CN115034788A

CN115034788A - Transaction risk assessment method and device, electronic equipment and storage medium

Info

Publication number: CN115034788A
Application number: CN202110257007.1A
Authority: CN
Inventors: 刘祥业
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2021-03-08
Filing date: 2021-03-08
Publication date: 2022-09-09

Abstract

The embodiment of the application discloses a transaction risk assessment method and a device, wherein the method comprises the following steps: acquiring a guest group to which a user to be assessed of transaction risk belongs, wherein the user to be assessed of transaction risk is included in the guest group; acquiring a first risk score output by a risk certainty model aiming at each user in a guest group, wherein the risk certainty model is constructed according to the risk characteristics of certainty dimensionality, and acquiring a second risk score output by an uncertainty newly-added model aiming at each user, and the uncertainty newly-added model is constructed according to the risk characteristics of non-certainty dimensionality; acquiring guest group intervals with different risk degrees according to the first risk scores and the second risk scores of all users in the guest group; and determining the transaction risk value of the user with the transaction risk to be evaluated according to the risk degree sequence among the guest group intervals and the risk degree of the guest group interval where the user with the transaction risk to be evaluated is located. The method and the device can ensure the accuracy of the transaction risk value.

Description

Transaction risk assessment method and device, electronic equipment and storage medium

Technical Field

The application relates to the technical field of information security, in particular to a transaction risk assessment method and device, electronic equipment and a computer-readable storage medium.

Background

According to the guidance of credit card organization, when dispute credit card transaction occurs, the cardholder can put forward a refusal payment application to the acquirer of the merchant through the credit card issuing mechanism, if the refusal payment application is accepted by the acquirer, the acquirer can cancel the related credit card transaction, and return the payment paid by the credit card to the cardholder through the issuing mechanism.

Every time the acquirer accepts a repudiation application, a certain loss is brought, so how to reduce the risk of repudiation of credit card transactions is a problem to be solved urgently at present.

Disclosure of Invention

In order to solve the above technical problem, embodiments of the present application provide a transaction risk assessment method and apparatus, an electronic device, and a computer-readable storage medium.

According to an aspect of an embodiment of the present application, there is provided a transaction risk assessment method, including: obtaining a guest group to which a user of a transaction risk to be evaluated belongs, wherein the user of the transaction risk to be evaluated is included in the guest group; acquiring a first risk score output by a risk certainty model aiming at each user in the guest group, wherein the risk certainty model is constructed according to the risk characteristics of certainty dimensionality, and acquiring a second risk score output by an uncertainty newly-added model aiming at each user, and the uncertainty newly-added model is constructed according to the risk characteristics of non-certainty dimensionality; acquiring guest group intervals with different risk degrees according to the first risk scores and the second risk scores of all users in the guest group, wherein the risk degrees of the guest group intervals are determined according to historical transaction information of a plurality of users in the guest group intervals; and determining the transaction risk value of the user with the transaction risk to be evaluated according to the risk degree sequence among the guest group intervals and the risk degree of the guest group interval in which the user with the transaction risk to be evaluated is located.

According to an aspect of an embodiment of the present application, there is provided a transaction risk assessment apparatus including: the system comprises a guest group acquisition module, a transaction risk evaluation module and a transaction risk evaluation module, wherein the guest group acquisition module is configured to acquire a guest group to which a user of a transaction risk to be evaluated belongs, and the user of the transaction risk to be evaluated is included in the guest group; a risk score obtaining module configured to obtain a first risk score output by a risk certainty model for each user in the guest group, the risk certainty model being constructed according to risk characteristics of a certainty dimension, and obtain a second risk score output by an uncertainty newly-added model for each user, the uncertainty newly-added model being constructed according to risk characteristics of a non-certainty dimension; the system comprises a guest group interval acquisition module, a guest group interval processing module and a guest group interval processing module, wherein the guest group interval acquisition module is configured to acquire guest group intervals with different risk degrees according to first risk scores and second risk scores of all users in a guest group, and the risk degrees of the guest group intervals are determined according to historical transaction information of a plurality of users in the guest group intervals; and the transaction risk acquisition module is configured to determine a transaction risk value of the user with the transaction risk to be evaluated according to the risk degree sequence among the guest group intervals and the risk degree of the guest group interval in which the user with the transaction risk to be evaluated is located.

According to an aspect of the embodiments of the present application, there is provided an electronic device including a processor and a memory, where the memory stores computer-readable instructions, and the computer-readable instructions, when executed by the processor, implement the transaction risk assessment method as described above.

According to an aspect of embodiments of the present application, there is provided a computer-readable storage medium having stored thereon computer-readable instructions which, when executed by a processor of a computer, cause the computer to execute a transaction risk assessment method as described above.

According to an aspect of embodiments herein, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the transaction risk assessment method provided in the various alternative embodiments described above.

In the technical scheme provided by the embodiment of the application, the transaction risk of the user is evaluated according to the customer group to which the user belongs, a risk certainty model and an uncertainty newly-added model are introduced in the evaluation process, and the transaction risk value of the user is obtained by carrying out customer group risk differentiation identification in the evaluation mode. The acquirer can quantify the transaction risk of the user by evaluating the transaction risk value of the user, and carry out risk handling processing on the transaction initiated by the user account, so that the credit card transaction refusal risk is reduced, and the loss of the acquirer is also reduced.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and, together with the description, serve to explain the principles of the application. It is obvious that the drawings in the following description are only some embodiments of the application, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. In the drawings:

FIG. 1 is a flow diagram of a transaction risk assessment method shown in an exemplary embodiment of the present application;

FIG. 2 is a schematic diagram of an exemplary risk profile variation;

FIG. 3 is another exemplary risk profile variation diagram;

FIG. 4 is a flow chart of step S150 in the embodiment shown in FIG. 1 in one embodiment;

FIG. 5 is a flow diagram of step S170 in the embodiment shown in FIG. 1 in one embodiment;

FIG. 6 is a schematic diagram of exemplary guest group data;

FIG. 7 is a schematic diagram of a transaction risk value distribution obtained by processing the customer base data shown in FIG. 6;

FIG. 8 is a block diagram of a transaction risk assessment device shown in an exemplary embodiment of the present application;

FIG. 9 illustrates a schematic structural diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.

The flowcharts shown in the figures are illustrative only and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.

Reference to "a plurality" in this application means two or more. "and/or" describe the association relationship of the associated objects, meaning that there may be three relationships, e.g., A and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

Currently, a mainstream risk scoring model system, namely a FICO credit scoring system, exists in the credit card transaction risk processing process, which is a credit scoring system widely used in X countries, and the credit level of a user is evaluated mainly from five dimensions, namely repayment history, credit account number, age of using credit, newly opened credit account and credit type being used. The credit score obtained by the FICO credit scoring system is generally in a range of 300-850 points, and the higher the credit score of the user is, the smaller the credit risk of the user is.

One important reason that the FICO credit scoring system has been widely used in X countries is that the FICO credit scoring system is a standardized, objective credit scoring system that is established by collecting a large number of personal credit records and performing strict model modification and stress tests. That is, the FICO credit scoring system relies on a large amount of historical data accumulated for the credit risk market, and is not applicable in other countries or in different business scenarios.

For example, in the business scenario of international payment bank card (hereinafter referred to as "external card" and referred to as a credit card of international credit card organization brand issued by a card issuing organization) transaction, the transaction can be performed only by ensuring the validity of information such as the filled credit card number, validity period, credit card security code and the like in the current external card transaction, most other information cannot be completely verified in validity, and the validity of real-name information is extremely difficult to verify. Since the external card acquiring organization does not have information such as accumulated credit risk, transaction behavior, real name information comparison and the like of a large number of users and lacks a large amount of characteristic data with remarkable characteristics, an effective transaction risk scoring model cannot be developed according to the FICO credit scoring system.

In the application, considering that the external card transaction business has a very wide customer group, an external card banking country and a very wide transaction initiation area, and transaction risk differences of different customer groups in different areas are obvious, and in addition, the characteristics that the current external card transaction business is in a transaction growth period, different customer groups may structurally grow or change in a certain area and the like are considered, a transaction risk evaluation scheme capable of accurately evaluating the transaction risk of the user is provided, and the detailed contents refer to the contents recorded in the subsequent embodiments.

It should be noted that the transaction risk assessment scheme provided by the present application is not limited to be used in the above-mentioned external card service scenario, but may also be applied to other types of credit card service scenarios, and the present embodiment does not limit this.

FIG. 1 is a flow chart of a transaction risk assessment method shown in an exemplary embodiment of the present application. As shown in fig. 1, the transaction risk assessment method at least includes steps S110 to S170, which are described in detail as follows:

step S110, a guest group to which a user with a transaction risk to be evaluated belongs is obtained, and the user with the transaction risk to be evaluated is included in the guest group.

The user with the transaction risk to be evaluated mentioned in the embodiment is understood as a user identifier, so that the user with the transaction risk to be evaluated is characterized by the user identifier. The user identifier may be, for example, a credit card account name used by the user whose transaction risk is to be assessed, or other identification information, which is not limited in this embodiment.

The guest group refers to a user set, and the guest group to which the user to be assessed the transaction risk belongs may be determined according to the service type of the transaction performed by the user using the credit card, for example, the user performing the transaction on the same service type is obtained as the user in the guest group, or the user having the transaction abnormality on the same service type is obtained as the user in the guest group, and the guest group may also include the users of the two types at the same time, which is not limited in this embodiment.

It should be noted that the service types of the transaction performed by the user using the credit card may include games, e-commerce, live broadcast, etc., and may also be determined according to the actual application scenario, which is not limited herein. The users who have transaction abnormity on the same service type in the customer group can provide more obvious risk characteristics for the subsequent transaction risk assessment process, so that the transaction risk assessment effect can be promoted.

It should be further noted that the transaction risk involved in this embodiment may include a transaction refusal payment risk, and may also include other types of transaction risks, and a specific risk type may be determined according to an actual business scenario.

Step S130, a first risk score output by a risk certainty model aiming at each user in the guest group is obtained, the risk certainty model is built according to the risk characteristics of the certainty dimensionality, and a second risk score output by an uncertainty newly added model aiming at each user is obtained, and the uncertainty newly added model is built according to the risk characteristics of the nondeterministic dimensionality.

The risk characteristics of the deterministic dimension refer to characteristic information capable of objectively and stably evaluating the transaction risk of the user, and the risk characteristics of the deterministic dimension are not easy to change for the transaction risk and do not involve frequent changes.

For example, in the external card transaction service scenario, the risk characteristics of the deterministic dimension may include external card banking countries (where different countries have different overall denial due to economic differences), external card account historical transaction records (where different countries have different risk conditions of old external card account numbers and new external card account numbers), account real-name conditions (for example, account-associated identity verification name conditions, account-associated passport real-name conditions, and the like), and the like, and these characteristics do not vary with the seasons or the external card transaction service development with large risk differences, for example, as shown in fig. 2, the external card denial rates of developed country a and developing country B do not vary with the seasons or the external card transaction service development with large risk differences.

The risk certainty model can be constructed according to risk characteristics of a certainty dimension collected in advance and data of risks in actual business, such as constructing a logistic regression model. Thus, risk deterministic models built from risk features of a deterministic dimension typically have long model update periods.

The risk characteristics of the uncertainty dimension refer to characteristic information that it is difficult to relatively objectively and stably evaluate the transaction risk of the user, and the risk characteristics of the uncertainty dimension are likely to change with respect to the transaction risk and involve frequent changes. Still taking the external card transaction business scenario as an example, the risk features of the uncertainty dimension may include features such as a regional rejection risk variation situation, a regional structural variation situation (for example, the region is in a business promotion period), a transaction technique variation, and an account cancellation channel variation, which may be iterated along with rapid changes of seasons, products, and the like.

Therefore, the newly added uncertainty model usually has a short update period, for example, when the risk features of the uncertainty dimension change, the newly added uncertainty model needs to be timely determined, and thus the newly added uncertainty model needs to have a fast iteration characteristic. The newly added uncertainty model can be constructed through an XGBOST machine learning model, a LightGBM machine learning model and a deep learning model.

For example, as shown in fig. 3, if it is assumed that the live broadcast platform C has a strict examination system in country a and has strict regulations for services such as recharging, the corresponding rejection rate of the external card is relatively stable, but the regulations in country B are not strict, and the policy of merchants influenced by public opinion in country B of these live broadcast merchants is neglected and changed frequently. If the newly-added uncertain model cannot be iterated quickly, when the live broadcast merchant tightens the policy in country B, a reasonable risk value cannot be obtained through the newly-added uncertain model, so that the reasonability of a transaction risk value evaluated by a user is influenced, when a risk coping policy is executed according to the transaction risk value of the user, a transaction risk policy threshold value cannot be timely and reasonably released, reasonable and normal transactions of a plurality of users can be intercepted, and the user experience is poor; when the direct-seeding merchant releases the policy in the country B, the risk transaction cannot be intercepted in time, and the payment refusal application received by the acquirer can be increased suddenly, so that the loss of the acquirer is increased.

The uncertainty added model is set in the embodiment, so that the transaction risk assessment of the new guest group is better, and the risk certainty model is set so that the transaction risk assessment of the old guest group is better. In the transaction risk assessment scheme provided by this embodiment, the transaction risk value of the user is assessed by combining the risk scores output by the two models for each user in the guest group to which the user to be assessed the transaction risk belongs, and the transaction risk assessment scheme has strong adaptability to an actual transaction service scene.

In this embodiment, the risk certainty model may obtain the first risk score of the user according to the information filled when the user initiates the transaction in the customer base and part of the historical transaction information, wherein the information filled when the user initiates the transaction may include information such as a credit card number, a validity period, and a credit security code. The newly added uncertainty model can obtain a second risk score of the user according to information such as transaction characteristics of the user, the affiliated customer group, transaction merchant changes and the like.

Therefore, in the embodiment, for each user in the guest group to which the user to be assessed the transaction risk belongs, the corresponding first risk score and the second risk score are obtained.

Step S150, obtaining a guest group interval with different risk degrees according to the first risk score and the second risk score of all users in the guest group, wherein the risk degree of the guest group interval is determined according to the historical transaction information of a plurality of users in the guest group interval.

According to the first risk score and the second risk score of all users in the guest group to which the user to be assessed the transaction risk belongs, the guest group is divided into a plurality of guest group intervals, and different guest group intervals have different risk degrees. The guest group interval can be understood as a two-dimensional interval formed by two dimensions of the first risk score and the second risk score, the guest group interval contains a plurality of users, and each user can find the corresponding first risk score and the second risk score in the guest group interval.

The risk degree of the guest group interval is determined according to historical transaction information of a plurality of users contained in the guest group interval, wherein the historical transaction information of the users comprises transaction risk information of the users in the historical transaction process, such as whether to apply for refusing payment. Due to different historical transaction conditions of different users, the risk degree of different customer group intervals is different.

It should be noted that the number of users in each guest group interval may be the same or different, and the guest group intervals may be divided according to actual needs. However, the number of users in each guest group interval cannot be too small, for example, the number cannot be smaller than a preset number threshold, so that the transaction risk of the guest group interval can be represented more accurately according to the historical transaction information of the users in each guest group interval.

Step S170, determining the transaction risk value of the user with the transaction risk to be evaluated according to the risk degree sequence among the guest group intervals and the risk degree of the guest group interval where the user with the transaction risk to be evaluated is located.

In this embodiment, the transaction risk value of the user is determined according to the risk degree of the guest group interval where the user to be assessed the transaction risk is located and the risk degree ranking among the multiple guest group intervals, so as to evaluate the transaction risk of the user according to the overall transaction risk condition of the guest group, and improve the accuracy of the finally obtained transaction risk value based on the consideration of the overall transaction risk of the guest group.

For example, the rank of the risk degree in the risk degree ranking of the guest group interval where the user with the transaction risk to be evaluated is located may be obtained, so as to calculate the transaction risk value of the user with the transaction risk to be evaluated according to the obtained rank. For different ranks, different transaction risk value calculation modes can exist to highlight the influence of the overall transaction risk condition of the customer base on the transaction risk of the user. For a detailed transaction risk value obtaining process, please refer to the contents recorded in the following embodiments, which are not described herein.

Therefore, in the method provided by this embodiment, the transaction risk of the user is evaluated according to the customer group to which the user belongs, and a risk certainty model and an uncertainty newly-added model are introduced in the evaluation process, so that the transaction risk value obtained for the user to be evaluated of the transaction risk is obtained by performing customer group risk differentiation identification, and this customer group risk differentiation identification manner is also very suitable for the current credit card transaction risk situation, for example, the situations such as transaction growth existing in the above-mentioned external card transaction service scenario, and can be correspondingly adjusted according to the actual transaction risk environment, so the user transaction risk value obtained by the method provided by this embodiment has extremely high accuracy.

And after the transaction risk value of the user is obtained through evaluation, corresponding risk response processing can be carried out on the user according to the obtained transaction risk value. For example, if the transaction risk value of the user exceeds the preset risk value, it indicates that the user has a high transaction risk, and by limiting the highest consumption amount or consumption times of the user, the condition of acquiring institution loss caused by user refusal can be reduced to a great extent. The specific risk handling processing manner may be determined according to an actual application scenario, which is not limited in this embodiment.

FIG. 4 is a flow chart of step S150 in the embodiment shown in FIG. 1 in one embodiment. As shown in fig. 4, the process of acquiring guest group intervals with different risk degrees according to the first risk score and the second risk score of all users in the guest group, which is described in step S150, includes steps S151 to S153, which are described in detail as follows:

step S151, forming a two-dimensional plane by the first risk scores and the second risk scores of all users in the guest group.

The embodiment uses a two-dimensional scoring system to evaluate the transaction risk of the user so as to realize the accuracy of the transaction risk of the user. The two-dimensional scoring system depends on risk scores output by a risk certainty model and an uncertainty newly-added model as two scoring dimensions, so that a two-dimensional plane needs to be formed according to first risk scores and second risk scores of all users in a guest group to which a user to be assessed the transaction risk belongs, and then two-dimensional scoring calculation is performed based on the formed two-dimensional plane to obtain the transaction risk value of the user to be assessed the transaction risk.

The first risk score and the second risk score of all users in the passenger group can be sorted from big to small respectively to obtain a first risk score sequence and a second risk score sequence, and then the first risk score sequence and the second risk score sequence are used as different dimensions of a two-dimensional plane, so that the two-dimensional plane is constructed. The dimensions of the two-dimensional plane include a transverse dimension and a longitudinal dimension, and can also be understood as including an X-axis dimension and a Y-axis dimension.

The formed two-dimensional plane is associated with the users in the guest group through the risk scores of two dimensions, and the first risk score and the second risk score of any user in the guest group can be mapped to the user in the two-dimensional plane, so that all the users in the guest group can be understood to be distributed in the two-dimensional plane according to the corresponding first risk score and second risk score.

Step S153, carrying out grid cross processing in the two-dimensional plane to obtain grid areas with different risk degrees in the two-dimensional plane, wherein the grid areas with different risk degrees correspond to the guest group intervals with different risk degrees.

In this embodiment, the grid intersection processing is performed in the two-dimensional plane, so as to perform risk area division on the users in the guest group associated with the two-dimensional plane. Each grid region obtained by grid intersection processing contains a plurality of users, so that the grid regions correspond to different guest group intervals, and the users contained in the grid regions are also the users in the corresponding guest group intervals. Because the transaction risk situation of each user is inconsistent, each grid region should have different risk degrees, i.e., each customer group interval has different risk degrees.

Illustratively, the grid intersection processing is performed in a two-dimensional plane, and the process of obtaining grid areas with different risk degrees in the two-dimensional plane includes the following steps:

dividing the two-dimensional plane into a plurality of grid areas according to the first risk score sequence and the second risk score sequence corresponding to the two-dimensional plane; and calculating the risk degree of the grid area according to the historical transaction information of the plurality of users contained in the grid area.

For the partition of the grid region, in some embodiments, the first risk score sequence and the second risk score sequence may be partitioned into a plurality of risk intervals having the same number, and each interval intersection formed between the risk intervals is taken as the grid region in the two-dimensional plane. In this embodiment, a specific manner of dividing the risk intervals corresponding to the first risk score sequence and the second risk score sequence is not limited, for example, each risk interval includes a first risk score or a second risk score corresponding to the average number of users, and each risk interval may also correspond to the average first risk score interval or the second risk score interval, and may be determined according to actual requirements in actual applications.

In other embodiments, considering that the grid area obtained according to the above embodiments may contain a smaller number of users, and the significance of the risk degree obtained according to the historical transaction information of the smaller number of users is not high, which affects the overall transaction risk condition of the guest group, after the step of dividing the first risk score sequence and the second risk score sequence into a plurality of risk intervals with the same number, the intersection of the intervals with the number of users being less than or equal to the number threshold value is merged with the intersection of adjacent intervals according to the number of users in the intersection of the intervals between the risk intervals, so that the number of users contained in the merged intersection of the intervals is greater than the number threshold value. After the combination of the interval intersections is completed, the interval intersections contained in the two-dimensional plane are used as grid areas in the two-dimensional plane.

Specifically, the intersection of adjacent regions may be searched in the two-dimensional plane for a region intersection where the number of users is less than or equal to the number threshold, and if a neighboring region intersection where the risk degree is closest to the risk degree of the region intersection where the number of users is less than or equal to the number threshold is searched, the region intersection where the number of users is less than or equal to the number threshold and the searched neighboring region intersection are merged. And if the number of the adjacent interval intersections with the closest risk degree is multiple, selecting the adjacent interval intersection with the smallest interval area from the searched adjacent interval intersections and combining the adjacent interval intersection with the number of the users smaller than or equal to the number threshold. And if the number of the intersections of the adjacent intervals with the minimum interval area is multiple, randomly selecting the intersections of the adjacent intervals in one direction for merging.

It should be noted that the intersection of adjacent regions includes a region intersection located at an upper, lower, left, and right direction of the region intersection where the number of users is smaller than the number threshold in the two-dimensional plane. Compared with the risk degree of the interval intersection obtained by combination before combination, the interval intersection combination mode can not change greatly, so that the influence on the overall transaction risk condition of the guest group is reduced as much as possible, and the accuracy of the finally obtained transaction risk value can be improved to a certain extent.

For the calculation of the risk degree of the grid area, the historical transaction information of all users contained in the grid area is obtained, the historical transaction information is used for indicating whether the users have transaction risks in the historical transaction process, for example, whether the users initiate credit card refusal application in the historical transaction process can be determined according to the historical transaction information of the users, the ratio of the number of the users with the transaction risks in the historical transaction process to the number of all users contained in the grid area is calculated, and the ratio can be used as the risk degree of the grid area.

Because the risk degree of the grid area is obtained by calculation according to the risk information of all users in the grid area in the historical transaction process, the risk degree of the grid area in the transaction of the guest group interval can be accurately represented.

To facilitate understanding of the above process of dividing the guest group of the user to be assessed for transaction risk into guest group intervals with different risk procedures, the following describes the process in detail by using a specific example:

assuming that the customer group to which the user to be assessed the transaction risk belongs includes 1000 users, that is, 1000 user accounts, and the risk certainty model and the uncertainty newly-added model both output a first risk score and a second risk score for each user. 100 of the users initiate the repudiation application in the historical transaction process, so the transaction risk comprises the repudiation risk.

Sorting the risk certainty models from low to high aiming at first risk scores output by all users to obtain a first risk score sequence; and each 20 users are taken as a risk interval respectively to obtain risk intervals X1, X2, … … and X50; by obtaining the first maximum risk score value and the first minimum risk score value corresponding to each risk interval, the respective risk intervals may be represented as [0, aa 1], [ aa1, aa2 ], [ aa2, aa 3], … …, [ aa49, 1). The uncertainty model is also processed similarly for the second risk scores output by all users, resulting in risk intervals Y1, Y2.. 9.. and Y50, which are represented using the second risk scores as [0, bb 1], [ bb1, bb2 ], [ bb2, bb 3., [ bb49, 1 ]).

According to the user condition in the interval intersection between the risk intervals, the following information is obtained:

{ [0, aa1), [0, bb1), (number of denied users, number of non-denied users) }

{ [ aa1, aa2), [ bb1, bb2), (number of declined users, number of non-declined users) }

……

And if the number of the rejected users plus the number of the normal users in a certain interval intersection is less than or equal to 5, merging the interval intersection with the adjacent interval intersection according to the interval intersection merging strategy, wherein the risk degree of the interval intersection is represented by the rejection rate of the users in the interval intersection, and the rejection rate of the users is the ratio of the number of the rejected users in the interval intersection to the number of all the users.

Risk interval	…	[bb15，bb16)	[bb16，bb17)	[bb17，bb18)	…
						…
[aa18，aa19)		(1，5)	(2，5)	(3，3)
						[aa19，aa20)	(2，5)	(2，2)	(4，3)
[aa20，aa21)		(3，3)	(2，5)	(4，2)
						…

TABLE 1

If all the interval intersections are represented as shown in table 1 above, and the intersection of the tables represents the number of rejected users and the number of non-rejected users in the interval intersection, it can be seen that the number of users contained in the interval intersection { [ aa19, aa20), [ bb16, bb17) } is less than 5, and the user rejection rate is closest to the adjacent interval intersection { [ aa19, aa20), [ bb17, bb18 }, then the two interval intersections are merged.

After all the interval intersections of which the number of the users is smaller than the preset number threshold 5 are merged, each interval intersection can be used as a grid area in a two-dimensional plane, namely, as a guest group interval with different risk degrees.

As can be seen from the above, in the two-dimensional scoring system provided in this embodiment, the grid search strategy is adopted to divide the guest group into guest group intervals with different risk degrees. The two-dimensional scoring system further includes a two-dimensional scoring calculation process to obtain a transaction risk value of the user whose transaction risk is to be evaluated, and the detailed two-dimensional scoring calculation process refers to the embodiment corresponding to fig. 5.

As shown in fig. 5, the process of determining the transaction risk value of the user whose transaction risk is to be evaluated according to the risk degree ranking among the guest group intervals and the risk degree of the guest group interval in which the user whose transaction risk is to be evaluated is located, which is described in step S170 in the embodiment shown in fig. 1, at least includes steps S171 to S173, which are described in detail as follows:

step S171, the rank of the risk degree of the guest group interval of the user with the transaction risk to be evaluated in the risk degree ranking is obtained.

Ranking the risk degree of the user in the guest group interval where the transaction risk to be evaluated is located in the risk degree ranking can be obtained by ranking the risk degrees among the guest group intervals.

Step S173, calculating the transaction risk value of the user to be assessed the transaction risk according to the ranking.

And if the rank corresponding to the user with the transaction risk to be evaluated is determined to be the lowest rank, calculating the transaction risk value according to the first risk score and the second risk score corresponding to the user with the transaction risk to be evaluated and the risk degree of the passenger group interval in which the user with the transaction risk to be evaluated is located.

And if the rank corresponding to the user with the transaction risk to be evaluated is higher than the lowest rank, calculating the transaction risk value according to the first risk score and the second risk score corresponding to the user with the transaction risk to be evaluated, the risk degree of the guest group interval where the user with the transaction risk to be evaluated is located, and the risk degree of the guest group interval where the rank is lower than the rank corresponding to the user with the transaction risk to be evaluated.

For example, the form r can be obtained by assuming that the multiple passenger group intervals are sorted according to the risk degree ₁ ＜r ₂ ＜r ₃ < … … case of ordering, where r ₁ Representing the risk degree of the passenger group interval with the lowest rank, and if the first risk score and the second risk score corresponding to the user with the transaction risk to be evaluated are respectively represented as x ₁ And y ₁ 。

When the rank corresponding to the user with the transaction risk to be evaluated is the lowest rank, the transaction risk value of the user with the transaction risk to be evaluated is (x) ₁ ² +y ₁ ² )*r ₁ To ensure that the value range of the transaction risk value of the user is (0, r) ₁ ) (ii) a When the rank corresponding to the user is higher than the lowest rank, for example, r _k (k is more than or equal to 2), the transaction risk value of the user to be evaluated for the transaction risk is (x) ₁ ² +y ₁ ² )*(r _k -r _k-1 )+r _k-1 。

Therefore, the transaction risk value of the user with the transaction risk to be evaluated is calculated according to the ranking of the risk degree of the user group interval where the user with the transaction risk to be evaluated is located in the risk degree ranking, the transaction risk value of the user belonging to the high risk area is higher than the transaction risk value of the user belonging to the low risk area, and the transaction risk value accords with an actual risk business scene, so that the obtained transaction risk value has high accuracy.

In another exemplary embodiment, passenger group intervals with different risk degrees are obtained for multiple times according to the first risk score and the second risk score of all users in the passenger group to which the user to be assessed the transaction risk belongs. The guest group interval obtained each time is generated according to a random risk interval division strategy, and by executing the strategy, the guest group interval obtained each time by division can have randomness.

And obtaining the transaction risk value of the user with the risk to be evaluated for multiple times correspondingly according to the passenger group intervals with different risk degrees obtained for multiple times. For a detailed acquisition process, please refer to the foregoing embodiment, which is not repeated herein.

And selecting a target transaction risk value from the transaction risk values acquired for multiple times, namely the target transaction risk value can be used as the transaction risk value of the transaction user to be evaluated. It should be noted that, in this embodiment, a specific manner of selecting the target transaction risk value is not limited, and a relatively reasonable transaction risk value with a strong risk differentiation capability may be selected as the target transaction risk value according to an actual application requirement, so as to further improve the accuracy of the finally obtained transaction risk value. Under the condition that the transaction risk value has high accuracy, the risk response processing performed aiming at the user subsequently can be ensured to have better effect.

In order to verify the significant effect of the transaction risk assessment scheme provided by the present application, the inventors of the present application performed a comparative experiment using the customer group data as illustrated in fig. 6, and the detailed process is as follows:

the guest group data shown in fig. 6 is processed according to the transaction risk assessment scheme provided by the application, so that the interval intersection condition shown in the following table 2 can be obtained, if the user initiates a payment refusal application in the historical transaction process, the identifier "1" is used, and otherwise, the identifier "0" is used. The intersection of the tables shown in the following table 2 represents the number of the refusal payment users and the number of the non-refusal payment users in the interval of the passenger group characterized by the interval of the transaction.

Risk interval	[0.01,0.103]	(0.103,0.185]	(0.185,0.34]	(0.34,0.77]
					[0.03,0.0775]	(0,5)
(0.0775,0.175]		(1,2)	(2,0)
					(0.175,0.31]		(0,2)	(0,3)
(0.31,0.8]				(3,2)

TABLE 2

According to the transaction risk assessment scheme provided by the application, the transaction risk value distribution situation of all users in the customer group shown in fig. 7 can be obtained from the interval intersection information shown in the above table 2. The first risk intervals shown in fig. 7 are obtained by dividing a first risk score sequence composed of the first risk scores of all users, and the second risk intervals are obtained by dividing a second risk score sequence composed of the second risk scores of all users. The risk level shown in FIG. 7 refers to the user rejection rate within the interval intersection.

According to fig. 7, a group of passenger group interval sequences which are sorted from small to large according to the user refusal payment rate as the risk degree can be obtained: { [0.03,0.0775], [0.01,0.103] } { (0.0175,0.31], (0.103,0.185] } { (0.175,0.31], (0.185,0.34] } { (0.0775,0.175], (0.103,0.185] } { (0.31,0.8], (0.34,0.77] } { (0.75, 0.175], (0.185,0.34] } with the risk degree ordering 0<0.333< 1.

The evaluation of KS (Kolmogorov-Smirnov, which is a verification method for measuring the discrimination of the model between positive and negative samples, and the larger the value, the better the model effect) is adopted to obtain the transaction risk evaluation scheme provided by the present application, the scheme for evaluating the transaction risk of the user only by using the risk certainty model, and the scheme for evaluating the transaction risk of the user only by using the newly added uncertainty model, the KS values respectively correspond to the following table 3:

	this application	Risk certainty model	Newly-added model of uncertainty
				KS value	78.60％	42.90％	50.00％

TABLE 3

It should be noted that other manners may also be adopted to evaluate the effects of the above three transaction risk value evaluation schemes, flow into the GINI evaluation manner, and the like, which is not limited herein.

From the above, the transaction risk assessment scheme provided by the application has a very high KS value, which can show that the transaction risk assessment scheme provided by the application has a very significant effect on the assessment of the user transaction risk value.

It should be further noted that the transaction risk assessment scheme provided by the present application may be deployed in any terminal or server to assess the transaction risk value of the user, and the specific deployment condition may be determined according to the actual application condition.

The terminal referred to here can be any electronic device capable of operating a video playing client, such as a smart phone, a tablet, a notebook computer, a computer, etc. The server referred to here may be an independent physical server, or a server cluster or a distributed system formed by a plurality of physical servers, where a plurality of servers may form a block chain, and the server is a node on the block chain; the server may also be a cloud server that provides basic cloud computing services such as cloud services, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, middleware services, a domain name service, a security service, a CDN (Content Delivery Network), a big data and artificial intelligence platform, and the like, which is not limited herein.

Fig. 8 is a block diagram of a transaction risk assessment device shown in an exemplary embodiment of the present application. As shown in fig. 8, the apparatus includes:

the guest group obtaining module 210 is configured to obtain a guest group to which a user to be assessed of a transaction risk belongs, and the user to be assessed of the transaction risk is included in the guest group; a risk score obtaining module 230 configured to obtain a first risk score output by a risk certainty model for each user in the guest group, the risk certainty model being constructed according to the risk characteristics of the certainty dimensionality, and obtain a second risk score output by an uncertainty newly-added model for each user, the uncertainty newly-added model being constructed according to the risk characteristics of the non-certainty dimensionality; a guest group interval obtaining module 250 configured to obtain guest group intervals with different risk degrees according to the first risk scores and the second risk scores of all users in the guest group, wherein the risk degrees of the guest group intervals are determined according to historical transaction information of a plurality of users in the guest group intervals; the transaction risk obtaining module 270 is configured to determine a transaction risk value of the user to be assessed for the transaction risk according to the risk degree ranking among the guest group intervals and the risk degree of the guest group interval in which the user to be assessed for the transaction risk is located.

In another exemplary embodiment, the guest group interval obtaining module 250 includes:

a two-dimensional plane forming unit configured to form a two-dimensional plane from the first risk scores and the second risk scores of all users in the guest group; and the grid area acquisition unit is configured to perform grid cross processing in the two-dimensional plane to obtain grid areas with different risk degrees in the two-dimensional plane, wherein the grid areas with different risk degrees correspond to the guest group intervals with different risk degrees.

In another exemplary embodiment, the two-dimensional plane forming unit includes:

the risk score sorting subunit is configured to sort the first risk scores and the second risk scores of all the users in the guest group from small to large respectively to obtain a first risk score sequence and a second risk score sequence; and the two-dimensional plane construction subunit is configured to construct a two-dimensional plane by taking the first risk score sequence and the second risk score sequence as different dimensions of the two-dimensional plane.

In another exemplary embodiment, the mesh region acquisition unit includes:

the grid area dividing subunit is configured to divide the two-dimensional plane into a plurality of grid areas according to the first risk score sequence and the second risk score sequence corresponding to the two-dimensional plane; and the risk degree calculating subunit is configured to calculate the risk degree of the grid area according to the historical transaction information of the plurality of users contained in the grid area.

In another exemplary embodiment, the mesh region dividing subunit includes:

a risk interval dividing subunit configured to divide the first risk score sequence and the second risk score sequence into a plurality of risk intervals of the same number; the interval intersection merging subunit is configured to merge, according to the number of users in the interval intersection between the risk intervals, the interval intersection in which the number of users is less than or equal to the number threshold with the adjacent interval intersection, so that the number of users contained in the interval intersection obtained by merging is greater than the number threshold; a mesh region obtaining subunit configured to use an intersection of the intervals formed in the two-dimensional plane as a mesh region in the two-dimensional plane.

In another exemplary embodiment, the range intersection merging subunit comprises:

the vector interval intersection searching subunit is configured to search the intersection between adjacent intervals aiming at the interval intersection with the number of the users smaller than the number threshold; the first merging subunit is configured to merge the interval intersections with the user number smaller than the quantity threshold value and the searched adjacent interval intersections if the adjacent interval intersections with the risk degrees closest to the risk degree of the interval intersections with the user number smaller than the quantity threshold value are searched; and the second merging subunit is configured to select the adjacent interval intersection with the smallest interval area from the searched adjacent interval intersections and the interval intersection with the number of the users smaller than the number threshold value for merging if the number of the searched adjacent interval intersections is multiple.

In another exemplary embodiment, the risk degree calculating subunit includes:

the historical transaction information acquisition subunit is configured to acquire historical transaction information of all users contained in the grid area, wherein the historical transaction information is used for indicating whether the users have transaction risks in historical transactions; and the Fengxi degree acquiring subunit is configured to calculate a ratio between the number of users with transaction risks in the historical transactions and the number of all users contained in the grid area, and the ratio is used as the risk degree of the grid area.

In another exemplary embodiment, the transaction risk acquisition module 270 includes:

the ranking obtaining unit is configured to obtain the ranking of the risk degree of the user group interval where the transaction risk to be evaluated is located in the risk degree ranking; and the transaction risk value calculating unit is configured to calculate the transaction risk value of the user with the transaction risk to be evaluated according to the ranking.

In another exemplary embodiment, the transaction risk value calculation unit includes:

the first calculating subunit is configured to calculate a transaction risk value according to a first risk score and a second risk score corresponding to a user of the transaction risk to be evaluated and a risk degree of a guest group interval in which the user of the transaction risk to be evaluated is located, if it is determined that the rank corresponding to the user of the transaction risk to be evaluated is the lowest rank; and the second calculating subunit is configured to calculate the transaction risk value according to the first risk score and the second risk score corresponding to the user with the transaction risk to be evaluated, the risk degree of the guest group interval in which the user with the transaction risk to be evaluated is located, and the risk degree of the guest group interval in which the user with the transaction risk to be evaluated is located.

In another exemplary embodiment, the apparatus further comprises:

the multi-time generation module of the guest group interval is configured to acquire the guest group intervals with different risk degrees for multiple times according to the first risk scores and the second risk scores of all users in the guest group, and the acquired guest group interval is generated according to a random risk interval division strategy each time; the transaction risk value multi-time calculation module is configured to acquire transaction risk values of users with transaction risks to be evaluated for multiple times according to the passenger group intervals with different risk degrees acquired for multiple times; and the transaction risk value selection module is configured to select a target transaction risk value from the transaction risk values acquired for multiple times as the transaction risk value of the transaction user to be evaluated.

It should be noted that the apparatus provided in the foregoing embodiment and the method provided in the foregoing embodiment belong to the same concept, and the specific manner in which each module and unit execute operations has been described in detail in the method embodiment, and is not described again here.

Embodiments of the present application further provide an electronic device, including a processor and a memory, where the memory has stored thereon computer-readable instructions, which when executed by the processor, implement the transaction risk assessment method as described above.

FIG. 9 is a block diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.

It should be noted that the computer system 1600 of the electronic device shown in fig. 9 is only an example, and should not bring any limitation to the functions and the application scope of the embodiments of the present application.

As shown in fig. 9, computer system 1600 includes a Central Processing Unit (CPU)1601, which can perform various appropriate actions and processes, such as executing the methods described in the above embodiments, according to a program stored in a Read-Only Memory (ROM) 1602 or a program loaded from a storage portion 1608 into a Random Access Memory (RAM) 1603. In the RAM 1603, various programs and data necessary for system operation are also stored. The CPU 1601, ROM 1602, and RAM 1603 are connected to each other via a bus 1604. An Input/Output (I/O) interface 1605 is also connected to the bus 1604.

The following components are connected to the I/O interface 1605: an input portion 1606 including a keyboard, a mouse, and the like; an output section 1607 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage portion 1608 including a hard disk and the like; and a communication section 1609 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 1609 performs communication processing via a network such as the internet. The driver 1610 is also connected to the I/O interface 1605 as needed. A removable medium 1611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 1610 as necessary so that a computer program read out therefrom is mounted in the storage portion 1608 as necessary.

In particular, according to embodiments of the application, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising a computer program for performing the method illustrated by the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via the communication portion 1609, and/or installed from the removable media 1611. When the computer program is executed by a Central Processing Unit (CPU)1601, various functions defined in the system of the present application are executed.

It should be noted that the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM), a flash Memory, an optical fiber, a portable Compact Disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with a computer program embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software or hardware, and the described units may also be disposed in a processor. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.

Yet another aspect of the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a transaction risk assessment method as described above. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist separately without being incorporated in the electronic device.

Another aspect of the application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to enable the computer device to execute the transaction risk assessment method provided in the various embodiments described above.

The above description is only a preferred exemplary embodiment of the present application, and is not intended to limit the embodiments of the present application, and those skilled in the art can easily make various changes and modifications according to the main concept and spirit of the present application, so that the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A transaction risk assessment method, comprising:

obtaining a guest group to which a user of a transaction risk to be evaluated belongs, wherein the user of the transaction risk to be evaluated is included in the guest group;

acquiring a first risk score output by a risk certainty model aiming at each user in the guest group, wherein the risk certainty model is constructed according to the risk characteristics of certainty dimensionality, and acquiring a second risk score output by an uncertainty newly-added model aiming at each user, and the uncertainty newly-added model is constructed according to the risk characteristics of non-certainty dimensionality;

acquiring guest group intervals with different risk degrees according to the first risk scores and the second risk scores of all users in the guest group, wherein the risk degrees of the guest group intervals are determined according to historical transaction information of a plurality of users in the guest group intervals;

and determining the transaction risk value of the user with the transaction risk to be evaluated according to the risk degree sequence among the guest group intervals and the risk degree of the guest group interval in which the user with the transaction risk to be evaluated is located.

2. The method of claim 1, wherein obtaining the guest group segments with different risk degrees according to the first risk score and the second risk score of all users in the guest group comprises:

forming a two-dimensional plane by the first risk scores and the second risk scores of all users in the guest group;

and carrying out grid cross processing in the two-dimensional plane to obtain grid areas with different risk degrees in the two-dimensional plane, wherein the grid areas with different risk degrees correspond to the guest group intervals with different risk degrees.

3. The method of claim 2, wherein forming a two-dimensional plane from the first risk score and the second risk score of all users in the guest group comprises:

respectively sorting the first risk scores and the second risk scores of all users in the passenger group from small to large to obtain a first risk score sequence and a second risk score sequence;

and constructing the two-dimensional plane by taking the first risk score sequence and the second risk score sequence as different dimensions of the two-dimensional plane.

4. The method according to claim 2, wherein the performing mesh intersection processing in the two-dimensional plane to obtain mesh regions with different risk degrees in the two-dimensional plane comprises:

dividing the two-dimensional plane into a plurality of grid areas according to the first risk score sequence and the second risk score sequence corresponding to the two-dimensional plane;

and calculating the risk degree of the grid area according to the historical transaction information of a plurality of users contained in the grid area.

5. The method according to claim 4, wherein the dividing the two-dimensional plane into a plurality of grid regions according to the first risk score sequence and the second risk score sequence corresponding to the two-dimensional plane comprises:

dividing the first risk score sequence and the second risk score sequence into a plurality of risk intervals with the same quantity;

merging the interval intersection with the number of users less than or equal to a number threshold with the adjacent interval intersection according to the number of users in the interval intersection between the risk intervals, so that the number of users contained in the interval intersection obtained by merging is greater than the number threshold;

and taking the interval intersection formed in the two-dimensional plane as a grid area in the two-dimensional plane.

6. The method of claim 5, wherein merging the interval intersection where the number of users is less than the number threshold with the adjacent interval intersection comprises:

searching adjacent interval intersections aiming at the interval intersections of which the number of the users is less than a number threshold;

and if the adjacent interval intersection with the risk degree closest to that of the interval intersection with the user number smaller than the number threshold is searched, merging the interval intersection with the user number smaller than the number threshold with the searched adjacent interval intersection.

7. The method of claim 6, further comprising:

and if the number of the searched adjacent interval intersections is multiple, selecting the adjacent interval intersection with the minimum interval area from the searched adjacent interval intersections and combining the adjacent interval intersection with the number of the users smaller than the number threshold.

8. The method of claim 4, wherein calculating the risk level of the grid area based on historical transaction information of a plurality of users included in the grid area comprises:

acquiring historical transaction information of all users contained in the grid area, wherein the historical transaction information is used for indicating whether the users have transaction risks in historical transactions;

and calculating the ratio of the number of users with transaction risks in the historical transactions to the number of all users contained in the grid area, and taking the ratio as the risk degree of the grid area.

9. The method of claim 1, wherein the determining the transaction risk value of the user with the transaction risk to be evaluated according to the risk degree ranking among the guest group intervals and the risk degree of the guest group interval where the user with the transaction risk to be evaluated is located comprises:

obtaining the ranking of the risk degree of the passenger group interval where the user with the transaction risk to be evaluated is located in the risk degree ranking;

and calculating the transaction risk value of the user with the transaction risk to be evaluated according to the ranking.

10. The method of claim 9, wherein said calculating a transaction risk value for the user at the transaction risk to be assessed according to the ranking comprises:

and if the rank corresponding to the user with the transaction risk to be evaluated is determined to be the lowest rank, calculating the transaction risk value according to the first risk score and the second risk score corresponding to the user with the transaction risk to be evaluated and the risk degree of the guest group interval in which the user with the transaction risk to be evaluated is located.

11. The method of claim 9, wherein said calculating a transaction risk value for the user at the transaction risk to be assessed according to the ranking comprises:

if the rank corresponding to the user with the transaction risk to be evaluated is higher than the lowest rank, calculating the transaction risk value according to the first risk score and the second risk score corresponding to the user with the transaction risk to be evaluated, the risk degree of the guest group interval where the user with the transaction risk to be evaluated is located, and the risk degree of the guest group interval where the rank is lower than the rank corresponding to the user with the transaction risk to be evaluated.

12. The method of claim 1, further comprising:

acquiring guest group intervals with different risk degrees for multiple times according to the first risk scores and the second risk scores of all users in the guest group, and generating the acquired guest group intervals each time according to a random risk interval division strategy;

acquiring transaction risk values of the users with the transaction risks to be evaluated for multiple times according to the passenger group intervals with different risk degrees acquired for multiple times;

and selecting a target transaction risk value from the transaction risk values acquired for multiple times as the transaction risk value of the transaction user to be evaluated.

13. A transaction risk assessment device, comprising:

the system comprises a guest group acquisition module, a transaction risk evaluation module and a transaction risk evaluation module, wherein the guest group acquisition module is configured to acquire a guest group to which a user of a transaction risk to be evaluated belongs, and the user of the transaction risk to be evaluated is included in the guest group;

a risk score acquisition module configured to acquire a first risk score output by a risk certainty model for each user in the guest group, the risk certainty model being constructed according to the risk characteristics of a certainty dimension, and acquire a second risk score output by an uncertainty new model for each user, the uncertainty new model being constructed according to the risk characteristics of a non-certainty dimension;

the system comprises a guest group interval acquisition module, a guest group interval processing module and a guest group interval processing module, wherein the guest group interval acquisition module is configured to acquire guest group intervals with different risk degrees according to first risk scores and second risk scores of all users in a guest group, and the risk degrees of the guest group intervals are determined according to historical transaction information of a plurality of users in the guest group intervals;

and the transaction risk acquisition module is configured to determine a transaction risk value of the user with the transaction risk to be evaluated according to the risk degree sequence among the guest group intervals and the risk degree of the guest group interval in which the user with the transaction risk to be evaluated is located.

14. An electronic device, comprising:

a memory storing computer readable instructions;

a processor to read computer readable instructions stored by the memory to perform the method of any of claims 1-12.

15. A computer-readable storage medium having computer-readable instructions stored thereon, which, when executed by a processor of a computer, cause the computer to perform the method of any one of claims 1-12.