Data screening method and device, computer equipment and storage medium

Abstract

The invention belongs to the technical field of artificial intelligence, and relates to a data screening method and device, computer equipment and a storage medium, and the method comprises the steps: reading a system database, and obtaining a historical data sample in the system database; performing data interface calling operation according to the historical data sample to obtain a calling result set; performing interface screening operation on the i data interfaces to obtain n screened data interfaces and n screened data interface data sets corresponding to the n screened data interfaces; performing data optimization operation on the screened data interface data set according to a genetic algorithm and a predefined data interface cost interval to obtain an optimized data combination; and performing data funnel analysis operation on the optimized data combination to obtain a target data combination with optimal risk control. According to the method, a plurality of individuals in a group can be processed by referencing the genetic algorithm, namely, a plurality of solutions in a search space are evaluated, so that the risk of falling into a local optimal solution is reduced.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a data screening method, device, computer equipment and storage medium. Background Art

[0002] Online loans, or Internet loans, are financial services that use Internet big data technology to provide, optimize and expand. During the pre-loan approval of Internet credit, the user must authorize the use of the customer's multi-dimensional data interface to obtain customer information, such as credit data, internal data, and legal third-party company data, and then use artificial intelligence technology for risk control approval. However, in the era of big data, huge data sources are homogeneous and risk control effects vary. How to accurately screen effective data has become a major problem; therefore, how to obtain the maximum risk control effect to achieve the goal of reducing costs and increasing efficiency while controlling the cost of data calls has become a problem to be solved.

[0003] There is a data screening method that achieves certain risk control purposes by introducing multi-party data interfaces and formulating risk control access rules and models.

[0004] However, the applicant found that the traditional data screening method did not consider the optimal cost risk control issue, especially when there were many data interfaces. There were reasons such as repeated use of homogeneous data, confusing use of data interfaces, and improper management of data interfaces, which led to the problem of unreasonable increase in risk control data costs. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a data screening method, apparatus, computer equipment and storage medium to solve the problem of unnecessary increase in risk control data costs in traditional data screening methods.

[0006] In order to solve the above technical problems, the present application embodiment provides a data screening method for risk assessment, which adopts the following technical solution:

[0007] Reading a system database, and obtaining historical data samples in the system database;

[0008] Performing a data interface calling operation according to the historical data sample to obtain a calling result set, wherein the calling result set includes i result sets corresponding to i data interfaces respectively, where i is an integer greater than zero;

[0009] Performing an interface screening operation on the i data interfaces to obtain n screened data interfaces and n screened data interface data sets corresponding to the n screened data interfaces, wherein n is an integer greater than zero and less than or equal to i;

[0010] Performing data optimization operations on the screening data interface data set according to a genetic algorithm and a predefined data interface cost interval to obtain an optimized data combination;

[0011] A data funnel analysis operation is performed on the optimized data combination to obtain the target data combination with the best risk control.

[0012] Furthermore, the step of performing an interface screening operation on the i data interfaces to obtain n screened data interfaces and n screened data interface data sets corresponding to the n screened data interfaces specifically includes the following steps:

[0013] According to the call result set, a risk control effect evaluation operation is performed on the i data interfaces respectively to obtain a risk control effect evaluation result;

[0014] Calculate the data interface similarity of the i data interfaces according to the risk control effect evaluation result;

[0015] An interface screening operation is performed on the i data interfaces according to the data interface similarities to obtain the n screened data interfaces and the n screened data interface data sets.

[0016] Furthermore, the data interface similarity ρ is expressed as:

[0017]

[0018] Among them, d i It represents the difference between the ith data and the th value, and n represents the total number of observed samples.

[0019] Furthermore, the step of performing data optimization operation on the screening data interface data set according to the genetic algorithm and the predefined data interface cost interval to obtain the optimized data combination specifically includes the following steps:

[0020] Performing population initialization and encoding operations on the screening data interface data set to obtain population encoding data;

[0021] A fitness calculation operation is performed on the population encoding data to obtain a fitness calculation result, wherein the fitness calculation result g(x) is expressed as:

[0022]

[0023] x j =0or1,j=1,2,3....i

[0024] Among them, w j represents the unit cost of data interface j, x j represents the decision variable of data interface j. If data interface j is selected, then xj =1 otherwise x j =0, W represents the maximum value of the data interface cost interval;

[0025] Performing a population screening operation on the population coding data according to the data interface cost interval and the fitness calculation result to obtain screened population coding data;

[0026] A multiplication operation is performed on the screening population coding data to obtain the optimized data combination.

[0027] Furthermore, the step of performing a population screening operation on the population coding data according to the data interface cost interval and the fitness calculation result to obtain the step of screening the population coding data specifically includes the following steps:

[0028] Deleting population coded data whose fitness calculation result is less than the maximum value of the data interface cost interval from the population coded data to obtain first population screening coded data;

[0029] The total value ratios of the first population screening coded data are calculated respectively, and the population coded data whose total value ratios are less than a preset total value threshold are deleted from the first population screening coded data to obtain the screening population coded data.

[0030] Furthermore, the step of performing a data funnel analysis operation on the optimized data combination to obtain the target data combination with the best risk control performance specifically includes the following steps:

[0031] Performing a data funnel analysis operation on the optimized data combination to obtain a first analysis result;

[0032] Determining whether the first analysis result meets the preset risk assessment requirements;

[0033] If the first analysis result meets the preset risk assessment requirement, taking the first analysis result as the target data combination;

[0034] If the first analysis result does not meet the preset risk assessment requirements, the data interface cost interval is adjusted, and the data optimization operation and the data funnel analysis operation are re-executed until the analysis result obtained by the data funnel analysis operation meets the preset risk assessment requirements, and the analysis result that meets the preset risk assessment requirements is used as the target data combination.

[0035] In order to solve the above technical problems, the embodiment of the present application further provides a data screening device for risk assessment, which adopts the following technical solution:

[0036] A historical data screening module, used for reading a system database and obtaining historical data samples in the system database;

[0037] A data interface calling module, used to perform a data interface calling operation according to the historical data sample to obtain a calling result set, wherein the calling result set includes i result sets corresponding to i data interfaces respectively, and i is an integer greater than zero;

[0038] An interface screening module, used for performing an interface screening operation on the i data interfaces to obtain n screened data interfaces and n screened data interface data sets corresponding to the n screened data interfaces, wherein n is an integer greater than zero and less than or equal to i;

[0039] A data optimization module, used for performing data optimization operations on the screening data interface data set according to a genetic algorithm and a predefined data interface cost interval to obtain an optimized data combination;

[0040] The data funnel analysis module is used to perform a data funnel analysis operation on the optimized data combination to obtain the target data combination with the best risk control.

[0041] Furthermore, the interface screening module includes:

[0042] A risk control effect evaluation submodule, configured to perform risk control effect evaluation operations on the i data interfaces respectively according to the call result set, to obtain a risk control effect evaluation result;

[0043] An interface similarity calculation submodule, used to calculate the data interface similarity of the i data interfaces according to the risk control effect evaluation result;

[0044] The interface screening submodule is used to perform interface screening operations on the i data interfaces according to the data interface similarities to obtain the n screened data interfaces and the n screened data interface data sets.

[0045] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0046] The system comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the data screening method applied to risk assessment as described above are implemented.

[0047] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0048] The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the data screening method for risk assessment described above are implemented.

[0049] The present application provides a data screening method for risk assessment, comprising: reading a system database, obtaining historical data samples from the system database; performing a data interface calling operation according to the historical data samples to obtain a calling result set, wherein the calling result set includes i result sets corresponding to i data interfaces respectively, and i is an integer greater than zero; performing an interface screening operation on the i data interfaces to obtain n screening data interfaces and n screening data interface data sets corresponding to the n screening data interfaces, wherein n is an integer greater than zero and less than or equal to i; performing a data optimization operation on the screening data interface data set according to a genetic algorithm and a predefined data interface cost interval to obtain an optimized data combination; performing a data funnel analysis operation on the optimized data combination to obtain an optimal target data combination for risk control. Compared with the prior art, the present application can process multiple individuals in a group by referring to a genetic algorithm, that is, to evaluate multiple solutions in the search space, thereby reducing the risk of falling into a local optimal solution. In addition, the fitness function value is used to evaluate the individual, and the domain of the fitness function can be set arbitrarily, so that the application range of the genetic algorithm is wide, and the information obtained from the evolutionary process is used for self-optimization, and individuals with large fitness have a higher probability of survival, and more adaptable and better results are obtained. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0052] Figure 2 is a flowchart of a data screening method for risk assessment provided in an embodiment of the present application;

[0053] Figure 3 is a schematic diagram of the structure of a data screening device for risk assessment provided in an embodiment of the present application;

[0054] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0056] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0057] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0058] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0059] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0060] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to the laptop computer 1011, tablet computer 1012 or mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0061] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0062] It should be noted that the data screening method for risk assessment provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the data screening device for risk assessment is generally set in the server / terminal device.

[0063] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0064] Continue to refer Figure 2 , shows a flow chart of an embodiment of a data screening method for risk assessment according to the present application. The data screening method for risk assessment includes: step S201, step S202, step S203, step S204 and step S205.

[0065] In step S201, a system database is read to obtain historical data samples from the system database.

[0066] In the embodiment of the present application, the system first accesses its built-in database. This database contains a large number of historical data samples, which may be various types of information about user behavior, transaction records, system performance, etc. The purpose of reading these data samples is to provide a basic data set for subsequent analysis and processing.

[0067] In the embodiment of the present application, after obtaining the data sample, normal customers and defaulting customers are marked according to the customer's credit history performance; and then the sample set M is collected in order from recent to far according to the time of the customer's credit behavior.

[0068] In step S202, a data interface calling operation is performed according to the historical data sample to obtain a calling result set, wherein the calling result set includes i result sets corresponding to i data interfaces respectively, and i is an integer greater than zero.

[0069] In an embodiment of the present application, the system will initiate a call request to multiple data interfaces (assuming there are i) based on the historical data samples obtained in the previous step. These data interfaces may come from different data sources, such as third-party service providers, internal system modules, etc. Each data interface will return a corresponding result set based on the received data sample. Therefore, after this step is completed, the system will obtain a call result set containing i result sets. These result sets may contain more detailed information, statistical data or analysis results, providing rich material for subsequent analysis.

[0070] In the embodiment of the present application, the sample data set M is used to call the interfaces N1 to N1 at one time. i , and get i result sets, namely {c1}, {c2}, {c3}...{c i}.

[0071] In step S203, an interface screening operation is performed on i data interfaces to obtain n screened data interfaces and n screened data interface data sets corresponding to the n screened data interfaces, where n is an integer greater than zero and less than or equal to i.

[0072] In an embodiment of the present application, the system will screen the i data interfaces obtained in the previous step. The screening criteria may be based on multiple dimensions such as the response speed of the interface, data quality, and data relevance. Through screening, the system can retain those data interfaces that are most valuable for subsequent analysis, i.e., n screened data interfaces (n≤i). At the same time, the system will also obtain n screened data interface data sets corresponding to these screened data interfaces. The purpose of this step is to reduce the complexity of subsequent analysis and improve the efficiency and accuracy of the analysis.

[0073] In an embodiment of the present application, the interface screening operation may include a data interface risk control effect evaluation operation, a data interface similarity calculation operation, and a data interface homogeneity check operation.

[0074] In an embodiment of the present application, the screening data interface data set may be as shown in Table 1 below.

[0075]

[0076] Table 1

[0077] In step S204, a data optimization operation is performed on the screened data interface data set according to the genetic algorithm and the predefined data interface cost interval to obtain an optimized data combination.

[0078] In an embodiment of the present application, the system uses a genetic algorithm to optimize the screened data interface data set. A genetic algorithm is a search algorithm that simulates natural selection and genetic mechanisms and can find an approximate optimal solution to a problem. The system will weigh between multiple data interfaces based on a predefined data interface cost interval (such as data acquisition cost, processing cost, etc.) to find the most cost-effective data combination. Through this step, the system can obtain an optimized data combination that meets the analysis requirements while also taking cost-effectiveness into account.

[0079] In the embodiment of the present application, the genetic algorithm may be used to optimize data:

[0080] If there are n data interfaces, for a data interface j, its unit cost is w j , the risk control effect is lift j , the maximum data cost is W, then the optimal cost of online credit approval by GA can be transformed into a mathematical model as follows:

[0081]

[0082] x j =0or1,j=1,2,3....i

[0083] Among them, x j is the decision variable of data interface j. If data interface j is selected, then x j =1 otherwise x j =0.

[0084] In step S205, a data funnel analysis operation is performed on the optimized data combination to obtain the target data combination with the best risk control.

[0085] In the embodiment of the present application, the system will perform a data funnel analysis on the optimized data combination obtained in the previous step. Data funnel analysis is a commonly used data analysis method used to track and analyze the user's behavior path and conversion rate in a certain process. Through this method, the system can identify which data is most critical for risk control decisions, thereby obtaining a target data combination with the best risk control. This combination will serve as the basis for the subsequent formulation and implementation of risk control strategies.

[0086] In the embodiment of the present application, in a given data cost interval: P min ~P max , the GA algorithm is used to quickly find data interfaces that meet the requirements from massive data interfaces, and perform risk control analysis (funnel analysis) on the data interfaces to maximize the risk control effect, that is: max (start-end).

[0087] In an embodiment of the present application, a data screening method for risk assessment is provided, including: reading a system database, obtaining historical data samples in the system database; performing a data interface calling operation according to the historical data samples to obtain a calling result set, wherein the calling result set includes i result sets corresponding to i data interfaces respectively, and i is an integer greater than zero; performing an interface screening operation on the i data interfaces to obtain n screening data interfaces and n screening data interface data sets corresponding to the n screening data interfaces, wherein n is an integer greater than zero and less than or equal to i; performing a data optimization operation on the screening data interface data set according to a genetic algorithm and a predefined data interface cost interval to obtain an optimized data combination; performing a data funnel analysis operation on the optimized data combination to obtain an optimal target data combination for risk control. Compared with the prior art, the present application can process multiple individuals in a group by referring to a genetic algorithm, that is, to evaluate multiple solutions in the search space, thereby reducing the risk of falling into a local optimal solution. In addition, the fitness function value is used to evaluate the individual, and the domain of the fitness function can be set arbitrarily, so that the application range of the genetic algorithm is wide, and the information obtained from the evolutionary process is used for self-optimization, and individuals with large fitness have a higher probability of survival, and more adaptable and better results are obtained.

[0088] In some optional implementations of the embodiments of the present application, the above step of performing an interface screening operation on i data interfaces to obtain n screened data interfaces and n screened data interface data sets corresponding to the n screened data interfaces specifically includes the following steps:

[0089] According to the call result set, risk control effect evaluation operations are performed on i data interfaces respectively to obtain risk control effect evaluation results;

[0090] Calculate the data interface similarity of i data interfaces based on the risk control effect evaluation results;

[0091] An interface screening operation is performed on i data interfaces according to data interface similarities to obtain n screened data interfaces and n screened data interface data sets.

[0092] In the embodiment of the present application, the above-mentioned interface screening operation may include a data interface risk control effect evaluation operation, a data interface similarity calculation operation, and a data interface homogeneity check operation, specifically:

[0093] Data interface risk control effect evaluation operation:

[0094] The data interface returns the result set, and the lift is calculated based on the rejection ratio s as the threshold, denoted as lift1~lift i, where the single data interface rejection ratio threshold s refers to the risk loss rate * risk magnification multiple, and the single data interface effect evaluation lift refers to the ratio of risk customers hit by the single data interface / the ratio of total risk customers under the single data interface rejection ratio threshold;

[0095] Calculate the data interface similarity operation:

[0096] Take the Spearman rank coefficient;

[0097]

[0098] Among them, d i It represents the difference between the ith data and the th value, and n represents the total number of observed samples;

[0099] Data interface homogeneity check operation:

[0100] The similarity of the data interfaces is calculated respectively. When the interfaces have high similarity (Spearman rank coefficient>0.6), the data interfaces with high lift are retained.

[0101] In some optional implementations of the embodiments of the present application, the above step of performing a data optimization operation on the screening data interface data set according to the genetic algorithm and the predefined data interface cost interval to obtain the optimized data combination specifically includes the following steps:

[0102] Perform population initialization and encoding operations on the screening data interface data set to obtain population encoding data;

[0103] Perform a fitness calculation operation on the population encoding data to obtain a fitness calculation result, where the fitness calculation result g(x) is expressed as:

[0104]

[0105] x j =0or1,j=1,2,3....i

[0106] Among them, w j represents the unit cost of data interface j, x j represents the decision variable of data interface j. If data interface j is selected, then x j =1 otherwise x j =0, W represents the maximum value of the data interface cost interval;

[0107] Perform a population screening operation on the population coding data according to the data interface cost interval and the fitness calculation result to obtain the screened population coding data;

[0108] Perform multiplication operations on the coded data of the screening population to obtain an optimized data combination.

[0109] In the embodiment of the present application, the population initialization and encoding operation can be to set the evolutionary algebra counter t=0, set the maximum evolutionary iteration threshold T, randomly generate M individuals as the initial population P(0), use binary coding to represent the candidate data interface, and each bit in the sequence represents the selection of the data interface. The corresponding relationship between binary coding and interface selection can be shown in Table 2 below.

[0110]

[0111] Table 2

[0112] In the embodiment of the present application, in the fitness calculation operation, the population code actually represents the data interface selection combination, and the price after the combination cannot exceed W, and the formula is:

[0113] value=M i <W

[0114] Calculate the risk control effect at the same time 1 to s are selected interfaces.

[0115] In the embodiment of the present application, the reproduction operation refers to the crossover, recombination and mutation operation, that is, selecting two interface combinations (chromosomes) that meet the requirements, performing crossover and recombination, and generating new offspring.

[0116] In an embodiment of the present application, when the data combination obtained after the above-mentioned reproduction operation does not meet the termination condition, the above-mentioned fitness calculation operation, population screening operation and reproduction operation can be continuously iterated until the termination condition is met to obtain an optimized data combination.

[0117] In some optional implementations of the embodiments of the present application, the above-mentioned step of performing a population screening operation on the population coding data according to the data interface cost interval and the fitness calculation result to obtain the step of screening the population coding data specifically includes the following steps:

[0118] The population coding data whose fitness calculation result is less than the maximum value of the data interface cost interval is deleted from the population coding data to obtain the first population screening coding data;

[0119] The total value ratios of the first population screening coded data are calculated respectively, and the population coded data whose total value ratios are less than a preset total value threshold are deleted from the first population screening coded data to obtain the screening population coded data.

[0120] In the embodiment of the present application, the population screening operation may be:

[0121] Eliminate data interface combinations (chromosomes) with prices greater than W, and select the remaining chromosomes according to their ratio to the total value, and whoever is selected can continue to reproduce.

[0122] In the embodiment of the present application, the total value ratio = the risk control effect of the selected chromosome i / sum (the total value of the selected chromosome).

[0123] In some optional implementations of the embodiments of the present application, the above step of performing a data funnel analysis operation on the optimized data combination to obtain the target data combination with the best risk control specifically includes the following steps:

[0124] Performing a data funnel analysis operation on the optimized data combination to obtain a first analysis result;

[0125] Determine whether the first analysis result meets the preset risk assessment requirements;

[0126] If the first analysis result meets the preset risk assessment requirements, the first analysis result is used as the target data combination;

[0127] If the first analysis result does not meet the preset risk assessment requirements, the data interface cost range is adjusted, and the data optimization operation and the data funnel analysis operation are re-executed until the analysis result obtained by the data funnel analysis operation meets the preset risk assessment requirements. The analysis result that meets the preset risk assessment requirements is used as the target data combination.

[0128] In an embodiment of the present application, the system will perform a data funnel analysis on the data combination optimized by the genetic algorithm. Data funnel analysis is an important data analysis method that can help us track the user's behavior path in a process, analyze the conversion rate of each step, and thus discover bottlenecks and problems in the process. For the optimized data combination, the system will evaluate its performance in practical applications through data funnel analysis, including the completeness, accuracy, timeliness of the data, and the degree of support for risk control decisions. The purpose of this step is to obtain a preliminary analysis result, that is, the first analysis result, as a basis for subsequent evaluation.

[0129] In the embodiment of the present application, after obtaining the first analysis result, the system needs to evaluate it to determine whether it meets the preset risk assessment requirements. These risk assessment requirements may include multiple aspects such as data accuracy, completeness, and timeliness, and may also involve specific indicators of risk control decisions, such as false alarm rate, missed alarm rate, risk coverage rate, etc. The system will evaluate the first analysis result item by item based on these requirements to determine whether it meets the preset risk assessment criteria.

[0130] In the embodiment of the present application, if the first analysis result meets the preset risk assessment requirements, it means that the optimized data combination performs well in practical applications and can support the formulation and implementation of risk control decisions. At this time, the system will use the first analysis result as the target data combination for subsequent risk control strategy formulation and data analysis.

[0131] In an embodiment of the present application, if the first analysis result does not meet the preset risk assessment requirements, it means that the optimized data combination still has some problems in practical application and needs further optimization and adjustment. At this time, the system will adjust the cost interval of the data interface to change the selection and combination of the data interface, thereby optimizing the quality and performance of the data combination. The adjusted data interface cost interval will be used as a new constraint to re-execute the data optimization operation and data funnel analysis operation. The purpose of this step is to find a data combination that meets the preset risk assessment requirements through continuous iteration and optimization.

[0132] In the embodiment of the present application, through continuous iteration and optimization, a target data combination that meets the preset risk assessment requirements is found. This process not only improves the efficiency and accuracy of data analysis, but also provides strong support for the subsequent risk control strategy formulation.

[0133] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0134] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0135] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0136] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0137] Further references Figure 3 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a data screening device for risk assessment, and the device embodiment is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0138] like Figure 3 As shown, the data screening device 200 applied to risk assessment in the embodiment of the present application includes:

[0139] The historical data screening module 210 is used to read the system database and obtain historical data samples in the system database;

[0140] The data interface calling module 220 is used to perform a data interface calling operation according to the historical data sample to obtain a calling result set, wherein the calling result set includes i result sets corresponding to i data interfaces respectively, where i is an integer greater than zero;

[0141] The interface screening module 230 is used to perform an interface screening operation on i data interfaces to obtain n screened data interfaces and n screened data interface data sets corresponding to the n screened data interfaces, where n is an integer greater than zero and less than or equal to i;

[0142] The data optimization module 240 is used to perform data optimization operations on the screening data interface data set according to the genetic algorithm and the predefined data interface cost interval to obtain an optimized data combination;

[0143] The data funnel analysis module 250 is used to perform a data funnel analysis operation on the optimized data combination to obtain the target data combination with the best risk control.

[0144] In an embodiment of the present application, a data screening device 200 for risk assessment is provided, including: a historical data screening module 210, which is used to read a system database and obtain historical data samples in the system database; a data interface calling module 220, which is used to perform a data interface calling operation based on the historical data samples to obtain a calling result set, wherein the calling result set includes i result sets corresponding to i data interfaces respectively, and i is an integer greater than zero; an interface screening module 230, which is used to perform an interface screening operation on i data interfaces to obtain n screened data interfaces and n screened data interface data sets corresponding to the n screened data interfaces, wherein n is an integer greater than zero and less than or equal to i; a data optimization module 240, which is used to perform a data optimization operation on the screened data interface data set according to a genetic algorithm and a predefined data interface cost interval to obtain an optimized data combination; a data funnel analysis module 250, which is used to perform a data funnel analysis operation on the optimized data combination to obtain an optimal target data combination for risk control. Compared with the prior art, the present application can process multiple individuals in a group by referring to a genetic algorithm, that is, to evaluate multiple solutions in the search space, thereby reducing the risk of falling into a local optimal solution. In addition, the fitness function value is used to evaluate the individual, and the domain of the fitness function can be set arbitrarily, so that the application range of the genetic algorithm is wide, and the information obtained from the evolutionary process is used for self-optimization, and individuals with large fitness have a higher probability of survival, and more adaptable and better results are obtained.

[0145] In some optional implementations of the embodiments of the present application, the interface screening module includes:

[0146] The risk control effect evaluation submodule is used to perform risk control effect evaluation operations on i data interfaces according to the call result set to obtain the risk control effect evaluation results;

[0147] The interface similarity calculation submodule is used to calculate the data interface similarity of i data interfaces according to the risk control effect evaluation results;

[0148] The interface screening submodule is used to perform interface screening operations on i data interfaces according to data interface similarities to obtain n screened data interfaces and n screened data interface data sets.

[0149] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of a computer device according to an embodiment of the present application.

[0150] The computer device 300 includes a memory 310, a processor 320, and a network interface 330 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 300 having components 310-330, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0151] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0152] The memory 310 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 310 can be an internal storage unit of the computer device 300, such as a hard disk or memory of the computer device 300. In other embodiments, the memory 310 can also be an external storage device of the computer device 300, such as a plug-in hard disk equipped on the computer device 300, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. Of course, the memory 310 can also include both the internal storage unit of the computer device 300 and its external storage device. In the embodiment of the present application, the memory 310 is generally used to store the operating system and various application software installed on the computer device 300, such as computer-readable instructions for the data screening method for risk assessment. In addition, the memory 310 can also be used to temporarily store various data that have been output or are to be output.

[0153] The processor 320 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 320 is generally used to control the overall operation of the computer device 300. In the embodiment of the present application, the processor 320 is used to run the computer-readable instructions stored in the memory 310 or process data, such as running the computer-readable instructions of the data screening method applied to risk assessment.

[0154] The network interface 330 may include a wireless network interface or a wired network interface. The network interface 330 is generally used to establish a communication connection between the computer device 300 and other electronic devices.

[0155] The computer device provided by the present application can process multiple individuals in a group by referring to a genetic algorithm, that is, it evaluates multiple solutions in the search space, thereby reducing the risk of falling into a local optimal solution. In addition, the fitness function value is used to evaluate the individual, and the domain of the fitness function can be set arbitrarily, so that the application range of the genetic algorithm is wide, and it uses the information obtained from the evolutionary process to optimize itself, and has a higher survival probability for individuals with large fitness, and obtains more adaptable and better results.

[0156] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the data screening method applied to risk assessment as described above.

[0157] The computer-readable storage medium provided by the present application can process multiple individuals in a group by referring to a genetic algorithm, that is, multiple solutions in the search space are evaluated, thereby reducing the risk of falling into a local optimal solution. In addition, the fitness function value is used to evaluate the individual, and the domain of the fitness function can be set arbitrarily, so that the application range of the genetic algorithm is wide, and the information obtained from the evolutionary process is used for self-optimization, so that individuals with large fitness have a higher probability of survival, and more adaptable and better results are obtained.

[0158] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0159] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A data screening method for risk assessment, characterized in that: The steps include: Reading a system database, and obtaining historical data samples in the system database; Performing a data interface calling operation according to the historical data sample to obtain a calling result set, wherein the calling result set includes i result sets corresponding to i data interfaces respectively, where i is an integer greater than zero; Performing an interface screening operation on the i data interfaces to obtain n screened data interfaces and n screened data interface data sets corresponding to the n screened data interfaces, wherein n is an integer greater than zero and less than or equal to i; Performing data optimization operations on the screening data interface data set according to a genetic algorithm and a predefined data interface cost interval to obtain an optimized data combination; A data funnel analysis operation is performed on the optimized data combination to obtain the target data combination with the best risk control.

2. The data screening method for risk assessment according to claim 1, characterized in that: The step of performing an interface screening operation on the i data interfaces to obtain n screened data interfaces and n screened data interface data sets corresponding to the n screened data interfaces specifically includes the following steps: According to the call result set, a risk control effect evaluation operation is performed on the i data interfaces respectively to obtain a risk control effect evaluation result; Calculate the data interface similarity of the i data interfaces according to the risk control effect evaluation result; An interface screening operation is performed on the i data interfaces according to the data interface similarities to obtain the n screened data interfaces and the n screened data interface data sets.

3. The data screening method for risk assessment according to claim 2, characterized in that: The data interface similarity ρ is expressed as: Among them, d i It represents the difference between the ith data and the th value, and n represents the total number of observed samples.

4. The data screening method for risk assessment according to claim 1, characterized in that: The step of performing a data optimization operation on the screening data interface data set according to the genetic algorithm and the predefined data interface cost interval to obtain an optimized data combination specifically includes the following steps: Performing population initialization and encoding operations on the screening data interface data set to obtain population encoding data; A fitness calculation operation is performed on the population encoding data to obtain a fitness calculation result, wherein the fitness calculation result g(x) is expressed as: x j =0or1,j=1,2,3....i Among them, w j represents the unit cost of data interface j, x j represents the decision variable of data interface j. If data interface j is selected, then x j =1 otherwise x j =0, W represents the maximum value of the data interface cost interval; Performing a population screening operation on the population coding data according to the data interface cost interval and the fitness calculation result to obtain screened population coding data; A multiplication operation is performed on the screening population coding data to obtain the optimized data combination.

5. The data screening method for risk assessment according to claim 4, characterized in that: The step of performing a population screening operation on the population coding data according to the data interface cost interval and the fitness calculation result to obtain the screened population coding data specifically includes the following steps: Deleting population coded data whose fitness calculation result is less than the maximum value of the data interface cost interval from the population coded data to obtain first population screening coded data; The total value ratios of the first population screening coded data are calculated respectively, and the population coded data whose total value ratios are less than a preset total value threshold are deleted from the first population screening coded data to obtain the screening population coded data.

6. The data screening method for risk assessment according to claim 1, characterized in that: The step of performing a data funnel analysis operation on the optimized data combination to obtain the target data combination with the best risk control performance specifically includes the following steps: Performing a data funnel analysis operation on the optimized data combination to obtain a first analysis result; Determining whether the first analysis result meets the preset risk assessment requirements; If the first analysis result meets the preset risk assessment requirement, taking the first analysis result as the target data combination; If the first analysis result does not meet the preset risk assessment requirements, the data interface cost interval is adjusted, and the data optimization operation and the data funnel analysis operation are re-executed until the analysis result obtained by the data funnel analysis operation meets the preset risk assessment requirements, and the analysis result that meets the preset risk assessment requirements is used as the target data combination.

7. A data screening device for risk assessment, characterized in that: include: A historical data screening module, used for reading a system database and obtaining historical data samples in the system database; A data interface calling module, used to perform a data interface calling operation according to the historical data sample to obtain a calling result set, wherein the calling result set includes i result sets corresponding to i data interfaces respectively, and i is an integer greater than zero; An interface screening module, used for performing an interface screening operation on the i data interfaces to obtain n screened data interfaces and n screened data interface data sets corresponding to the n screened data interfaces, wherein n is an integer greater than zero and less than or equal to i; A data optimization module, used for performing data optimization operations on the screening data interface data set according to a genetic algorithm and a predefined data interface cost interval to obtain an optimized data combination; The data funnel analysis module is used to perform a data funnel analysis operation on the optimized data combination to obtain the target data combination with the best risk control.

8. The data screening device for risk assessment according to claim 7, characterized in that: The interface screening module comprises: A risk control effect evaluation submodule, configured to perform risk control effect evaluation operations on the i data interfaces respectively according to the call result set, to obtain a risk control effect evaluation result; An interface similarity calculation submodule, used to calculate the data interface similarity of the i data interfaces according to the risk control effect evaluation result; The interface screening submodule is used to perform interface screening operations on the i data interfaces according to the data interface similarities to obtain the n screened data interfaces and the n screened data interface data sets.

9. A computer device comprising a memory and a processor, characterized in that: The memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the data screening method for risk assessment according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the data screening method for risk assessment according to any one of claims 1 to 6 are implemented.

Images