include transfer-out account information, transfer-in account information, fund transfer amount, and the like; for another example, the target service is an online account opening service, and the service data may include an IP address corresponding to a device operated by the account opening party, identity information of the account opening party, and the like.

Step S104, carrying out risk detection processing on the service data based on a multi-layer risk detection strategy system which is constructed in advance to obtain risk detection result information; the risk detection system comprises a risk detection strategy system and a risk detection strategy system, wherein the risk detection strategy system is provided with a plurality of strategy containers, each strategy container comprises at least one risk detection strategy which accords with a risk constraint condition of the strategy container, and the risk constraint condition of the strategy container is determined by dividing information of a plurality of dimensions related to a service; the strategy container is deployed in a risk detection strategy system according to the hierarchy of the strategy container and risk constraint conditions; the hierarchy of policy containers characterizes the priority of the risk detection process;

the risk constraint condition is a condition that the risk detection policy in the policy container needs to meet, and specific contents of the risk constraint condition can be referred to in the following relevant description. The multiple dimensions related to the service may include a user type dimension of a user related to the service, an industry type dimension of an industry to which the service belongs, a region dimension of a region where the service is handled, and the like. The higher the hierarchy of the policy container, the higher the priority that can characterize the risk detection process; the higher the hierarchy of the policy container, the lower the priority that can also characterize the risk detection process; the relationship between the hierarchy of the policy container and the priority of the risk detection processing can be set by the user in practical application according to the requirement. Because the risk detection strategy system has a plurality of hierarchies, the risk detection strategy system can be a multi-layer three-dimensional structure.

Further, taking passive fraud of fund transfer as an example, considering that in the prior art, the fund transfer is generally performed based on the following two single-layer wind control strategies: the first is a general policy that does not define the payee, and the second is a special policy that defines the payee. For the first general strategy, coverage is insufficient, since the characterization of risk behaviors is usually very severe in order to ensure accuracy; if the coverage rate is considered preferentially, the accuracy rate cannot be guaranteed because the collection forms and the transaction frequencies of users in different industries are different. For the second special strategy, risk behaviors are usually carefully described, so that the accuracy is high; but for the cheating party, the cheating success rate is not high, so that the cheating party can be quickly transferred to another merchant; and the special strategies for each merchant on line one by one tend to cause the fraudulent party to flow around, but the prevention and control difficulty is increased, and the prevention and control can be realized only by disturbing more merchants. Based on this, a multi-layer risk detection policy system is established in advance in the present specification, and the risk detection processing is performed on the business data based on the multi-layer risk detection policy system. Because in the multi-layer risk detection strategy system, the risk constraint conditions met by the risk detection strategies among the layers are different, so that the multi-aspect risk characterization is realized, the accuracy rate of risk detection can be improved, and the coverage rate is greatly improved. It should be noted that the multi-layered risk detection policy system in the present specification can be applied not only to risk detection of passive fraud, but also to risk detection in aspects such as credit risk, compliance risk, technical risk, and the like. Hereinafter, passive fraud is explained as an example.

And step S106, performing corresponding service processing on the target service according to the risk detection result information.

Specifically, when the risk detection result represents that the service data has a risk, the risk prompting processing can be performed, and the target service can be prevented from being performed; when the risk detection result indicates that the service data has no risk, corresponding processing, such as resource transfer processing, account opening processing and the like, can be performed according to the service data.

In one or more embodiments of the present specification, a multi-layer risk detection policy system is pre-established, where a plurality of policy containers are deployed in the risk detection policy system, and each policy container includes at least one risk detection policy that meets risk constraints of the policy container; the risk constraint condition of the strategy container is determined by dividing information of multiple dimensions related to the business, and the strategy container is deployed in a risk detection strategy system according to the hierarchy of the strategy container and the risk constraint condition; and when the business data of the target business to be subjected to risk detection processing is obtained, performing risk detection processing on the business data based on the risk detection strategy system, and performing corresponding business processing on the target business according to the risk detection result information. Because in the multi-layer risk detection strategy system, the risk constraint conditions met by the risk detection strategies among the layers are different, so that the risk characterization in multiple aspects is realized, the accuracy of the risk detection can be improved, the coverage rate is greatly improved, and the effective detection of risks such as passive fraud is realized. Moreover, because the risk detection strategy system is multilayer, namely a three-dimensional cellular structure, the condition that the whole body is moved by pulling can not occur, and the whole system can not be influenced by misoperation or misconfiguration of any risk detection strategy, so that the operation cost of the risk detection strategy is reduced, and the stability of the strategy system is improved. Moreover, the multilayer three-dimensional risk detection strategy system can more intuitively reflect the positions of the strategy containers, and is beneficial for managers to adjust the strategy containers so as to change the whole risk detection strategy system.

In order to ensure the effectiveness of risk detection processing and avoid the occurrence of phenomena such as missing detection and repeated detection, in one or more embodiments of the present application, risk detection processing is performed on service data to be subjected to risk detection processing based on a risk detection policy system according to a preset matching policy and a hierarchical order of the risk detection policy system. Specifically, as shown in fig. 3, the step S104 may include the following steps S104-2 to S104-6:

step S104-2, determining a strategy container for matching the business data for the first time in a risk detection strategy system according to a preset matching strategy, and inputting the business data into the determined strategy container to match the business data with the risk detection strategy in the determined strategy container;

the matching policy may be set in actual application according to the relevant information of the risk detection policy in each policy container, for example, the matching policy is determined according to the risk constraint condition that the risk detection policy needs to satisfy.

Step S104-4, if the risk detection result can be determined according to the matching result, outputting risk detection result information, and executing step S106;

step S104-6, if the risk detection result cannot be determined according to the matching result, inputting the service data into the corresponding strategy container layer by layer according to the hierarchical sequence of the risk detection strategy system for matching processing; until the risk detection result can be determined according to the matching result, or the business data is subjected to matching processing by a strategy container of the final layer to obtain a final layer matching result, determining the risk detection result according to the final layer matching result, outputting risk detection result information, and executing the step S106;

after the business data is matched with the strategy container of the current layer except the final layer, if the risk detection result cannot be determined according to the matching result, the business data is input into the strategy container corresponding to the next layer of the current layer according to the hierarchical sequence of the risk detection strategy system to be matched.

In order to facilitate the construction of a risk detection policy system and the generation of related risk detection policies, in one or more embodiments of the present specification, risk constraints of each policy container are predetermined. Specifically, before step S102, the method may further include:

dividing information corresponding to the strategy container in each dimension on a plurality of dimensions related to the service; determining multi-dimensional mapping information of the strategy container according to the information corresponding to each dimension of the divided strategy container; and determining the risk constraint conditions of the strategy container according to the multi-dimensional mapping information of the strategy container.

Specifically, on a user type dimension, dividing user type information corresponding to each policy container; dividing industry type information corresponding to each strategy container in an industry type dimension; determining mapping information of the user type and the industry type of the strategy container according to the user type information and the industry type information corresponding to each divided strategy container; and determining risk constraint conditions of the corresponding strategy containers according to the mapping information. The information in each dimension may be divided according to the acquired historical service data of the service, or the information in each dimension may be divided based on the service attribute. The user type information can comprise students, mothers, old people, white collars, family men and the like; the industry type information may include consumer electronics industry, gaming industry, general entertainment industry, travel industry, etc.; the multidimensional mapping information can comprise mapping information of any user type information and any industry type information in the student-consumer electronics industry, the student-game industry, the student-general entertainment industry, the student-tourism industry, the mom-consumer electronics industry, the mom-game industry, the mom-general entertainment industry and the like.

In order to implement effective risk detection, in one or more embodiments of the present specification, a risk detection policy system is further pre-constructed, and specifically, as shown in fig. 3, step S102 may further include the following step S100-2 to step S100-6 before:

step S100-2, obtaining historical service data of a plurality of services;

optionally, receiving historical service data of a plurality of services imported by a user; or, acquiring historical service data of the corresponding service from a service database of the corresponding service provider according to a preset access interface. The historical service data obtained in this step may be the same as or different from the historical service data obtained when the risk constraint condition is determined. In order to improve the coverage rate and accuracy rate of risk monitoring, the plurality of businesses in the specification may be a plurality of businesses related to different industries and different user types, such as a consumer electronics industry, a game industry, a general entertainment industry, a travel industry, and the like; accordingly, the types of users involved may include students, mothers, elders, white-collar workers, family men, and the like.

Step S100-4, generating a plurality of strategy containers corresponding to each predetermined risk constraint condition based on historical business data;

specifically, a pre-trained strategy generation model is adopted, a risk detection strategy which meets each predetermined risk constraint condition is generated based on historical business data, and the generated risk detection strategy is stored in a generated strategy container corresponding to each risk constraint condition. The training process of the strategy generation model can refer to the existing model training mode, and the details are not described in this specification.

The fraud mode is a part-time swipe, considering that some fraud is usually targeted to a certain industry and a certain user group, for example, a fraudster may sneak into a school part-time group to find a potential victim. But students in colleges and universities generally have poor consumption capability, so fraudsters can develop matched products for the students, namely, suitable money receiving merchants and commodities are customized, such as refuelling card recharge of a certain bank and the like, and each unit is 1000 yuan so as to be suitable for student groups. However, this manipulation is not common in other people, such as white-collar workers and children. For another example, the enterprise logging in the account number of the cheating party mall pays a similar bill, and focuses on the group of mothers and the consumer electronics industry. Based on this, in one or more embodiments of the present description, a special strategy can be formulated from a certain industry type dimension and a certain user type dimension. Specifically, the determining the risk constraint condition of the policy container according to the multidimensional mapping information of the policy container may include: and determining user type information and industry type information corresponding to the at least one multi-dimensional mapping information as a first risk constraint condition. That is, the risk constraints may include at least one first risk constraint that includes first target user type information and first target industry type information; accordingly, step S100-4 may include:

creating a corresponding first policy container according to each predetermined first risk constraint condition; screening first target historical service data which are matched with the target user type and the first target industry type information at the same time from the acquired historical service data; determining a first risk factor forming a designated risk based on first target historical service data according to a preset mode; and generating a first risk detection strategy according to the first risk factor, and storing the first risk detection strategy into a corresponding first strategy container.

Taking the designated risk as a passive fraud example for explanation, for example, if first target user type information included in a certain first risk constraint condition is a student and first target industry type information is a civil student, a corresponding first policy container is created according to the first risk constraint condition; and screening first target historical service data, of which the service-related users are students and the service industry belongs to is civilian, from the historical service data, determining a first risk factor forming passive fraud based on the first target historical service data by adopting a pre-trained strategy generation model, generating a first risk detection strategy according to the first risk factor, and storing the first risk detection strategy into a corresponding first strategy container. The first risk factor may include a consumption amount range, a transaction time range, a transaction mode, collection account information, and the like.

Since the first risk detection policy (i.e., the special policy) is subdivided into the user type and the industry type, the number of first risk factors is not required to be excessive, and the passive fraud can be locked accurately, for example, the number of first risk factors is within 5.

Further, it is considered that in practical applications, some fraudulent activities are not restricted to a certain user group, i.e. not to the user type. For example, in the gaming industry, cheating parties often guide victims to add value in a small amount and a plurality of amounts, so as to avoid auditing large amount mutation-type strategies, such as 200 yuan, 50 payments, and the like. Passive fraud in the form of such transactions is generally not restricted to a certain group of users. Based on the above, in one or more embodiments of the present specification, the industry policy can be established from a certain industry type dimension without limiting the user type. Specifically, the determining the risk constraint condition of the policy container according to the multidimensional mapping information of the policy container may include: and determining the industry type information included in the at least one multi-dimensional mapping information as a second risk constraint condition. That is, the risk constraints may further include at least one second risk constraint, the second risk constraint including second target industry type information: it should be noted that the second risk constraint may further include first information characterizing each user type information, and when the second risk constraint does not include the first information, each user type information is defaulted. Accordingly, step S100-4 may include:

creating a corresponding second policy container according to each predetermined second risk constraint condition; screening second target historical service data matched with second target industry type information from the historical service data; determining a second risk factor forming the designated risk based on the second target historical service data according to a preset mode; and generating a second risk detection strategy according to the second risk factor, and storing the second risk detection strategy into a corresponding second strategy container.

For example, if the second target industry type information included in the second risk constraint condition is a game industry, the business processing device creates a corresponding second policy container according to the second risk constraint condition; and screening second target historical service data belonging to the game industry from the historical service data, determining a second risk factor forming passive fraud based on the second target historical service data by adopting a pre-trained strategy generation model, generating a second risk detection strategy according to the second risk factor, and storing the second risk detection strategy into a corresponding second strategy container. Wherein, the second risk factor can be set in practical application according to the requirement.

Since the second risk policy (i.e., the industry policy) is not limited to the user type, the number of second risk factors is greater than the number of first risk factors, which may be 6-10, for example.

Further, it is considered that in practical applications, there may be some special cases, for example, during the spring festival, there may be many time confusion among various communities due to the child being left at home. The cheating party generally guides the child to pay by using the mobile phone of the parent according to the opportunity, such as giving away a free game skin. Based on this, in one or more embodiments of the present description, a general policy may also be formulated from the dimension of each industry type and each user type, which is wider in coverage than the aforementioned second risk detection policy. Specifically, the determining the risk constraint condition of the policy container according to the multidimensional mapping information of the policy container may include: and determining each user type information and each industry type information corresponding to the multi-dimensional mapping information as a third risk constraint condition. That is, the risk constraint may include a third risk constraint, where the third risk constraint includes first information representing information of each user type and second information representing information of each industry type: accordingly, step S100-4 may include:

creating a third policy container according to the determined third risk constraint condition; determining a third risk factor forming the designated risk based on historical service data according to a preset mode; and generating a third risk detection strategy according to the third risk factor, and storing the third risk detection strategy into a third strategy container.

Specifically, a third policy container is created according to a third risk constraint; and determining a third risk factor forming the passive fraud based on the acquired historical service data by adopting a pre-trained strategy generation model, generating a third risk detection strategy according to the third risk factor, and storing the third risk detection strategy into a created third strategy container. Further, the specific form of the first information and the second information may be set by itself in practical application as required, for example, the first information is 00, the second information is 11, and the like.

Since the third risk detection policy (i.e., the general policy) is not limited to the industry type and the user type, the number of the third risk factors may be more, such as at least 10, etc. In the above exemplary fraudulent transaction of guiding a child to make a payment using a parent's mobile phone, the age of a payer (i.e., the child) may be predicted in combination with the age prediction by face recognition, and the predicted age may be matched to the age of the holder (parent) of the payment account. Accordingly, the third risk factor may include, among other things, that the payer age does not match the age of the holder of the payment account. The specific content of the third risk factor can be set in practical application according to the needs. When the risk is designated as active fraud and passive fraud, the third risk constraint may further include account information of collection accounts where fraud risk has historically occurred, and so on, to prevent mis-audit for non-risk or very low risk merchants.

Further, considering the transaction fraud case, the fraudulent party usually creates a transaction order under the IP of its location or the IP of the server where the fraudulent party rents, and packages the payment link into a form of two-dimensional code or the like to send the payment to the victim for payment, and the fraud mode is not limited to the user type and the industry type. Based on this, in one or more embodiments of the present specification, special policies for rosting classes may also be formulated from industry type dimensions and user type dimensions. Specifically, the determining the risk constraint condition of the policy container according to the multidimensional mapping information of the policy container may include: determining each user type information, each industry type information and list type information corresponding to the multi-dimensional mapping information as fourth risk constraint conditions; alternatively, the list type information is determined as the fourth risk constraint. It should be noted that, when there is no related information characterizing the user type information and the industry type information in the fourth risk constraint, the default is each user type information and each industry type information. That is, the risk constraint may include a fourth risk constraint, the fourth risk constraint including list type information: accordingly, step S100-4 may include:

creating a fourth policy container according to the determined fourth risk constraint condition; determining a target list which has a designated risk and is matched with the list type information based on historical service data according to a preset mode; and generating a fourth risk detection strategy according to the target list, and storing the fourth risk detection strategy into a fourth strategy container.

For example, the list type information included in the fourth risk constraint condition is an IP address, and the service processing apparatus creates a corresponding fourth policy container according to the fourth risk constraint condition; and determining an IP address with a passive fraud risk based on the acquired historical service data by adopting a pre-trained strategy generation model, taking the determined IP address as a target list, generating a fourth risk detection strategy according to the target list, and storing the fourth risk detection strategy into a created fourth strategy container. For another example, the list type information included in the fourth risk constraint condition is a collection account, the service processing apparatus determines collection account information with a passive fraud risk based on the acquired historical service data by using a pre-trained policy generation model, and generates a fourth risk detection policy according to a target list with the determined collection account information as the target list, and stores the fourth risk detection policy in a created fourth policy container.

By generating the fourth risk detection strategy, the fraud risk can be quickly detected based on the 'list', and the detection efficiency and accuracy are improved.

Further, consider that some fraud cases do not occur in an industry and a group of users, such as cases in which a boredom threatens Hedgehog, and generally do not cause any damage in the travel ticketing industry. Therefore, in order to prevent mis-audit, in one or more embodiments of the present disclosure, a global policy may be further formulated to globally release corresponding services. Specifically, the risk constraint condition may include a fifth risk constraint condition, where the fifth risk constraint condition includes second target user type information and screening information of a third target industry type corresponding to characterizing and screening a service without a specified risk; accordingly, step S100-4 may include:

screening second target user type information and third target industry type information based on historical service data according to a preset mode; creating a fifth strategy container and generating a fifth risk detection strategy according to the second target user type information and the third target industry type information; and saving the fifth risk detection strategy into a fifth strategy container.

For example, the second target user type information screened based on the obtained historical service data by using the pre-trained policy generation model includes a lewd male, the corresponding third target industry type information is a tourism industry, a corresponding fifth policy container is created according to the lewd male and the tourism industry, a fifth risk detection policy is generated, and the fifth risk detection policy is stored in the fifth policy container.

By generating the fifth risk detection strategy, release processing can be directly performed when the service data to be subjected to risk detection processing is matched with the fifth risk detection strategy, and risk detection processing does not need to be performed again based on other risk detection strategies, so that the risk detection strategy can be improved.

S100-6, determining the hierarchy of the strategy containers, and deploying the generated strategy containers according to the hierarchy of the strategy containers and risk constraint conditions to form a multi-layer risk detection strategy system;

specifically, determining the hierarchy of a corresponding policy container according to policy attribute information of each risk detection policy; determining information of multiple dimensionalities related to the service according to historical service data; mapping and combining the information of the multiple dimensions to form a multi-dimensional information set; determining multi-dimensional information corresponding to the risk constraint conditions of the strategy container in the multi-dimensional information set; and according to the multi-dimensional information and the hierarchy of the strategy container, carrying out deployment processing on the strategy container to obtain a risk detection strategy system. Wherein the information of the multiple dimensions may include user type information of a user type dimension and industry type information of an industry type dimension. The policy attribute information may be set by itself as needed in actual application, and in one embodiment, the policy attribute information may be application range information and/or priority information of the risk detection policy, for example, the larger the application range is, the higher the determined hierarchy is, and the smaller the application range is, the lower the determined hierarchy is; for another example, the higher the priority, the higher the hierarchy is determined to be, the lower the priority, the lower the hierarchy is determined to be, and the like.

Corresponding to the above-described steps S100-2 to S100-6, as shown in fig. 3, the step S104 may include the following steps S104-8:

step S104-8, based on a multi-layer risk detection strategy system which is constructed in advance, carrying out risk detection processing on the service data to obtain risk detection result information;

further, in order to ensure the comprehensiveness of the information of multiple dimensions related to the business, in one or more embodiments of the present specification, the business processing apparatus may further obtain information of multiple dimensions (e.g., user type information, industry type information, and the like) submitted by an administrator, and determine the information of multiple dimensions determined according to the historical business data and the obtained information of multiple dimensions submitted by the administrator as the information of multiple dimensions related to the business.

For convenience of understanding, the multi-dimensional information includes user type information of a user type dimension and industry type information of an industry type dimension, which are used as examples for explanation in this specification. In order to prevent and control risks such as passive fraud and the like on the basis of ensuring low audit volume and high accuracy, after multi-dimensional information related to a service is determined, a two-dimensional plane chessboard can be drawn according to the determined multi-dimensional information, and a policy container is deployed on the plane chessboard according to the multi-dimensional information corresponding to risk constraint conditions of the policy container in a multi-dimensional information set and the hierarchy of the policy container, so that a risk detection policy system is obtained.

The user type information comprises students, mothers, house men, male with lewd and children, the industry type information comprises consumer electronics, games, general entertainment, folk lives and travel, the abscissa represents the user type information, and the ordinate represents the industry type information as an example, a drawn plane chessboard is shown in fig. 4 and comprises a plurality of independent unit grids, wherein each unit grid corresponds to one user type information and one industry type information; accordingly, when creating each policy container, the policy container with the corresponding size may be created according to the risk constraint condition of the policy container. It will be appreciated that industry type information may also be represented on the abscissa and user type information on the ordinate. And when the determined service-related dimension is more than two dimensions, drawing a corresponding multi-dimensional stereo chessboard.

Based on the flat chessboard shown in fig. 4, it can be understood that, since the first risk detection policy is subdivided into the user type dimension and the industry type dimension, the first policy container may correspond to each cell of the flat chessboard, for example, in the order of the flat chessboard from left to right and from top to bottom, the first policy container corresponding to the multi-dimensional information "student-game", the second cell arranged in the first column of the flat chessboard shown in fig. 4, and so on. Since the second risk detection policy (i.e., the industry policy) is not limited to the user type dimension, the second policy container may adopt a three-dimensional form that corresponds to a certain industry type and covers all user types and runs through the chessboard from left to right, i.e., may correspond to each cell corresponding to information of a certain industry type on the planar chessboard; and through generating the second risk detection strategy, can prevent some novel fraud gimmicks from conducting between each cell of chess board, prevent the repeated construction of trade specific gimmicks in each cell of chess board simultaneously, can reduce tactics quantity, prevent that the system load that long-term tactics operation leads to is too big and the operating efficiency reduces. Since the third risk detection policy (i.e., the general policy) is not limited to the industry type dimension and the user type dimension, the third policy container may be in a stereoscopic form that covers all industry type dimensions and all user type dimensions, throughout the entire planar checkerboard, i.e., corresponding to the cells of the planar checkerboard. Since the fourth risk detection policy (list-type policy) is not limited to the user type dimension and the industry type dimension, and is a list-type policy such as an IP address, a collection account, and the like, the fourth policy container may not have a regular correspondence, that is, it is not necessary to completely correspond to the user type information and the industry type information in the flat chessboard. Since the fifth risk detection policy (i.e., the global policy) can be characterized by specific user type dimensions and industry type dimensions, and the business data conforming to the fifth risk detection policy is released from the global, the fifth policy container can correspond to the independent cells of the chessboard, and the hollowed-out carving is performed on the basis of the first policy container to the third policy container.

Further, the first policy container, the second policy container and the third policy container may also be referred to as a common policy container because the first policy container, the second policy container and the third policy container can correspond to cells of the planar chessboard and do not penetrate through multiple hierarchies, and the risk detection policy in the common policy container may also be referred to as a common risk detection policy. The fourth policy container does not need to correspond to a specific cell in the planar chessboard, and the fifth policy container needs to run through multiple hierarchies, so the fourth policy container and the fifth policy container can also be called special containers, and the risk detection policy in the special containers can also be called special risk detection policy.

In an example of an implementation manner, the corresponding cells of the policy container on the planar chessboard can be determined according to the multi-dimensional information of the policy container; and determining the hierarchy of the corresponding policy container in the risk detection policy hierarchy based on the application scope information and/or the priority information of the risk detection policy. The corresponding cells of the determined policy container on the planar chessboard and the hierarchy in the risk detection policy system can be determined as the deployment position of the policy container. When a certain created policy container is determined to be a common policy container, the deployment position of the policy container can be determined and deployed according to the mode. In particular, considering that some special risk detection strategies exist, that is, special strategy containers exist, for some special strategy containers, the corresponding cells on the planar chessboard can be preset or randomly selected; for other special policy containers, there may be multiple levels, that is, the policy containers may be deployed throughout multiple levels. Therefore, when a certain created policy container is determined to be a special policy container, the deployment position of the special policy container can be determined and deployed according to specific situations and requirements.

Further, optionally, after the policy containers are created, determining a deployment position of each policy container according to the hierarchy of each policy container and a risk constraint condition, and deploying the corresponding policy container according to the deployment position to form a risk detection policy system; or determining a creation sequence according to the policy attribute information of each risk detection policy, sequentially creating each policy container according to the creation sequence, determining the deployment position of each policy container according to the hierarchy of the policy container and the risk constraint condition when each policy container is created, and deploying the policy containers according to the determined deployment position.

Taking an example of determining a hierarchy where a corresponding policy container is located based on priority information in the policy attribute information, for example, the priority information of the first risk detection policy to the fifth risk detection policy is: a first risk detection strategy < a second risk detection strategy < a third risk detection strategy < a fourth risk detection strategy < a fifth risk detection strategy, and determining the order of priority from low to high as a creation order, and explaining an example of deploying the currently created policy container on a planar chessboard every time a policy container is created, where the creation process of the risk detection policy system is shown in fig. 5. It should be noted that fig. 5 is only used for illustration and not for limitation, and the specific three-dimensional form of each policy container may be set in practical application as required, as long as it can be adapted to the drawn planar chessboard and maintain the corresponding relationship when corresponding to the user type and the industry type.

Based on the constructed risk detection policy system, the preset matching policy may include that the policy container for performing matching processing on the service data for the first time is a fifth policy container; correspondingly, step S104 may include:

inputting the service data into a fifth policy container to match the service data with a fifth risk detection policy in the fifth policy container; if the risk detection result can be determined according to the matching result, outputting risk detection result information; if the risk detection result cannot be determined according to the matching result, inputting the service data into the corresponding strategy container layer by layer according to the hierarchical sequence of the risk detection strategy system for matching; determining a risk detection result according to the matching result, or obtaining a final layer matching result after the business data is subjected to matching processing by a strategy container of the final layer, determining a risk detection result according to the final layer matching result, and outputting risk detection result information; after the business data is matched with the strategy container of the current layer except the final layer, if the risk detection result cannot be determined according to the matching result, the business data is input into the strategy container corresponding to the next layer of the current layer according to the hierarchical sequence of the risk detection strategy system to be matched.

Specifically, the risk detection result in the embodiment of the present application may include a risk detection pass and a risk detection fail, where the risk detection determines that the business data does not have the specified risk based on the risk detection policy system through the characterization, and the risk detection fails to determine that the business data has the specified risk based on the risk detection policy system through the characterization. Taking the risk detection policy system shown in fig. 5 as an example for description, the process of performing risk detection processing on the business data may include: inputting the service data into a fifth policy container to match the service data with a fifth risk detection policy in the fifth policy container, and if a risk detection result can be determined according to the matching result information, outputting risk detection result information (that is, user type information and service type information obtained by analyzing the service data are matched with second target user type information and third target service type information in the fifth risk detection policy, determining that the service data meet release conditions, no designated risk exists, and at this time, no risk detection is required based on other risk detection policies, so that risk detection result information representing that the risk detection passes is output); if the risk detection result cannot be determined according to the matching result (namely, at least one of the user type information and the service type information obtained by analyzing the service data fails to be matched with the second target user type information and the third target service type information in the fifth risk detection strategy, and the condition of forming a designated risk is determined, because the service data may meet the condition corresponding to any one of the first risk detection strategy to the fourth risk detection strategy, the risk detection result cannot be determined temporarily, and further matching operation is required), according to the hierarchical order of the risk detection strategy system, the service data is input into a fourth strategy container to match the service data with a fourth risk detection strategy in the fourth strategy container from top to bottom, and if the risk detection result can be determined according to the matching result, outputting risk detection result information (namely, successfully matching the business data with a target list which corresponds to the fourth risk detection strategy and has a designated risk, determining that the business data has the designated risk, and thus, no further matching operation is needed at this moment, and outputting risk detection result information which represents that the risk detection fails); if the risk detection result cannot be determined according to the matching result (i.e. the business data fails to match the target list corresponding to the fourth risk detection strategy and having the designated risk, and since it only indicates that the business data does not hit the target list but may satisfy the risk factor corresponding to any one of the first risk detection strategy to the third risk detection strategy and constituting the designated risk, the risk detection result cannot be determined temporarily, and further matching operation is required), the business data is input into a third strategy container to match the business data with the third risk detection strategy in the third strategy container, and if the risk detection result can be determined according to the matching result, the risk detection result information is output (i.e. the business data satisfies the third risk factor corresponding to the third risk detection strategy and constituting the designated risk), thus outputting risk detection result information characterizing the failure of risk detection); if the risk detection result cannot be determined according to the matching result (namely the business data cannot meet the third risk factor which corresponds to the third risk detection strategy and forms the designated risk; but the business data may meet the risk factor which corresponds to any one of the first risk detection strategy and the second risk detection strategy and forms the designated risk, so that the risk detection result cannot be determined temporarily, and further matching operation is needed), the business data is input into a second strategy container to match the business data with the second risk detection strategy in the second strategy container, and if the risk detection result can be determined according to the matching result, the risk detection result information is output (namely the business data meets the second risk factor which corresponds to the second risk detection strategy and forms the designated risk; further matching operation is not needed at this time, so that the risk detection result information which represents that the risk detection fails is output); if the risk detection result cannot be determined according to the matching result (i.e. the business data does not satisfy the second risk factor corresponding to the second risk detection policy and constituting the designated risk; but the business data may satisfy the first risk factor corresponding to the first risk detection policy and constituting the designated risk, therefore the risk detection result cannot be determined temporarily, and further matching operation is required), the business data is input into the first policy container to match the business data with the first risk detection policy in the first policy container, and the risk detection result is output according to the matching result (i.e. when the business data satisfies the first risk factor corresponding to the first risk detection policy and constituting the designated risk, detection result information representing that the risk detection fails is output; when the business data does not satisfy the first risk factor corresponding to the first risk detection policy and constituting the designated risk, output test result information characterizing the passing of the risk test).

It should be noted that, when there are multiple policy containers in the current layer, the service data may be sequentially input into each policy container in the current layer to match the service data with the risk detection policy in the corresponding policy container until it is determined that the service data fails the risk detection according to the matching result, and risk detection result information is output; or after the last strategy container of the current layer is matched, the business data is determined to pass risk detection, and the business data is input into the strategy container corresponding to the next layer of the current layer for matching. Or, when there are a plurality of policy containers in the current layer, if the corresponding information to be matched (for example, user type information and industry type information) can be determined according to the service data, inputting the service data into the policy container corresponding to the determined information to be matched in the current layer for matching processing. For example, the current layer is the first layer of the risk detection policy system shown in fig. 5, and the information to be matched determined according to the business data includes user type information "student" and industry type information "game", and then the business data is input into the first policy container of the cell corresponding to the student and the game arranged on the flat chessboard in the first layer.

Therefore, risk detection processing is carried out on the acquired service data based on the multilayer three-dimensional risk detection strategy system, the accuracy rate of risk detection can be improved, and the coverage rate is greatly improved.

In order to ensure the effectiveness of the risk detection policy system, in one or more embodiments of the present specification, the method may further include:

if the condition that the preset container adjustment condition is met is determined, performing corresponding adjustment processing on a strategy container in a risk detection strategy system; wherein the adjustment process comprises one or more of: adding, deleting and modifying policy containers;

and if the preset container arrangement adjusting conditions are determined to be met, adjusting the spatial arrangement of the strategy containers in the risk detection strategy system.

Wherein determining that the preset container adjustment condition is satisfied may include: the service processing device detects whether the service mode of each service changes according to a preset rule, if so, the service processing device determines that a preset container adjustment condition is met, and if not, the service processing device determines that the preset container adjustment condition is not met. Or, if the service processing apparatus obtains a container adjustment instruction sent by an administrator or a designated device, it is determined that a preset container adjustment condition is satisfied. The container adjustment conditions may be set as needed in practical applications, and this is not particularly limited in this specification.

Further, adding the policy container, that is, adding the policy container, determining that the arrangement adjustment condition is satisfied when performing addition processing of the policy container, and performing arrangement processing on the added policy container according to the policy attribute information of the risk detection policy in the added policy container. Deleting the strategy container, namely deleting a certain strategy container, determining whether the preset arrangement adjustment condition is met or not according to the deleted container, and if so, adjusting the rest strategy containers to carry out spatial arrangement according to the strategy attribute information of the risk detection strategies in the rest strategy containers. For example, when a certain aforementioned first policy container is deleted, it may be determined that the preset arrangement adjustment condition is not satisfied, and when the aforementioned third policy container is deleted, it may be determined that the preset arrangement adjustment condition is satisfied. And modifying, namely modifying the risk detection strategy in the strategy container, determining whether the preset arrangement adjustment condition is met according to the strategy attribute information of the modified risk detection strategy, and if so, adjusting the spatial arrangement of the strategy container. For example, if the priority is determined to be changed according to the modified policy attribute information of the risk detection policy, it is determined that the preset configuration adjustment condition is satisfied, and if the priority is determined to be not changed according to the modified policy attribute information of the risk detection policy, it is determined that the preset configuration adjustment condition is not satisfied.

Further, when the service processing apparatus determines to perform the addition processing of the policy container, the corresponding risk detection policy may be generated according to the above manner, and stored in the policy container created correspondingly.

In a specific embodiment, the relevant dimensions of the business are exemplified by a user type dimension and an industry type dimension, and as shown in fig. 6, the method may include:

step S10, obtaining historical service data of a plurality of services;

step S12, generating a plurality of strategy containers corresponding to each risk constraint condition determined in advance based on the historical business data; the strategy container comprises at least one risk detection strategy which meets the risk constraint condition; the risk constraint condition of the strategy container is determined by dividing the information of a plurality of dimensionalities related to the business;

step S14, determining the hierarchy of the corresponding strategy container according to the strategy attribute information of the risk detection strategy;

step S16, determining user type information and industry type information related to the service according to the historical service data;

step S18, drawing a plane chessboard according to the determined user type information and industry type information;

step S20, mapping and combining the determined user type information and industry type information to form a combined information set;

step S22, determining the corresponding combination information of the risk constraint conditions of each strategy container in the combination information set;

step S24, according to the determined hierarchy and combination information of the strategy container, deploying the strategy container at a corresponding position in a plane chessboard to form a multi-layer risk detection strategy system;

step S26, if business data of a target business to be subjected to risk detection processing are obtained, performing risk detection processing on the business data based on a multi-layer risk detection strategy system constructed in advance to obtain risk detection result information;

and step S28, performing corresponding service processing on the target service according to the risk detection result information.

The specific implementation process of step S12 to step S28 can refer to the related description, and repeated details are not repeated here.

Corresponding to the business processing method described above, based on the same technical concept, one or more embodiments of the present specification further provide a method for constructing a risk detection policy system, and fig. 7 is a schematic flow diagram of the method for constructing the risk detection policy system provided by one or more embodiments of the present specification, as shown in fig. 7, the method includes the following steps:

step S202, obtaining historical service data of a plurality of services;

step S204, generating a plurality of strategy containers corresponding to each predetermined risk constraint condition based on historical business data; the strategy container comprises at least one risk detection strategy which meets the risk constraint condition; the risk constraint condition of the strategy container is determined by dividing the information of a plurality of dimensionalities related to the business;

step 206, deploying a plurality of policy containers according to the determined hierarchy of the policy containers and risk constraint conditions to form a risk detection policy system; the risk detection strategy system is used for carrying out risk detection processing on the service data of the target service to be subjected to the risk detection processing, and the hierarchy of the strategy container represents the priority of the risk detection processing.

Optionally, in step S206, deploying a plurality of policy containers according to the determined hierarchy of the policy containers and the risk constraint condition to form a risk detection policy system, including:

determining information of multiple dimensionalities related to the service according to historical service data;

mapping and combining the information of multiple dimensions to form a multi-dimensional information set;

determining multi-dimensional information corresponding to the risk constraint conditions of the strategy container in the multi-dimensional information set;

and according to the determined multi-dimensional information and the hierarchy of the strategy container, carrying out deployment processing on the strategy container to obtain a risk detection strategy system.

Optionally, the information of multiple dimensions related to the service includes user type information of a user type dimension and industry type information of an industry type dimension; the risk constraint conditions comprise at least one first risk constraint condition, and the first risk constraint condition comprises first target user type information and first target industry type information; accordingly, step S204 may include:

creating a corresponding first policy container according to each predetermined first risk constraint condition;

screening first target historical service data which are matched with the first target user type and the first target industry type information at the same time from the historical service data;

determining a first risk factor forming a designated risk based on first target historical service data according to a preset mode;

and generating a first risk detection strategy according to the first risk factor, and storing the first risk detection strategy into a corresponding first strategy container.

Optionally, the information of the plurality of dimensions related to the business comprises industry type information of an industry type dimension; the risk constraints include at least one second risk constraint that includes second target industry type information: accordingly, step S204 may include:

creating a corresponding second policy container according to each predetermined second risk constraint condition;

screening second target historical service data matched with second target industry type information from the historical service data;

determining a second risk factor forming the designated risk based on the second target historical service data according to a preset mode;

and generating a second risk detection strategy according to the second risk factor, and storing the second risk detection strategy into a corresponding second strategy container.

Optionally, the information of multiple dimensions related to the service includes user type information of a user type dimension and industry type information of an industry type dimension; the risk constraint conditions comprise third risk constraint conditions, wherein the third risk constraint conditions comprise first information representing each user type information and second information representing each industry type information: accordingly, step S204 may include:

creating a third policy container according to a predetermined third risk constraint condition;

determining a third risk factor forming the designated risk based on historical service data according to a preset mode;

and generating a third risk detection strategy according to the third risk factor, and storing the third risk detection strategy into a third strategy container.

Optionally, the risk constraint includes a fourth risk constraint, the fourth risk constraint including at least one list type information: accordingly, step S204 may include:

creating a fourth policy container according to a predetermined fourth risk constraint condition;

determining a target list which has risks and is matched with the list type information based on historical service data according to a preset mode;

and generating a fourth risk detection strategy according to the target list, and storing the fourth risk detection strategy into a fourth strategy container.

Optionally, the risk constraint condition includes a fifth risk constraint condition, where the fifth risk constraint condition includes second target user type information and screening information of a third target industry type corresponding to characterizing and screening a service without a specified risk; accordingly, step S204 may include:

screening second target user type information and third target industry type information based on historical service data according to a preset mode;

creating a fifth strategy container and generating a fifth risk detection strategy according to the second target user type information and the third target industry type information;

and saving the fifth risk detection strategy into a fifth strategy container.

Optionally, generating a plurality of policy containers corresponding to the determined risk constraints based on the historical business data includes:

generating a risk detection strategy which accords with each predetermined risk constraint condition based on historical business data by adopting a pre-trained strategy generation model;

and saving the generated risk detection strategy into the generated strategy container corresponding to each risk constraint condition.

Optionally, the method further comprises: and if the business data of the target business to be subjected to risk detection are acquired, performing risk detection processing on the business data based on the constructed risk detection strategy system.

The specific implementation manner of each step can be referred to the corresponding description in the foregoing, and the repetition is not repeated here.

In one or more embodiments of the present specification, a plurality of policy containers corresponding to predetermined risk constraints are generated based on historical business data, where a policy container includes at least one risk detection policy that meets the risk constraints, and the risk constraints of the policy container are determined by dividing information of multiple dimensions related to a business; and deploying according to the hierarchy of the strategy container and the risk constraint condition to form a risk detection strategy system for performing risk detection processing on the service data of the target service to be subjected to the risk detection processing. Because the risk detection strategies among all layers in the multi-layer risk detection strategy system are different in the risk constraint conditions, the multi-aspect risk characterization is realized, the accuracy rate of risk detection can be improved, the coverage rate is greatly improved, and the effective detection of risks such as passive fraud is realized. Moreover, because the risk detection strategy system is multilayer, namely a three-dimensional cellular structure, the condition that the whole body is moved by pulling can not occur, and the whole system can not be influenced by misoperation or misconfiguration of any risk detection strategy, so that the operation cost of the risk detection strategy is reduced, and the stability of the strategy system is improved. Moreover, the multilayer three-dimensional risk detection strategy system can more intuitively reflect the positions of the strategy containers, and is beneficial for managers to adjust the strategy containers so as to change the whole risk detection strategy system.

Corresponding to the service processing method described above, based on the same technical concept, one or more embodiments of the present specification further provide a service processing apparatus. Fig. 8 is a schematic block diagram of a service processing apparatus according to one or more embodiments of the present disclosure, and as shown in fig. 8, the apparatus includes:

an obtaining module 301, configured to obtain service data of a target service to be subjected to risk detection processing;

the detection module 302 is used for performing risk detection processing on the service data based on a multi-layer risk detection strategy system which is constructed in advance to obtain risk detection result information; the risk detection system comprises a risk detection strategy system and a risk detection strategy system, wherein a plurality of strategy containers are deployed in the risk detection strategy system, the strategy containers comprise at least one risk detection strategy which meets risk constraint conditions of the strategy containers, and the risk constraint conditions of the strategy containers are determined by dividing information of a plurality of dimensions related to business; the strategy container is deployed in the risk detection strategy system according to the hierarchy of the strategy container and risk constraint conditions; the hierarchy of the policy container characterizes a priority of risk detection processing;

and the processing module 303 performs corresponding service processing on the target service according to the risk detection result information.

Optionally, the detection module 302 determines, according to a preset matching policy, a policy container for performing matching processing on the service data for the first time in the risk detection policy system, and inputs the service data into the determined policy container to perform matching processing on the service data and a risk detection policy in the policy container;

if the risk detection result can be determined according to the matching result, outputting risk detection result information;

if the risk detection result cannot be determined according to the matching result, inputting the service data into a corresponding strategy container layer by layer according to the hierarchical sequence of the risk detection strategy system for matching; until a risk detection result can be determined according to a matching result, or a final layer matching result is obtained after the business data is subjected to matching processing by a strategy container of a final layer, and a risk detection result is determined according to the final layer matching result;

after the business data is matched with the strategy container of the current layer except the final layer, if the risk detection result cannot be determined according to the matching result, the business data is input into the strategy container corresponding to the next layer of the current layer according to the hierarchical sequence of the risk detection strategy system for matching.

Optionally, the apparatus further comprises: a determination module;

the determining module is used for dividing the information corresponding to the strategy container in each dimension in a plurality of dimensions related to the service;

determining multi-dimensional mapping information of the strategy container according to the information corresponding to each dimension of the divided strategy container;

and determining the risk constraint condition of the strategy container according to the multi-dimensional mapping information of the strategy container.

Optionally, the apparatus further comprises: an adjustment module;

the adjusting module is used for correspondingly adjusting the strategy container in the risk detection strategy system if the preset container adjusting condition is met; wherein the adjustment process comprises one or more of: adding, deleting and modifying policy containers;

Optionally, the apparatus further comprises: building a module;

the construction module is used for acquiring historical service data of a plurality of services; and the number of the first and second groups,

generating a plurality of policy containers corresponding to each of the predetermined risk constraints based on the historical business data;

determining the hierarchy of the policy container, and deploying the policy containers according to the hierarchy of the policy container and risk constraint conditions to form the risk detection policy system.

In a service processing apparatus provided in one or more embodiments of the present specification, a multi-layer risk detection policy system is pre-established, where a plurality of policy containers are deployed in the risk detection policy system, and each policy container includes at least one risk detection policy that meets risk constraint conditions of the policy container; the risk constraint condition of the strategy container is determined by dividing information of multiple dimensions related to the business, and the strategy container is deployed in a risk detection strategy system according to the hierarchy of the strategy container and the risk constraint condition; and when the business data of the target business to be subjected to risk detection processing is obtained, performing risk detection processing on the business data based on the risk detection strategy system, and performing corresponding business processing on the target business according to the risk detection result information. Because in the multi-layer risk detection strategy system, the risk constraint conditions met by the risk detection strategies among the layers are different, so that the risk characterization in multiple aspects is realized, the accuracy of the risk detection can be improved, the coverage rate is greatly improved, and the effective detection of risks such as passive fraud is realized. Moreover, because the risk detection strategy system is multilayer, namely a three-dimensional cellular structure, the condition that the whole body is moved by pulling can not occur, and the whole system can not be influenced by misoperation or misconfiguration of any risk detection strategy, so that the operation cost of the risk detection strategy is reduced, and the stability of the strategy system is improved. Moreover, the multilayer three-dimensional risk detection strategy system can more intuitively reflect the positions of the strategy containers, and is beneficial for managers to adjust the strategy containers so as to change the whole risk detection strategy system.

It should be noted that the embodiment of the service processing apparatus in this specification and the embodiment of the service processing method in this specification are based on the same inventive concept, and therefore, for specific implementation of this embodiment, reference may be made to implementation of the service processing method described above, and repeated details are not described again.

Further, based on the same technical concept, one or more embodiments of the present specification further provide a device for constructing a risk detection policy system, corresponding to the above-described method for constructing a risk detection policy system. Fig. 9 is a schematic block diagram of a device for constructing a risk detection policy system according to one or more embodiments of the present disclosure, where as shown in fig. 9, the device includes:

an obtaining module 401, configured to obtain historical service data of multiple services;

a generating module 402, which generates a plurality of policy containers corresponding to predetermined risk constraints based on the historical business data; wherein, the strategy container comprises at least one risk detection strategy meeting the risk constraint condition; the risk constraint condition of the strategy container is determined by dividing information of a plurality of dimensions related to the business;

the building module 403 deploys the policy containers according to the determined hierarchy of the policy containers and risk constraint conditions to form a risk detection policy system; the risk detection strategy system is used for carrying out risk detection processing on the service data of the target service to be subjected to the risk detection processing, and the hierarchy of the strategy container represents the priority of the risk detection processing.

Optionally, the building module 403 determines information of multiple dimensions related to the service according to the historical service data; and the number of the first and second groups,

mapping and combining the information of the multiple dimensions to form a multi-dimensional information set;

determining multi-dimensional information corresponding to the risk constraint conditions of the policy container in the multi-dimensional information set;

and deploying the strategy container according to the determined multi-dimensional information and the hierarchy of the strategy container to obtain the risk detection strategy system.

The risk detection policy system construction apparatus provided in one or more embodiments of the present specification generates, based on historical business data, a plurality of policy containers corresponding to predetermined risk constraints, where a policy container includes at least one risk detection policy that meets the risk constraints thereof, and the risk constraints of the policy container are determined by dividing information of multiple dimensions related to a business; and deploying according to the hierarchy of the strategy container and the risk constraint condition to form a risk detection strategy system for performing risk detection processing on the service data of the target service to be subjected to the risk detection processing. Because the risk detection strategies among all layers in the multi-layer risk detection strategy system are different in the risk constraint conditions, the multi-aspect risk characterization is realized, the accuracy rate of risk detection can be improved, the coverage rate is greatly improved, and the effective detection of risks such as passive fraud is realized. Moreover, because the risk detection strategy system is multilayer, namely a three-dimensional cellular structure, the condition that the whole body is moved by pulling can not occur, and the whole system can not be influenced by misoperation or misconfiguration of any risk detection strategy, so that the operation cost of the risk detection strategy is reduced, and the stability of the strategy system is improved. Moreover, the multilayer three-dimensional risk detection strategy system can more intuitively reflect the positions of the strategy containers, and is beneficial for managers to adjust the strategy containers so as to change the whole risk detection strategy system.

It should be noted that, in this specification, the embodiment of the apparatus for constructing the risk detection policy system and the embodiment of the method for constructing the risk detection policy system in this specification are based on the same inventive concept, and therefore, for specific implementation of this embodiment, reference may be made to implementation of the method for constructing the risk detection policy system, and repeated details are not described herein.

Further, corresponding to the service processing method described above, based on the same technical concept, one or more embodiments of the present specification further provide a service processing device, where the service processing device is configured to execute the service processing method described above, and fig. 10 is a schematic structural diagram of a service processing device provided in one or more embodiments of the present specification.

As shown in fig. 10, the business processing device may have a relatively large difference due to different configurations or performances, and may include one or more processors 501 and a memory 502, where the memory 502 may store one or more stored applications or data. Memory 502 may be, among other things, transient or persistent storage. The application program stored in memory 502 may include one or more modules (not shown), each of which may include a series of computer-executable instructions in a business processing device. Still further, processor 501 may be configured to communicate with memory 502 to execute a series of computer-executable instructions in memory 502 on a business processing device. The traffic processing apparatus may also include one or more power supplies 503, one or more wired or wireless network interfaces 504, one or more input-output interfaces 505, one or more keyboards 506, etc.

In one particular embodiment, a business processing apparatus includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the business processing apparatus, and configured for execution by the one or more processors the one or more programs include computer-executable instructions for:

acquiring service data of a target service to be subjected to risk detection processing;

based on a multi-layer risk detection strategy system which is constructed in advance, carrying out risk detection processing on the service data to obtain risk detection result information; the risk detection system comprises a risk detection strategy system and a risk detection strategy system, wherein a plurality of strategy containers are deployed in the risk detection strategy system, the strategy containers comprise at least one risk detection strategy which meets risk constraint conditions of the strategy containers, and the risk constraint conditions of the strategy containers are determined by dividing information of a plurality of dimensions related to business; the strategy container is deployed in the risk detection strategy system according to the hierarchy of the strategy container and risk constraint conditions; the hierarchy of the policy container characterizes a priority of risk detection processing;

and performing corresponding service processing on the target service according to the risk detection result information.

Optionally, when executed, the computer-executable instructions perform risk detection processing on the business data based on a pre-constructed multi-layer stereoscopic risk detection policy system, where the risk detection processing includes:

determining a policy container for performing matching processing on the business data for the first time in the risk detection policy system according to a preset matching policy, and inputting the business data into the determined policy container to perform matching processing on the business data and a risk detection policy in the policy container;

Optionally, the computer executable instructions, when executed, further comprise:

if the condition that the preset container adjustment condition is met is determined, performing corresponding adjustment processing on a strategy container in the risk detection strategy system; wherein the adjustment process comprises one or more of: adding, deleting and modifying policy containers;

Optionally, when executed, the computer-executable instructions, before acquiring the service data of the target service to be subjected to the risk detection processing, further include:

acquiring historical service data of a plurality of services;

In the service processing device provided in one or more embodiments of the present specification, a multi-layer risk detection policy system is pre-established, where a plurality of policy containers are deployed in the risk detection policy system, and each policy container includes at least one risk detection policy that meets risk constraint conditions of the policy container; the risk constraint condition of the strategy container is determined by dividing information of multiple dimensions related to the business, and the strategy container is deployed in a risk detection strategy system according to the hierarchy of the strategy container and the risk constraint condition; and when the business data of the target business to be subjected to risk detection processing is obtained, performing risk detection processing on the business data based on the risk detection strategy system, and performing corresponding business processing on the target business according to the risk detection result information. Because in the multi-layer risk detection strategy system, the risk constraint conditions met by the risk detection strategies among the layers are different, so that the risk characterization in multiple aspects is realized, the accuracy of the risk detection can be improved, the coverage rate is greatly improved, and the effective detection of risks such as passive fraud is realized. Moreover, because the risk detection strategy system is multilayer, namely a three-dimensional cellular structure, the condition that the whole body is moved by pulling can not occur, and the whole system can not be influenced by misoperation or misconfiguration of any risk detection strategy, so that the operation cost of the risk detection strategy is reduced, and the stability of the strategy system is improved. Moreover, the multilayer three-dimensional risk detection strategy system can more intuitively reflect the positions of the strategy containers, and is beneficial for managers to adjust the strategy containers so as to change the whole risk detection strategy system.

It should be noted that the embodiment of the service processing apparatus in this specification and the embodiment of the service processing method in this specification are based on the same inventive concept, and therefore, for specific implementation of this embodiment, reference may be made to implementation of the corresponding service processing method, and repeated details are not described again.

Further, corresponding to the above-described method for constructing a risk detection policy system, based on the same technical concept, one or more embodiments of the present specification further provide a device for constructing a risk detection policy system, where the device is configured to execute the above-described method for constructing a risk detection policy system, and fig. 11 is a schematic structural diagram of the device for constructing a risk detection policy system provided in one or more embodiments of the present specification.

As shown in fig. 11, the risk detection policy system building device may have a relatively large difference due to different configurations or performances, and may include one or more processors 601 and a memory 602, where one or more storage applications or data may be stored in the memory 602. Wherein the memory 602 may be transient or persistent storage. The application program stored in memory 602 may include one or more modules (not shown), each of which may include a series of computer-executable instructions in a build device of a risk detection policy hierarchy. Still further, processor 601 may be configured to communicate with memory 602 to execute a series of computer-executable instructions in memory 602 on a risk detection policy framework building device. The risk detection policy architecture building apparatus may also include one or more power supplies 603, one or more wired or wireless network interfaces 604, one or more input-output interfaces 605, one or more keyboards 606, and the like.

In a particular embodiment, a risk detection policy framework building apparatus includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the risk detection policy framework building apparatus, and the one or more programs configured to be executed by one or more processors include computer-executable instructions for:

acquiring historical service data of a plurality of services;

generating a plurality of policy containers corresponding to the determined risk constraints based on the historical business data; wherein the policy container comprises at least one risk detection policy meeting corresponding risk constraints;

determining the arrangement position of the strategy container in a risk detection strategy system to be constructed according to the strategy attribute information of the risk detection strategy;

constructing a multilayer three-dimensional risk detection strategy system based on the plurality of strategy containers and the arrangement positions thereof; the risk detection strategy system is used for carrying out risk detection processing on the service data of the target service to be subjected to the risk detection processing.

Optionally, the computer executable instructions, when executed, further comprise, after obtaining historical service data of a plurality of services:

determining user type information of related users of the business and industry type information of the business industry according to the historical business data;

drawing a plane chessboard according to the user type information and the industry type information;

the method for constructing a multilayer three-dimensional risk detection strategy system based on the multiple strategy containers and the arrangement positions thereof comprises the following steps:

and according to the arrangement positions, carrying out three-dimensional arrangement processing on the strategy containers on the plane chessboard to obtain a multilayer three-dimensional risk detection strategy system.

The risk detection policy system construction device provided in one or more embodiments of the present specification generates, based on historical business data, a plurality of policy containers corresponding to predetermined risk constraints, where a policy container includes at least one risk detection policy that meets the risk constraints thereof, and the risk constraints of the policy container are determined by dividing information of multiple dimensions related to a business; and deploying according to the hierarchy of the strategy container and the risk constraint condition to form a risk detection strategy system for performing risk detection processing on the service data of the target service to be subjected to the risk detection processing. Because the risk detection strategies among all layers in the multi-layer risk detection strategy system are different in the risk constraint conditions, the multi-aspect risk characterization is realized, the accuracy rate of risk detection can be improved, the coverage rate is greatly improved, and the effective detection of risks such as passive fraud is realized. Moreover, because the risk detection strategy system is multilayer, namely a three-dimensional cellular structure, the condition that the whole body is moved by pulling can not occur, and the whole system can not be influenced by misoperation or misconfiguration of any risk detection strategy, so that the operation cost of the risk detection strategy is reduced, and the stability of the strategy system is improved. Moreover, the multilayer three-dimensional risk detection strategy system can more intuitively reflect the positions of the strategy containers, and is beneficial for managers to adjust the strategy containers so as to change the whole risk detection strategy system.

It should be noted that, the embodiment of the apparatus for constructing the risk detection policy system in this specification and the embodiment of the method for constructing the risk detection policy system in this specification are based on the same inventive concept, and therefore, specific implementation of this embodiment may refer to implementation of the method for constructing the risk detection policy system described above, and repeated details are not described again.

Further, based on the same technical concept, one or more embodiments of the present specification further provide a storage medium for storing computer-executable instructions, where in a specific embodiment, the storage medium may be a usb disk, an optical disk, a hard disk, and the like, and when the storage medium stores computer-executable instructions, the following processes can be implemented when the storage medium is executed by a processor:

Optionally, when executed by a processor, the computer-executable instructions stored in the storage medium perform risk detection processing on the business data based on a pre-constructed multi-layer stereoscopic risk detection policy system, including:

Optionally, when executed by a processor, the computer-executable instructions stored in the storage medium, before acquiring the service data of the target service to be subjected to the risk detection processing, further include:

dividing information corresponding to the strategy container in each dimension on a plurality of dimensions related to the service;

Optionally, the storage medium stores computer-executable instructions that, when executed by the processor, further comprise:

acquiring historical service data of a plurality of services;

One or more embodiments of the present disclosure provide a storage medium storing computer executable instructions that, when executed by a processor, pre-establish a multi-tiered risk detection policy system, where a plurality of policy containers are deployed in the risk detection policy system, and each policy container includes at least one risk detection policy that meets its risk constraint; the risk constraint condition of the strategy container is determined by dividing information of multiple dimensions related to the business, and the strategy container is deployed in a risk detection strategy system according to the hierarchy of the strategy container and the risk constraint condition; and when the business data of the target business to be subjected to risk detection processing is obtained, performing risk detection processing on the business data based on the risk detection strategy system, and performing corresponding business processing on the target business according to the risk detection result information. Because in the multi-layer risk detection strategy system, the risk constraint conditions met by the risk detection strategies among the layers are different, so that the risk characterization in multiple aspects is realized, the accuracy of the risk detection can be improved, the coverage rate is greatly improved, and the effective detection of risks such as passive fraud is realized. Moreover, because the risk detection strategy system is multilayer, namely a three-dimensional cellular structure, the condition that the whole body is moved by pulling can not occur, and the whole system can not be influenced by misoperation or misconfiguration of any risk detection strategy, so that the operation cost of the risk detection strategy is reduced, and the stability of the strategy system is improved. Moreover, the multilayer three-dimensional risk detection strategy system can more intuitively reflect the positions of the strategy containers, and is beneficial for managers to adjust the strategy containers so as to change the whole risk detection strategy system.

In another specific embodiment, the storage medium may be a usb disk, an optical disk, a hard disk, or the like, and the storage medium stores computer executable instructions that, when executed by the processor, implement the following process:

acquiring historical service data of a plurality of services;

generating a plurality of policy containers corresponding to predetermined risk constraints based on the historical business data; wherein, the strategy container comprises at least one risk detection strategy meeting the risk constraint condition; the risk constraint condition of the strategy container is determined by dividing information of a plurality of dimensions related to the business;

deploying the multiple strategy containers according to the determined hierarchy of the strategy containers and risk constraint conditions to form a risk detection strategy system; the risk detection strategy system is used for carrying out risk detection processing on the service data of the target service to be subjected to the risk detection processing, and the hierarchy of the strategy container represents the priority of the risk detection processing.

Optionally, when executed by a processor, the computer-executable instructions stored in the storage medium deploy the policy containers according to the determined hierarchy of the policy containers and the risk constraint condition to form a risk detection policy system, including:

determining information of multiple dimensions related to the service according to the historical service data;

One or more embodiments of the present specification provide a storage medium storing computer-executable instructions that, when executed by a processor, generate a plurality of policy containers corresponding to predetermined risk constraints based on historical business data, where a policy container includes at least one risk detection policy that meets the risk constraints thereof, and the risk constraints of the policy container are determined by dividing information of multiple dimensions related to a business; and deploying according to the hierarchy of the strategy container and the risk constraint condition to form a risk detection strategy system for performing risk detection processing on the service data of the target service to be subjected to the risk detection processing. Because the risk detection strategies among all layers in the multi-layer risk detection strategy system are different in the risk constraint conditions, the multi-aspect risk characterization is realized, the accuracy rate of risk detection can be improved, the coverage rate is greatly improved, and the effective detection of risks such as passive fraud is realized. Moreover, because the risk detection strategy system is multilayer, namely a three-dimensional cellular structure, the condition that the whole body is moved by pulling can not occur, and the whole system can not be influenced by misoperation or misconfiguration of any risk detection strategy, so that the operation cost of the risk detection strategy is reduced, and the stability of the strategy system is improved. Moreover, the multilayer three-dimensional risk detection strategy system can more intuitively reflect the positions of the strategy containers, and is beneficial for managers to adjust the strategy containers so as to change the whole risk detection strategy system.

It should be noted that the embodiment of the storage medium in this specification and the method embodiment in this specification are based on the same inventive concept, and therefore, for specific implementation of this embodiment, reference may be made to implementation of the foregoing corresponding method, and repeated details are not described here.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: the ARC625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the units may be implemented in the same software and/or hardware or in multiple software and/or hardware when implementing the embodiments of the present description.

One skilled in the art will recognize that one or more embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, one or more embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

One or more embodiments of the present description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. One or more embodiments of the specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of this document and is not intended to limit this document. Various modifications and changes may occur to those skilled in the art from this document. Any modifications, equivalents, improvements, etc. which come within the spirit and principle of the disclosure are intended to be included within the scope of the claims of this document.

Claims

1. A service processing method comprises the following steps:

2. The method according to claim 1, wherein the performing risk detection processing on the business data based on a pre-constructed multi-layer risk detection policy system includes:

3. The method according to claim 1, wherein before acquiring the service data of the target service to be subjected to the risk detection processing, the method further comprises:

4. The method of claim 3, wherein the dividing information corresponding to the policy container in each dimension in the plurality of dimensions related to the service comprises:

dividing user type information corresponding to the strategy container in a user type dimension; dividing the industry type information corresponding to the strategy container in an industry type dimension;

the determining the multi-dimensional mapping information of the policy container according to the information corresponding to each dimension of the divided policy container includes:

and determining the mapping information of the user type and the industry type of the strategy container according to the user type information and the industry type information corresponding to the divided strategy container.

5. The method according to claim 1, wherein before acquiring the service data of the target service to be subjected to the risk detection processing, the method further comprises:

acquiring historical service data of a plurality of services;

6. The method of claim 5, the deploying the plurality of policy containers according to the hierarchy of policy containers and risk constraints to form the risk detection policy hierarchy, comprising:

and deploying the strategy container according to the multi-dimensional information and the hierarchy of the strategy container to obtain the risk detection strategy system.

7. The method of claim 5, the business related information of the plurality of dimensions comprising user type information of a user type dimension and industry type information of an industry type dimension; the risk constraints include at least one first risk constraint that includes first target user type information and first target industry type information;

the generating a plurality of policy containers corresponding to each of the predetermined risk constraints based on the historical business data comprises:

determining a first risk factor forming a designated risk based on the first target historical service data according to a preset mode;

and generating a first risk detection strategy according to the first risk factor, and storing the first risk detection strategy into the corresponding first strategy container.

8. The method of claim 5, the business related information of the plurality of dimensions comprising industry type information of an industry type dimension; the risk constraints include at least one second risk constraint that includes second target industry type information:

screening second target historical business data matched with the second target industry type information from the historical business data;

determining a second risk factor forming a designated risk based on the second target historical service data according to a preset mode;

and generating a second risk detection strategy according to the second risk factor, and storing the second risk detection strategy into the corresponding second strategy container.

9. The method of claim 5, the business related information of the plurality of dimensions comprising user type information of a user type dimension and industry type information of an industry type dimension; the risk constraint conditions comprise third risk constraint conditions, wherein the third risk constraint conditions comprise first information representing each user type information and second information representing each industry type information:

creating a third policy container according to the predetermined third risk constraint condition;

determining a third risk factor forming a designated risk based on the historical service data according to a preset mode;

and generating a third risk detection strategy according to the third risk factor, and storing the third risk detection strategy into the third strategy container.

10. The method of claim 5, the risk constraint comprising a fourth risk constraint comprising list type information:

creating a fourth policy container according to the predetermined fourth risk constraint condition;

determining a target list which has a designated risk and is matched with the list type information based on the historical service data according to a preset mode;

and generating a fourth risk detection strategy according to the target list, and storing the fourth risk detection strategy into the fourth strategy container.

11. The method of claim 5, the business related information of the plurality of dimensions comprising user type information of a user type dimension and industry type information of an industry type dimension; the risk constraint conditions comprise fifth risk constraint conditions, and the fifth risk constraint conditions comprise second target user type information and screening information of a third target industry type corresponding to the business without specified risk represented and screened;

screening the second target user type information and the third target industry type information based on the historical service data according to a preset mode;

saving the fifth risk detection policy to the fifth policy container.

12. The method of claim 1, further comprising:

13. A method for constructing a risk detection strategy system comprises the following steps:

acquiring historical service data of a plurality of services;

14. The method of claim 13, the deploying the plurality of policy containers to form a risk detection policy hierarchy according to the determined hierarchy of policy containers and risk constraints, comprising:

15. The method of claim 13, the business related information of the plurality of dimensions comprising user type information of a user type dimension and industry type information of an industry type dimension; the risk constraints include at least one first risk constraint that includes first target user type information and first target industry type information;

the generating a plurality of policy containers corresponding to predetermined risk constraints based on the historical business data comprises:

16. The method of claim 13, the business related information of the plurality of dimensions comprising industry type information of an industry type dimension; the risk constraints include at least one second risk constraint that includes second target industry type information:

17. The method of claim 13, the business related information of the plurality of dimensions comprising user type information of a user type dimension and industry type information of an industry type dimension; the risk constraint conditions comprise third risk constraint conditions, wherein the third risk constraint conditions comprise first information representing each user type information and second information representing each industry type information:

18. The method of claim 13, the risk constraint comprising a fourth risk constraint comprising at least one roster type information:

determining a target list which has risks and is matched with the list type information based on the historical service data according to a preset mode;

19. The method of claim 13, the business related information of the plurality of dimensions comprising user type information of a user type dimension and industry type information of an industry type dimension; the risk constraint conditions comprise fifth risk constraint conditions, and the fifth risk constraint conditions comprise second target user type information and screening information of a third target industry type corresponding to the business without specified risk represented and screened;

saving the fifth risk detection policy to the fifth policy container.

20. A traffic processing apparatus, comprising:

the acquisition module is used for acquiring the service data of the target service to be subjected to risk detection processing;

the detection module is used for carrying out risk detection processing on the service data based on a multi-layer risk detection strategy system which is constructed in advance to obtain risk detection result information; the risk detection system comprises a risk detection strategy system and a risk detection strategy system, wherein a plurality of strategy containers are deployed in the risk detection strategy system, the strategy containers comprise at least one risk detection strategy which meets risk constraint conditions of the strategy containers, and the risk constraint conditions of the strategy containers are determined by dividing information of a plurality of dimensions related to business; the strategy container is deployed in the risk detection strategy system according to the hierarchy of the strategy container and risk constraint conditions; the hierarchy of the policy container characterizes a priority of risk detection processing;

and the processing module is used for carrying out corresponding service processing on the target service according to the risk detection result information.

21. A device for constructing a risk detection strategy system comprises:

the acquisition module is used for acquiring historical service data of a plurality of services;

the generating module is used for generating a plurality of strategy containers corresponding to each predetermined risk constraint condition based on the historical business data; wherein, the strategy container comprises at least one risk detection strategy meeting the risk constraint condition; the risk constraint condition of the strategy container is determined by dividing information of a plurality of dimensions related to the business;

the building module is used for deploying the strategy containers according to the determined hierarchy of the strategy containers and risk constraint conditions to form a risk detection strategy system; the risk detection strategy system is used for carrying out risk detection processing on the service data of the target service to be subjected to the risk detection processing, and the hierarchy of the strategy container represents the priority of the risk detection processing.

22. A traffic processing device, comprising:

a processor; and;

a memory arranged to store computer executable instructions that, when executed, cause the processor to:

23. A risk detection policy system construction device comprises:

a processor; and;

acquiring historical service data of a plurality of services;

24. A storage medium storing computer-executable instructions that when executed implement the following:

25. A storage medium storing computer-executable instructions that when executed implement the following:

acquiring historical service data of a plurality of services;