CN115829705A

CN115829705A - Method and device for risk processing according to failure information

Info

Publication number: CN115829705A
Application number: CN202211455410.6A
Authority: CN
Inventors: 朱江波; 谭健
Original assignee: Bank of China Ltd
Current assignee: Bank of China Ltd
Priority date: 2022-11-21
Filing date: 2022-11-21
Publication date: 2023-03-21

Abstract

The invention provides a method and a device for risk processing according to failure information, which relate to the technical field of computer data processing, and the method comprises the following steps: the bank server determines the corresponding relation between the risk prediction model and the failure matrix according to the transaction data of the bank; the bank server issues the corresponding relation between the determined risk prediction model and the failure matrix to each website edge system; each network point edge system determines a failure matrix of each network point edge system in the current period according to the failure transaction data of each network point edge system in the current period; each net point edge system determines a risk prediction model of each net point edge system in the current period according to the corresponding relation among the failure matrix, the risk prediction model and the failure matrix of each net point edge system in the current period; and carrying out risk control on the transaction of each network point edge system in the current period by each network point edge system according to the risk prediction model in the current period.

Description

Method and device for risk processing according to failure information

Technical Field

The present invention relates to the field of computer data processing technologies, and in particular, to a method and an apparatus for risk processing according to failure information.

Background

This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.

Currently, when a user conducts a transaction at a bank front-end system (such as a self-service terminal interface), whether the transaction can be conducted is judged only based on transaction failure information of a background system. However, the transaction failure information may also include other useful information, such as risk information, but there is no method for effectively performing risk control based on the transaction failure information.

Disclosure of Invention

In order to solve the problems in the prior art, the invention provides a method and a device for risk processing according to failure information.

In a first aspect of the embodiments of the present invention, a method for risk processing according to failure information is provided, including:

the bank server determines the corresponding relation between the risk prediction model and the failure matrix according to the transaction data of the bank;

the bank server issues the determined corresponding relation between the risk prediction model and the failure matrix to each website edge system;

each network point edge system determines a failure matrix of each network point edge system in the current period according to the failure transaction data of each network point edge system in the current period;

each net point edge system determines a risk prediction model of each net point edge system in the current period according to the corresponding relation among the failure matrix, the risk prediction model and the failure matrix of each net point edge system in the current period;

and carrying out risk control on the transaction of each network point edge system in the current period by each network point edge system according to the risk prediction model in the current period.

In a second aspect of the embodiments of the present invention, an apparatus for risk processing according to failure information is provided, including:

the bank server is used for determining the corresponding relation between the risk prediction model and the failure matrix according to the transaction data of the bank;

the bank server is also used for issuing the determined corresponding relation between the risk prediction model and the failure matrix to each website edge system;

each network point edge system is used for determining a failure matrix of each network point edge system in the current period according to the failure transaction data of each network point edge system in the current period;

each net point edge system is also used for determining a risk prediction model of each net point edge system in the current period according to the corresponding relation among the failure matrix, the risk prediction model and the failure matrix of each net point edge system in the current period;

and each network point edge system is also used for carrying out risk control on the transaction of each network point edge system in the current period according to the risk prediction model in the current period.

In a third aspect of the embodiments of the present invention, a computer device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the processor implements a method for risk processing according to failure information.

In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, and the computer program, when executed by a processor, implements a method for risk processing according to failure information.

In a fifth aspect of embodiments of the present invention, a computer program product is presented, the computer program product comprising a computer program, which when executed by a processor, implements a method of risk handling in dependence of failure information.

According to the method and the device for risk processing according to the failure information, the bank server determines the corresponding relation between a risk prediction model and a failure matrix according to the transaction data of the bank; the bank server issues the determined corresponding relation between the risk prediction model and the failure matrix to each website edge system; each network point edge system determines a failure matrix of each network point edge system in the current period according to the failure transaction data of each network point edge system in the current period; each net point edge system determines a risk prediction model of each net point edge system in the current period according to the corresponding relation among the failure matrix, the risk prediction model and the failure matrix of each net point edge system in the current period; according to the method, the system and the system, each network point edge system carries out risk control on the transaction of each network point edge system in the current period according to the risk prediction model in the current period.

Drawings

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

Fig. 1 is a flowchart illustrating a method for risk processing according to failure information according to an embodiment of the invention.

Fig. 2 is a flowchart illustrating a process of determining a correspondence between a risk prediction model and a failure matrix according to an embodiment of the present invention.

Fig. 3 is a flow chart illustrating a process of determining a failure matrix of each dot edge system in a current period according to an embodiment of the present invention.

Fig. 4 is a flowchart illustrating a process of determining a risk prediction model of each dot edge system in the current period according to an embodiment of the present invention.

Fig. 5 is a schematic diagram of an apparatus for risk processing according to failure information according to an embodiment of the invention.

Fig. 6 is a schematic structural diagram of a computer device according to an embodiment of the present invention.

Detailed Description

The principles and spirit of the present invention will be described with reference to a number of exemplary embodiments. It is understood that these embodiments are given solely for the purpose of enabling those skilled in the art to better understand and to practice the invention, and are not intended to limit the scope of the invention in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

As will be appreciated by one skilled in the art, embodiments of the present invention may be embodied as a system, apparatus, device, method, or computer program product. Accordingly, the present disclosure may be embodied in the form of: entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.

According to the embodiment of the invention, a method and a device for risk processing according to failure information are provided, and the method and the device relate to the technical field of computer data processing.

The principles and spirit of the present invention are explained in detail below with reference to several exemplary embodiments of the present invention.

Fig. 1 is a flowchart illustrating a method for risk processing according to failure information according to an embodiment of the invention. As shown in fig. 1, the method includes:

s1, a bank server determines a corresponding relation between a risk prediction model and a failure matrix according to transaction data of a bank;

s2, the bank server issues the determined corresponding relation between the risk prediction model and the failure matrix to each website edge system;

s3, determining a failure matrix of each network point edge system in the current period by each network point edge system according to the failure transaction data of each network point edge system in the current period;

s4, determining a risk prediction model of each net point edge system in the current period by each net point edge system according to the corresponding relation among the failure matrix, the risk prediction model and the failure matrix of each net point edge system in the current period;

and S5, carrying out risk control on the transaction of each network point edge system in the current period according to the risk prediction model in the current period by each network point edge system.

In order to clearly explain the method for risk processing based on failure information, the following detailed description is made with reference to each step.

In S1, referring to fig. 2, the bank server determines a corresponding relationship between the risk prediction model and the failure matrix according to transaction data of the bank, including:

s11, classifying the transaction data of the bank into a plurality of transaction data sets;

s12, determining a risk characteristic value corresponding to each transaction data set;

s13, determining a plurality of potential risk data sets according to the risk characteristic values;

s14, for each potential risk data set, determining a failure matrix corresponding to the potential risk data set according to failure transaction data contained in the potential risk data set;

s15, training a prediction model according to the potential risk data set to obtain a risk prediction model corresponding to the potential risk data set;

and S16, determining the corresponding relation between the risk prediction model and the failure matrix according to the failure matrix and the risk prediction model corresponding to the potential risk data set.

In one embodiment, (S12) determining a risk characteristic value corresponding to each transaction data set includes:

s12-1, determining a user category and a transaction category corresponding to each transaction data in the transaction data set;

s12-2, regarding each user category, taking the transaction data of which the corresponding user category in the transaction data set is the user category as the transaction data corresponding to the user category;

s12-3, dividing the transaction data corresponding to the user category into the transaction data corresponding to each transaction category according to the transaction categories;

s12-4, taking the proportion of the risk trading data in the trading data of each trading category corresponding to the user category as the risk proportion of the trading category corresponding to the user category;

s12-5, determining a risk matrix corresponding to the transaction data set, wherein rows of the risk matrix correspond to user categories, columns of the risk matrix correspond to transaction categories, for each element of the risk matrix, determining the user category and the transaction category corresponding to the element, and taking the risk ratio of the determined user category to the transaction category as the value of the element;

s12-6, determining a risk matrix corresponding to the transaction data set according to the risk matrix corresponding to the transaction data set;

and S12-7, taking the characteristic value of the risk square matrix corresponding to the transaction data set, which is not 0, as the risk characteristic value corresponding to the transaction data set.

In one embodiment, (S12-6) determining a risk matrix corresponding to the transaction data set according to the risk matrix corresponding to the transaction data set, includes:

when the number of the user categories is the same as that of the transaction categories, taking the risk matrix corresponding to the transaction data set as a risk square matrix corresponding to the transaction data set;

when the number of the user categories is larger than the number of the transaction categories, according to the difference between the number of the user categories and the number of the transaction categories, the column of the risk matrix corresponding to the transaction data set is supplemented with 0, and the obtained square matrix is used as the risk square matrix corresponding to the transaction data set;

and when the number of the user categories is smaller than the number of the transaction categories, supplementing 0 to the row of the risk matrix corresponding to the transaction data set according to the difference between the number of the transaction categories and the number of the user categories, and taking the obtained square matrix as the risk square matrix corresponding to the transaction data set.

In one embodiment, (S13) determining a plurality of sets of risk potential data according to the risk feature values, including:

and for each transaction data set, if the maximum value of the modular length of the risk characteristic value corresponding to the transaction data set is greater than the risk threshold value, taking the transaction data set as a potential risk data set.

In one embodiment, (S14) for each risk potential data set, determining a failure matrix corresponding to the risk potential data set according to the failed transaction data included in the risk potential data set, including:

s14-1, determining a failure code corresponding to the failure transaction data for each failure transaction data contained in the potential risk data set, and taking a user category to which a user corresponding to the failure transaction data belongs as a user category corresponding to the failure transaction data;

s14-2, for each user category and each failure code, selecting the corresponding user category and failure code from the failure transaction data contained in the potential risk data set, wherein the user category and the failure code are respectively the failure transaction data of the user category and the failure code, and taking the transaction quantity of the selected failure transaction data as the failure quantity of the potential risk data set relative to the user category and the failure code;

and S14-3, determining a failure matrix corresponding to the risk potential data set, wherein rows of the failure matrix correspond to the user categories, columns of the failure matrix correspond to the failure codes, and the value of each element of the failure matrix is equal to the failure number of the risk potential data set related to the user categories and the failure codes corresponding to the elements.

In S2, the bank server issues the corresponding relation between the determined risk prediction model and the failure matrix to each website edge system.

In S3, referring to fig. 3, each website edge system determines a failure matrix of each website edge system in the current period according to the failed transaction data of each website edge system in the current period, including:

s31, for each network point edge system, determining a failure code corresponding to each failure transaction data of the network point edge system in the current period, and taking a user category to which a user corresponding to the failure transaction data belongs as a user category corresponding to the failure transaction data;

s32, for each user category and each failure code, selecting the failure transaction data of which the corresponding user category and the failure code are respectively the user category and the failure code from the failure transaction data of the website edge system in the current period, and taking the transaction quantity of the selected failure transaction data as the failure quantity of the website edge system about the user category and the failure code;

and S33, determining a failure matrix of the network point edge system in the current period, wherein the rows of the failure matrix correspond to the user categories, the columns of the failure matrix correspond to failure codes, and the value of each element of the failure matrix is equal to the failure number of the network point edge system on the user categories and the failure codes corresponding to the element.

In S4, referring to fig. 4, determining, by each dot edge system, a risk prediction model of each dot edge system in the current period according to a corresponding relationship between the failure matrix, the risk prediction model, and the failure matrix of each dot edge system in the current period includes:

s41, taking a failure matrix contained in the corresponding relation between the risk prediction model and the failure matrix as a to-be-selected failure matrix;

s42, for each to-be-selected failure matrix, determining a difference matrix between the to-be-selected failure matrix and each net point edge system according to the to-be-selected failure matrix and the failure matrix of each net point edge system in the current period;

s43, determining a potential failure matrix of each net point edge system in the current period according to the difference matrix;

and S44, determining a risk prediction model of each net point edge system in the current period according to the corresponding relation among the potential failure matrix, the risk prediction model and the failure matrix of each net point edge system in the current period.

In one embodiment, (S42) for each candidate failure matrix, determining a difference matrix between the candidate failure matrix and each dot edge system according to the candidate failure matrix and the failure matrix of each dot edge system in the current period, including:

and taking the difference between the to-be-selected failure matrix and the failure matrix of each net point edge system in the current period as a difference matrix between the to-be-selected failure matrix and each net point edge system.

It should be noted that, when the difference calculation is performed on the matrices, the time ranges of the transaction data of each transaction matrix are kept consistent;

alternatively, a matrix position in the matrix is selected during calculation, for example, the number of rows is 1 and the number of columns is 1, values at other positions in the matrix are corrected according to values of the two matrices at the position, and then calculation is performed according to the corrected matrix.

In one embodiment, (S43) determining a potential failure matrix for each dot edge system in the current period according to the difference matrix, includes:

s43-1, for each dot edge system and each candidate failure matrix, when the difference matrix between the candidate failure matrix and the dot edge system is a square matrix, taking the maximum value of the modular length of the characteristic value of the difference matrix as the difference modular length between the candidate failure matrix and the dot edge system;

when the difference matrix of the to-be-selected failure matrix and the mesh point edge system is not a square matrix, performing 0 complementing according to the row number and the column number of the difference matrix to obtain the square matrix, and taking the maximum value of the modular length of the characteristic value of the obtained square matrix as the difference modular length of the to-be-selected failure matrix and the mesh point edge system;

s43-2, determining whether a to-be-selected failure matrix exists in each dot edge system, and meeting the condition p: the difference modular length between the to-be-selected failure matrix and the dot edge system is smaller than a set threshold;

when the candidate failure matrix meets the condition p, taking the candidate failure matrix meeting the condition p as a potential failure matrix of the net point edge system in the current period;

when the candidate failure matrix does not meet the condition p, taking the network point edge system as a current edge system, and circularly executing the following 5 steps (S01 to S05) until the candidate failure matrix meets the condition p:

s01, determining a related edge system of a current edge system;

s02, taking a related edge system of the current edge system as a potential edge system;

s03, updating a failure matrix of the network point edge system in the current period according to the failure transaction data of the potential edge system in the current period;

s04, updating the difference modular length between each to-be-selected failure matrix and the net point edge system according to the updated corresponding relation among the failure matrix, the risk prediction model and the failure matrix of the net point edge system in the current period;

(in practical application scenarios, the method for updating the difference modular length between each candidate failure matrix and the dot edge system can refer to the methods of S41 to S44 and S43-1.)

S05, updating the current edge system into a potential edge system;

and S06, when the candidate failure matrix meets the condition p, taking the candidate failure matrix meeting the condition p as a potential failure matrix of the net point edge system in the current period.

In one embodiment, (S01) determining a relevant edge system of the current edge system comprises:

for each current edge system, taking other mesh point edge systems except the current edge computing system as potential edge systems;

for each potential edge system, determining whether each user of the potential edge system is a user of the current edge system and whether each user of the current edge system is a user of the potential edge system;

taking users of the potential edge system that are also users of the current edge system as common users of the potential edge system and the current edge system;

taking users of the potential edge system who are not users of the current edge system as owned users of the potential edge system, and taking users of the current edge system who are not users of the potential edge system as owned users of the current edge system;

taking the correlation coefficient of each owned user of the potential edge system and each owned user of the current edge system as the candidate correlation coefficient of the potential edge system and the current edge system;

determining correlation coefficients of the potential edge system and the current edge system according to the number of common users of the potential edge system and the current edge system and candidate correlation coefficients of the potential edge system and the current edge system;

and determining a relevant edge system of the current edge system according to the relevant coefficients of each potential edge system and the current edge system.

In one embodiment, the method further comprises the following steps of determining the correlation coefficient between the users:

receiving related user hashes corresponding to the users and determined by the user systems and correlation coefficients of the users and the corresponding related user hashes, wherein the related user hashes determined by the user systems are determined based on the same hash function;

for each user, taking a set formed by the relevant user hashes corresponding to the user determined by each user system as a relevant user hash set corresponding to the user;

for each user system, if the relevant user hash exists in the relevant user hash set corresponding to the user and the relevant user hash is satisfied to be included in the relevant user hash corresponding to the user determined by the user system, the user system is used as the user system corresponding to the relevant user hash and the user. Taking the correlation coefficient of the hash of the user and the related user determined by the user system as the correlation coefficient of the hash of the user and the related user in the user system;

determining the correlation coefficient of the user and the related user hash as the maximum value of the correlation coefficient of the user and the related user hash in each corresponding user system;

for any two users, if the intersection of the relevant user hash sets corresponding to the two users is not empty, the following 3 steps are sequentially executed:

taking the intersection as a public user hash set corresponding to the two users;

for each related user hash contained in the public user hash set corresponding to the two users, determining the potential correlation coefficient of the related user hash corresponding to the two users according to the related user hash and the correlation coefficient of the two users;

and determining the correlation coefficient between the two users according to the potential correlation coefficient of each relevant user hash contained in the public user hash set corresponding to the two users.

It should be noted that although the operations of the method of the present invention have been described in the above embodiments and the accompanying drawings in a particular order, this does not require or imply that these operations must be performed in this particular order, or that all of the operations shown must be performed, to achieve the desired results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.

Having described the method of the exemplary embodiment of the present invention, an apparatus for risk processing based on failure information of the exemplary embodiment of the present invention will be described next with reference to fig. 5.

The implementation of the apparatus for performing risk processing according to the failure information may refer to the implementation of the above method, and repeated details are not repeated. The term "module" or "unit" used hereinafter may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.

Based on the same inventive concept, the present invention further provides an apparatus for risk processing according to failure information, as shown in fig. 5, the apparatus includes:

In one embodiment, the determining, by the bank server, the corresponding relationship between the risk prediction model and the failure matrix according to the transaction data of the bank includes:

classifying transaction data of a bank into a plurality of transaction data sets;

determining a risk characteristic value corresponding to each transaction data set;

determining a plurality of potential risk data sets according to the risk characteristic values;

for each potential risk data set, determining a failure matrix corresponding to the potential risk data set according to failure transaction data contained in the potential risk data set;

training a prediction model according to the potential risk data set to obtain a risk prediction model corresponding to the potential risk data set;

and determining the corresponding relation between the risk prediction model and the failure matrix according to the failure matrix and the risk prediction model corresponding to the potential risk data set.

In one embodiment, determining the risk characteristic value corresponding to each transaction data set includes:

determining a user category and a transaction category corresponding to each transaction data in the transaction data set;

for each user category, taking the transaction data of which the corresponding user category in the transaction data set is the user category as the transaction data corresponding to the user category;

dividing the transaction data corresponding to the user category into the transaction data corresponding to each transaction category of the user category according to the transaction categories;

taking the proportion of the risk transaction data in the transaction data of each transaction category corresponding to the user category as the risk proportion of the transaction category corresponding to the user category;

determining a risk matrix corresponding to the transaction data set, wherein rows of the risk matrix correspond to user categories, columns of the risk matrix correspond to transaction categories, for each element of the risk matrix, determining the user category and the transaction category corresponding to the element, and taking the risk ratio of the determined user category to the transaction category as the value of the element;

determining a risk matrix corresponding to the transaction data set according to the risk matrix corresponding to the transaction data set;

and taking the characteristic value of the risk square matrix corresponding to the transaction data set, which is not 0, as the risk characteristic value corresponding to the transaction data set.

In an embodiment, determining the risk matrix corresponding to the transaction data set according to the risk matrix corresponding to the transaction data set includes:

when the number of the user categories is larger than the number of the transaction categories, according to the difference between the number of the user categories and the number of the transaction categories, complementing 0 for the column of the risk matrix corresponding to the transaction data set, and taking the obtained square matrix as the risk square matrix corresponding to the transaction data set;

In an embodiment, for each potentially-risky data set, determining a failure matrix corresponding to the potentially-risky data set according to the failed transaction data included in the potentially-risky data set includes:

for each failed transaction data contained in the potential risk data set, determining a failure code corresponding to the failed transaction data, and taking a user category to which a user corresponding to the failed transaction data belongs as a user category corresponding to the failed transaction data;

for each user category and each failure code, selecting the corresponding user category and failure code from the failure transaction data contained in the potential risk data set, wherein the user category and the failure code are respectively the failure transaction data of the user category and the failure code, and taking the transaction quantity of the selected failure transaction data as the failure quantity of the potential risk data set relative to the user category and the failure code;

and determining a failure matrix corresponding to the latent risk data set, wherein rows of the failure matrix correspond to user categories, columns of the failure matrix correspond to failure codes, and the value of each element of the failure matrix is equal to the number of failures of the latent risk data set on the user category and the failure codes corresponding to the element.

In one embodiment, each of the network point edge systems determines a failure matrix of each of the network point edge systems at the current time based on the failed transaction data of each of the network point edge systems at the current time, including:

for each network point edge system, determining a failure code corresponding to each failure transaction data of the network point edge system in the current period, and taking the user category to which the user corresponding to the failure transaction data belongs as the user category corresponding to the failure transaction data;

for each user category and each failure code, selecting the corresponding user category and failure code from the failure transaction data of the website edge system in the current period, wherein the user category and the failure code are respectively the failure transaction data of the user category and the failure code, and taking the transaction quantity of the selected failure transaction data as the failure quantity of the website edge system about the user category and the failure code;

determining a failure matrix of the net-point edge system in the current period, wherein the rows of the failure matrix correspond to user categories, the columns of the failure matrix correspond to failure codes, and the value of each element of the failure matrix is equal to the failure number of the net-point edge system about the user category and the failure codes corresponding to the element.

In an embodiment, determining, by each dot edge system, a risk prediction model of each dot edge system in the current period according to a correspondence between a failure matrix, a risk prediction model, and a failure matrix of each dot edge system in the current period includes:

taking a failure matrix contained in the corresponding relation between the risk prediction model and the failure matrix as a to-be-selected failure matrix;

for each to-be-selected failure matrix, determining a difference matrix between the to-be-selected failure matrix and each mesh point edge system according to the to-be-selected failure matrix and the failure matrix of each mesh point edge system in the current period;

determining a potential failure matrix of each net point edge system in the current period according to the difference matrix;

and determining the risk prediction model of each net point edge system in the current period according to the corresponding relation among the potential failure matrix, the risk prediction model and the failure matrix of each net point edge system in the current period.

In one embodiment, determining a potential failure matrix for each mesh point edge system at the current time based on the gap matrix comprises:

for each dot edge system and each candidate failure matrix, when the difference matrix between the candidate failure matrix and the dot edge system is a square matrix, taking the maximum value of the modular length of the characteristic value of the difference matrix as the difference modular length between the candidate failure matrix and the dot edge system;

for each dot edge system, determining whether a candidate failure matrix exists or not, and meeting the condition p: the difference modular length between the to-be-selected failure matrix and the dot edge system is smaller than a set threshold;

when no candidate failure matrix meets the condition p, taking the net point edge system as a current edge system, and circularly executing the following 5 steps until the candidate failure matrix meets the condition p:

determining a relevant edge system of a current edge system;

taking the relevant edge system of the current edge system as a potential edge system;

updating a failure matrix of the network point edge system in the current period according to the failure transaction data of the potential edge system in the current period;

updating the difference modular length between each failure matrix to be selected and the net point edge system according to the updated corresponding relation of the failure matrix, the risk prediction model and the failure matrix of the net point edge system in the current period;

updating the current edge system to a potential edge system;

and when the candidate failure matrix meets the condition p, taking the candidate failure matrix meeting the condition p as a potential failure matrix of the net point edge system in the current period.

It should be noted that although in the above detailed description several modules of the apparatus for risk handling in dependence of failure information are mentioned, such a division is merely exemplary and not mandatory. Indeed, the features and functions of two or more of the modules described above may be embodied in one module according to embodiments of the invention. Conversely, the features and functions of one module described above may be further divided into embodiments by a plurality of modules.

Based on the aforementioned inventive concept, as shown in fig. 6, the present invention further provides a computer device 600, which includes a memory 610, a processor 620, and a computer program 630 stored in the memory 610 and capable of running on the processor 620, wherein the processor 620 executes the computer program 630 to implement the aforementioned risk processing method according to failure information.

Based on the foregoing inventive concept, the present invention proposes a computer-readable storage medium storing a computer program which, when executed by a processor, implements the foregoing method of risk processing according to failure information.

Based on the aforementioned inventive concept, the present invention proposes a computer program product comprising a computer program which, when being executed by a processor, implements a method of risk handling in dependence of failure information.

According to the technical scheme, the data acquisition, storage, use, processing and the like meet the relevant regulations of national laws and regulations.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, 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 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.

Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for risk processing based on failure information, comprising:

2. The method of claim 1, wherein the bank server determines a correspondence between the risk prediction model and the failure matrix based on transaction data of the bank, comprising:

3. The method of claim 2, wherein determining a risk characteristic value for each transaction data set comprises:

taking the proportion of the risk trading data in the trading data of each trading category corresponding to the user category as the risk proportion of the trading category corresponding to the user category;

4. The method of claim 3, wherein determining the risk matrix corresponding to the transaction data set according to the risk matrix corresponding to the transaction data set comprises:

5. The method of claim 2, wherein for each potentially-risky data set, determining a failure matrix corresponding to the potentially-risky data set according to the failed transaction data included in the potentially-risky data set comprises:

for each failed transaction data contained in the potential risk data set, determining a failure code corresponding to the failed transaction data, and taking the user category to which the user corresponding to the failed transaction data belongs as the user category corresponding to the failed transaction data;

and determining a failure matrix corresponding to the latent risk data set, wherein rows of the failure matrix correspond to the user categories, columns of the failure matrix correspond to the failure codes, and the value of each element of the failure matrix is equal to the number of failures of the latent risk data set on the user categories and the failure codes corresponding to the elements.

6. The method of claim 1, wherein each of the point edge systems determining a failure matrix for each of the point edge systems at the current time based on the failed transaction data for each of the point edge systems at the current time, comprises:

for each user category and each failure code, selecting the corresponding user category and failure code from the failure transaction data of the website edge system in the current period, wherein the user category and the failure code are respectively the failure transaction data of the user category and the failure code, and taking the transaction number of the selected failure transaction data as the failure number of the website edge system about the user category and the failure code;

7. The method of claim 1, wherein each mesh-point edge system determines a risk prediction model for each mesh-point edge system at the current time based on a correspondence of the failure matrix, the risk prediction model, and the failure matrix of each mesh-point edge system at the current time, comprising:

8. The method of claim 7, wherein determining a potential failure matrix for each mesh point edge system at a current stage based on the gap matrix comprises:

when the condition p is satisfied by the candidate failure matrix, taking the net point edge system as a current edge system, and circularly executing the following 5 steps until the condition p is satisfied by the candidate failure matrix:

determining a relevant edge system of a current edge system;

taking a relevant edge system of the current edge system as a potential edge system;

updating the failure matrix of the network point edge system in the current period according to the failure transaction data of the potential edge system in the current period;

updating the difference modular length between each to-be-selected failure matrix and the net point edge system according to the updated corresponding relation among the failure matrix, the risk prediction model and the failure matrix of the net point edge system in the current period;

updating the current edge system to a potential edge system;

9. An apparatus for risk processing based on failure information, comprising:

10. The apparatus of claim 9, wherein the bank server determines the correspondence between the risk prediction model and the failure matrix according to transaction data of the bank, comprising:

11. The apparatus of claim 10, wherein determining a corresponding risk characteristic value for each set of transaction data comprises:

12. The apparatus of claim 11, wherein determining the risk matrix corresponding to the transaction data set according to the risk matrix corresponding to the transaction data set comprises:

13. The apparatus of claim 10, wherein for each potentially-risky data set, determining a failure matrix corresponding to the potentially-risky data set according to the failed transaction data included in the potentially-risky data set comprises:

14. The apparatus of claim 9, wherein each dot edge system determines a failure matrix for each dot edge system at a current time based on data of failed transactions of each dot edge system at the current time, comprising:

determining a failure matrix of the network point edge system in the current period, wherein the rows of the failure matrix correspond to user categories, the columns of the failure matrix correspond to failure codes, and the value of each element of the failure matrix is equal to the failure number of the network point edge system about the user category and the failure codes corresponding to the element.

15. The apparatus of claim 9, wherein each mesh-point edge system determines a risk prediction model for each mesh-point edge system at the current time based on a correspondence of the failure matrix, the risk prediction model, and the failure matrix of each mesh-point edge system at the current time, comprises:

16. The apparatus of claim 15, wherein determining a potential failure matrix for each dot edge system at a current stage based on the gap matrix comprises:

for each mesh point edge system and each to-be-selected failure matrix, when the difference matrix between the to-be-selected failure matrix and the mesh point edge system is a square matrix, taking the maximum value of the modular length of the characteristic value of the difference matrix as the difference modular length between the to-be-selected failure matrix and the mesh point edge system;

for each dot edge system, determining whether a candidate failure matrix exists or not, and meeting the condition p: the difference modular length between the fail matrix to be selected and the dot edge system is smaller than a set threshold;

determining a relevant edge system of a current edge system;

updating the current edge system to a potential edge system;

17. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 8 when executing the computer program.

18. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the method of any one of claims 1 to 8.

19. A computer program product, characterized in that the computer program product comprises a computer program which, when being executed by a processor, carries out the method of any one of claims 1 to 8.