Financial risk data processing method and device, storage medium and electronic equipment

Abstract

The invention discloses a financial risk data processing method and device, a storage medium and electronic equipment, and relates to the field of financial science and technology and the field of information security. The method comprises the following steps: determining a system risk value and a regulation and control parameter from financial risk data of a financial transaction system; in the iteration process of the particle swarm, determining an inertia factor and a learning factor which change along with continuous iteration of the particle swarm; and determining a target control coefficient for the financial transaction system according to the minimum value of the target function. According to the method and the device, the problem that the analysis result of the financial risk data is inaccurate due to the defects that the particle swarm algorithm is easy to fall into local optimum and the later convergence speed is extremely slow when the particle swarm algorithm is used for analyzing the financial risk data in the prior art is solved; and the risk factors of the financial transaction system cannot be timely and accurately checked, so that the transaction risk is uncontrollable.

Description

Technical Field

[0001] The present invention relates to the fields of financial technology and information security, and in particular to a method, device, storage medium and electronic device for processing financial risk data. Background Art

[0002] Financial risk refers to the possibility that a financial entity may suffer economic losses due to its own or external factors, including credit risk, market risk, liquidity risk, operational risk, legal risk, business risk, etc. All of the above risks are complex, uncertain and random, and have a significant impact on financial markets and financial institutions. Therefore, the financial industry has an increasingly urgent need for risk management.

[0003] At present, the risk assessment models commonly used in the financial industry are the following three: decision tree, support vector machine and prediction method based on deep learning neural network. In addition, there are many algorithms in the industry for solving the optimal solution of the model. Among them, the particle swarm algorithm has the advantages of easy convergence, few related parameters, and few restrictions on the objective function, which is suitable for use in solving financial risk systems. However, when using the particle swarm algorithm to analyze financial risk data in the prior art, the particle swarm algorithm is prone to fall into the local optimum and the convergence speed is extremely slow in the later stage, resulting in inaccurate analysis results for financial risk data, which in turn makes it impossible to timely and accurately identify the risk factors of the financial transaction system, resulting in uncontrollable transaction risks.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The main purpose of the present application is to provide a method, device, storage medium and electronic device for processing financial risk data, so as to at least solve the technical problem in the prior art of using a particle swarm algorithm to analyze financial risk data, that is, when the particle swarm algorithm is used to analyze financial risk data, the analysis results of the financial risk data are inaccurate due to the defects that the particle swarm algorithm is prone to fall into local optimality and has an extremely slow convergence speed in the later stage.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of an embodiment of the present application, a method for processing financial risk data is provided, comprising: determining a system risk value and a control parameter from the financial risk data of a financial transaction system, wherein the system risk value represents the risk value of the financial transaction system caused by data interference, and the control parameter is used to adjust the risk value; in the iterative process of a particle swarm, determining an inertia factor and a learning factor that change with the continuous iteration of the particle swarm, wherein the particle swarm is used to determine the minimum value of an objective function based on the inertia factor and the learning factor, the inertia factor is a numerical value that changes nonlinearly, the learning factor is a value that changes according to the evolution speed and aggregation degree of the particle swarm, and the objective function is used to determine the volatility of the system risk value; determining a target control coefficient for the financial transaction system based on the minimum value of the target function, wherein the target control coefficient is used as a reference threshold for financial institutions when regulating the financial transaction system.

[0007] Optionally, determining a system risk value from financial risk data of a financial transaction system comprises: determining a first type of risk value and a second type of risk value from the financial risk data, wherein the first type of risk value represents a transaction risk value caused by interference from data within the financial transaction system, and / or a transaction risk value caused by interference from data outside the financial transaction system; the second type of risk value represents a transaction risk value derived from the first type of risk value; and the first type of risk value and the second type of risk value are used as system risk values.

[0008] Optionally, after determining the system risk value and the control parameters from the financial risk data of the financial transaction system, the method further includes: setting the number of particles in the particle swarm, the current position of each particle, the target position of each particle, the target position of the particle swarm, the flight speed of each particle in the search space, and the upper and lower limits of the flight speed, wherein each particle represents a process for solving the objective function, the current position of each particle represents the progress of the particle in solving the objective function, the target position of each particle represents the minimum value obtained by the particle for the objective function, the target position of the particle swarm represents the minimum value obtained by all particles in the particle swarm for the objective function, and the flight speed of each particle represents the speed at which the particle solves the objective function.

[0009] Optionally, during the iteration process of the particle swarm, an inertia factor that changes with continuous iterations of the particle swarm is determined, including: obtaining a maximum number of iterations, a maximum inertia factor, a minimum inertia factor, and a random speed parameter set for the particle swarm; and determining the inertia factor corresponding to each particle in the particle swarm at the current number of iterations based on the current number of iterations, the maximum number of iterations, the maximum inertia factor, the minimum inertia factor, and the random speed parameter of the particle swarm.

[0010] Optionally, during the iteration process of the particle swarm, a learning factor that changes with the continuous iteration of the particle swarm is determined, including: when the particle swarm performs the nth iteration, determining the aggregation parameter and speed parameter corresponding to the particle swarm at the nth iteration, wherein n is an integer greater than 1, the aggregation parameter is used to quantitatively characterize the aggregation degree of the particle swarm, and the speed parameter is used to quantitatively characterize the iteration speed of the particle swarm; determining the learning factor corresponding to the particle swarm at the nth iteration according to the initialized learning factor, the aggregation parameter and speed parameter corresponding to the particle swarm at the nth iteration, the weight value corresponding to the aggregation parameter, and the weight value corresponding to the speed parameter.

[0011] Optionally, when the particle swarm performs an nth iteration, determining a speed parameter corresponding to the particle swarm at the nth iteration includes: when the particle swarm performs an nth iteration, taking a solution value of the xth particle in the particle swarm to the objective function as a first value, wherein the xth particle is any particle in the particle swarm; when the particle swarm performs an n-1th iteration, taking a solution value of the xth particle in the particle swarm to the objective function as a second value; determining a minimum value and a maximum value between the first value and the second value; and calculating a ratio of a minimum value to a maximum value between the first value and the second value to obtain a speed parameter corresponding to the particle swarm at the nth iteration.

[0012] Optionally, when the particle swarm performs an nth iteration, determining the aggregation parameter corresponding to the particle swarm at the nth iteration includes: after the particle swarm performs an nth iteration, obtaining the solution value of each particle of the particle swarm for the objective function in this iteration process, and calculating the average value of all solution values ​​corresponding to all particles; when the particle swarm performs an nth iteration, taking the solution value of the xth particle in the particle swarm for the objective function as the first value, wherein the xth particle is any particle in the particle swarm; determining the maximum and minimum values ​​among the average value and the first value; calculating the ratio of the average value, the minimum value and the maximum value among the first value, and obtaining the aggregation parameter corresponding to the particle swarm at the nth iteration.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of an embodiment of the present application, a financial risk data processing device is also provided, including: a first determination unit, determining a system risk value and a control parameter from the financial risk data of a financial transaction system, wherein the system risk value represents the risk value caused by data interference to the financial transaction system; the control parameter is used to adjust the risk value; a second determination unit, during the iteration process of the particle swarm, determining an inertia factor and a learning factor that change with the continuous iteration of the particle swarm, wherein the particle swarm is used to determine the minimum value of an objective function based on the inertia factor and the learning factor, the inertia factor is a numerical value that changes nonlinearly, and the learning factor is a value that changes according to the evolution speed and aggregation degree of the particle swarm, and the objective function is used to determine the volatility of the system risk value; a third determination unit, determining a target control coefficient for the financial transaction system based on the minimum value of the target function, wherein the target control coefficient is used as a reference threshold for financial institutions when regulating the financial transaction system.

[0014] According to another aspect of an embodiment of the present application, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above-mentioned method for processing financial risk data.

[0015] According to another aspect of an embodiment of the present application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned method for processing financial risk data.

[0016] According to another aspect of an embodiment of the present application, a computer program product is also provided, including computer instructions, which implement the steps of the above-mentioned method for processing financial risk data when executed by a processor.

[0017] In an embodiment of the present application, first, a system risk value and a control parameter are determined from the financial risk data of the financial transaction system, wherein the system risk value represents the risk value caused by data interference in the financial transaction system, and the control parameter is used to adjust the risk value. Then, in the iterative process of the particle swarm, an inertia factor and a learning factor that change with the continuous iteration of the particle swarm are determined, wherein the particle swarm is used to determine the minimum value of the objective function based on the inertia factor and the learning factor, wherein the inertia factor is a numerical value that changes nonlinearly, and the learning factor is a value that changes according to the evolution speed and aggregation degree of the particle swarm, and the objective function is used to determine the volatility of the system risk value, and then the target control coefficient for the financial transaction system is determined according to the minimum value of the objective function, wherein the target control coefficient is used as a reference threshold for financial institutions when regulating the financial transaction system.

[0018] From the above content, it can be seen that this application first extracts key risk data from the financial transaction system and analyzes the system risk value and control parameters. The system risk value comprehensively reflects the risks caused by the interference of internal and external factors in the financial transaction system, and the control parameters serve as a lever to adjust the risk value. Its optimization selection is the key to this application.

[0019] Subsequently, within the framework of the particle swarm algorithm, this application innovatively and dynamically adjusts the inertia factor and learning factor to adapt to the changing environment during the algorithm iteration process. The inertia factor adopts a nonlinear change strategy to better balance global search and local search, ensuring that the algorithm efficiently explores in the early stages of iteration and converges finely in the later stages of iteration to avoid falling into local optimality. The dynamic adjustment of the learning factor is based on the evolution speed and aggregation degree of the particles. By introducing speed parameters and aggregation parameters, the search range and convergence speed of the particle swarm are accurately controlled to ensure the flexibility and stability of the algorithm during the iteration process.

[0020] In addition, the particle swarm algorithm is used to calculate the minimum value of the objective function, which is directly related to the risk volatility of the financial system. The process of finding the minimum value is essentially to find the best target control coefficient in the control parameter space to achieve the goal of minimizing financial risk.

[0021] It can be seen that through the technical solution of the present application, the purpose of establishing a nonlinear system model of financial risk and optimizing the particle swarm algorithm is achieved, thereby solving the problem that the particle swarm algorithm is prone to fall into local optimality and has an extremely slow convergence speed in the later stage, and the improved particle swarm algorithm is applied to the nonlinear system model of financial risk to achieve the technical effect of improving the ability to prevent and control financial risks, thereby solving the technical problem of inaccurate analysis results of financial risk data when using the particle swarm algorithm to analyze financial risk data in the prior art due to the defect that the particle swarm algorithm is prone to fall into local optimality and has an extremely slow convergence speed in the later stage. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0023] Figure 1 A hardware structure block diagram of a computer terminal for implementing a method for processing financial risk data is shown;

[0024] Figure 2 is a flowchart of an optional method for processing financial risk data according to an embodiment of the present application;

[0025] Figure 3is a flowchart of an optional improved particle swarm algorithm applied in a financial risk model according to an embodiment of the present application;

[0026] Figure 4 is a schematic diagram of a device for processing financial risk data provided in an embodiment of the present application;

[0027] Figure 5 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] It should also be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with relevant laws, regulations and standards, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0031] According to an embodiment of the present application, a method embodiment of a method for processing financial risk data is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0032] It should be noted that a financial risk data processing system can be used as the execution subject of the financial risk data processing method of the embodiment of the present application. It is understandable that the financial risk data processing method provided in the embodiment of the present application can also be executed by other systems or devices, and the embodiment of the present application does not specifically limit this.

[0033] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for processing financial risk data is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0034] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuit may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be fully or partially integrated into any of the other components in the computer terminal 10 (or mobile device). As in the method for processing financial risk data involved in the embodiments of the present application, the data processing circuit serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0035] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the method for processing financial risk data in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the above-mentioned method for processing financial risk data is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0036] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0037] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0038] Under the above operating environment, this application provides Figure 2 The method of processing financial risk data shown. Figure 2 FIG. 1 is a flowchart of an optional method for processing financial risk data according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0039] Step S201, determining the system risk value and control parameters from the financial risk data of the financial transaction system.

[0040] In step S201, the system risk value represents the risk value caused by data interference in the financial transaction system, and the control parameter is used to adjust the risk value.

[0041] Alternatively, the system risk value maps the degree of risk that a financial trading system is exposed to when faced with internal and external data disturbances, and is a key indicator for assessing the robustness of the financial system.

[0042] Optionally, the definition of regulatory parameters aims to provide a flexible adjustment mechanism for the management and control of financial risks, ensuring that the financial system can effectively respond to risks and maintain its stable operation in a dynamic environment.

[0043] Optionally, the system risk value mainly includes X and y, wherein X represents the total system risk value under the impact of internal and external factors in the first stage; y represents the total system risk value of the internal contagion effect of the system in the second stage.

[0044] Optionally, the control parameters mainly include z, where z represents the control of systemic risk by various financial institutions in the third stage.

[0045] Optionally, the nonlinear system model of financial risk is as follows: X: the total risk value of the system under the impact of internal and external factors in the first stage; y: the total risk value of the system under the internal contagion effect in the second stage; z: the regulation of system risk by various financial institutions in the third stage; a, b represent the risk level in the first two stages; c represents the control strength in the third stage, a, b∈R + , c>1.

[0046]

[0047] From formula (1), we can see that when the regulatory intensity c of each financial institution on system risk decreases, the system will gradually lose control and enter a chaotic state, affecting the operation of the system.

[0048] Step S202, during the iteration process of the particle swarm, determining the inertia factor and the learning factor that change with the continuous iteration of the particle swarm.

[0049] In step S202, the particle swarm is used to determine the minimum value of the objective function based on the inertia factor and the learning factor. The inertia factor is a nonlinearly changing value, and the learning factor is a value that changes according to the evolution speed and aggregation degree of the particle swarm. The objective function is used to determine the volatility of the system risk value.

[0050] Optionally, the financial risk data processing system implements a dynamic iteration mechanism to timely adjust the core parameters of the particle swarm algorithm: inertia factor and learning factor, ensuring that the algorithm continues to evolve during the iteration process. During the iteration process of the particle swarm, the nonlinear change characteristics of the inertia factor are combined with the dynamic adjustment strategy of the learning factor to form a unique parameter optimization solution.

[0051] Optionally, as the iterative process progresses, the inertia and learning behavior of the particle motion are gradually tuned to optimize the search process, avoid local optimal traps, and promote the discovery of the global optimal solution.

[0052] Optionally, a dynamic adjustment strategy of the inertia factor ensures that the movement of particles in the search space is guided by historical trajectories while being able to properly explore new areas, thereby accelerating the exploration speed in the early stages of iterations and fine-tuning the search strategy in the later stages of iterations to improve the convergence quality.

[0053] Optionally, the learning factor changes according to the evolution speed and aggregation degree of the particle swarm, dynamically balancing the contribution of individual learning and group experience, ensuring the flexibility and efficiency of the algorithm throughout the iteration process.

[0054] Optionally, the objective function L of the total risk value X takes the root mean square sum of X as the objective function, and the formula is as follows:

[0055] L=ρ1rms(X)+ρ2max(X) (2)

[0056] Where rms represents the mean square error of X, max represents the maximum value of X, and ρ1 and ρ2 are weighting coefficients. That is, achieving the lowest risk of the financial risk system is equivalent to solving the minimum value of the L function. When the risk degree parameters a and b are fixed, the particle swarm algorithm is used to solve the appropriate c value to achieve the minimum solution of the L function.

[0057] Step S203: determining a target control coefficient for the financial transaction system according to the minimum value of the target function.

[0058] In step S203, the target control coefficient is used as a reference threshold for financial institutions when regulating the financial transaction system.

[0059] Optionally, the financial risk data processing system uses a particle swarm algorithm to accurately solve the minimum value of the objective function. Based on the solution, the target control coefficient for a specific financial transaction system can be scientifically determined.

[0060] Optionally, the target control coefficient is used as a reference threshold for financial institutions when regulating financial transaction systems, and comprehensively reflects the optimal strategy for risk regulation of financial transaction systems.

[0061] It can be seen from the contents of steps S201 to S203 that in an embodiment of the present application, first, a system risk value and a control parameter are determined from the financial risk data of the financial transaction system, wherein the system risk value represents the risk value caused by data interference in the financial transaction system, and the control parameter is used to adjust the risk value, and then in the iteration process of the particle swarm, an inertia factor and a learning factor that change with the continuous iteration of the particle swarm are determined, wherein the particle swarm is used to determine the minimum value of the objective function based on the inertia factor and the learning factor, the inertia factor is a numerical value that changes nonlinearly, and the learning factor is a value that changes according to the evolution speed and aggregation degree of the particle swarm, and the objective function is used to determine the volatility of the system risk value, and then the target control coefficient for the financial transaction system is determined according to the minimum value of the target function, wherein the target control coefficient is used as a reference threshold for financial institutions when regulating the financial transaction system.

[0062] From the above content, it can be seen that this application first extracts key risk data from the financial transaction system and analyzes the system risk value and control parameters. The system risk value comprehensively reflects the risks caused by the interference of internal and external factors in the financial transaction system, and the control parameters serve as a lever to adjust the risk value. Its optimization selection is the key to this application.

[0063] Subsequently, within the framework of the particle swarm algorithm, this application innovatively and dynamically adjusts the inertia factor and learning factor to adapt to the changing environment during the algorithm iteration process. The inertia factor adopts a nonlinear change strategy to better balance global search and local search, ensuring that the algorithm efficiently explores in the early stages of iteration and converges finely in the later stages of iteration to avoid falling into local optimality. The dynamic adjustment of the learning factor is based on the evolution speed and aggregation degree of the particles. By introducing speed parameters and aggregation parameters, the search range and convergence speed of the particle swarm are accurately controlled to ensure the flexibility and stability of the algorithm during the iteration process.

[0064] In addition, the particle swarm algorithm is used to calculate the minimum value of the objective function, which is directly related to the risk volatility of the financial system. The process of finding the minimum value is essentially to find the best target control coefficient in the control parameter space to achieve the goal of minimizing financial risk.

[0065] It can be seen that through the technical solution of the present application, the purpose of establishing a nonlinear system model of financial risk and optimizing the particle swarm algorithm is achieved, thereby solving the problem that the particle swarm algorithm is prone to fall into local optimality and has an extremely slow convergence speed in the later stage, and the improved particle swarm algorithm is applied to the nonlinear system model of financial risk to achieve the technical effect of improving the ability to prevent and control financial risks, thereby solving the technical problem of inaccurate analysis results of financial risk data when using the particle swarm algorithm to analyze financial risk data in the prior art due to the defect that the particle swarm algorithm is prone to fall into local optimality and has an extremely slow convergence speed in the later stage.

[0066] In an optional embodiment, the financial risk data processing system first determines a first type of risk value and a second type of risk value from the financial risk data, wherein the first type of risk value represents the transaction risk value caused by data interference within the financial transaction system, and / or the transaction risk value caused by data interference outside the financial transaction system; the second type of risk value represents the transaction risk value derived from the first type of risk value, and then the first type of risk value and the second type of risk value are used as system risk values.

[0067] Optionally, the financial risk data processing system carefully distinguishes and determines two types of risk values ​​from the financial risk data, namely, a first type of risk value (X) and a second type of risk value (y).

[0068] Optionally, the first type of risk value (X) represents the total risk value of the system under the impact of internal and external factors in the first stage; the second type of risk value (y) represents the total risk value of the system due to the internal contagion effect of the system in the second stage.

[0069] Optionally, the system risk value, as the basic unit of risk assessment for financial trading systems, covers the risk quantification indicators caused by data disturbances within the system, as well as the impact of data fluctuations outside the system on trading stability. These two aspects of risk value together constitute a comprehensive description of the inherent risks of the financial trading system.

[0070] Optionally, for the nonlinear system model of financial risk, for example, when a=4, b=8, the total system risk value x changes with the control intensity parameter c, and it can be concluded that when c gradually decreases, the financial system enters an out-of-control state. And, for example, when c is in [4.5, 7], the financial risk system enters a relatively stable movement and is in a relatively stable state. Therefore, solving the appropriate c value is particularly important for the smooth operation of the financial risk system.

[0071] From the above content, it can be seen that the financial risk data processing system can obtain a comprehensive and sophisticated risk assessment system by determining the first and second risk values, and using the first and second risk values ​​as the system risk value. It reflects the multidimensional characteristics of financial transaction system risks and provides a solid data foundation for subsequent risk management and regulatory strategies.

[0072] In an optional embodiment, after determining the system risk value and control parameters from the financial risk data of the financial transaction system, the financial risk data processing system sets the number of particles in the particle swarm, the current position of each particle, the target position of each particle, the target position of the particle swarm, the flight speed of each particle in the search space, and the upper and lower limits of the flight speed, wherein each particle represents a process for solving the objective function, the current position of each particle represents the progress of the particle in solving the objective function, the target position of each particle represents the minimum value obtained by the particle for the objective function, the target position of the particle swarm represents the minimum value obtained by all particles in the particle swarm for the objective function, and the flight speed of each particle represents the speed at which the particle solves the objective function.

[0073] Optionally, the financial risk data processing system sets the size of the particle group, that is, the number of particles. The determination of the number of particles needs to be based on a deep understanding of the financial risk data and its characteristics to ensure the efficiency and effectiveness of the algorithm operation.

[0074] Optionally, the financial risk data processing system initializes the position of each particle in the high-dimensional search space, and this position represents the initial exploration state of the particle on the target function during the search process.

[0075] Optionally, the financial risk data processing system defines the individual optimal position of each particle, as well as the group optimal position. These two position parameters respectively mark the optimal objective function values ​​achieved by the individual and the group in each iteration, and play a decisive role in guiding the search direction and optimization target of the particle swarm.

[0076] Optionally, there is an example for introducing the particle swarm algorithm: Assume that the particle swarm contains M particles, and the current position of particle i is x i , the optimal position of particle i is Pbest i , the optimal position of the particle swarm is Gbest, and the flying speed of particle i in the search space is v i To prevent the particle speed from exceeding the set search range, the particle speed can be set to meet -v max <=v<=v max If it exceeds the set range, the boundary value is taken and the number of iterations is n.

[0077] Then the current optimal position of particle i is shown in formula (3):

[0078]

[0079] The current optimal position of the entire particle swarm is shown in formula (4):

[0080] Gbest(n)=min{Pbest1(n),Pbest2(m),...,Pbest M (n)}(4)

[0081] The speed and position update formula of particle i in the nth generation is shown in formula (5):

[0082] v i (n) = ωv i (n-1)+c1r1(Pbest i -x i (n-1))+c2r2(Gbest-x i (n-1))

[0083] x i (n) = x i (n-1)+v i (n) (5)

[0084] Where ω is the inertia factor, c1 and c2 are learning factors, and r1 and r2 are random numbers between [0,1].

[0085] From the above content, it can be seen that the financial risk data processing system deeply analyzes the initialization parameter setting logic of the particle swarm algorithm and the role of each particle in the algorithm's dynamic solution to the minimum value of the objective function. It can intelligently and efficiently explore the financial risk regulation parameter space and find the optimal solution that minimizes the objective function, thereby providing financial institutions with accurate risk management strategies.

[0086] In an optional embodiment, the financial risk data processing system first obtains the maximum number of iterations, the maximum inertia factor, the minimum inertia factor and the random speed parameter set for the particle swarm, and then determines the inertia factor corresponding to each particle in the particle swarm at the current number of iterations based on the current number of iterations, the maximum number of iterations, the maximum inertia factor, the minimum inertia factor and the random speed parameter of the particle swarm.

[0087] Optionally, the maximum number of iterations is based on an evaluation of the complexity of the problem and consideration of computing resources, aiming to balance the convergence speed and solution accuracy of the algorithm.

[0088] Optionally, the maximum inertia factor and the minimum inertia factor together constitute the adjustment range of the inertia factor, reflecting the changing trend of the particle's dependence on historical information during the search process, as well as the intensity of exploration of the current direction.

[0089] Optionally, there is a method to dynamically adjust the inertia factor and the learning factor, so that the algorithm can find a good point and converge quickly in the early stage of iteration, and maintain the diversity of the population in the later stage of iteration, so as to maximize the possibility of searching for other optimal solutions in the later stage. The value of the inertia factor ω is improved, and changes nonlinearly, so as to ensure that the algorithm can more effectively seek the optimal solution, as shown in formula (6):

[0090]

[0091] Where t represents the number of current iterations, T represents the maximum number of iterations, and ω max represents the maximum inertia factor of the setting, ω min It indicates the minimum inertia factor set, and r is the random speed parameter, which is generally set to 2. It can be found that the inertia factor changes nonlinearly, and the speed decreases significantly, which improves the search ability of the algorithm in the entire cycle.

[0092] From the above content, it can be seen that the financial risk data processing system determines the inertia factor corresponding to each particle in the particle swarm under the current number of iterations according to the current number of iterations, maximum number of iterations, maximum inertia factor, minimum inertia factor and random speed parameters of the particle swarm, so that the particle swarm algorithm can dynamically adjust the search strategy and continuously optimize the solution process of the objective function.

[0093] In an optional embodiment, the financial risk data processing system first determines the aggregation parameter and speed parameter corresponding to the particle swarm at the nth iteration when the particle swarm performs the nth iteration, wherein n is an integer greater than 1, the aggregation parameter is used to quantitatively characterize the degree of aggregation of the particle swarm, and the speed parameter is used to quantitatively characterize the iteration speed of the particle swarm, and then determines the learning factor corresponding to the particle swarm at the nth iteration based on the initialized learning factor, the aggregation parameter and speed parameter corresponding to the particle swarm at the nth iteration, the weight value corresponding to the aggregation parameter, and the weight value corresponding to the speed parameter.

[0094] Optionally, the financial risk data processing system calculates and determines two key parameters reflecting the dynamic characteristics of the particle swarm: an aggregation parameter and a speed parameter.

[0095] Optionally, the aggregation parameter (denoted as k a ) quantifies the concentration of the particle swarm in the search space, reveals the exploration and convergence status of the group during the iteration process, and helps to accurately judge the diversity and information exchange efficiency of the particle swarm.

[0096] Optionally, the speed parameter (denoted as k v ) quantifies the iteration speed of the particle swarm, that is, how fast the particle swarm as a whole moves in the search space, providing real-time insights into the algorithm convergence dynamics and search efficiency.

[0097] Optionally, the learning factor can be adjusted in a timely manner according to the particle evolution speed and aggregation degree, so that the algorithm can find the optimal solution more efficiently.

[0098] Optionally, the optimization formula of the learning factor is as shown in formula (7):

[0099] c1(n)=c2(n)=c start -k a c a +k v c v (7)

[0100] where c start is the initial learning factor, c a , c v They are used to adjust the aggregation parameter k a and the aggregation parameter k a A constant parameter, which can be set to 2 here.

[0101] From the above content, it can be seen that the financial risk data processing system determines the learning factor corresponding to the particle swarm at the nth iteration based on the initialized learning factor, the aggregation parameter and speed parameter corresponding to the particle swarm at the nth iteration, the weight value corresponding to the aggregation parameter, and the weight value corresponding to the speed parameter. This promotes the global search capability of the particle swarm algorithm in the early stage of iteration, and also ensures that the algorithm maintains sufficient population diversity and convergence stability in the later stage of iteration, avoiding the common trap of falling into local optimality.

[0102] In an optional embodiment, the financial risk data processing system first uses the solution value of the x-th particle in the particle swarm to the objective function as the first value when the particle swarm performs the n-th iteration, wherein the x-th particle is any particle in the particle swarm, and then uses the solution value of the x-th particle in the particle swarm to the objective function as the second value when the particle swarm performs the n-1-th iteration, and then determines the minimum and maximum values ​​of the first and second values, and finally calculates the ratio of the minimum and maximum values ​​of the first and second values ​​to obtain the speed parameter corresponding to the particle swarm at the n-th iteration.

[0103] Optionally, when the particle swarm enters the nth iteration cycle, the financial risk data processing system monitors and analyzes the solution status of individual particles in real time. Select any particle in the particle swarm, that is, the xth particle, and record and evaluate its current solution value for the objective function, and define this value as the first value.

[0104] Optionally, at the n-1th iteration, the solution value of the xth particle to the objective function is recorded and defined as the second value.

[0105] Optionally, for the speed parameter k v, defined as shown in formula (8):

[0106]

[0107] Wherein, L[x(n)] represents the solution value (i.e., the first value) of the objective function obtained by the x-th particle in the particle swarm when the particle swarm performs the n-th iteration; L[x(n-1)] represents the solution value (i.e., the second value) of the objective function obtained by the x-th particle in the particle swarm when the particle swarm performs the n-1-th iteration.

[0108] It can be seen from the formula that when the distance between the nth generation and the n-1th generation particles is far, k v The smaller the value, the faster the particle evolution speed is. The value of the learning factor should be reduced so that the algorithm can continue to search in a larger range. If the particle evolution speed is slow, the value of the learning factor should be increased to reduce the search range so that the algorithm converges.

[0109] From the above content, it can be seen that the financial risk data processing system provides direct guidance for the dynamic adjustment of the algorithm in the later stage by calculating the speed parameters corresponding to the nth iteration, ensuring that the particle swarm algorithm can quickly converge to the potential optimal solution during the iteration process, avoid falling into the local optimum too early, and maintain the diversity and dynamics of the population.

[0110] In an optional embodiment, the financial risk data processing system first obtains the solution value of the objective function for each particle in the particle swarm during the iteration process after the particle swarm performs the nth iteration, and calculates the average value of all solution values ​​corresponding to all particles. Then, when the particle swarm performs the nth iteration, the solution value of the xth particle in the particle swarm for the objective function is used as the first value, wherein the xth particle is any particle in the particle swarm, and then the average value and the maximum and minimum values ​​in the first value are determined. Finally, the ratio of the average value, the minimum value and the maximum value in the first value is calculated to obtain the aggregation parameter corresponding to the particle swarm at the nth iteration.

[0111] Optionally, the financial risk data processing system obtains the latest solution value of each particle in the particle swarm for the objective function, and then calculates the average value of the corresponding solution values ​​of all particles, which provides a key quantitative indicator for evaluating the overall solution efficiency and convergence state of the particle swarm.

[0112] Optionally, for the aggregation parameter k a , the formula is shown in formula (9):

[0113]

[0114] Among them, L avg(n) is the average value of the objective function solved by all particles in the nth iteration, indicating the solution value (i.e., the first value) of the objective function by the xth particle in the particle swarm when the particle swarm performs the nth iteration.

[0115] It can be seen from the formula that if the particles are more concentrated, k a The larger the value, the smaller the learning factor should be to increase the diversity of the population and expand the search capability of the algorithm in the later stage. On the contrary, the larger the learning factor should be to speed up the convergence of the algorithm.

[0116] From the above content, it can be seen that the financial risk data processing system provides an important basis for the dynamic adjustment of the algorithm in the later stage by calculating the aggregation parameters corresponding to the particle swarm at the nth iteration, ensuring that the particle swarm algorithm can maintain population diversity and accelerate convergence to the optimal solution when solving complex financial risk problems.

[0117] It can be seen from the above content that according to the technical solution of this application, at least the following technical effects can be achieved:

[0118] 1. Nonlinear financial models fully consider complex internal and external risks, as well as the mutual impact of internal and external risks. They can better predict the risks of financial markets and play an important role in avoiding and controlling risks.

[0119] 2. The optimized particle swarm algorithm can find the optimal value quickly in the early stage of the algorithm, promote the convergence speed of the algorithm, and in the later stage of the algorithm, it can still maintain excellent search capabilities and prevent the loss of population diversity.

[0120] 3. Combined with the optimized particle swarm algorithm, it can accurately and quickly find the appropriate control parameter c value for the nonlinear financial risk model, so that the financial risk system can enter a stable movement.

[0121] In an optional embodiment, Figure 3 The flowchart of an optional improved particle swarm algorithm in the financial risk model according to the embodiment of the present application is shown. By improving the values ​​of the inertia factor and learning factor of the particle swarm algorithm, the algorithm's search ability is enhanced in the early stage, the convergence ability is improved, and in the later stage of the algorithm, the population diversity is guaranteed to prevent the algorithm from falling into the local optimum. The improved particle swarm algorithm is applied to the financial risk model to solve the appropriate control parameter c so that the total risk value is minimized. The main process is as follows:

[0122] Step 1: First, initialize the population, where each c value represents a particle, and initialize the population size, speed, position, Pbest, and Gbest.

[0123] Step 2: Calculate the value of each particle in the objective function L, and update the historical optimal position of each particle and the historical optimal position of the entire population.

[0124] Step three: Update the speed and position of each particle.

[0125] Step 4: Determine whether the particle swarm has reached the maximum number of iterations. If not, return to step 2 to continue calculating the value of each particle in the objective function L, and update the historical optimal position of each particle and the historical optimal position of the entire swarm.

[0126] Step 5: If the maximum number of iterations is reached, the algorithm ends and the optimal c is obtained.

[0127] According to another aspect of the embodiment of the present application, a device for processing financial risk data is also provided, wherein: Figure 4 is a schematic diagram of an optional financial risk data processing device according to an embodiment of the present application, such as Figure 4 As shown, the apparatus for processing financial risk data includes: a first determining unit 401 , a second determining unit 402 , and a third determining unit 403 .

[0128] The first determination unit 401 determines the system risk value and the control parameters from the financial risk data of the financial transaction system, wherein the system risk value represents the risk value caused by the data interference of the financial transaction system; the control parameters are used to adjust the risk value; the second determination unit 402 determines the inertia factor and the learning factor that change with the continuous iteration of the particle swarm during the iteration process of the particle swarm, wherein the particle swarm is used to determine the minimum value of the objective function based on the inertia factor and the learning factor, the inertia factor is a numerical value that changes nonlinearly, and the learning factor is a value that changes according to the evolution speed and aggregation degree of the particle swarm, and the objective function is used to determine the volatility of the system risk value; the third determination unit 403 determines the target control coefficient for the financial transaction system according to the minimum value of the target function, wherein the target control coefficient is used as a reference threshold for the financial institution when regulating the financial transaction system.

[0129] Optionally, the first determination unit 401 includes: a first determination subunit and a first processing subunit. The first determination subunit is used to determine a first type of risk value and a second type of risk value from the financial risk data, wherein the first type of risk value represents a transaction risk value caused by data interference within the financial transaction system and / or a transaction risk value caused by data interference outside the financial transaction system; the second type of risk value represents a transaction risk value derived from the first type of risk value; and the first processing subunit is used to use the first type of risk value and the second type of risk value as a system risk value.

[0130] Optionally, the financial risk data processing device also includes: a processing unit, used to set the number of particles in the particle swarm, the current position of each particle, the target position of each particle, the target position of the particle swarm, the flight speed of each particle in the search space, and the upper and lower limits of the flight speed, wherein each particle represents a process for solving the objective function, the current position of each particle represents the progress of the particle in solving the objective function, the target position of each particle represents the minimum value of the particle for the objective function, the target position of the particle swarm represents the minimum value of all particles in the particle swarm for the objective function, and the flight speed of each particle represents the speed at which the particle solves the objective function.

[0131] Optionally, the second determination unit 402 includes: a first acquisition subunit and a second determination subunit. The first acquisition subunit is used to acquire the maximum number of iterations, the maximum inertia factor, the minimum inertia factor and the random speed parameter set for the particle swarm; the second determination subunit is used to determine the inertia factor corresponding to each particle in the particle swarm at the current number of iterations according to the current number of iterations, the maximum number of iterations, the maximum inertia factor, the minimum inertia factor and the random speed parameter of the particle swarm.

[0132] Optionally, the second determination unit 402 includes: a third determination subunit and a fourth determination subunit. The third determination subunit is used to determine the aggregation parameter and speed parameter corresponding to the particle swarm at the nth iteration when the particle swarm performs the nth iteration, wherein n is an integer greater than 1, the aggregation parameter is used to quantitatively characterize the aggregation degree of the particle swarm, and the speed parameter is used to quantitatively characterize the iteration speed of the particle swarm; the fourth determination subunit is used to determine the learning factor corresponding to the particle swarm at the nth iteration according to the initialized learning factor, the aggregation parameter and speed parameter corresponding to the particle swarm at the nth iteration, the weight value corresponding to the aggregation parameter, and the weight value corresponding to the speed parameter.

[0133] Optionally, the third determination subunit includes: a first processing module, a second processing module, a first determination module and a first calculation module. The first processing module is used to use the solution value of the x-th particle in the particle swarm to the objective function as the first value when the particle swarm performs the n-th iteration, wherein the x-th particle is any particle in the particle swarm; the second processing module is used to use the solution value of the x-th particle in the particle swarm to the objective function as the second value when the particle swarm performs the n-1-th iteration; the first determination module is used to determine the minimum and maximum values ​​of the first and second values; the first calculation module is used to calculate the ratio of the minimum and maximum values ​​of the first and second values ​​to obtain the speed parameter corresponding to the particle swarm at the n-th iteration.

[0134] Optionally, the third determination subunit includes: a first acquisition module, a third processing module, a second determination module and a second calculation module. The first acquisition module is used to obtain the solution value of each particle of the particle swarm for the objective function in this iteration process after the particle swarm performs the nth iteration, and calculate the average value of all solution values ​​corresponding to all particles; the third processing module is used to use the solution value of the xth particle in the particle swarm for the objective function as the first value when the particle swarm performs the nth iteration, wherein the xth particle is any particle in the particle swarm; the second determination module is used to determine the average value and the maximum and minimum values ​​in the first value; the second calculation module is used to calculate the ratio of the average value, the minimum value and the maximum value in the first value, and obtain the aggregation parameter corresponding to the particle swarm at the nth iteration.

[0135] An embodiment of the present application may provide an electronic device, Figure 5 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 5 As shown, the electronic device may include: one or more ( Figure 5 Only one is shown) a processor, a memory, a storage controller, and a peripheral interface, wherein the peripheral interface is connected to a radio frequency module, an audio module, and a display.

[0136] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0137] It can be understood by those skilled in the art that Figure 5 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 5 The structure of the electronic device is not limited. Figure 5 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 5 Different configurations are shown.

[0138] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0139] According to another aspect of the present application, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, wherein when the computer program runs, the device where the computer-readable storage medium is located executes the above-mentioned method for processing financial risk data.

[0140] According to another aspect of the present application, a computer program product is also provided, wherein the computer program product includes computer instructions, wherein when the computer instructions are executed, the device where the computer program product is located executes the above-mentioned method for processing financial risk data.

[0141] The above-mentioned embodiments or examples disclosed in the present application are not exhaustive, but are only illustrative of some embodiments or examples, and are not intended to be specific limitations on the scope of protection disclosed in the present application. In the absence of contradiction, each step in a certain embodiment or example in the present application can be implemented as an independent example, and the steps can be combined arbitrarily. For example, the scheme after removing some steps in a certain embodiment or example can also be implemented as an independent example, and the order of the steps in a certain embodiment or example can be arbitrarily exchanged. In addition, the optional methods or optional examples in a certain embodiment or example can be combined arbitrarily; in addition, the various embodiments or examples can be combined arbitrarily, for example, some or all steps of different embodiments or examples can be combined arbitrarily, and a certain embodiment or example can be combined arbitrarily with the optional methods or optional examples of other embodiments or examples.

[0142] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0143] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0144] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0145] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0146] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0147] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0148] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for processing financial risk data, characterized in that: include: Determine a system risk value and a control parameter from the financial risk data of the financial transaction system, wherein the system risk value represents the risk value of the financial transaction system caused by data interference, and the control parameter is used to adjust the risk value; In the iterative process of the particle swarm, an inertia factor and a learning factor that change with the continuous iteration of the particle swarm are determined, wherein the particle swarm is used to determine the minimum value of the objective function according to the inertia factor and the learning factor, the inertia factor is a nonlinearly changing value, the learning factor is a value that changes according to the evolution speed and aggregation degree of the particle swarm, and the objective function is used to determine the volatility of the system risk value; A target control coefficient for the financial transaction system is determined according to the minimum value of the target function, wherein the target control coefficient is used as a reference threshold when a financial institution regulates the financial transaction system.

2. The method for processing financial risk data according to claim 1, characterized in that: Determine the system risk value from the financial risk data of the financial trading system, including: Determining a first type of risk value and a second type of risk value from the financial risk data, wherein the first type of risk value represents a transaction risk value caused by data interference within the financial transaction system and / or a transaction risk value caused by data interference outside the financial transaction system; and the second type of risk value represents a transaction risk value derived from the first type of risk value; The first risk value and the second risk value are used as the system risk value.

3. The method for processing financial risk data according to claim 2, characterized in that: After determining the system risk value and the control parameters from the financial risk data of the financial transaction system, the method further includes: The number of particles in the particle swarm, the current position of each particle, the target position of each particle, the target position of the particle swarm, the flight speed of each particle in the search space, and the upper and lower limits of the flight speed are set, wherein each particle represents a process for solving the objective function, the current position of each particle represents the progress of the particle in solving the objective function, the target position of each particle represents the minimum value obtained by the particle for the objective function, the target position of the particle swarm represents the minimum value obtained by all particles in the particle swarm for the objective function, and the flight speed of each particle represents the speed at which the particle solves the objective function.

4. The method for processing financial risk data according to claim 1, characterized in that: During the iteration process of the particle swarm, an inertia factor that changes with the continuous iteration of the particle swarm is determined, including: Obtaining a maximum number of iterations, a maximum inertia factor, a minimum inertia factor, and a random velocity parameter set for the particle swarm; The inertia factor corresponding to each particle in the particle swarm at the current iteration number is determined according to the current iteration number of the particle swarm, the maximum iteration number, the maximum inertia factor, the minimum inertia factor and the random speed parameter.

5. The method for processing financial risk data according to claim 1, characterized in that: During the iteration process of the particle swarm, a learning factor that changes with the continuous iteration of the particle swarm is determined, including: When the particle swarm performs an nth iteration, determining an aggregation parameter and a speed parameter corresponding to the particle swarm at the nth iteration, wherein n is an integer greater than 1, the aggregation parameter is used to quantitatively characterize the aggregation degree of the particle swarm, and the speed parameter is used to quantitatively characterize the iteration speed of the particle swarm; The learning factor corresponding to the particle swarm at the nth iteration is determined according to the initialized learning factor, the aggregation parameter and speed parameter corresponding to the particle swarm at the nth iteration, the weight value corresponding to the aggregation parameter, and the weight value corresponding to the speed parameter.

6. The method for processing financial risk data according to claim 5, characterized in that: When the particle swarm performs an nth iteration, determining a speed parameter corresponding to the particle swarm at the nth iteration includes: When the particle swarm performs an nth iteration, a solution value of the objective function obtained by an xth particle in the particle swarm is used as a first value, wherein the xth particle is any particle in the particle swarm; When the particle swarm performs an n-1th iteration, taking a solution value of the objective function obtained by the xth particle in the particle swarm as a second value; determining a minimum value and a maximum value among the first value and the second value; The ratio of the minimum value to the maximum value of the first value and the second value is calculated to obtain the speed parameter corresponding to the particle swarm at the nth iteration.

7. The method for processing financial risk data according to claim 5, characterized in that: When the particle swarm performs an nth iteration, determining an aggregation parameter corresponding to the particle swarm at the nth iteration includes: After the particle swarm performs the nth iteration, obtaining the solution value of each particle of the particle swarm for the objective function in this iteration process, and calculating the average value of all solution values ​​corresponding to all particles; When the particle swarm performs an nth iteration, a solution value of the objective function obtained by an xth particle in the particle swarm is used as a first value, wherein the xth particle is any particle in the particle swarm; determining a maximum value and a minimum value among the average value and the first value; The average value, and the ratio of the minimum value to the maximum value in the first values ​​are calculated to obtain the aggregation parameter of the particle group corresponding to the nth iteration.

8. A device for processing financial risk data, characterized in that: include: A first determination unit determines a system risk value and a control parameter from financial risk data of a financial transaction system, wherein the system risk value represents a risk value of the financial transaction system caused by data interference; and the control parameter is used to adjust the risk value; A second determination unit, during the iteration process of the particle swarm, determines an inertia factor and a learning factor that change with the continuous iteration of the particle swarm, wherein the particle swarm is used to determine the minimum value of the objective function according to the inertia factor and the learning factor, the inertia factor is a nonlinearly changing value, the learning factor is a value that changes according to the evolution speed and aggregation degree of the particle swarm, and the objective function is used to determine the volatility of the system risk value; A third determining unit is configured to determine a target control coefficient for the financial transaction system according to a minimum value of the target function, wherein the target control coefficient is used as a reference threshold when a financial institution regulates the financial transaction system.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the computer-readable storage medium is located is controlled to execute the method for processing financial risk data according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the financial risk data processing method described in any one of claims 1 to 7.

11. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the method for processing financial risk data described in any one of claims 1 to 7 are implemented.

Images