Service approval method and device, electronic equipment and computer readable storage medium

Abstract

The invention provides a business approval method and device, electronic equipment and a computer readable storage medium, and relates to the technical field of big data and artificial intelligence, and the method comprises the steps: obtaining business approval data of a user in response to a business approval request of the user; determining a service approval score of the service approval request through a preset service approval model based on the service approval data; obtaining a current first score threshold value and a current second score threshold value, if the service approval score is lower than the first score threshold value, rejecting the service approval request, and returning rejected information of the service approval request to the user; if the service examination and approval score is not lower than the first score threshold value and not higher than the second score threshold value, sending the service examination and approval request to a preset service examination and approval interface; if the service approval score is higher than a second score threshold, passing the service approval request, and returning passing information of the service approval request to the user; wherein the second score threshold value is higher than the first score threshold value. The business approval efficiency can be effectively improved.

Description

Technical Field

[0001] The present application relates to the field of big data and artificial intelligence technology, and in particular to a business approval method, a business approval device, an electronic device and a computer-readable storage medium. Background Art

[0002] At present, business approval is usually done manually, especially for financial business approval, such as personal consumer loan business approval. Due to the large amount of data involved in loan information, traditional methods often have slow processing speeds due to manual intervention. Personal consumer loans refer to loans issued by banks to individual customers for designated consumer purposes. With the popularization of personal consumer loans, the risk of default is also increasing. In order to control risks, banks and financial institutions usually conduct loan risk assessments before issuing loans, and decide whether to issue loans based on the assessment results. At present, banks or financial institutions usually automatically approve loans based on risk control models, or, in the absence of risk control models, complete loan approval manually. However, the existing risk control models have low accuracy and cannot effectively control loan risks. Relying on manual approval is inefficient. With the increase in personal consumer loans, traditional business approval methods are difficult to improve business approval efficiency while controlling risks. Summary of the invention

[0003] The present application provides a business approval method, a business approval device, an electronic device and a computer-readable storage medium, which are used to solve the problem that the existing business approval method is difficult to improve the business approval efficiency while controlling risks.

[0004] In a first aspect of the present application, a business approval method is provided, comprising:

[0005] In response to a business approval request from a user, sending a business approval data acquisition request to the user, and acquiring the business approval data of the user upon receiving confirmation information from the user;

[0006] Based on the business approval data, determining a business approval score for the business approval request through a preset business approval model;

[0007] Obtaining the current first scoring threshold and second scoring threshold, and if the business approval score is lower than the first scoring threshold, rejecting the business approval request, and returning rejection information of the business approval request to the user; if the business approval score is not lower than the first scoring threshold and not higher than the second scoring threshold, sending the business approval request to a preset business approval interface; if the business approval score is higher than the second scoring threshold, passing the business approval request, and returning approval information of the business approval request to the user;

[0008] The second scoring threshold is higher than the first scoring threshold.

[0009] Optionally, the business approval data at least includes:

[0010] The user's basic information data, the user's credit data and the user's behavior data;

[0011] The business approval model includes:

[0012] Business approval data scoring sub-model and business approval scoring calculation sub-model;

[0013] The business approval data scoring sub-model at least includes data scores corresponding to different basic information data, credit data and behavior data;

[0014] The business approval score calculation sub-model includes a mapping relationship between the data scores corresponding to the basic information data, the credit data and the behavior data and the business approval score.

[0015] Optionally, the business approval request includes a financial business approval request, and the basic information data includes:

[0016] One or more of the user's age, gender, and education level;

[0017] The credit information data includes:

[0018] One or more of the number of historical business defaults of the corresponding user and the amount of historical business defaults of the corresponding user;

[0019] The behavioral data includes:

[0020] One or more of the number of consumption times, consumption amount and consumption interval time of the corresponding user within the preset time period.

[0021] Optionally, the mapping relationship includes:

[0022] The business approval score is the sum of the data scores corresponding to the basic information data, the credit data and the behavior data.

[0023] Optionally, before obtaining the current first scoring threshold and the second scoring threshold, the method further includes:

[0024] In response to the threshold adjustment instruction of the current adjustment cycle, obtaining the pending business approval requests that have not yet completed the approval, determining the business approval score of each pending business approval request based on the business approval model, and determining that among the pending business approval requests, the business approval score of the pending business approval request is not lower than the first historical score threshold corresponding to the previous adjustment cycle and is not higher than the first number of the second historical score threshold corresponding to the previous adjustment cycle, and the second historical score threshold is higher than the first historical score threshold; and

[0025] Acquire a second quantity of approval resources corresponding to the preset business approval interface in the current adjustment period and determine an adjustment coefficient of the second quantity;

[0026] The first historical scoring threshold and the second historical scoring threshold are adjusted according to the first number, the second number and the adjustment coefficient, and the adjusted first historical scoring threshold and the second historical scoring threshold are used as the current first scoring threshold and the second scoring threshold.

[0027] Optionally, adjusting the first historical scoring threshold and the second historical scoring threshold according to the first number, the second number, and the adjustment coefficient includes:

[0028] S1, taking the product of the second quantity and the adjustment coefficient as the third quantity;

[0029] S2. If the first quantity is greater than the third quantity, execute step S3; otherwise, execute step S4;

[0030] S3, reducing the second historical scoring threshold by a first preset step size, updating the second historical scoring threshold with the second historical scoring threshold reduced by the first preset step size, updating the first number with the number of pending business approval requests whose business approval scores are not lower than the first historical scoring threshold and not higher than the second historical scoring threshold among the pending business approval requests, and executing step S2;

[0031] S4. Use the first historical scoring threshold as the first scoring threshold, and use the second historical scoring threshold as the second scoring threshold.

[0032] Optionally, before reducing the second historical scoring threshold by a first preset step size, step S3 further includes:

[0033] If the number of times the second historical scoring threshold is reduced according to the first preset step length reaches the adjustment number threshold, executing step S5;

[0034] The step S5 comprises:

[0035] The first historical scoring threshold is increased according to a second preset step length, the adjustment times are reset, and step S2 is executed.

[0036] Optionally, the method further comprises:

[0037] Based on the business approval data, determining the default probability of the user by means of a logistic regression algorithm, and generating an alarm signal when the default probability is higher than a default probability threshold;

[0038] The logistic regression algorithm includes:

[0039]

[0040] Among them, P(Y=1|X) is the default probability of the corresponding user, b 0 is the intercept term, b n is the weight of the nth business approval data, X n is the characteristic score of the nth business approval data, and e is a natural constant.

[0041] Optionally, the feature score of the business approval data is calculated by the following formula:

[0042] Score=(Factor*FeatureValue)+BaseScore

[0043] Among them, Factor is the logistic regression coefficient of the business approval data, FeatureValue is the actual value of the business approval data, and BaseScore is the basic score.

[0044] In a second aspect of the present application, a business approval device is provided, comprising:

[0045] The data acquisition module is configured to send a business approval data acquisition request to the user in response to the user's business approval request, and acquire the user's business approval data when receiving the user's confirmation information;

[0046] A calculation module is configured to determine a business approval score of the business approval request based on the business approval data and through a preset business approval model;

[0047] The business approval module is configured to obtain a current first scoring threshold and a second scoring threshold, and when the business approval score is lower than the first scoring threshold, reject the business approval request and return rejection information of the business approval request to the user; when the business approval score is not lower than the first scoring threshold and not higher than the second scoring threshold, send the business approval request to a preset business approval interface; when the business approval score is higher than the second scoring threshold, approve the business approval request and return approval information of the business approval request to the user;

[0048] The second scoring threshold is higher than the first scoring threshold.

[0049] According to a third aspect of the present application, an electronic device is provided, comprising: a processor, and a memory communicatively connected to the processor;

[0050] The memory stores computer-executable instructions;

[0051] The processor executes the computer-executable instructions stored in the memory to implement the above method.

[0052] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to implement the above-mentioned method when executed by a processor.

[0053] In a fifth aspect of the present application, a computer program product is provided, including a computer program, which implements the above method when executed by a processor.

[0054] This application uses a pre-built business approval model to calculate business approval scores for business approval data related to business requests, matches the calculation results with multiple real-time scoring thresholds, and executes different business approval actions based on the matching results, thereby effectively improving business approval efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0056] Figure 1 A method flow chart of a business approval method provided in an embodiment of the present application;

[0057] Figure 2 A schematic block diagram of a business approval device provided in an embodiment of the present application;

[0058] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0059] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme 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. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0061] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0062] In addition, if there are descriptions of "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by this application. It can be understood that in the technical solution of this application, the acquisition, collection, storage, use, processing, transmission, provision, disclosure and application of data are all in compliance with the provisions of relevant laws and regulations. It should be noted that in the embodiments of the present application, some existing solutions in the industry such as software, components, models, etc. may be mentioned, and they should be considered as exemplary. Their purpose is only to illustrate the feasibility of the implementation of the technical solution of this application, but it does not mean that the applicant has or must use the solution.

[0063] like Figure 1 As shown, in the first aspect of the present application, a business approval method is provided, comprising:

[0064] S100, in response to a business approval request from a user, sending a business approval data acquisition request to the user, and acquiring the business approval data of the user upon receiving confirmation information from the user;

[0065] S200, based on the business approval data, determining a business approval score for the business approval request through a preset business approval model;

[0066] S300. Obtain the current first scoring threshold and second scoring threshold. If the business approval score is lower than the first scoring threshold, reject the business approval request and return rejection information of the business approval request to the user. If the business approval score is not lower than the first scoring threshold and not higher than the second scoring threshold, send the business approval request to the preset business approval interface. If the business approval score is higher than the second scoring threshold, pass the business approval request and return approval information of the business approval request to the user. The second scoring threshold is higher than the first scoring threshold.

[0067] In this way, the present application calculates the business approval score for the business approval data related to the business request through a pre-built business approval model, matches the calculation result with multiple real-time scoring thresholds, and executes different business approval actions according to the matching results, thereby effectively improving the business approval efficiency.

[0068] With the development of personal consumer loan business, the number of consumer loan business approval requests is increasing. At the same time, the risk of default is also increasing. In order to control risks, banks and other financial institutions need to conduct risk assessments when approving business approval requests and determine the approval results based on the assessment results. How to improve loan approval efficiency while controlling risks is an urgent problem that financial institutions need to solve.

[0069] In step S100, when the system receives a business approval request from a user, such as a loan approval request from user A, the system first returns a business approval data acquisition request for risk assessment to the user end of user A. If confirmation information from user A is received, it is determined that user A has confirmed the authorization, and the business approval data of user A is collected.

[0070] In this application, the business approval request includes a financial business approval request, such as a loan approval request. The business approval data includes: basic information data of the user, credit data of the user, and behavior data of the user. Among them, the basic information data includes: the age, gender, education, occupation, income and other information of the corresponding user; the credit data includes: the credit history of the corresponding user, such as loan record, repayment record, overdue situation, etc., and the expected situation includes the number of historical business defaults, the amount of historical business defaults of the corresponding user, etc.; the behavior data includes: the number of consumptions, the amount of consumption, and the consumption interval time of the corresponding user within a preset time period, such as the average number of monthly consumptions, the average monthly consumption amount, the consumption interval time, etc. of the user, wherein the consumption interval time can be the consumption interval time of large-amount consumption such as exceeding the set amount. It can be understood that in order to further improve the calculation accuracy of the business approval model, in this application, the credit data can also include the user's legal litigation information and traffic violation information, such as the user's court judgment or bankruptcy record and other public records.

[0071] In step S200, the business approval model of the present application includes: a business approval data scoring sub-model and a business approval scoring calculation sub-model; wherein the business approval data scoring sub-model includes at least data scores corresponding to different basic information data, credit data and behavioral data; the business approval scoring calculation sub-model includes a mapping relationship between data scores corresponding to basic information data, credit data and behavioral data and business approval scores.

[0072] Among them, the business approval data scoring sub-model is constructed based on the user's business approval data. For example, a basic information scoring card, a credit scoring card, and a consumption habit scoring card are respectively established. Among them, the basic information scoring card includes the age, gender, occupation, education, income, all housing conditions, marital conditions, children's conditions, etc. of the loan applicant, and the scores corresponding to each component of the basic information scoring card are respectively constructed; the components of the credit scoring card include the number of overdue payments and the overdue amount, and the scores of each component of the credit scoring card are respectively constructed. For example, different overdue times correspond to different scores, and different overdue amounts correspond to different scores; the credit scoring card can also include personal legal proceedings, traffic violations, etc. For example, if the user has legal proceedings information, it corresponds to different scores, and if the user has traffic violation information, it corresponds to different scores, or different legal proceedings correspond to different scores, and different traffic violations correspond to different scores; the components of the consumption habit scoring card include the average monthly consumption times, the average monthly consumption amount, and the interval time of large consumption, and the scores of each component of the consumption habit scoring card are respectively constructed. For example, different average monthly consumption times, different average monthly consumption amounts, and different interval time of large consumption correspond to different scores.

[0073] The business approval score calculation sub-model includes the mapping relationship between the data scores corresponding to the basic information data, credit data and behavioral data and the business approval score, including: the business approval score is the sum of the data scores corresponding to the basic information data, credit data and behavioral data. That is, the business approval score calculation sub-model sums the scores corresponding to each component factor in the basic information score card, credit score card and consumption habit score card to obtain the user's business approval score, such as the consumer loan score. In this way, the present application comprehensively constructs a business approval model based on the user's basic information, credit information, and consumption habit information, which can more accurately and comprehensively quantify the risks of the user's business request, thereby realizing efficient and accurate automatic approval of the user's business request.

[0074] In step S300, after the business approval score of the user is calculated by the business approval model, the current first score threshold and the second score threshold are obtained. In this application, according to the personal consumption loan score of the user, the system automatically makes three decisions on the personal consumption loan application: automatic rejection, automatic approval, and manual approval. The first score threshold is set as the score threshold corresponding to the automatic rejection, and the second score threshold is set as the automatic approval threshold, wherein the second score threshold is greater than the first score threshold. When the personal consumption loan score is less than the automatic rejection threshold, the system automatically rejects the personal consumption loan application; when the personal consumption loan application score is greater than the automatic approval threshold, the system automatically approves the personal consumption loan application; when the personal consumption loan application score is greater than or equal to the automatic rejection threshold and less than or equal to the automatic approval threshold, the system sends the current user's personal consumption loan application to the manual approval interface for manual approval. In this way, by setting different thresholds, the system automatically executes the operation of passing, rejecting, or sending to the manual approval interface for the approval request, thereby effectively improving the processing efficiency of business approval.

[0075] In order to further improve the processing efficiency of approval business, in this application, the automatic rejection threshold and the automatic approval threshold are adaptively and dynamically adjusted according to the score and number of business approval requests. Specifically, before obtaining the current first scoring threshold and the second scoring threshold, the method of this application also includes:

[0076] S10, in response to the threshold adjustment instruction of the current adjustment cycle, obtain the pending business approval requests that have not been approved, determine the business approval score of each pending business approval request based on the business approval model, determine that the business approval score of each pending business approval request is not less than the first historical scoring threshold corresponding to the previous adjustment cycle, and is not higher than the first number of the second historical scoring threshold corresponding to the previous adjustment cycle, and the second historical scoring threshold is higher than the first historical scoring threshold; and obtain the second number of approval resources corresponding to the preset business approval interface in the current adjustment cycle and determine the adjustment coefficient of the second number; wherein the threshold adjustment instruction is a periodic trigger instruction, for example, an adjustment cycle is 7 days, then when the current time reaches the new adjustment cycle, such as 0:00 on the 8th day, the threshold adjustment instruction is automatically triggered, the system automatically obtains all current business approval requests that have not been approved, and calls the business approval model to calculate the business approval score for each business approval request. According to the calculation result, the first historical scoring threshold and the second historical scoring threshold, the number of business approval requests that need to be manually approved is obtained, wherein the first historical scoring threshold and the second historical scoring threshold are the scoring thresholds corresponding to the previous threshold adjustment cycle. It is understandable that the preset business approval interface is a manual business approval interface, and the second number of approval resources corresponding to it is the number of approval personnel who can perform approval. Among them, the number of approval personnel who can perform approval can be predetermined, and the adjustment coefficient of the second number can also be pre-configured.

[0077] S20: Adjust the first historical scoring threshold and the second historical scoring threshold according to the first number, the second number and the adjustment coefficient, and use the adjusted first historical scoring threshold and the second historical scoring threshold as the current first scoring threshold and the second scoring threshold.

[0078] Specifically, adjusting the first historical scoring threshold and the second historical scoring threshold according to the first quantity, the second quantity and the adjustment coefficient includes:

[0079] S1, taking the product of the second quantity and the adjustment coefficient as the third quantity;

[0080] S2. If the first quantity is greater than the third quantity, execute step S3; otherwise, execute step S4;

[0081] S3. If the number of times the second historical scoring threshold is reduced by the first preset step length reaches the adjustment number threshold, execute step S5; otherwise, the second historical scoring threshold is reduced by the first preset step length, and the second historical scoring threshold is updated with the second historical scoring threshold reduced by the first preset step length, and the first number is updated with the number of pending business approval requests whose business approval scores are not lower than the first historical scoring threshold and not higher than the updated second historical scoring threshold among the pending business approval requests, and execute step S2; wherein the number of adjustments can be set to 2, and the first preset supplement can be 5%;

[0082] S4. Using the first historical scoring threshold as the first scoring threshold and using the second historical scoring threshold as the second scoring threshold;

[0083] S5. Increase the first historical scoring threshold according to a second preset step, reset the number of adjustments, and execute step S2, wherein the second preset step may be 5%, and resetting the number of adjustments means setting the number of adjustments to an initial value of the number of adjustments.

[0084] The following is a specific example to illustrate the above process:

[0085] For example, taking an adjustment cycle of one week as an example, when the time reaches the adjustment time, if the number of personal consumer loans that have not been approved before the adjustment date is N1, and the number of people who can approve personal consumer loans in the week after the adjustment date is N2, then the personal consumer loans that have not been completed before the adjustment date are scored and calculated. Assuming that the number of personal consumer loan requests that need manual approval calculated according to the automatic rejection threshold and automatic approval threshold set in the previous adjustment cycle is N3, and the adjustment coefficient is 20, N3 is compared with 20*N2. If N3>20*N2, the automatic approval threshold is reduced first. For example, the value reduced each time is 5% of the current automatic approval threshold, and the automatic approval threshold is reduced by 5%. After the threshold is reduced, N3 is compared with 20*N2 again. If N3>20*N2, the automatic pass threshold is continued to be reduced; if N3>20*N2 after the automatic pass threshold is reduced twice, the automatic rejection threshold is increased. For example, the increased value may be 5% of the current automatic rejection threshold. After the automatic rejection threshold is increased, N3 is compared with 20*N2. If N3>20*N2, the process returns to the step of reducing the automatic pass threshold and the above process is repeated until N3<=20*N2. The current automatic rejection threshold, i.e., the first historical scoring threshold, is used as the first scoring threshold of the current adjustment period, and the current automatic pass threshold, i.e., the second historical scoring threshold, is used as the second scoring threshold of the current adjustment period.

[0086] In the present application, after calculating the business approval score for the current business approval request, the method of the present application also includes: determining the user's default probability based on the business approval data through a logistic regression algorithm, and generating an alarm signal when the default probability is higher than the default probability threshold.

[0087] Among them, the logistic regression algorithm includes:

[0088]

[0089] Among them, P(Y=1|X) is the default probability of the corresponding user, b 0 is the intercept term, b n is the weight of the nth business approval data, where b n The value of X can be determined in advance. n is the feature score of the nth business approval data, for example, it can be the user's age, gender, number of defaults, default finance, etc., n is a positive integer, and e is a natural constant.

[0090] The characteristic score of business approval data is calculated by the following formula:

[0091] Score=(Factor*FeatureValue)+BaseScore

[0092] Among them, Factor is the logistic regression coefficient of the business approval data, FeatureValue is the actual value of the business approval data, and BaseScore is the basic score, where the logistic regression coefficient is a constant. The basic score can be obtained by the intercept term b 0 For example, the base score can be calculated by the following formula: BaseScore = (b 0 ×Factor) / ln(10).

[0093] like Figure 2 As shown, in a second aspect of the present application, a business approval device is provided, comprising:

[0094] The data acquisition module is configured to send a business approval data acquisition request to the user in response to the user's business approval request, and acquire the user's business approval data when receiving the user's confirmation information;

[0095] A calculation module is configured to determine a business approval score of the business approval request through a preset business approval model based on the business approval data;

[0096] The business approval module is configured to obtain the current first scoring threshold and the second scoring threshold, and when the business approval score is lower than the first scoring threshold, reject the business approval request and return rejection information of the business approval request to the user; when the business approval score is not lower than the first scoring threshold and not higher than the second scoring threshold, send the business approval request to the preset business approval interface; when the business approval score is higher than the second scoring threshold, approve the business approval request and return approval information of the business approval request to the user;

[0097] The second scoring threshold is higher than the first scoring threshold.

[0098] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the data acquisition module can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The function of the above data acquisition module. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together, or they can be implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0099] According to a third aspect of the present application, an electronic device is provided, comprising: a processor, and a memory communicatively connected to the processor;

[0100] The memory stores computer-executable instructions;

[0101] The processor executes the computer-executable instructions stored in the memory to implement the above method.

[0102] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3 As shown, the electronic device may include: a transceiver 121 , a processor 122 , and a memory 123 .

[0103] The processor 122 executes the computer execution instructions stored in the memory, so that the processor 122 executes the scheme in the above embodiment. The processor 122 can be a general-purpose processor, including a central processing unit CPU, a network processor (network processor, NP), etc.; it can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0104] The memory 123 is connected to the processor 122 via a system bus and completes communication between them. The memory 123 is used to store computer program instructions.

[0105] The transceiver 121 may be used to obtain tasks to be executed and configuration information of the tasks to be executed.

[0106] The system bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The transceiver is used to realize the communication between the database access device and other computers (such as clients, read-write libraries, and read-only libraries). The memory may include random access memory (RAM) and may also include non-volatile memory.

[0107] The electronic device provided in the embodiment of the present application may be the terminal device of the above embodiment.

[0108] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to implement the above-mentioned method when executed by a processor.

[0109] In a fifth aspect of the present application, a computer program product is provided, including a computer program, which implements the above method when executed by a processor.

[0110] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0111] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A business approval method, characterized in that: include: In response to a business approval request from a user, sending a business approval data acquisition request to the user, and acquiring the business approval data of the user upon receiving confirmation information from the user; Based on the business approval data, determining a business approval score for the business approval request through a preset business approval model; Obtaining the current first scoring threshold and second scoring threshold, and if the business approval score is lower than the first scoring threshold, rejecting the business approval request, and returning rejection information of the business approval request to the user; if the business approval score is not lower than the first scoring threshold and not higher than the second scoring threshold, sending the business approval request to a preset business approval interface; if the business approval score is higher than the second scoring threshold, passing the business approval request, and returning approval information of the business approval request to the user; The second scoring threshold is higher than the first scoring threshold.

2. The business approval method according to claim 1, characterized in that: The business approval data at least includes: The user's basic information data, the user's credit data and the user's behavior data; The business approval model includes: Business approval data scoring sub-model and business approval scoring calculation sub-model; The business approval data scoring sub-model at least includes data scores corresponding to different basic information data, credit data and behavior data; The business approval score calculation sub-model includes a mapping relationship between the data scores corresponding to the basic information data, the credit data and the behavior data and the business approval score.

3. The business approval method according to claim 2, characterized in that: The business approval request includes a financial business approval request, and the basic information data includes: One or more of the user's age, gender, and education level; The credit information data includes: One or more of the number of historical business defaults of the corresponding user and the amount of historical business defaults of the corresponding user; The behavioral data includes: One or more of the number of consumption times, consumption amount and consumption interval time of the corresponding user within the preset time period.

4. The business approval method according to claim 3, characterized in that: The mapping relationship includes: The business approval score is the sum of the data scores corresponding to the basic information data, the credit data and the behavior data.

5. The business approval method according to claim 1, characterized in that: Before obtaining the current first scoring threshold and the second scoring threshold, the method further includes: In response to the threshold adjustment instruction of the current adjustment cycle, obtaining the pending business approval requests that have not yet completed the approval, determining the business approval score of each pending business approval request based on the business approval model, and determining that among the pending business approval requests, the business approval score of the pending business approval request is not lower than the first historical score threshold corresponding to the previous adjustment cycle and is not higher than the first number of the second historical score threshold corresponding to the previous adjustment cycle, and the second historical score threshold is higher than the first historical score threshold; and Acquire a second quantity of approval resources corresponding to the preset business approval interface in the current adjustment period and determine an adjustment coefficient of the second quantity; The first historical scoring threshold and the second historical scoring threshold are adjusted according to the first number, the second number and the adjustment coefficient, and the adjusted first historical scoring threshold and the second historical scoring threshold are used as the current first scoring threshold and the second scoring threshold.

6. The business approval method according to claim 5, characterized in that: Adjusting the first historical scoring threshold and the second historical scoring threshold according to the first number, the second number, and the adjustment coefficient includes: S1, taking the product of the second quantity and the adjustment coefficient as the third quantity; S2. If the first quantity is greater than the third quantity, execute step S3; otherwise, execute step S4; S3, reducing the second historical scoring threshold by a first preset step size, updating the second historical scoring threshold with the second historical scoring threshold reduced by the first preset step size, updating the first number with the number of pending business approval requests whose business approval scores are not lower than the first historical scoring threshold and not higher than the second historical scoring threshold among the pending business approval requests, and executing step S2; S4. Use the first historical scoring threshold as the first scoring threshold, and use the second historical scoring threshold as the second scoring threshold.

7. The business approval method according to claim 6, characterized in that: Before reducing the second historical scoring threshold according to the first preset step size, the step S3 further includes: If the number of times the second historical scoring threshold is reduced according to the first preset step length reaches the adjustment number threshold, executing step S5; The step S5 comprises: The first historical scoring threshold is increased according to a second preset step length, the adjustment times are reset, and step S2 is executed.

8. The business approval method according to claim 3, characterized in that: The method further comprises: Based on the business approval data, determining the default probability of the user by means of a logistic regression algorithm, and generating an alarm signal when the default probability is higher than a default probability threshold; The logistic regression algorithm includes: Among them, P(Y=1|X) is the default probability of the corresponding user, b0 is the intercept term, and b n is the weight of the nth business approval data, X n is the characteristic score of the nth business approval data, and e is a natural constant.

9. The business approval method according to claim 8, characterized in that: The characteristic score of the business approval data is calculated by the following formula: Score=(Factor*FeatureValue)+BaseScore Among them, Factor is the logistic regression coefficient of the business approval data, FeatureValue is the actual value of the business approval data, and BaseScore is the basic score.

10. A business approval device, characterized in that: include: The data acquisition module is configured to send a business approval data acquisition request to the user in response to the user's business approval request, and acquire the user's business approval data when receiving the user's confirmation information; A calculation module is configured to determine a business approval score of the business approval request based on the business approval data and through a preset business approval model; The business approval module is configured to obtain a current first scoring threshold and a second scoring threshold, and when the business approval score is lower than the first scoring threshold, reject the business approval request and return rejection information of the business approval request to the user; when the business approval score is not lower than the first scoring threshold and not higher than the second scoring threshold, send the business approval request to a preset business approval interface; when the business approval score is higher than the second scoring threshold, approve the business approval request and return approval information of the business approval request to the user; The second scoring threshold is higher than the first scoring threshold.

11. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 9 when executed by a processor.

13. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 9 when being executed by a processor.

Images