CN115689578A

CN115689578A - Method, device, equipment and medium for identifying marketing cheating risk

Info

Publication number: CN115689578A
Application number: CN202211418857.6A
Authority: CN
Inventors: 徐晓辉
Original assignee: Alipay Labs Singapore Pte Ltd
Current assignee: Advanced Nova Technology Singapore Holdings Ltd
Priority date: 2022-11-14
Filing date: 2022-11-14
Publication date: 2023-02-03

Abstract

The embodiment of the specification discloses a method, a device, equipment and a medium for identifying marketing cheating risks. The scheme comprises the following steps: acquiring a data acquisition request which is sent by a second organization and used for acquiring transaction data of a participating object of a payment order outside the second organization; the information acquisition request comprises an object identifier of the participating object; acquiring transaction data generated by the participating object in another organization according to the object identification; desensitizing the transaction data to obtain desensitized transaction data; and sending the desensitized transaction data to the second institution so that the second institution identifies whether the payment order has marketing cheating risks according to the desensitized transaction data.

Description

Method, device, equipment and medium for identifying marketing cheating risk

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a medium for identifying a risk of marketing cheating.

Background

With the development of computer technology, marketing modes such as issuing preferential offers, popularizing rewards and new user rewards are generally adopted by electronic commerce and internet platforms, and the operation income of the electronic commerce and internet platforms is improved. Some grey and black industries similar to the wool party are also generated, and the normal marketing business in the Internet platform is seriously influenced.

Therefore, how to more accurately identify the marketing cheating risk is a technical problem to be solved urgently.

Disclosure of Invention

The embodiment of the specification provides a method, a device, equipment and a medium for identifying marketing cheating risks, and aims to solve the problem of inaccurate identification caused by data islands in the existing identification method.

In order to solve the above technical problem, the embodiments of the present specification are implemented as follows:

the method for identifying marketing cheating risks provided by the embodiment of the specification is applied to a first mechanism and comprises the following steps:

acquiring a data acquisition request which is sent by a second organization and used for acquiring transaction data of a participating object of a payment order outside the second organization; the information acquisition request comprises an object identifier of the participating object;

acquiring transaction data generated by the participating object in another organization according to the object identification;

desensitizing the transaction data to obtain desensitized transaction data;

and sending the desensitized transaction data to the second institution so that the second institution identifies whether the payment order has marketing cheating risks according to the desensitized transaction data.

acquiring a risk identification request sent by a second organization and used for carrying out marketing cheating risk identification on a payment order; the risk identification request comprises order information of the payment order;

acquiring transaction data of a participating object of the payment order outside the second organization according to the order information;

identifying whether the payment order has marketing cheating risks or not according to the transaction data to obtain an identification result;

feeding back the recognition result to the second mechanism.

The device for identifying marketing cheating risks provided by the embodiment of the specification comprises:

the request acquisition module is used for acquiring a data acquisition request which is sent by a second mechanism and used for acquiring transaction data of a participating object of a payment order outside the second mechanism; the information acquisition request comprises an object identifier of the participating object;

the data acquisition module is used for acquiring transaction data of the participating object generated by other organizations according to the object identification;

the desensitization module is used for performing desensitization processing on the transaction data to obtain desensitized transaction data;

and the data sending module is used for sending the desensitized transaction data to the second mechanism so that the second mechanism can identify whether the payment order has marketing cheating risks according to the desensitized transaction data.

the request acquisition module is used for acquiring a risk identification request which is sent by a second organization and used for carrying out marketing cheating risk identification on the payment order; the risk identification request comprises order information of the payment order;

the data acquisition module is used for acquiring transaction data of a participating object of the payment order outside the second organization according to the order information;

the risk identification module is used for identifying whether the payment order has marketing cheating risks or not according to the transaction data to obtain an identification result;

and the result feedback module is used for feeding back the identification result to the second mechanism.

The equipment for identifying marketing cheating risks provided by the embodiment of the specification comprises:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to:

desensitizing the transaction data to obtain desensitized transaction data;

at least one processor; and the number of the first and second groups,

feeding back the recognition result to the second mechanism.

Embodiments of the present specification provide a computer readable medium having stored thereon computer readable instructions executable by a processor to implement a method of identifying a risk of marketing cheating.

One embodiment of the present description achieves the following advantageous effects:

in the embodiment of the specification, marketing cheating risk identification can be performed on a payment order generated by a second organization, transaction data generated by a participating object of the payment order in other organizations can be acquired for marketing cheating risk identification, the problem of data island existing in the marketing cheating risk identification can be solved, and the method is crossed with the method for identifying by only adopting the transaction data in the second organization.

In addition, in the embodiment of the description, even if the user initiating payment has a small number of transactions in the second institution or is a new user, the user can be identified based on the transaction data of the user in other institutions, and the accuracy of identifying the marketing cheating risk can be improved.

Drawings

In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the description below are only some embodiments described in the present application, and for those skilled in the art, other drawings may be obtained according to the drawings without creative efforts.

FIG. 1 is a schematic flow chart illustrating an overall scheme of a method for identifying marketing cheating risks in an embodiment of the present disclosure;

FIG. 2 is a flow chart illustrating a method for identifying a risk of marketing cheating according to an embodiment of the present disclosure;

fig. 3 is a schematic diagram of a wind control identification policy system provided in an embodiment of the present specification;

FIG. 4 is a swim lane diagram corresponding to the method of identifying a risk of marketing cheating of FIG. 2 provided by an embodiment of the present specification;

FIG. 5 is a flowchart illustrating a method for identifying a risk of marketing cheating according to an embodiment of the present disclosure;

FIG. 6 is a swim lane diagram corresponding to the method of identifying risk of marketing cheating provided by embodiments of the present specification and of FIG. 5;

fig. 7 is a schematic structural diagram of an apparatus for identifying a risk of marketing cheating, corresponding to fig. 2, provided in an embodiment of the present specification;

fig. 8 is a schematic structural diagram of an apparatus for identifying a risk of marketing cheating, corresponding to fig. 5, provided in an embodiment of the present specification;

fig. 9 is a schematic structural diagram of an apparatus for identifying a risk of marketing cheating according to an embodiment of the present disclosure.

Detailed Description

To make the objects, technical solutions and advantages of one or more embodiments of the present disclosure more apparent, the technical solutions of one or more embodiments of the present disclosure will be described in detail and completely with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments that can be derived by a person skilled in the art from the embodiments given herein without making any creative effort fall within the scope of protection of one or more embodiments of the present specification.

The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.

In the prior art, for the prevention and control of common marketing anti-cheating, a common method is to build and identify cheating behaviors according to own data through a quantitative strategy. This may cause a problem that the cheating behavior cannot be recognized or cannot be recognized accurately due to a small amount of data.

In order to solve the defects in the prior art, the scheme provides the following embodiments:

fig. 1 is a schematic flowchart of an overall scheme of a method for identifying marketing cheating risks in an embodiment of the present specification. As shown in fig. 1, the solution may comprise a second mechanism 1 as well as a first mechanism 2. The second institution 1 may be an institution capable of receiving a payment order initiated by a user, and the second institution 1 may further obtain transaction data, provided by the first institution 2, of the participating object of the payment order in other institutions, and may perform marketing cheating risk identification on the payment order based on the transaction data in other institutions. Moreover, in order to ensure the security and compliance of transaction data transmission, the first institution 2 may perform desensitization processing on data to be transmitted, and the second institution 1 may perform marketing cheating risk identification based on the desensitized data. As another embodiment, the first organization 2 may also have a risk identification capability, the second organization 1 may also send a risk identification request for identifying the marketing cheating risk for the payment order to the first organization 2, and the first organization 2 may identify the marketing cheating risk based on the transaction information related to the payment order in the second organization and other organizations and feed back the identification result to the second organization 1. In the embodiment of the specification, the marketing cheating risk identification can be performed on the payment order of the user in the second organization by combining the transaction data of the user in other organizations, the problem of data islanding can be avoided, and the accuracy of the marketing cheating risk identification is improved.

Next, a method for identifying marketing cheating risks provided by the embodiments of the specification will be described in detail with reference to the accompanying drawings:

fig. 2 is a flowchart illustrating a method for identifying a risk of marketing cheating according to an embodiment of the present disclosure. From the viewpoint of a program, the execution subject of the flow may be a program installed in an application server or an application client. In particular, the method may be applied to a first institution capable of carrying financial transaction functions.

As shown in fig. 2, the process may include the following steps:

step 202: acquiring a data acquisition request which is sent by a second organization and used for acquiring transaction data of a participating object of a payment order outside the second organization; the information acquisition request comprises the object identification of the participating object.

Wherein the second institution may be an institution capable of receiving the user-initiated payment order. In practical application, the user performs online transaction through the terminal application, and the second institution may be an institution providing online transaction service. From a level point of view, the second institution may also be a server capable of receiving a payment order initiated by the user. For example, the user may make an online purchase, pay a living fee online, and the like, and the second organization may provide the user with an online service and obtain order information submitted by the user.

The second institution may generate a data acquisition request for acquiring transaction data related to the payment order based on the payment order submitted by the user, and send the data acquisition request to the first institution. The first mechanism can be an organization with a financial transaction function, and can provide financial transaction service for a plurality of organizations. In this way, the first institution may perform financial transactions for payment orders received by the second institution, and may also perform financial transactions according to the needs of other institutions. The first institution may contain transaction data for institutions other than the second institution. For example, a user a purchases online through APP1 and pays for life through APP2, and the first organization may provide financial transaction services for APP1 and APP2, so that the first organization may include transaction data executed by the user in each application.

In practical application, the second mechanism may also send the obtained order information of the payment order to the first mechanism, so that the first mechanism may also obtain information or object identifiers of each participating object in the payment order.

Step 204: and acquiring transaction data generated by the participating object in another organization according to the object identification.

The additional mechanism may comprise a mechanism other than the second mechanism. In the embodiment of the present specification, the participating object may include at least one of a transaction party, a transaction object, and a transaction medium corresponding to the order payment request; the transaction data may include at least one of a transaction time, a transaction amount, and a payment method. The transaction medium may include a terminal where the user initiates a transaction, or may include network information and the like used by the terminal transaction. The transaction object may represent an item purchased by the user.

In practical applications, the payment order received by the second institution may include information of both parties of the transaction, transaction amount, transaction time, information of the transaction object, and the like. The participating objects may include those directly obtained from order information of the payment order, for example, two parties to a transaction, a transaction object, and the like; the information further analyzed according to the order information may also be included, for example, the second organization may further obtain a terminal which logs in and uses the account according to the payment account in the payment order, and may also obtain network information, such as IP information, etc., of the user submitting the payment order. Step 206: desensitizing the transaction data to obtain desensitized transaction data.

Step 208: and sending the desensitized transaction data to the second institution so that the second institution identifies whether the payment order has marketing cheating risks according to the desensitized transaction data.

In the embodiment of the description, in order to ensure the security of the transaction data and the compliance of information transmission, the first mechanism may perform desensitization processing on the transaction data and then send the transaction data to the second mechanism. The second organization may perform identification of marketing cheating risks based on the desensitized data.

It should be understood that the order of some steps in the method described in one or more embodiments of the present disclosure may be interchanged according to actual needs, or some steps may be omitted or deleted.

In the method in fig. 2, in the embodiment of the present specification, marketing cheating risk identification may be performed on a payment order generated by a second organization, and transaction data generated by a participating object of the payment order in other organizations may be acquired to perform marketing cheating risk identification, so that a data islanding problem existing in the marketing cheating risk identification may be solved, and a method of performing identification only by using the transaction data in the second organization is intersected.

Based on the method of fig. 2, the present specification also provides some specific embodiments of the method, which are described below.

In order to obtain data with a higher reference value and improve the identification accuracy, in an embodiment of the present specification, optionally, the obtaining transaction data generated by the participant at another institution may specifically include:

and acquiring transaction data of the participating object generated by other organizations except the second organization within a preset time period before the data acquisition request.

The data acquisition request sent by the second mechanism can be acquired as a time node, and the transaction data related to the participation object of the payment order in a preset time period before the time node is acquired. For example, transaction data may be obtained over the last month.

In practical application, the first mechanism can also send the processed transaction data of each mechanism to the mechanism needing marketing cheating risk identification according to a preset period. The second organization can also acquire information related to the order to be identified according to the transaction data provided by the first organization recently acquired, and identify the risk of marketing cheating.

Optionally, in this embodiment of the present specification, the desensitizing process on the transaction data may specifically include:

sensitive information in the transaction data is obtained;

determining desensitization data corresponding to the sensitive information according to a preset desensitization algorithm;

replacing the sensitive information in the transaction data with the desensitization data.

The preset desensitization algorithm may include an encryption algorithm, a preset mapping relationship, and the like. The specific content of the sensitive information may be determined according to relevant laws and regulations, and may include sensitive information such as a user name, a mobile phone number, a device ID, and the like. In the embodiment of the present specification, the pre-trained sensitive information extraction model may be used to extract the sensitive information in the transaction data, the preset sensitive information library may also be used to determine the sensitive information in the transaction data, or a manner of extracting the sensitive information in the prior art may also be used, which is not limited specifically here.

In practical application, in order to facilitate risk identification, the same sensitive information can correspond to the same desensitization information, and the desensitization information is used for replacing the sensitive information to carry out risk identification. It is understood that the same sensitive information may correspond to different desensitization information, and the specific form is not particularly limited as long as it can be reasonably utilized.

The second institution in the embodiment of the present specification may further include local transaction data of a transaction event in which the participant participates in the second institution; the second institution identifies whether the payment order has a risk of marketing cheating according to the desensitized transaction data, and specifically may include:

and the second organization identifies whether the payment order has marketing cheating risks according to the desensitized transaction data and the local transaction data.

The transaction event transaction data of the participating object participating in the second institution may be data generated by the second institution or data sent by the first institution to the second institution. In embodiments of the present description, the second institution may perform risk identification based on transaction data that the user has engaged in at the second institution as well as other institutions.

The first mechanism in embodiments of the present description may include a mechanism that carries financial transaction functionality; the transaction data may comprise transaction data generated by an entity other than the second entity, the first entity being the carrier and the participant. For example, a first institution may represent a wallet institution, and may process transaction requests initiated by a second institution as well as other institutions.

The second institution may include an institution that obtains the user-initiated transaction operation. For example, the second organization may provide a platform for online shopping, and the first organization may be an organization capable of processing transactions generated by the platform.

With the development of international business, the payment order may be the payment order of the international business, and for more accurate identification of marketing cheating, the identification may be performed by using transaction information generated by the user in each country or region. In order to meet the data transmission requirements of countries or regions, the SAAS service area center can be set, and marketing cheating risk identification can be performed on the basis that data cannot exit the area center, so that the risk identification capability of the country organization is weak, and the country organization with data exit and compliance problems can also perform relatively accurate risk identification. Optionally, in this embodiment, the second mechanism may include an SAAS-based service area center corresponding to the first mechanism; the SAAS service area center is used for providing service for a first mechanism of a plurality of areas.

In the embodiment of the specification, a wind control engine can be deployed in the second mechanism; the wind control engine can comprise a wind control identification strategy for identifying marketing cheating risks of at least one transaction object of a consumer, a merchant, a transaction account and a transaction medium. The second organization may utilize the wind-controlled engine to identify the risk of marketing cheating from a different perspective.

Fig. 3 is a schematic diagram of a wind control identification policy system provided in an embodiment of the present specification. As shown in fig. 3, in this embodiment of the present specification, the wind control identification policy for identifying marketing cheating risks may include risk identification for a user side, and may also include risk identification for a merchant side, which specifically includes: basic strategy, special strategy, group strategy, model strategy, black yield strategy, etc.

The basic strategy can be used for identifying whether marketing cheating risks exist in behavior characteristics of transaction participants, and the behavior characteristics can include characteristics of transaction code cutting behaviors, transaction frequency, subsidy user aggregation degree and the like. In practical application, if the user carries out multiple transactions in a short time, the subsidy obtained by the user is higher than other users, or the proportion of the transaction obtained by the user to the total transaction volume of the user is higher, if the payment order initiated by the user at present is also an order related to marketing rewards or subsidies, the suspected risk of marketing cheating of the user can be identified. For the merchant, if high subsidy user aggregation, short-time code cutting transaction, marketing cheating merchant and the like exist in the merchant, certain marketing cheating risk of the merchant can be reflected. The practical application can evaluate the client side through the number of times of marketing activities participated by the user, for example, when the number of times of marketing activities participated by the user is mostly close to the set maximum number of times, that is, the user is closer to the range of single activity number, the corresponding marketing cheating risk possibly existing in the user can be reflected. For a merchant, a risk threshold may also be set, and when the risk value of the merchant exceeds the risk threshold, the merchant may be considered as a risk merchant. In practical application, if the risk value of a merchant is located closer to the risk threshold value within a period of time or for multiple times, the merchant may be considered as a bottom-line risk merchant, and if the time that the merchant belongs to the bottom-line risk merchant is longer, the merchant may also be considered as having a corresponding marketing cheating risk.

The special strategy can be used for identifying the transaction account of the transaction participant and whether the transaction medium has marketing cheating risks. Whether the user account submitting the order is at risk or not can be determined based on the age, the mobile phone number, the KYC grade, the registration duration of the user account, a blacklist and the like of the user; it may also be determined whether the submitted order is media risky based on the device, network, etc. used by the user. For the merchant, whether the merchant has the risk of risk user aggregation can also be determined from the age of the user, the mobile phone number, the KYC grade of the user, the risk user list and the like.

A group strategy is used to identify the group nature of the transaction participants; the buyer and the buyer can be identified based on the policies such as the same equipment registration account, the same ID card registration account, the same mailbox registration account, the same mobile phone registration account and the like. Whether medium aggregation exists at the merchant end can also be determined based on risk device aggregation, network IP/Wifimac aggregation, device multi-account and the like.

The model strategy is used for carrying out marketing cheating risk identification according to at least one model of an unsupervised exception model, a credible user model, an anti-cheating model and a group graph model.

In practical application, the unsupervised abnormal model may be a model method for unsupervised learning to identify users in different groups by characterizing user behaviors, basic information of the users (such as repeated devices, registration time, whether KYC is available), and the like, and perform identification alarm for user groups with large deviation. The behavior of the user can include the behaviors of transaction number, frequency, page browsing and the like; the basic information of the user may include information of a duplicate device, a registration time period, a KYC rating, and the like.

The credible user model may be a model such as a decision tree or a score card, which is used to identify the credibility of the user according to the basic attributes and historical behaviors of the user. The historical behavior may include, among other things, registration duration, historical purchase transaction type habits, whether KYC is available, historical use of non-marketing subsidy purchases, marketing subsidy rate of historical use of marketing fund purchase transactions, user stickiness, behavior of user device associated groups, and so forth. The trustworthiness may be used to reflect whether the user is a normal user, rather than a grey-black product, etc.

The transaction anti-cheating model can identify whether cheating behaviors exist in the transaction by using a decision tree type model (such as XGBOOST) and the like according to the historical transaction behaviors of the user, the basic information of the user and the current transaction behaviors. The historical transaction behaviors can include historical behaviors such as historical purchase transaction type habits, frequency habits, historical use non-marketing subsidy purchase conditions, historical use marketing subsidy rates of marketing fund purchase transactions, risks of user equipment associated groups and the like; the basic information of the user can comprise information such as registration duration, whether KYC is available, whether the user is mature and the like; the current transaction behavior may include information such as a subsidy rate of the current transaction, a number of repetitions of device environment information, and the like.

The group graph model may be a graph calculation method, which uses the aforementioned trading party information, trading object information, trading medium information, etc. to perform group association, and calculates the historical cheating risk concentration in each group to determine the suspicious degree of grey and black production of the users in the group. The group analysis can be performed by, for example, environment information such as terminal device-related information and ClientIP (client IP).

The black-out strategy can be used for identifying marketing cheating risks according to a black-out list. The black list may be a list of users with violations determined from historical data.

As shown in fig. 3, in the wind control identification policy system provided in the embodiment of the present specification, the identified risky users and risky merchants may be stored, and comprehensive analysis and the like may be performed on the stored and precipitated risky users and risky merchants, so that the risk of marketing cheating may be identified more accurately.

In order to enable the identification of marketing cheating risks to be circulated or used between different organizations, embodiments of the present specification may also include a joint defense strategy, which may be a sharing of strategies for sharing identification between different organizations. For example, the results identified by the second organization may be sent to the first organization; the result identified by the first mechanism can also be sent to the second mechanism for information sharing.

As an implementation manner, in this embodiment, the identifying, by the second institution, whether there is a risk of marketing cheating in the payment order according to the desensitized transaction data may specifically include:

determining a first risk value of marketing cheating risks existing in the behavior characteristics of the consuming user according to the desensitized transaction data; the behavior characteristics of the user comprise at least one of transaction code switching frequency, marketing transaction frequency and marketing subsidy rate;

determining a second risk value of the marketing cheating risk existing in the behavior characteristics of the merchant according to the desensitized transaction data; the behavior characteristics of the merchant comprise at least one of the aggregation degree of subsidizing users and the degree of processing short-time code cutting transaction;

and judging whether the payment order has marketing cheating risks or not based on the first risk value and the second risk value.

In practical application, usually some cheating users have characteristics of short-time transaction code cutting, high marketing subsidy rate, high-frequency marketing attempt and the like, and in the embodiment of the description, the behavior characteristics of the users can be analyzed from historical transaction information of the users, so that the level or probability of marketing cheating risks of the users can be determined. Wherein the first risk value may represent a level or probability that the user initiating the payment order is at risk of marketing cheating.

For merchants, some cheating merchants or cheated merchants usually have characteristics of high subsidy user aggregation, short-time code-cutting transaction and the like. In the embodiment of the present specification, the behavior characteristics of the merchant may be analyzed from the historical transaction information of the merchant, so as to determine the level or probability of the merchant having the risk of marketing cheating. Wherein the second risk value may represent a level or probability that the merchant participating in the payment order is at risk of marketing cheating.

The embodiment of the specification can comprehensively analyze whether the payment order has marketing cheating risks from the perspective of users and merchants. The weighted sum of the first risk value and the second risk value can be determined in a weighted sum mode, and if the weighted sum is larger than or equal to a preset threshold value, it can be determined that the payment order has the risk of marketing cheating. In practical application, different risk levels can be divided according to different risk values, and the marketing cheating risk level of the payment order can be determined according to the first risk value and the second risk value.

In the embodiment of the description, the risk can be identified according to information such as a transaction account number and transaction equipment. Optionally, in this embodiment of the present specification, the second institution identifies whether the payment order has a risk of marketing cheating according to the desensitized transaction data, and specifically may include:

determining a third risk value of marketing cheating risk in the transaction account according to the transaction account information in the desensitized transaction data; the transaction account information comprises at least one of transaction user age group information, transaction mobile phone number information, KYC grade information and account registration duration information;

determining a fourth risk value of marketing cheating risk in the transaction medium according to the medium information in the desensitized transaction data; the medium information comprises at least one of equipment information and IP information;

determining a fifth risk value of the marketing cheating risk of the merchant according to the merchant information in the desensitized transaction data; the merchant information comprises at least one of the aggregation degree of the aged users in the merchants, the aggregation degree of the mobile phone number sections, the aggregation degree of new users, the aggregation degree of KYC low users and the aggregation degree of risk list users;

and judging whether the payment order has marketing cheating risks or not based on the third risk value, the fourth risk value and the fifth risk value.

In this embodiment of the present specification, whether a risk exists in a transaction account of a user may be analyzed from the acquired transaction information. In practical application, if the conditions of age group abnormality, risk mobile phone number group, low KYC grade, long account registration time, wallet blacklist and the like exist, such as the gathering of old people, the transaction account of the payment order can be considered to have risk. Wherein the third risk value may represent a level or probability that an account executing the payment order is at risk of marketing cheating.

Whether media risk exists with the media that executes the payment order may also be determined from the perspective of risky device labels, high risk IP/wifi mac, device risk identification, and the like. Wherein the fourth risk value may represent a level or probability that the medium executing the payment order is at risk of marketing cheating.

For a merchant, whether the merchant has the phenomenon of risk user aggregation can be determined from the aspects of old user aggregation, mobile phone number segment aggregation, new user aggregation, KYC low user aggregation, risk list user aggregation and the like, and if yes, the merchant can also be proved to have marketing cheating risks. Wherein the fifth risk value may represent a level or probability that the merchant executing the payment order is at risk of marketing cheating.

In the embodiment of the specification, whether the payment order has the risk of marketing cheating can be comprehensively analyzed from the aspects of user accounts, media, merchant risk aggregation and the like. Similarly, the comprehensive risk value can also be determined in a weighted summation mode, and if the value is greater than or equal to the preset threshold value, the payment order can be determined to have the risk of marketing cheating. Different risk levels can be divided according to different risk values, and the marketing cheating risk level of the payment order can be determined according to each risk value.

To more clearly illustrate the lane diagrams of the above-described method of identifying risk of marketing cheating provided in the examples of this specification. Fig. 4 is a swim lane diagram corresponding to the method of fig. 2 for identifying risk of marketing cheating provided by the embodiments of the present specification. As shown in fig. 4, the method may include a data request phase, a data processing phase, and a risk identification phase, and specifically may include:

step 402: the second organization sends a data acquisition request for acquiring transaction data of a participating object of the payment order outside the second organization to the first organization;

step 404: the first mechanism acquires transaction data generated by the participating object in another mechanism according to the data acquisition request;

step 406: desensitizing the acquired transaction data to obtain desensitized transaction data;

step 408: sending the desensitized transaction data to a second institution;

step 410: the second mechanism acquires the desensitized transaction data sent by the first mechanism;

step 412: and the second organization identifies whether the payment order has marketing cheating risks according to the desensitized transaction data. In practical applications, if there is a risk of marketing cheating in the payment order, it may indicate that the payment order may be initiated by a cheating user, and the processing of the payment order may be terminated.

In the embodiment of the description, the first organization may also have the capability of identifying the risk of marketing cheating, and the second organization may also request the first organization to identify the risk of marketing cheating and feed back the identification result to the second organization, so that the problem of data islanding can be avoided. As an implementation manner, another method for identifying marketing cheating risks is provided in the embodiments of this specification, and fig. 5 is a flowchart illustrating the method for identifying marketing cheating risks provided in the embodiments of this specification. From the viewpoint of a program, the execution subject of the flow may be a program installed in an application server or an application client. In particular, the method may be applied to a first institution capable of carrying financial transaction functions.

As shown in fig. 5, the process may include the following steps:

step 502: acquiring a risk identification request sent by a second organization and used for carrying out marketing cheating risk identification on a payment order; the risk identification request comprises order information of the payment order.

The first mechanism in embodiments of the present description may include a mechanism that carries financial transaction functionality; the second mechanism may include a mechanism for acquiring a transaction operation initiated by a user, and may also be an SAAS-based service area center corresponding to the first mechanism; wherein the SAAS-enabled service area center is configured to provide services to a first organization of the plurality of areas.

Step 504: and acquiring transaction data of the participating object of the payment order outside the second institution according to the order information.

The transaction data may include transaction data generated by an organization with the first organization as a carrier and the participating object being outside the second organization.

In practical applications, the order information may include information of each participating object participating in the order information, such as information of both parties to trade, a trading object, trading time, trading amount, and the like. In the embodiment of the present specification, the participating object may include at least one of a transaction party, a transaction object, and a transaction medium corresponding to the order payment request; the transaction data may include at least one of a transaction time, a transaction amount, and a payment method. The transaction medium may include a terminal where the user initiates a transaction, or may include network information and the like used by the terminal transaction. The transaction object may represent an item purchased by the user.

The second mechanism may also perform desensitization processing on the sensitive information in the order information and send the desensitized sensitive information to the first mechanism, or may also send the identifier inclusion request of each participating object included in the payment order to the first mechanism.

Step 506: and identifying whether the payment order has marketing cheating risks or not according to the transaction data to obtain an identification result.

The first institution may include transaction data of a participating object of a payment order initiated in the second institution in other institutions, and may perform identification of marketing cheating risks by combining the transaction data in other institutions according to an identification request sent by the second institution.

Step 508: feeding back the recognition result to the second mechanism.

The identification result may indicate whether the payment order has the result of marketing cheating risk, or indicate the result of the payment order with the level or degree of marketing cheating risk. The second mechanism may further determine whether to process the payment order based on the fed back identification result.

In practical application, if the first mechanism is a mechanism capable of performing payment process processing on a payment order submitted by the second mechanism, if it is determined that the payment order has a risk of marketing cheating or the risk level reaches a threshold value, the processing on the payment process of the payment order may also be terminated, and a processing result may also be fed back to the second mechanism, so that the second mechanism feeds back the result of the payment order to the user.

In order to obtain data with a higher reference value and improve the identification accuracy, in an embodiment of the present specification, optionally, the obtaining transaction data of a participating object of the payment order outside the second institution may specifically include:

and acquiring transaction data of the participating object generated by other organizations except the second organization within a preset time period before the risk identification request is received.

The risk identification request sent by the second mechanism can be acquired as a time node, and transaction data related to the participation object of the payment order in a preset time period before the time node is acquired. For example, transaction data may be obtained over a recent period of one month, two months, etc.

In this embodiment of this specification, the first mechanism may further include transaction data of a transaction service in which a participant in a payment order sent by the second mechanism participates in the second mechanism, and the method in this embodiment of this specification may further include: obtaining local transaction data of a transaction event in which the participant participates in the second institution; identifying whether the payment order has a risk of marketing cheating according to the transaction data specifically may include:

and identifying whether the payment order has marketing cheating risks or not according to the transaction data and the local transaction data.

The transaction event transaction data of the participation object participating in the second institution may be generated by the second institution and transmitted to the first institution, or may be generated in the first institution. In embodiments of the present description, a first institution may identify a risk based on transaction data that a user has engaged in at a second institution as well as other institutions.

Similar to the first method described above, the first mechanism in the embodiments of the present specification may include a mechanism that carries financial transaction functions; the transaction data comprises transaction data generated by other mechanisms except the second mechanism by taking the first mechanism as a carrier and the participating object; and/or the second mechanism comprises a mechanism for acquiring transaction operation initiated by a user or an SAAS service area center corresponding to the first mechanism; the SAAS service area center is used for providing service for a first mechanism of a plurality of areas.

In the embodiment of the specification, a wind control engine can be deployed in a first mechanism; the wind control engine can comprise a wind control identification strategy for identifying marketing cheating risks of at least one transaction object of a consumer, a merchant, a transaction account and a transaction medium. The first mechanism can utilize the wind control engine to identify the marketing cheating risks from different angles. The deployed wind control identification strategy may be a wind control strategy as shown in fig. 3. And will not be described in detail herein.

As an implementation manner, in this embodiment of the present specification, the identifying whether there is a risk of marketing cheating in the payment order according to the transaction data specifically includes:

determining a first risk value of a marketing cheating risk existing in the behavior characteristics of the user according to the transaction data; the behavior characteristics of the user comprise at least one of transaction code switching frequency, marketing transaction frequency and marketing subsidy rate;

determining a second risk value of the marketing cheating risk existing in the behavior characteristics of the merchant according to the transaction data; the behavior characteristics of the merchant comprise at least one of subsidizing user aggregation degree and processing short-time code cutting transaction degree;

In this embodiment of the present description, a risk may also be identified according to information such as a transaction account number and a transaction device, and optionally, in this embodiment of the present description, identifying whether a marketing cheating risk exists in the payment order according to the transaction data may specifically include:

determining a third risk value of marketing cheating risk of the transaction account according to the transaction account information in the transaction data; the transaction account information comprises at least one of transaction user age group information, transaction mobile phone number information, KYC grade information and account registration duration information;

determining a fourth risk value of the marketing cheating risk of the trading medium according to the medium information in the trading data; the medium information comprises at least one of equipment information and IP information;

determining a fifth risk value of the marketing cheating risk of the merchant according to the merchant information in the transaction data; the merchant information comprises at least one of the aggregation degree of the aged users in the merchants, the aggregation degree of mobile phone number sections, the aggregation degree of new users, the aggregation degree of KYC low users and the aggregation degree of risk list users;

The second method for identifying the risk of marketing cheating provided in the embodiments of the present specification has the same or similar parts as those in the first method, and details of the same or similar parts are not repeated herein.

To more clearly illustrate the lane diagram of the above-mentioned method for identifying the risk of marketing cheating provided in the embodiments of the present specification. Fig. 6 is a swim lane diagram corresponding to the method for identifying marketing cheating risks in fig. 5 provided in the embodiments of the present specification. As shown in fig. 6, the method may include an identification request stage, an identification stage, and a result determination stage, and specifically may include:

step 602: and the risk identification request which is sent by the second organization and is used for carrying out marketing cheating risk identification on the payment order is sent to the first organization. Wherein the risk identification request may include order information for the payment order.

Step 604: and the first mechanism acquires the transaction data of the participating object of the payment order outside the second mechanism according to the order information.

Step 606: and identifying whether the payment order has marketing cheating risks or not according to the transaction data to obtain an identification result.

Step 608: the first mechanism sends the recognition result to the second mechanism.

Step 610: and the second mechanism receives the identification result fed back by the first mechanism.

Based on the same idea, the embodiment of the present specification further provides a device corresponding to the above method. Fig. 7 is a schematic structural diagram of an apparatus for identifying marketing cheating risks, corresponding to fig. 2, provided in an embodiment of the present specification. As shown in fig. 7, the apparatus may include:

a request obtaining module 702, configured to obtain a data obtaining request sent by a second institution for obtaining transaction data of a participating object of a payment order outside the second institution; the information acquisition request comprises an object identifier of the participating object;

a data obtaining module 704, configured to obtain transaction data generated by the participating object at another institution according to the object identifier;

a desensitization module 706, configured to perform desensitization processing on the transaction data to obtain desensitized transaction data;

a data sending module 708, configured to send the desensitized transaction data to the second institution, so that the second institution identifies whether the payment order has a risk of marketing cheating according to the desensitized transaction data.

Fig. 8 is a schematic structural diagram of an apparatus for identifying marketing cheating risks, corresponding to fig. 5, provided in an embodiment of the present specification. As shown in fig. 8, the apparatus may include:

a request obtaining module 802, configured to obtain a risk identification request sent by a second organization for performing marketing cheating risk identification on a payment order; the risk identification request comprises order information of the payment order;

a data obtaining module 804, configured to obtain, according to the order information, transaction data of a participating object of the payment order outside the second institution;

a risk identification module 806, configured to identify whether a marketing cheating risk exists in the payment order according to the transaction data, so as to obtain an identification result;

a result feedback module 808, configured to feed back the identification result to the second mechanism.

Based on the same idea, the embodiment of the present specification further provides a device corresponding to the above method.

Fig. 9 is a schematic structural diagram of an apparatus for identifying a risk of marketing cheating according to an embodiment of the present disclosure. As shown in fig. 9, the apparatus 900 may include:

at least one processor 910; and the number of the first and second groups,

a memory 930 communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory 930 stores instructions 920 that are executable by the at least one processor 910;

corresponding to the method of identifying marketing cheating risk illustrated in fig. 2 in an embodiment of the present specification, the instructions are executed by the at least one processor 910 to enable the at least one processor 910 to:

desensitizing the transaction data to obtain desensitized transaction data;

Corresponding to the method of identifying marketing cheating risks illustrated in fig. 5 in an embodiment of the present specification, the instructions are executed by the at least one processor 910 to enable the at least one processor 910 to:

feeding back the recognition result to the second mechanism.

Based on the same idea, the embodiment of the present specification further provides a computer-readable medium corresponding to the above method. The computer readable medium has computer readable instructions stored thereon that are executable by the processor to implement the above-described method of identifying a risk of marketing cheating.

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, as for the apparatus shown in fig. 9, since it is substantially similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment.

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 character system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate a dedicated integrated circuit chip. Furthermore, nowadays, instead of manually manufacturing 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, CUPL (core universal Programming Language), HDCal, jhddl (Java Hardware Description Language), lava, lola, HDL, PALASM, rhyd (Hardware Description Language), and vhigh-Language (Hardware Description Language), which is currently used in most popular applications. It will also be apparent to those skilled in the art that hardware circuitry for implementing the logical method flows can be readily obtained by a mere need to program the method flows with some of the hardware description languages described above and into an integrated circuit.

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, atmelAT SAM, microchip PIC18F26K20, and silicon 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, respectively. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention 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 present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. 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 permanent and non-permanent, removable and non-removable media, may implement the 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 Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium which can be used to store information which 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 a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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 application 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. The application 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 above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method of identifying marketing cheating risks applied to a first organization, comprising:

desensitizing the transaction data to obtain desensitized transaction data;

and sending the desensitized transaction data to the second institution so that the second institution identifies whether the payment order has a marketing cheating risk or not according to the desensitized transaction data.

2. The method according to claim 1, wherein the acquiring transaction data of the participant at another institution comprises:

3. The method according to claim 1, wherein the desensitizing the transaction data comprises:

sensitive information in the transaction data is obtained;

4. The method of claim 1, further comprising, in the second institution, local trade data for a trade event in which the participant object participates in the second institution;

the second institution identifies whether the payment order has a risk of marketing cheating according to the desensitized transaction data, and specifically comprises the following steps:

5. The method according to claim 1, wherein the participating object comprises at least one of a trading party, a trading object and a trading medium corresponding to the order payment request; the transaction data includes at least one of transaction time, transaction amount, and payment method.

6. The method of claim 1, the first institution comprising an institution that carries financial transaction functions; the transaction data comprises transaction data generated by other mechanisms except the second mechanism by taking the first mechanism as a carrier and the participating object;

and/or the presence of a gas in the gas,

the second mechanism comprises a mechanism for acquiring transaction operation initiated by a user or an SAAS service area center corresponding to the first mechanism; the SAAS service area center is used for providing service for a first mechanism of a plurality of areas.

7. The method of claim 1, a wind-controlled engine deployed in the second organization; the wind control engine comprises a wind control identification strategy for identifying marketing cheating risks of at least one transaction object of a consumer, a merchant, a transaction account and a transaction medium.

8. The method of claim 7, wherein the second institution identifies whether the payment order is at risk of marketing cheating based on the desensitized transaction data, comprising:

determining a second risk value of the marketing cheating risk existing in the behavior characteristics of the merchant according to the desensitized transaction data; the behavior characteristics of the merchant comprise at least one of subsidizing user aggregation degree and processing short-time code cutting transaction degree;

9. The method of claim 7, wherein the second institution identifies whether the payment order is at risk of marketing cheating based on the desensitized transaction data, comprising:

10. A method for identifying marketing cheating risks, applied to a first organization, comprises the following steps:

feeding back the recognition result to the second mechanism.

11. The method according to claim 10, wherein the obtaining of transaction data of the participating object of the payment order outside the second institution specifically comprises:

and acquiring transaction data generated by the participating object at other institutions except the second institution within a preset time period before the risk identification request is received.

12. The method of claim 10, further comprising:

obtaining local transaction data of a transaction event in which the participant participates in the second institution;

identifying whether the payment order has marketing cheating risks according to the transaction data specifically comprises the following steps:

and identifying whether the payment order has marketing cheating risks according to the transaction data and the local transaction data.

13. The method of claim 10, the first mechanism having a wind-controlled engine disposed therein; the wind control engine comprises a wind control identification strategy for identifying marketing cheating risks of at least one transaction object of a consumer, a merchant, a transaction account and a transaction medium.

14. The method of claim 13, wherein identifying whether the payment order is at risk of marketing cheating based on the transaction data comprises:

15. The method of claim 13, wherein identifying whether the payment order is at risk of marketing cheating based on the transaction data comprises:

determining a fifth risk value of marketing cheating risks of the merchant according to the merchant information in the transaction data; the merchant information comprises at least one of the aggregation degree of the aged users in the merchants, the aggregation degree of the mobile phone number sections, the aggregation degree of new users, the aggregation degree of KYC low users and the aggregation degree of risk list users;

16. An apparatus to identify marketing cheating risks, comprising:

17. An apparatus to identify marketing cheating risks, comprising:

18. An apparatus to identify marketing cheating risks, comprising:

at least one processor; and the number of the first and second groups,

the memory stores instructions executable by the at least one processor to cause the at least one processor to:

desensitizing the transaction data to obtain desensitized transaction data;

19. An apparatus to identify marketing cheating risks, comprising:

at least one processor; and the number of the first and second groups,

feeding back the recognition result to the second mechanism.

20. A computer readable medium having computer readable instructions stored thereon that are executable by a processor to implement the method of identifying marketing cheating risk of any of claims 1-15.