CN115564573A

CN115564573A - Financing risk identification method, device, equipment and storage medium

Info

Publication number: CN115564573A
Application number: CN202211369672.0A
Authority: CN
Inventors: 邓洋; 刘涛; 程呈
Original assignee: Agricultural Bank of China
Current assignee: Agricultural Bank of China
Priority date: 2022-11-03
Filing date: 2022-11-03
Publication date: 2023-01-03

Abstract

The invention discloses a financing risk identification method, a financing risk identification device, financing risk identification equipment and a financing risk storage medium. The method comprises the following steps: acquiring supply chain characteristics of a user to be tested; screening the supply chain characteristics of a user to be tested through a pre-trained characteristic extraction model to obtain a characteristic subset associated with financing; and identifying the feature subset through a pre-trained classifier to obtain a financing risk result, wherein the financing risk result comprises high risk or low risk. The method comprises the steps of carrying out feature screening according to a unified standard on supply chain features of users to be tested, which are obtained by a feature extraction model according to different links, obtaining a feature subset associated with financing, and deleting interference features irrelevant to user financing, so that when the screened feature subset is subjected to financing risk assessment through a classifier, a financing risk result of the users to be tested can be accurately obtained, and the financing risk coefficient of a financial institution is reduced.

Description

Financing risk identification method, device, equipment and storage medium

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for identifying financing risks.

Background

The small and medium-sized micro-enterprises bring the development of urban and rural economy in many aspects, and the provision of short-term and medium-term financing support is a good channel for serving the small and medium-sized micro-enterprises because of the continuous and stable development of the supply chain of the small and medium-sized micro-enterprises.

However, in the supply chain financing system, the conditions of enterprise legal customers are complex and changeable, and the enterprise legal customers can play different financing roles in different chains, but because the risk information of the customers in different chains is not ideal, the risk level of one customer in different chains is different; and the data of the client are disordered, the influence of each characteristic on the financing risk is consistent and contradicts with the actual situation, so the existing technical scheme can not accurately acquire the financing risk condition of the user, thereby improving the financing risk coefficient of the financial institution.

Disclosure of Invention

The invention provides a financing risk identification method, a financing risk identification device, financing risk identification equipment and a storage medium, which are used for identifying financing risks.

According to an aspect of the present invention, there is provided a method for identifying a financing risk, comprising: acquiring supply chain characteristics of a user to be detected;

screening the supply chain characteristics of the user to be tested through a pre-trained characteristic extraction model to obtain a characteristic subset associated with financing;

and identifying the feature subset through a pre-trained classifier to obtain a financing risk result, wherein the financing risk result comprises high risk or low risk.

According to another aspect of the present invention, there is provided an apparatus for identifying a financing risk, comprising: the supply chain characteristic acquisition module is used for acquiring the supply chain characteristics of the user to be detected;

the characteristic subset acquisition module is used for screening the supply chain characteristics of the user to be tested through a pre-trained characteristic extraction model to acquire a characteristic subset associated with financing;

and the financing risk result acquisition module is used for identifying the feature subset through a pre-trained classifier to acquire a financing risk result, wherein the financing risk result comprises a high risk or a low risk.

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

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

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the method according to any of the embodiments of the invention.

According to another aspect of the present invention, there is provided a computer-readable storage medium having stored thereon computer instructions for causing a processor to execute a method according to any one of the embodiments of the present invention.

According to the technical scheme of the embodiment of the invention, the feature extraction model is used for carrying out feature screening according to the unified standard aiming at the supply chain features of the user to be tested, which are acquired by different links, so as to acquire the feature subset associated with financing, and delete the interference features irrelevant to the financing of the user, so that when the screened feature subset is used for carrying out the financing risk assessment, the financing risk result of the user to be tested can be accurately acquired, and the financing risk coefficient of a financial institution is reduced.

It should be understood that the statements in this section are not intended to identify key or critical features of the embodiments of the present invention, nor are they intended to limit the scope of the invention. Other features of the present invention will become apparent from the following description.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, 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 flow chart of a financing risk identification method according to an embodiment of the present invention;

FIG. 2 is a flow chart of a financing risk identification method according to a second embodiment of the present invention;

FIG. 3 is a schematic structural diagram of a financing risk identification apparatus according to a third embodiment of the present invention;

fig. 4 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.

Detailed Description

In order to make those skilled in the art better understand the technical solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Moreover, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example one

Fig. 1 is a flowchart of a financing risk identification method according to an embodiment of the present invention, where the embodiment is applicable to a situation of identifying a financing risk, and the method may be executed by a financing risk identification device, which may be implemented in the form of hardware and/or software. As shown in fig. 1, the method includes:

step S101, obtaining supply chain characteristics of a user to be tested.

Optionally, the obtaining of the supply chain characteristics of the user to be tested includes: acquiring supply chain financing information of a user to be tested, wherein the supply chain financing information comprises registration basic data, credit investigation data and transaction data; preprocessing supply chain financing information of a user to be detected to obtain the preprocessed supply chain financing information; and performing feature extraction on the preprocessed supply chain financing information by adopting feature engineering to obtain supply chain features.

Specifically, the user to be tested in this embodiment may be a corporate client, and the supply chain financing platform may obtain supply chain financing information corresponding to a plurality of supply chain chains of the user to be tested by interfacing with an Enterprise Resource Planning (ERP) system, where the supply chain financing information may be as shown in table 1 below:

TABLE 1

The space limitation table 1 is only for illustrating the supply chain financing information, and does not limit the specific content of the supply chain financing information.

It should be noted that, since invalid information, such as information missing or error, may exist in the supply chain financing information, the acquired supply chain financing information needs to be preprocessed, and the preprocessing operation may include related operations such as classification, cleaning, or data set balancing, and the specific type of the preprocessing operation is not limited in this embodiment. And performing feature extraction by adopting feature engineering according to the preprocessed supply chain financing information to obtain supply chain features. At this time, the acquired supply chain characteristics include all the characteristics of the supply chain of the user to be detected after denoising, but there may be irrelevant characteristics determined with the financing risk, and if the financing risk is determined according to all the acquired supply chain characteristics, the irrelevant characteristics not only interfere with the determination of the financing risk, but also affect the determination efficiency of the financing risk due to excessive data.

And S102, screening the supply chain characteristics of the user to be tested through a pre-trained characteristic extraction model, and acquiring a characteristic subset associated with financing.

Optionally, before the feature extraction is performed on the supply chain financing information by using the pre-trained feature extraction model, the method further includes: acquiring supply chain characteristics of sample users, wherein the supply chain characteristics of the sample users consist of a supply chain training set of the sample users and a supply chain testing set of the sample users; training a supply chain training set of a sample user by adopting a genetic algorithm to obtain an initial model; and testing the initial model by adopting a supply chain test set of a sample user, and taking the initial model passing the test as a feature extraction model.

The genetic algorithm can directly operate the structural object, functions are not needed to have continuity, derivation limitation does not exist, the method has inherent parallelism and better global optimization capability, the optimization method based on probability theory is adopted, the optimized search space can be automatically obtained and guided without a determined rule, and the search direction can be self-adaptively adjusted. Therefore, in the embodiment, after the feature extraction model is obtained by training the supply chain features of the sample user by using the genetic algorithm, the feature subset associated with financing can be screened from the obtained supply chain features of the user to be tested by using the obtained feature extraction model.

Optionally, the method for obtaining a feature subset associated with financing by screening the supply chain features of the user to be tested through a pre-trained feature extraction model includes: encoding the supply chain characteristics of a user to be detected to obtain a chromosome; inputting each chromosome into a pre-trained feature extraction model, and acquiring the optimal chromosome corresponding to the optimal fitness when the iteration times are reached; and decoding the optimal chromosome to obtain the feature subset.

It should be noted that, in the embodiment, the supply chain characteristics of the sample user are obtained, and the supply chain characteristics of the sample user are split into a supply chain training set and a supply chain testing set according to a certain proportion. For example, the number of supply chain features is 100, while the number of supply chain training sets is 70 and the number of supply chain test sets is 30. And training 70 supply chain training sets by adopting a genetic algorithm to obtain an initial model, wherein the obtained initial model comprises relevant parameters such as a fitness function, a selection operator, a crossover operator and a mutation operator used by the genetic algorithm. And testing the obtained initial model by adopting a supply chain test set of a sample user to verify the accuracy of the initial model, and when the accuracy is determined to exceed a preset threshold value, passing the test, and taking the obtained initial model as a feature extraction model. Since the specific principle of the genetic algorithm is not the focus of the present application, the detailed description thereof is omitted.

Specifically, after the feature extraction model is obtained, the feature extraction model may be used to screen the supply chain features of the user to be tested, for example, the supply chain features of the enterprise user a are obtained, and the supply chain features are encoded to obtain a chromosome, because the performance of the genetic algorithm depends on the search efficiency and the algorithm convergence speed, the problem of too long character strings may be caused by ordinary binary encoding, and therefore, in the present application, an encoding manner in which binary and real variables are mixed is used, which is, of course, only an example in the present embodiment, and a specific manner for encoding the supply chain features is not limited. When the feature extraction model is adopted for feature extraction, relevant operations such as selection, intersection and mutation are carried out on the obtained chromosomes according to the determined relevant parameters such as the fitness function, the selection operator, the intersection operator and the mutation operator, the iteration times are set for the feature extraction model, for example, the iteration times are 100, when the iteration times are determined to reach 100, the chromosome corresponding to the optimal fitness is obtained, at the moment, the obtained optimal chromosome is decoded according to the inverse operation during coding, a feature value subset is obtained, and at the moment, the obtained feature subset contains supply chain features closely related to the financing of the enterprise user A.

And step S103, identifying the feature subset through a pre-trained classifier to obtain a financing risk result.

Optionally, before the feature subset is identified by the pre-trained classifier to obtain the financing risk result, the method further includes: acquiring a characteristic subset of a sample user; adding a risk label to the feature subset of the sample user to obtain a classification sample, wherein the risk label comprises high risk or low risk; and training according to the classification samples to obtain a classifier, wherein the classifier comprises the corresponding relation between the feature subset and the risk label.

Optionally, identifying the feature subset through a pre-trained classifier to obtain a financing risk result includes: inputting the feature subset into a classifier; determining a classification sample with the highest similarity with the feature subset through a classifier; and acquiring a risk label corresponding to the classification sample with the highest similarity, and taking the corresponding risk label as a financing risk result.

Specifically, in the embodiment, after the feature subset closely associated with the financing of the enterprise user a is obtained, the feature subset is further identified by the classifier to obtain a financing risk result, where the financing risk result includes a high risk or a low risk. Before specific recognition, training is carried out by adopting the characteristic subset of the sample user to obtain the classifier. The specific training process may be to receive a risk label added to the feature subset of the sample user by the user, where the risk label specifically includes a high risk or a low risk, so as to perform model training according to the classification sample to which the risk label is added, so as to obtain a classifier, and thus it can be known that the classifier includes a corresponding relationship between the feature subset and the classification label. Therefore, after the feature subset 1 of the user to be tested is input into the classifier, the classification sample 2 with the highest similarity to the feature subset 1 is identified, and the feature subset 2 and the risk label 2 are included in the classification sample 2, so that the similarity between the feature subset 1 and the feature subset 2 is the highest, and because the feature subset 2 corresponds to the high risk, the financing risk result corresponding to the feature subset 1 can be determined to be the high risk. Of course, this embodiment is merely an example, and the specific manner of obtaining the financing risk result based on the feature subset is not limited.

In the embodiment, the feature extraction model is used for screening the supply chain features of the user to be tested, which are acquired by different links, according to the unified standard to acquire the feature subset associated with financing, so that the interference features irrelevant to the financing of the user are deleted, and when the screened feature subset is used for financing risk assessment, the financing risk result of the user to be tested can be accurately acquired, so that the financing risk coefficient of a financial institution is reduced.

Example two

Fig. 2 is a flowchart of a financing risk identification method according to a second embodiment of the present invention, where this embodiment is based on the foregoing embodiment, and after a financing risk result is obtained, a risk alarm is performed when it is determined that the financing risk result is a high risk, as shown in fig. 2, the method includes:

step S201, obtaining a supply chain characteristic of a user to be tested.

Optionally, the obtaining of the supply chain characteristics of the user to be tested includes: acquiring supply chain financing information of a user to be tested, wherein the supply chain financing information comprises registration basic data, credit investigation data and transaction data; preprocessing supply chain financing information of a user to be detected, and acquiring the preprocessed supply chain financing information; and performing feature extraction on the preprocessed supply chain financing information by adopting feature engineering to obtain supply chain features.

Step S202, the supply chain characteristics of the user to be tested are screened through a pre-trained characteristic extraction model, and a characteristic subset related to financing is obtained.

Optionally, before performing feature extraction on the supply chain financing information through a pre-trained feature extraction model, the method further includes: acquiring supply chain characteristics of sample users, wherein the supply chain characteristics of the sample users consist of a supply chain training set of the sample users and a supply chain testing set of the sample users; training a supply chain training set of a sample user by adopting a genetic algorithm to obtain an initial model; and testing the initial model by adopting a supply chain test set of a sample user, and taking the initial model passing the test as a feature extraction model.

Step S203, identifying the feature subset through a pre-trained classifier to obtain a financing risk result.

And step S204, performing risk alarm when the financing risk result is determined to be high risk.

Specifically, when it is determined that the financing risk result for the enterprise user a is high risk, it indicates that there is a record of losing credit in the previous credit investigation of the enterprise user a, or there is a case that payment is overdue in the transaction with other core enterprises, at this time, if the financial institution puts away money for the enterprise user a, the probability that the payment will not be received is very high, at this time, an alarm prompt is generated, for example, "the current user is a high risk user, please pay attention to the verification", the alarm prompt may be specifically in a voice form or an image form, and a specific display form of the alarm prompt is not limited in this embodiment.

It should be noted that, the financial institution may perform focus attention check on the user according to the alarm, and when it is determined that the user has a payment risk through the check, the release of the payment to the enterprise user a may be terminated, thereby reducing the financing risk coefficient.

In the embodiment, the feature extraction model is used for screening the supply chain features of the user to be detected, which are acquired by aiming at different links, according to the unified standard to acquire the feature subset associated with financing, so that the interference features irrelevant to the financing of the user are deleted, and when the screened feature subset is used for financing risk assessment, the financing risk result of the user to be detected can be accurately acquired, so that the financing risk coefficient of a financial institution is reduced. And when the financing risk result is determined to be high risk, risk alarming is carried out, and the financial institution can carry out focus attention check on the user according to the alarming so as to further reduce the financing risk coefficient.

EXAMPLE III

Fig. 3 is a schematic structural diagram of an identification apparatus for financing risk according to a third embodiment of the present invention. As shown in fig. 3, the apparatus includes: a supply chain feature acquisition module 310, a feature subset acquisition module 320, and a financing risk result acquisition module 330.

A supply chain characteristic obtaining module 310, configured to obtain a supply chain characteristic of a user to be tested;

the feature subset acquisition module 320 is configured to screen supply chain features of a user to be tested through a pre-trained feature extraction model, and acquire a feature subset associated with financing;

the financing risk result obtaining module 330 is configured to obtain a financing risk result by identifying the feature subset through a pre-trained classifier, where the financing risk result includes a high risk or a low risk.

Optionally, the supply chain characteristic obtaining module is configured to obtain supply chain financing information of the user to be tested,

wherein, the supply chain financing information comprises registration basic data, credit investigation data and transaction data;

preprocessing supply chain financing information of a user to be detected to obtain the preprocessed supply chain financing information;

and performing feature extraction by adopting feature engineering aiming at the preprocessed supply chain financing information to obtain supply chain features.

Optionally, the apparatus further includes a feature extraction model training module, configured to obtain supply chain features of the sample user, where the supply chain features of the sample user are formed by a supply chain training set of the sample user and a supply chain test set of the sample user;

training a supply chain training set of a sample user by adopting a genetic algorithm to obtain an initial model;

and testing the initial model by adopting a supply chain test set of a sample user, and taking the initial model passing the test as a feature extraction model.

Optionally, the feature subset obtaining module is configured to encode supply chain features of the user to be tested to obtain a chromosome;

inputting each chromosome into a pre-trained feature extraction model, and acquiring the optimal chromosome corresponding to the optimal fitness when the iteration times are reached;

and decoding the optimal chromosome to obtain the feature subset.

Optionally, the apparatus further includes a classifier training module, configured to obtain a feature subset of the sample user;

adding a risk label to the feature subset of the sample user to obtain a classification sample, wherein the risk label comprises high risk or low risk;

and training according to the classification samples to obtain a classifier, wherein the classifier comprises the corresponding relation between the feature subset and the risk label.

Optionally, the financing risk result obtaining module is configured to input the feature subset into the classifier;

determining a classification sample with the highest similarity with the feature subset through a classifier;

and acquiring a risk label corresponding to the classification sample with the highest similarity, and taking the corresponding risk label as a financing risk result.

Optionally, the apparatus further comprises an alarm module for alarming risk when it is determined that the financing risk result is a high risk.

The financing risk identification device provided by the embodiment of the invention can execute the financing risk identification method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

Example four

FIG. 4 shows a schematic block diagram of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 4, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 may also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 11 performs the various methods and processes described above, such as a financing risk identification method.

In some embodiments, the financing early warning method for a crop may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When loaded into RAM 13 and executed by processor 11, the computer program may perform one or more of the steps of the financing early warning method for crops described above. Alternatively, in other embodiments, processor 11 may be configured to perform the financing risk identification method by any other suitable means (e.g., by way of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on 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 or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.

The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for identifying a financing risk, comprising:

acquiring supply chain characteristics of a user to be detected;

2. The method of claim 1, wherein the obtaining supply chain characteristics of the user under test comprises:

acquiring supply chain financing information of a user to be tested, wherein the supply chain financing information comprises registration basic data, credit investigation data and transaction data;

preprocessing the supply chain financing information of the user to be detected to obtain the preprocessed supply chain financing information;

and performing feature extraction on the preprocessed supply chain financing information by adopting feature engineering to obtain the supply chain features.

3. The method of claim 1, wherein prior to feature extracting the supply chain financing information by a pre-trained feature extraction model, further comprising:

obtaining supply chain characteristics of sample users, wherein the supply chain characteristics of the sample users comprise a supply chain training set of the sample users and a supply chain testing set of the sample users;

training the supply chain training set of the sample user by adopting a genetic algorithm to obtain an initial model;

and testing the initial model by adopting the supply chain test set of the sample user, and taking the initial model passing the test as the feature extraction model.

4. The method of claim 3, wherein the filtering supply chain features of the user to be tested through a pre-trained feature extraction model to obtain a feature subset associated with financing comprises:

encoding the supply chain characteristics of the user to be detected to obtain a chromosome;

inputting each chromosome into the pre-trained feature extraction model, and obtaining the optimal chromosome corresponding to the optimal fitness when the iteration times are reached;

and decoding the optimal chromosome to obtain the feature subset.

5. The method of claim 1, wherein before identifying the subset of features by the pre-trained classifier to obtain a financing risk result, the method further comprises:

acquiring a characteristic subset of a sample user;

and training according to the classification sample to obtain the classifier, wherein the classifier comprises the corresponding relation between the feature subset and the risk label.

6. The method of claim 1, wherein identifying the subset of features by a pre-trained classifier to obtain financing risk results comprises:

inputting the subset of features into the classifier;

determining, by the classifier, the classified sample with the highest similarity to the feature subset;

and acquiring a risk label corresponding to the classification sample with the highest similarity, and taking the corresponding risk label as the financing risk result.

7. The method of claim 1, wherein after identifying the subset of features by the pre-trained classifier to obtain a financing risk result, the method further comprises:

and when the financing risk result is determined to be high risk, carrying out risk alarm.

8. An apparatus for identifying financing risk, comprising:

the supply chain characteristic acquisition module is used for acquiring the supply chain characteristics of the user to be detected;

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A computer-readable storage medium, having stored thereon computer instructions for causing a processor, when executed, to implement the method of any one of claims 1-7.