Financial risk behavior assessment method and device, equipment and medium
By using neural network models to extract user feature information and cluster analysis, financial risk behavior is evaluated, and the problem of low accuracy of traditional methods is solved, and more efficient identification and evaluation of financial risk behavior is achieved.
Patent Information
- Application Number
- CN202411708582.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-26
- Publication Date
- 2025-03-04
AI Technical Summary
Traditional financial risk behavior assessment methods rely on manual review and rule matching, resulting in reduced accuracy and it is difficult to effectively identify illegal trading behaviors in the financial market.
By obtaining user information and transaction information, the user feature information is extracted using the preset neural network model, and the users are clustered to form a target cluster. Then, the financial risk behavior in each target cluster is evaluated based on the transaction information between the pair of users.
It improves the accuracy of financial risk behavior assessment and can more effectively identify target clusters with illegal transactions, thereby ensuring the fairness and stability of the financial market.
Smart Images
Figure CN119558857A_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present invention relate to the field of financial security technology, and in particular, to a method, device, equipment and medium for evaluating financial risk behavior. Background Art
[0002] At present, financial risk behavior in the financial field is a serious problem, which will not only cause huge economic losses to financial institutions and individuals, but also undermine the fairness and stability of the financial market. Therefore, the evaluation method of financial risk behavior is crucial.
[0003] Traditional assessment methods for financial risk behaviors mainly rely on manual review and rule matching. As financial risk behaviors become more diverse and hidden, the problem of reduced accuracy has gradually been exposed. Summary of the invention
[0004] The embodiments of the present invention provide a method, device, equipment and medium for evaluating financial risk behavior, which can improve the accuracy of evaluation.
[0005] In a first aspect, an embodiment of the present invention provides a method for evaluating financial risk behavior, comprising:
[0006] Obtaining user information corresponding to multiple users and transaction information between two users; wherein the user information includes user name and user account; the transaction information includes transaction amount, transaction number, transaction direction, transaction time and transaction serial number;
[0007] Inputting the user information and the transaction information between two users into a preset neural network model to obtain feature information of each user;
[0008] Clustering multiple users according to the feature information to obtain at least one target cluster;
[0009] For each target cluster, the financial risk behaviors in the target cluster are evaluated according to the transaction information between the two users; wherein the financial risk behaviors include the existence of illegal transactions and the absence of illegal transactions.
[0010] In a second aspect, an embodiment of the present invention further provides a financial risk behavior assessment device, the device comprising:
[0011] An information acquisition module is used to acquire user information corresponding to multiple users and transaction information between two users; wherein the user information includes user name and user account; the transaction information includes transaction amount, transaction number, transaction direction, transaction time and transaction serial number;
[0012] A feature information acquisition module, used to input the user information and the transaction information between two users into a preset neural network model to obtain feature information of each user;
[0013] A clustering module, used to cluster multiple users according to the feature information to obtain at least one target cluster;
[0014] The financial risk behavior assessment module is used to assess the financial risk behavior in each target cluster based on the transaction information between the two users; wherein the financial risk behavior includes the presence of illegal transactions and the absence of illegal transactions.
[0015] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:
[0016] at least one processor; and
[0017] a memory communicatively connected to the at least one processor; wherein,
[0018] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for evaluating financial risk behavior described in an embodiment of the present invention.
[0019] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for evaluating financial risk behavior described in the embodiment of the present invention when executed.
[0020] In a fifth aspect, an embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the method for evaluating financial risk behavior described in an embodiment of the present invention.
[0021] The embodiments of the present invention disclose a method, apparatus, device and medium for evaluating financial risk behaviors, including: obtaining user information corresponding to multiple users and transaction information between two users; wherein the user information includes a user name and a user account; the transaction information includes a transaction amount, a number of transactions, a transaction direction, a transaction time and a transaction serial number; inputting the user information and the transaction information between two users into a preset neural network model to obtain feature information of each user; clustering the multiple users according to the feature information to obtain at least one target cluster; for each target cluster, evaluating the financial risk behaviors in the target cluster according to the transaction information between two users; wherein the financial risk behaviors include the presence of illegal transactions and the absence of illegal transactions. The above technical solution specifically considers the impact of user information and transaction information on financial risk behavior, thereby obtaining user information corresponding to multiple users and transaction information between two users; at the same time, the user information and transaction information between two users are input into the preset neural network model. Since the preset neural network model has a strong feature extraction capability, the feature information of each user can be accurately extracted from the user information and the transaction information between two users; and, according to the feature information of each user, multiple users are clustered to obtain at least one target cluster, which can improve the accuracy of clustering; finally, for each target cluster obtained by clustering, the financial risk behavior in the target cluster is evaluated according to the transaction information between two users, which can improve the accuracy of financial risk behavior evaluation. Compared with the prior art, the technical solution provided by this embodiment can accurately extract the feature information of each user from the user information and the transaction information between two users, and cluster multiple users according to the user's feature information, which can improve the accuracy of clustering, and then improve the accuracy of financial risk behavior evaluation, thereby ensuring the fairness and stability of the financial market. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] Figure 1 It is a flow chart of a method for evaluating financial risk behavior in Embodiment 1 of the present invention;
[0023] Figure 2 It is a flow chart of a method for evaluating financial risk behavior in Embodiment 2 of the present invention;
[0024] Figure 3 It is a structural schematic diagram of a financial risk behavior assessment device in Embodiment 3 of the present invention;
[0025] Figure 4 It is a structural schematic diagram of an electronic device in Embodiment 4 of the present invention. DETAILED DESCRIPTION
[0026] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.
[0027] Embodiment 1
[0028] Figure 1 This is a flowchart of a method for evaluating financial risk behavior provided in the first embodiment of the present invention. This embodiment is applicable to the situation of evaluating financial risk behavior. The method can be executed by a financial risk behavior evaluation device, which can be implemented in the form of software and / or hardware. Optionally, it can be implemented by an electronic device, which can be a mobile terminal, a PC or a server. Specifically, it includes the following steps:
[0029] S110: Obtain user information corresponding to multiple users and transaction information between any two users.
[0030] In this embodiment, the user can be understood as a user of a financial institution, and the user information can be understood as key information related to the user, such as user information can include a user name and a user account. Further, the application scenario of this embodiment can be a transaction scenario between users, and the transaction information can be understood as information generated when a transaction occurs between two users, such as transaction information can include transaction amount, transaction number, transaction direction, transaction time, and transaction serial number. Among them, the transaction number can be understood as the number of transfers between two users; illustratively, when the transaction direction is 'C', it indicates the credit side, and when it is 'D', it indicates the debit side; the transaction serial number can be understood as a number that uniquely identifies each transaction.
[0031] Optionally, the method of obtaining user information corresponding to multiple users and transaction information between two users may be: obtaining viewing authority of a database in a financial institution; and obtaining user information corresponding to multiple users and transaction information between two users from the database.
[0032] S120: Input user information and transaction information between two users into a preset neural network model to obtain feature information of each user.
[0033] In this embodiment, the preset neural network model is a pre-trained model with strong feature extraction capabilities, and can accurately extract feature information of each user from user information and transaction information between two users. The feature information of the user can be the user information of the user, the user information of the user's neighbor users, and the transaction information between the user and its neighbor users. The neighbor users of the user can be understood as users who have transactions with the user. Exemplarily, assuming that the users who have transactions with user a are user b and user c, the feature information of user a can be the user information of user a, the user information of user b and user c, the transaction information between user a and user b, and the transaction information between user a and user c.
[0034] Specifically, user information and transaction information between two users are input into a preset neural network model. The local transition function in the preset neural network model can be used to realize the fusion of the user information of the user, the user information of the user's neighbor users, and the transaction information between the user and its neighbor users, so as to obtain the characteristic information of the user.
[0035] S130: Cluster multiple users according to feature information to obtain at least one target cluster.
[0036] In this embodiment, the target cluster includes at least two users. Optionally, any clustering algorithm may be used to cluster multiple users, such as K-Means clustering algorithm.
[0037] In this embodiment, one implementation method of clustering multiple users according to feature information to obtain at least one target cluster can be described as the following steps:
[0038] a1) obtaining multiple clustering methods, wherein the number of clusters between the clustering methods is different;
[0039] In this embodiment, the number of clusters can be understood as the number of different clusters obtained after dividing multiple users by a clustering algorithm. Further, before clustering multiple users, the number of clusters, ie, the number of clusters, needs to be determined in advance.
[0040] Exemplarily, the multiple clustering methods may be clustering method 1, clustering method 2, ..., clustering method n; wherein the numbers of clusters corresponding to them are: k1, k2, ..., kn.
[0041] b1) For each clustering method, multiple users are clustered according to feature information to obtain clusters corresponding to the clustering method;
[0042] Exemplarily, taking clustering method 1 as an example, clustering method 1 is adopted, and multiple users are clustered according to feature information to obtain k1 clusters corresponding to clustering method 1.
[0043] c1) determining the clustering effect analysis information of the clusters corresponding to each clustering method;
[0044] In this embodiment, the clustering effect analysis information is used to evaluate the quality of the clustering results obtained after the clustering algorithm clusters multiple users. In this embodiment, a clustering effect evaluation index can be used to determine the clustering effect analysis information of the clusters corresponding to each clustering method. Exemplarily, the clustering effect evaluation index can be the Davies-Bouldin Index (DBI), which measures the clustering quality based on the intra-cluster distance and the inter-cluster distance. The smaller the value, the better the clustering effect.
[0045] Exemplarily, the clustering effect analysis information of the clusters corresponding to clustering method 1, clustering method 2, ..., clustering method n determined by DBI are d1, d2, ..., dn respectively.
[0046] d1) Determine the target clustering method based on the clustering effect analysis information, and use the cluster corresponding to the target clustering method as the target cluster.
[0047] In this embodiment, the implementation method of determining the target clustering method based on the clustering effect analysis information can be: the clustering method corresponding to the minimum clustering effect analysis information is used as the target clustering method. Among them, the clustering effect of the clustering method corresponding to the minimum clustering effect analysis information is the best, and the clustering method with the best clustering effect is selected as the target clustering method, which can improve the accuracy of clustering.
[0048] Exemplarily, assuming that the clustering effect analysis information d2 of clustering method 2 is the minimum value among the n clustering effect analysis information, clustering method 2 is used as the target clustering method, and the k2 clusters corresponding to clustering method 2 are used as target clusters.
[0049] S140: For each target cluster, evaluate the financial risk behavior in the target cluster based on transaction information between two users.
[0050] In this embodiment, the financial risk behavior includes the presence of illegal transactions and the absence of illegal transactions. Further, after obtaining at least one target cluster, it is necessary to determine whether there is an illegal transaction in each target cluster.
[0051] Optionally, the method of evaluating the financial risk behaviors in the target cluster according to the transaction information between two users may be: evaluating the financial risk behaviors in the target cluster according to the transaction amount and the number of transactions in the transaction information between two users.
[0052] The technical solution of this embodiment obtains user information corresponding to multiple users and transaction information between two users; inputs the user information and transaction information between two users into a preset neural network model to obtain feature information of each user; clusters multiple users according to the feature information to obtain at least one target cluster; for each target cluster, evaluates the financial risk behavior in the target cluster according to the transaction information between two users. The above technical solution specifically considers the impact of user information and transaction information on financial risk behavior, thereby obtaining user information corresponding to multiple users and transaction information between two users; at the same time, inputs the user information and transaction information between two users into the preset neural network model, and since the preset neural network model has a strong feature extraction capability, the feature information of each user can be accurately extracted from the user information and the transaction information between two users; and, clusters multiple users according to the feature information of each user to obtain at least one target cluster, which can improve the accuracy of clustering; finally, for each target cluster obtained by clustering, the financial risk behavior in the target cluster is evaluated according to the transaction information between two users, which can improve the accuracy of financial risk behavior evaluation. The technical solution provided in this embodiment can accurately extract the characteristic information of each user from the user information and the transaction information between two users, and cluster multiple users according to the user's characteristic information, which can improve the accuracy of clustering and further improve the accuracy of financial risk behavior assessment, thereby ensuring the fairness and stability of the financial market.
[0053] Embodiment 2
[0054] Figure 2 This is a flow chart of a method for evaluating financial risk behavior provided in Embodiment 2 of the present invention. Based on the above embodiment, the method includes the following steps:
[0055] S210: Obtain user information corresponding to multiple users and transaction information between any two users.
[0056] S220: construct a transaction knowledge graph based on user information and transaction information between two users.
[0057] In this embodiment, the transaction knowledge graph represents the user information of each user and the transaction information between two users in the form of a graph structure, which can clearly show the transaction relationship between users.
[0058] In this embodiment, one implementation method of constructing a transaction knowledge graph based on user information and transaction information between two users can be described as the following steps:
[0059] a2) determining multiple transaction triplets based on user information and transaction information between two users;
[0060] In this embodiment, the transaction triplet includes user information of the first user, user information of the second user, and transaction information between the first user and the second user.
[0061] Exemplarily, assuming that there is a transaction between user a and user c, user a is the first user, and user c is the second user, then the user information of user a, the user information of user c, and the transaction information between user a and user c are determined as a transaction triplet; similarly, for transactions between other pairs of users, the above method is also used to determine the transaction triplet, thereby obtaining multiple transaction triplets.
[0062] b2) Construct a transaction knowledge graph based on multiple transaction triples.
[0063] In this embodiment, a knowledge graph construction tool may be used to process multiple transaction triples to obtain a transaction knowledge graph, such as a Neo4j graph database.
[0064] S230: Input the transaction knowledge graph into a preset neural network model to obtain feature information of each user in the transaction knowledge graph.
[0065] In this embodiment, the preset neural network model may be a graph neural network model.
[0066] S240: Cluster multiple users according to feature information to obtain at least one target cluster.
[0067] S250: For each target cluster, extract the transaction amount and transaction number from the transaction information between two users to obtain multiple transaction amounts and multiple transaction numbers.
[0068] In this embodiment, the transaction amount in the transaction information between every two users is extracted to obtain multiple transaction amounts; the transaction number in the transaction information between every two users is extracted to obtain multiple transaction numbers.
[0069] S260: Determine an average value of multiple transaction amounts to obtain an average transaction amount.
[0070] In this embodiment, an average value is taken for multiple transaction amounts, and the average value of the multiple transaction amounts is taken as the average transaction amount.
[0071] S270. Evaluate the financial risk behavior in the target cluster based on the sum of multiple transaction times and the average transaction amount.
[0072] Among them, financial risk behaviors include the existence of illegal transactions and the absence of illegal transactions.
[0073] In this embodiment, one implementation method of evaluating the financial risk behavior in the target cluster based on the sum of multiple transaction times and the average transaction amount can be described as: if the average transaction amount is greater than a first set threshold and the sum of multiple transaction times is greater than a second set threshold, then the financial risk behavior in the target cluster is the existence of illegal transactions.
[0074] Continuing with the above description, the first set threshold and the second set threshold are extracted set values. Specifically, if the average transaction amount is greater than the first set threshold and the sum of multiple transaction times is less than or equal to the second set threshold, then the financial risk behavior in the target cluster is that there is no illegal transaction; if the average transaction amount is less than or equal to the first set threshold and the sum of multiple transaction times is greater than the second set threshold, then the financial risk behavior in the target cluster is that there is no illegal transaction; if the average transaction amount is less than or equal to the first set threshold and the sum of multiple transaction times is less than or equal to the second set threshold, then the financial risk behavior in the target cluster is that there is no illegal transaction.
[0075] The technical solution of this embodiment obtains user information corresponding to multiple users and transaction information between two users; constructs a transaction knowledge graph based on the user information and transaction information between two users; inputs the transaction knowledge graph into a preset neural network model to obtain feature information of each user in the transaction knowledge graph; clusters multiple users according to the feature information to obtain at least one target cluster; for each target cluster, extracts the transaction amount and transaction number from the transaction information between two users to obtain multiple transaction amounts and multiple transaction numbers; determines the average of multiple transaction amounts to obtain an average transaction amount; and evaluates the financial risk behavior in the target cluster based on the sum of multiple transaction numbers and the average transaction amount. The above technical scheme specifically considers the impact of user information and transaction information on financial risk behavior, thereby obtaining user information corresponding to multiple users and transaction information between two users; at the same time, a transaction knowledge graph is constructed based on user information and transaction information between two users, which can clearly show the transaction relationship between users in the form of a graph structure; then, the transaction knowledge graph is input into a preset neural network model, wherein the preset neural network model is a graph neural network model, and the graph neural network model can accurately extract the characteristic information of each user from the transaction knowledge graph in the form of a graph structure; and, according to the characteristic information of each user, multiple users are clustered to obtain at least one target cluster, which can improve the accuracy of clustering; then, considering the impact of the transaction amount and transaction number in the transaction information between two users on the financial risk behavior for each target cluster, the transaction amount and transaction number in the transaction information between two users are extracted to obtain multiple transaction amounts and multiple transaction numbers; finally, the average value of the multiple transaction amounts is determined, and the financial risk behavior in the target cluster is evaluated based on the sum of the multiple transaction numbers and the average transaction amount, which can improve the accuracy of the financial risk behavior evaluation. The technical solution provided in this embodiment constructs a transaction knowledge graph based on user information and transaction information between two users, which can clearly display the transaction relationship between users in the form of a graph structure. Then, the graph neural network model can accurately extract the characteristic information of each user from the transaction knowledge graph in the form of a graph structure, and then cluster multiple users according to the characteristic information of each user, which can improve the accuracy of clustering and further improve the accuracy of financial risk behavior assessment, thereby ensuring the fairness and stability of the financial market.
[0076] Embodiment 3
[0077] Figure 3 This is a schematic diagram of the structure of a financial risk behavior assessment device provided by Embodiment 3 of the present invention, such as Figure 3 As shown, the device comprises:
[0078] The information acquisition module 310 is used to acquire user information corresponding to multiple users and transaction information between two users; wherein the user information includes user name and user account; the transaction information includes transaction amount, transaction number, transaction direction, transaction time and transaction serial number;
[0079] The feature information acquisition module 320 is used to input the user information and the transaction information between two users into a preset neural network model to obtain the feature information of each user;
[0080] A clustering module 330, configured to cluster multiple users according to the feature information to obtain at least one target cluster;
[0081] The financial risk behavior assessment module 340 is used to assess the financial risk behavior in each target cluster according to the transaction information between the two users; wherein the financial risk behavior includes the presence of illegal transactions and the absence of illegal transactions.
[0082] Optionally, the feature information obtaining module 320 may specifically include:
[0083] A transaction knowledge graph construction unit, configured to construct a transaction knowledge graph based on the user information and the transaction information between the two users;
[0084] A feature information acquisition unit is used to input the transaction knowledge graph into a preset neural network model to obtain feature information of each user in the transaction knowledge graph; wherein the preset neural network model is a graph neural network model.
[0085] Optionally, the transaction knowledge graph construction unit may be specifically used for:
[0086] Determine a plurality of transaction triplets according to the user information and the transaction information between the two users; wherein the transaction triplets include the user information of the first user, the user information of the second user, and the transaction information between the first user and the second user;
[0087] A transaction knowledge graph is constructed according to the multiple transaction triples.
[0088] Optionally, the clustering module 330 may be specifically used for:
[0089] Obtain multiple clustering methods; wherein the number of clusters between each clustering method is different;
[0090] For each clustering method, clustering multiple users according to the characteristic information to obtain a cluster corresponding to the clustering method;
[0091] Determine the clustering effect analysis information of the clusters corresponding to each clustering method;
[0092] A target clustering method is determined based on the clustering effect analysis information, and a cluster corresponding to the target clustering method is used as a target cluster.
[0093] Optionally, the financial risk behavior assessment module 340 may specifically include:
[0094] An extraction unit, used to extract the transaction amount and transaction number from the transaction information between the two users, and obtain multiple transaction amounts and multiple transaction numbers;
[0095] an average transaction amount determination unit, configured to determine an average of the plurality of transaction amounts to obtain an average transaction amount;
[0096] A risk assessment unit is used to assess the financial risk behavior in the target cluster based on the sum of multiple transaction times and the average transaction amount.
[0097] Optionally, the risk assessment unit may be specifically used for:
[0098] If the average transaction amount is greater than a first set threshold and the sum of multiple transaction times is greater than a second set threshold, the financial risk behavior in the target cluster is illegal transactions.
[0099] The above device can execute the methods provided by all the above embodiments of the present invention, and has the corresponding functional modules and beneficial effects of executing the above methods. For technical details not described in detail in this embodiment, please refer to the methods provided by all the above embodiments of the present invention.
[0100] Embodiment 4
[0101] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.
[0102] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate 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 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0103] 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, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0104] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for evaluating financial risk behavior.
[0105] In some embodiments, the method for evaluating financial risk behavior may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for evaluating financial risk behavior described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for evaluating financial risk behavior in any other appropriate manner (e.g., by means of firmware).
[0106] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0107] Computer programs 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, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0108] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, 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 portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0109] To provide interaction with a user, the systems and techniques described herein may 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 the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may 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 input, voice input, or tactile input).
[0110] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0111] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0112] An embodiment of the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements a method for evaluating financial risk behavior as provided in any embodiment of the present application.
[0113] In the process of implementation, the computer program product can be written in one or more programming languages or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).
[0114] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.
[0115] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution 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 evaluating financial risk behavior, characterized in that: include: Obtaining user information corresponding to multiple users and transaction information between two users; wherein the user information includes user name and user account; the transaction information includes transaction amount, transaction number, transaction direction, transaction time and transaction serial number; Inputting the user information and the transaction information between two users into a preset neural network model to obtain feature information of each user; Clustering multiple users according to the feature information to obtain at least one target cluster; For each target cluster, the financial risk behaviors in the target cluster are evaluated according to the transaction information between the two users; wherein the financial risk behaviors include the existence of illegal transactions and the absence of illegal transactions.
2. The method according to claim 1, characterized in that The user information and the transaction information between two users are input into a preset neural network model to obtain characteristic information of each user, including: Building a transaction knowledge graph based on the user information and the transaction information between the two users; The transaction knowledge graph is input into a preset neural network model to obtain feature information of each user in the transaction knowledge graph; wherein the preset neural network model is a graph neural network model.
3. The method according to claim 2, characterized in that Constructing a transaction knowledge graph based on the user information and the transaction information between two users, including: Determine a plurality of transaction triplets according to the user information and the transaction information between the two users; wherein the transaction triplets include the user information of the first user, the user information of the second user, and the transaction information between the first user and the second user; A transaction knowledge graph is constructed according to the multiple transaction triples.
4. The method according to claim 1, characterized in that: Clustering multiple users according to the feature information to obtain at least one target cluster includes: Obtain multiple clustering methods; wherein the number of clusters between each clustering method is different; For each clustering method, clustering multiple users according to the characteristic information to obtain a cluster corresponding to the clustering method; Determine the clustering effect analysis information of the clusters corresponding to each clustering method; A target clustering method is determined based on the clustering effect analysis information, and a cluster corresponding to the target clustering method is used as a target cluster.
5. The method according to claim 1, characterized in that Evaluating the financial risk behavior in the target cluster according to the transaction information between the two users, including: Extracting the transaction amount and transaction number from the transaction information between the two users, and obtaining multiple transaction amounts and multiple transaction numbers; Determine an average of the multiple transaction amounts to obtain an average transaction amount; The financial risk behavior in the target cluster is evaluated based on the sum of multiple transaction times and the average transaction amount.
6. The method according to claim 5, characterized in that Evaluating the financial risk behavior in the target cluster based on the sum of multiple transaction times and the average transaction amount includes: If the average transaction amount is greater than a first set threshold and the sum of multiple transaction times is greater than a second set threshold, the financial risk behavior in the target cluster is illegal transactions.
7. A financial risk behavior assessment device, characterized in that: include: An information acquisition module is used to acquire user information corresponding to multiple users and transaction information between two users; wherein the user information includes user name and user account; the transaction information includes transaction amount, transaction number, transaction direction, transaction time and transaction serial number; A feature information acquisition module, used to input the user information and the transaction information between two users into a preset neural network model to obtain feature information of each user; A clustering module, used to cluster multiple users according to the feature information to obtain at least one target cluster; The financial risk behavior assessment module is used to assess the financial risk behavior in each target cluster based on the transaction information between the two users; wherein the financial risk behavior includes the presence of illegal transactions and the absence of illegal transactions.
8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for evaluating financial risk behavior according to any one of claims 1-6.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for evaluating financial risk behavior according to any one of claims 1 to 6 when executed.
10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method for evaluating financial risk behavior according to any one of claims 1 to 6.