Generation method and device of approval adjustment information, storage medium and electronic equipment

Abstract

The embodiment of the invention provides an approval adjustment information generation method and device, a storage medium and electronic equipment, and the method comprises the steps: obtaining N groups of credit approval data; obtaining a target approval log of the target approval node from a credit approval system according to the N groups of credit approval data; determining examination and approval efficiency data of the target examination and approval node from the target examination and approval log; and generating approval adjustment information of the target approval node by using the approval efficiency data. Through the method and the device, the problem that the approval process cannot be timely optimized in related technologies is solved, and the effect of improving the approval efficiency is achieved.

Description

Technical Field

[0001] The embodiments of the present application relate to the computer field, and specifically, to a method and device for generating approval adjustment information, a storage medium, and an electronic device. Background Art

[0002] Credit approval is one of the core businesses of banks and other financial institutions, involving multiple links such as risk assessment, quota allocation, and approval decision-making. Traditional credit approval relies on manual review and decision-making, which is inefficient and easily affected by subjective factors, resulting in long approval time, low accuracy and poor customer experience.

[0003] In addition, the approval process in relevant technologies lacks effective monitoring methods and cannot improve approval efficiency in a timely manner. Summary of the invention

[0004] The embodiments of the present application provide a method and device for generating approval adjustment information, a storage medium, and an electronic device, so as to at least solve the problem in the related art that the approval process cannot be optimized in a timely manner.

[0005] According to an embodiment of the present application, a method for generating approval adjustment information is provided, comprising: obtaining N groups of credit approval data, wherein the N groups of the credit approval data include process data for approving credit applications of N users, and the N groups of the credit approval data are all data for performing approval operations through M approval nodes in a credit approval system, and the N and the M are both natural numbers greater than 1; obtaining a target approval log of a target approval node from the credit approval system according to the N groups of the credit approval data, wherein the target approval node is any one of the M approval nodes; determining approval efficiency data of the target approval node from the target approval log, wherein the approval efficiency data includes at least one of the following: approval time, approval pass rate, credit risk assessment data, evaluation data of the user, and feedback data of other approval nodes; generating approval adjustment information of the target approval node using the approval efficiency data, wherein the approval adjustment information is used to instruct the target approval node to adjust the process of executing the approval operation.

[0006] In an exemplary embodiment, before obtaining N groups of credit approval data, the method further includes: receiving credit requests sent by N users; parsing the user information and credit fund information included in the N credit requests to obtain N groups of initial credit request data; performing data processing operations on the N groups of initial credit request data to obtain N groups of credit request data, wherein the data processing operations include data verification operations and data format conversion operations, and the data verification operations include verification of data integrity and verification of data logic; respectively inputting the N groups of credit request data into the credit approval system to respectively perform the approval operations on the N groups of credit request data through the M approval nodes; collecting process data when the M approval nodes respectively perform the approval operations on the N groups of credit request data through the data collection service provided in the approval system to obtain the N groups of credit approval data; converting the N groups of credit approval data into data in a target format and storing them in a target database.

[0007] In an exemplary embodiment, obtaining N groups of credit approval data includes: receiving a node approval request, wherein the node approval request is used to request approval of the target approval node; responding to the node approval request, obtaining from a target database credit approval data that matches the target node information of the target approval node, the target approval process of the target node, and the approval time period included in the node approval request, to obtain N groups of the credit approval data.

[0008] In an exemplary embodiment, determining the approval efficiency data of the target approval node from the target approval log includes: converting the target approval log into a structured data format to obtain target approval data; extracting the approval process of the target approval node from the target approval data, and calculating the approval time from the approval process, wherein the approval time includes: approval start time, approval end time, and pause or waiting time during the approval process; calculating the average approval time using the approval start time, approval end time, and pause or waiting time during the approval process; counting the approval result data of the target approval node from the target approval data, and calculating the ratio between the number of approved credit approval data in N groups and N from the approval result data to obtain the approval pass rate; extracting the risk score made by the target approval node based on the user information and the user's historical credit data, and the user's historical repayment data from the target approval data; and calculating the approval result data of the target approval node based on the user information and the user's historical credit data. The above risk score and the above historical repayment data calculate the proportion of credit overdue and / or credit default of the above users, and determine the frequency of the above target approval node triggering the credit risk warning mechanism and the corresponding processing result after triggering the above credit risk warning mechanism; determine the credit risk assessment data based on the above ratio and the above processing result; extract the satisfaction score data and approval feedback data of the above users from the above target approval data, wherein the above satisfaction score data is data collected from the approval questionnaire or user feedback system; quantify the above satisfaction score data and approval feedback data to obtain the evaluation data of the above users; obtain the feedback data of the upstream approval node and the feedback data of the downstream approval node of the above target approval node from the above target approval data to obtain the feedback data of other approval nodes, wherein the feedback data of the above upstream approval node includes the preparation data transferred to the above target approval node, and the feedback data of the above downstream approval node includes the evaluation data of the approval decision made for the above target approval node.

[0009] In an exemplary embodiment, after calculating the average approval time using the approval start time, the approval end time, and the pause or waiting time in the approval process, the method further includes: generating a distribution trend graph of the approval time; identifying the time delay in the approval process of the target approval node from the distribution trend graph, and marking the time delay.

[0010] In an exemplary embodiment, the approval adjustment information of the target approval node is generated using the approval efficiency data, including: determining the abnormal type of the target approval node according to the approval efficiency data; and generating the approval adjustment information of the target approval node according to the abnormal type.

[0011] In an exemplary embodiment, determining the abnormality type of the target approval node according to the approval efficiency data includes: when the approval efficiency data includes approval time, and the average approval time in the approval time is greater than the preset approval time, and the fluctuation range of the approval time is greater than the preset fluctuation range, determining that the abnormality of the target approval node is the first abnormality type; when the approval efficiency data includes approval pass rate and credit risk assessment data, and there is an abnormality in the data correlation relationship between the approval pass rate and the credit risk assessment data, determining that the abnormality of the target approval node is the second abnormality type; when the approval efficiency data includes the user's evaluation data, and the probability that the user satisfaction in the evaluation data is greater than the preset satisfaction is less than the preset probability, determining that the abnormality of the target approval node is the third abnormality type; when the approval efficiency data includes feedback data of other approval nodes, and there is no correlation between the feedback data of the other approval nodes and the approval result of the target approval node, determining that the abnormality of the target approval node is the fourth abnormality type.

[0012] According to another embodiment of the present application, a device for generating approval adjustment information is provided, comprising: a first acquisition module, used to acquire N credit approval data, wherein the N credit approval data include process data for approving credit applications of N users, and the N credit approval data are all data for performing approval operations through M approval nodes in a credit approval system, and both N and M are natural numbers greater than 1; a second acquisition module, used to acquire a target approval log of a target approval node from the credit approval system according to the N credit approval data, wherein the target approval node is any one of the M approval nodes; a determination module, used to determine the approval efficiency data of the target approval node from the target approval log, wherein the approval efficiency data includes at least one of the following: approval time, approval pass rate, credit risk assessment data, evaluation data of the user, and feedback data of other approval nodes; a generation module, used to generate approval adjustment information of the target approval node using the approval efficiency data, wherein the approval adjustment information is used to instruct the target approval node to adjust the process of performing the approval operation.

[0013] According to another embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0014] According to another embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any one of the above method embodiments when running.

[0015] According to another embodiment of the present application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0016] Through this application, N groups of credit approval data matching the approval processing of credit requests of N users are obtained, and based on this, the target approval log of the target approval node is obtained from the credit approval system to determine the average approval time, approval pass rate, the proportion of users with credit overdue and / or credit default, etc., and then the abnormal type of the target approval node is determined based on the above data, and the approval adjustment information of the target approval node is generated according to the abnormal type. Therefore, the problem of the inability to optimize the approval process in a timely manner in the related technology can be solved, thereby achieving the effect of improving the approval efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a hardware environment diagram of a method for generating approval adjustment information according to an embodiment of the present application;

[0018] Figure 2 is a flow chart of a method for generating approval adjustment information according to an embodiment of the present application;

[0019] Figure 3 It is a flow chart of a method for generating approval adjustment information of a credit approval system according to an embodiment of the present application;

[0020] Figure 4 It is a structural block diagram of a device for generating approval adjustment information according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0023] The method embodiments provided in the embodiments of the present application can be executed in a server device or a similar computing device. Taking running on a server device as an example, Figure 1 Schematic diagram of the hardware environment of a method for generating approval adjustment information in an embodiment of the present application. Figure 1 As shown, the server device may include one or more ( Figure 1Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the server device may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above server device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0024] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as a computer program corresponding to a method for generating approval adjustment information in an embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the server device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0025] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the server device. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0026] In this embodiment, a method for generating approval adjustment information is provided. Figure 2 is a flow chart of a method for generating approval adjustment information according to an embodiment of the present application. Figure 2 As shown, the process includes the following steps:

[0027] Step S202, obtaining N sets of credit approval data, wherein the N sets of credit approval data include process data of approving credit applications of N users, and the N sets of credit approval data are data of approval operations performed by M approval nodes in the credit approval system, and both N and M are natural numbers greater than 1;

[0028] Optionally, this embodiment can be applied in a credit approval system, including but not limited to a blockchain-based credit approval system, a cloud-native architecture credit approval platform, and an edge computing-based instant approval system.

[0029] Optionally, in this embodiment, the credit approval data is process data for approving the user's credit application, including but not limited to: information of the approval node that performs the approval operation on the credit approval data, and the credit request corresponding to the credit approval data.

[0030] Optionally, the approval operation in this embodiment includes, but is not limited to: data verification, credit assessment, decision on whether to approve the loan, determination of repayment conditions, risk detection and early warning.

[0031] Step S204, obtaining a target approval log of a target approval node from the credit approval system according to the N groups of credit approval data, wherein the target approval node is any one of the M approval nodes;

[0032] Optionally, the target approval log in this embodiment is used to record the data generated by the target approval node when performing the approval operation, including but not limited to: approval start time, approval end time, pause or waiting time during the approval process, approval result data, user satisfaction score data and approval feedback data.

[0033] Step S206, determining the approval efficiency data of the target approval node from the target approval log, wherein the approval efficiency data includes at least one of the following: approval time, approval pass rate, credit risk assessment data, the user's evaluation data, and feedback data from other approval nodes;

[0034] Optionally, the calculation method of the approval pass rate in this embodiment includes dividing the number of approved items in N groups of credit approval data by N.

[0035] Step S208: generating approval adjustment information of the target approval node using the approval efficiency data, wherein the approval adjustment information is used to instruct the target approval node to adjust the process of executing the approval operation.

[0036] Optionally, the approval adjustment information in this implementation is used to adjust the process of approval operations, including but not limited to: process optimization suggestions, such as shortening the processing time of specific approval nodes and simplifying redundant steps in the approval process; decision rule adjustment, adjusting the parameters of the credit scoring model based on the approval pass rate and risk assessment data, and optimizing the approval decision rules; training and coaching needs, based on the performance of the approval personnel, making personalized training suggestions to improve the quality and efficiency of approval; improving the risk warning mechanism, optimizing the risk identification algorithm, reducing false alarms, and improving the accuracy and timeliness of warnings; improving the user feedback mechanism, improving the user feedback collection and processing process, and improving customer satisfaction and service levels.

[0037] Through the above steps, based on the N sets of credit approval data obtained, the approval log of the target approval node is obtained, and the approval efficiency data is extracted from the approval log. Then, the approval adjustment information is generated using the approval efficiency data to instruct the target approval node to optimize the approval process. This solves the problem of the inability to adjust the approval process in a timely manner in related technologies, and achieves the effect of improving approval efficiency and reducing approval time.

[0038] In an exemplary embodiment, before obtaining N groups of credit approval data, the method further includes: receiving credit requests sent by N users; parsing the user information and credit fund information included in the N credit requests to obtain N groups of initial credit request data; performing data processing operations on the N groups of initial credit request data to obtain N groups of credit request data, wherein the data processing operations include data verification operations and data format conversion operations, and the data verification operations include verification of data integrity and verification of data logic; respectively inputting the N groups of credit request data into the credit approval system to respectively perform the approval operations on the N groups of credit request data through the M approval nodes; collecting process data when the M approval nodes respectively perform the approval operations on the N groups of credit request data through the data collection service provided in the approval system to obtain the N groups of credit approval data; converting the N groups of credit approval data into data in a target format and storing them in a target database.

[0039] Optionally, in this embodiment, user information includes but is not limited to basic personal information, such as name, ID number, contact information, residential address, occupation information, etc.; credit history, including the user's past credit record, repayment history, overdue or default information; financial information, including proof of income, list of assets, bank statements, debt records, etc.; and some optional information, such as educational background, marital status, living conditions, etc.

[0040] Optionally, in this embodiment, the credit fund information includes but is not limited to loan type, such as personal loan, business loan, home loan, car loan, etc.; loan amount, the specific loan amount applied for by the user; loan purpose, the purpose of the funds, such as education, entrepreneurship, house purchase, car purchase, etc.; repayment method, including loan terms such as repayment period, repayment frequency, interest rate, etc.; and some additional conditions, such as whether there is insurance, whether there is a co-borrower, whether a mortgage is required, etc.

[0041] Optionally, in this embodiment, the verification of data integrity can be specifically: checking whether all required fields in each credit request have been filled in, such as the borrower's name, ID number, contact information, income status, loan purpose, etc.; verifying whether the data conforms to the expected format, such as whether the ID number is 18 digits, whether the mobile phone number format is correct, whether the date format is unified, etc.; checking whether the data in different parts are consistent with each other, for example, whether the income shown in the income certificate matches the income stated by the borrower, and whether the total asset value in the financial data is consistent with the asset list; the system may cross-verify with external databases (such as credit bureaus, public records, etc.) to ensure that the information provided is consistent with data from third-party sources.

[0042] Optionally, in this embodiment, the data logic may be verified such that the loan amount cannot exceed a certain multiple of income, the loan term should be appropriate to the loan type, and the user's declared income is much higher than the industry average, and the system may mark it as abnormal for further review.

[0043] Optionally, in this embodiment, the data in the target format includes, but is not limited to: Extensible Markup Language (XML) files, JavaScript Object Notation (JSON), and table formats in a database.

[0044] Through the above steps, the user's credit request is received, the request data is parsed, data verification and format conversion are performed, the processed credit request data is input into the credit approval system, the approval operation is executed, and the approval process data is collected, converted into a unified format and stored, ensuring the accuracy and consistency of the credit approval data, and facilitating centralized management and analysis of credit approval data.

[0045] In an exemplary embodiment, obtaining N groups of credit approval data includes: receiving a node approval request, wherein the node approval request is used to request approval of the target approval node; responding to the node approval request, obtaining from a target database credit approval data that matches the target node information of the target approval node, the target approval process of the target node, and the approval time period included in the node approval request, to obtain N groups of the credit approval data.

[0046] Optionally, in this embodiment, the node approval request is used to request approval of the target approval node, which may specifically be to approve whether the review time of the target approval node is reasonable, whether the review conditions are compliant, etc.

[0047] Through the above steps, upon receiving an approval request for a specific approval node (corresponding to the above target approval node), the credit approval data matching the request information is retrieved from the database, and the approval information of the specific approval node can be accurately located and obtained.

[0048] In an exemplary embodiment, determining the approval efficiency data of the target approval node from the target approval log includes: converting the target approval log into a structured data format to obtain target approval data; extracting the approval process of the target approval node from the target approval data, and calculating the approval time from the approval process, wherein the approval time includes: approval start time, approval end time, and pause or waiting time during the approval process; calculating the average approval time using the approval start time, approval end time, and pause or waiting time during the approval process; counting the approval result data of the target approval node from the target approval data, and calculating the ratio between the number of approved credit approval data in N groups and N from the approval result data to obtain the approval pass rate; extracting the risk score made by the target approval node based on the user information and the user's historical credit data, and the user's historical repayment data from the target approval data; and calculating the approval result data of the target approval node based on the user information and the user's historical credit data from the target approval data. The above risk score and the above historical repayment data calculate the proportion of credit overdue and / or credit default of the above users, and determine the frequency of the above target approval node triggering the credit risk warning mechanism and the corresponding processing result after triggering the above credit risk warning mechanism; determine the credit risk assessment data based on the above ratio and the above processing result; extract the satisfaction score data and approval feedback data of the above users from the above target approval data, wherein the above satisfaction score data is data collected from the approval questionnaire or user feedback system; quantify the above satisfaction score data and approval feedback data to obtain the evaluation data of the above users; obtain the feedback data of the upstream approval node and the feedback data of the downstream approval node of the above target approval node from the above target approval data to obtain the feedback data of other approval nodes, wherein the feedback data of the above upstream approval node includes the preparation data transferred to the above target approval node, and the feedback data of the above downstream approval node includes the evaluation data of the approval decision made for the above target approval node.

[0049] Optionally, the approval performance data in this embodiment can be intuitively displayed in the approval interface in the form of a cockpit dashboard.

[0050] Optionally, in this embodiment, the average approval time is the ratio of the time consumed for performing approval operations on M credit requests at the target approval node to M, where M is a natural number greater than or equal to 1.

[0051] Optionally, the time consumed for the target approval node to perform the approval operation on the credit request in this embodiment is calculated using the approval start time and approval end time of the target approval node performing the approval operation on the credit request.

[0052] Optionally, the risk score in this embodiment can be obtained through a machine learning model or a risk scoring algorithm, by inputting user information and user historical credit data, and using a machine learning model or a risk scoring algorithm to obtain the user's risk score.

[0053] Optionally, in this embodiment, the step of calculating the proportion of credit overdue and / or credit default of users using risk score and historical repayment data can be: analyzing historical repayment records, calculating the number of times that users fail to repay on time (overdue) or fail to repay loans (default) within a certain period of time (such as the past year), and the corresponding total loan amount, and then calculating the initial overdue and / or default ratio of each user based on the number of overdue or default times and the total loan amount. For example, if a user has 3 loans, 1 of which is overdue, the total loan amount is 1 million yuan, and the overdue amount is 300,000 yuan, then the initial overdue ratio is 30%. Then, the above ratio is combined with the user's risk score to evaluate the risk level of credit overdue and default of the user, and the final proportion of credit overdue and / or credit default of the user is obtained. For example, for users with higher risk scores, based on the initial overdue ratio obtained after analyzing the historical repayment records, the final proportion of credit overdue and / or credit default is increased accordingly.

[0054] Optionally, in this embodiment, the frequency of the target approval node triggering the credit risk warning mechanism is the ratio of the number of credit requests that trigger the credit risk warning mechanism when the target approval node performs an approval operation among M credit requests to M, where M is a natural number greater than or equal to 1.

[0055] Optionally, in this embodiment, the corresponding processing results after triggering the credit risk warning mechanism include but are not limited to approval decision adjustment, warning notification, and secondary approval. For example: if the risk warning mechanism is triggered, the system may require the approval personnel to review the application again, or automatically adjust the approval conditions, such as reducing the loan amount, increasing the interest rate, requiring additional guarantees, etc.

[0056] Optionally, in this embodiment, the feedback data of the upstream approval node includes preparation data for transfer to the target approval node, including but not limited to user fund verification operations, user loan amount confirmation, etc.

[0057] Optionally, in this embodiment, the feedback data of the downstream approval node includes evaluation data of the approval decision made by the target approval node, including but not limited to decision confirmation or adjustment (the downstream approval node may confirm the decision of the target approval node, or make a decision adjustment suggestion based on subsequent review findings), risk review results (the downstream approval node may conduct a secondary risk assessment to ensure that the risk of the loan issuance decision is controllable), loan conditions and terms (based on the decision of the target approval node, the downstream approval node may set specific loan conditions, such as loan time, loan amount, loan interest rate, etc.), and subsequent process guidance (the downstream approval node may provide guidance on subsequent credit processes, such as guiding borrowers on how to repay after the loan is issued, providing loan management services, etc.). For example, if the target approval node (such as a loan approval node) decides to approve a user's loan application, the downstream approval node (such as a loan management node) may evaluate the risk of the decision and set loan conditions, such as requiring the user to complete all loan procedures before a specific date, otherwise a re-evaluation is required.

[0058] Through the above steps, the target approval log is converted into structured data, and approval efficiency data such as approval time, approval rate, risk assessment, user evaluation and other node feedback are extracted. Then, various indicators such as average approval time, approval rate, credit risk ratio, user satisfaction, etc. are calculated, providing a data basis for quantitative evaluation of approval efficiency, and providing a basis for subsequent identification of potential problems and improvement points in the approval process.

[0059] In an exemplary embodiment, after calculating the average approval time using the approval start time, the approval end time, and the pause or waiting time in the approval process, the method further includes: generating a distribution trend graph of the approval time; identifying the time delay in the approval process of the target approval node from the distribution trend graph, and marking the time delay.

[0060] Optionally, in this embodiment, the distribution trend graph of the approval time may be displayed in the form of a line graph, a scatter graph, and a box graph. For example, the approval time is arranged in chronological order, and the approval time data corresponding to each time point is connected with a line; the approval time data is distributed in the form of points in a coordinate system; a five-number summary of the approval time data (minimum value, lower quartile, median, upper quartile, maximum value) can be displayed through a box graph.

[0061] Through the above steps, the distribution trend of approval time is analyzed, the time delays in the approval process are identified, and the identified time delays are marked. This can accurately locate the links of approval time delays, facilitate subsequent targeted adjustments, and optimize the approval process.

[0062] In an exemplary embodiment, the approval adjustment information of the target approval node is generated using the approval efficiency data, including: determining the abnormal type of the target approval node according to the approval efficiency data; and generating the approval adjustment information of the target approval node according to the abnormal type.

[0063] Optionally, in this embodiment, the exception types include, but are not limited to, approval time exception, decision risk exception, approval node allocation exception, rule execution exception, and user experience exception.

[0064] Optionally, in this embodiment, targeted training can be provided to relevant reviewers based on the type of anomaly. For example, those with slow review speeds may need process familiarity training, while those with high error rates may need compliance and risk awareness training. At the same time, a system can be built that can recommend appropriate training resources based on the specific needs of reviewers. The recommendation strategy can be adaptively adjusted based on the reviewer's historical participation and personal interests, and a personalized training plan can be generated for each reviewer, including course selection, learning path, and expected goals. This training plan can be adjusted based on the reviewer's performance changes after completing the training. After the training is implemented, the effectiveness of the training can be further determined by determining whether there are anomalies in the target approval node, so that the training plan can be further adjusted in real time.

[0065] Through the above steps, the types of exceptions in the approval process are determined based on the approval efficiency data, and then approval adjustment information is generated for different exception types, which enables accurate adjustment of the approval process and solves the problem in a targeted manner. By adjusting the approval process, the approval efficiency and quality can be further improved.

[0066] In an exemplary embodiment, determining the abnormality type of the target approval node according to the approval efficiency data includes: when the approval efficiency data includes approval time, and the average approval time in the approval time is greater than the preset approval time, and the fluctuation range of the approval time is greater than the preset fluctuation range, determining that the abnormality of the target approval node is the first abnormality type; when the approval efficiency data includes approval pass rate and credit risk assessment data, and there is an abnormality in the data correlation relationship between the approval pass rate and the credit risk assessment data, determining that the abnormality of the target approval node is the second abnormality type; when the approval efficiency data includes the user's evaluation data, and the probability that the user satisfaction in the evaluation data is greater than the preset satisfaction is less than the preset probability, determining that the abnormality of the target approval node is the third abnormality type; when the approval efficiency data includes feedback data of other approval nodes, and there is no correlation between the feedback data of the other approval nodes and the approval result of the target approval node, determining that the abnormality of the target approval node is the fourth abnormality type.

[0067] Optionally, in this embodiment, the first abnormal type of the target approval node may be an approval time limit abnormality, which indicates that the approval node may have an efficiency bottleneck, such as uneven task allocation of approval personnel, unreasonable approval process design, system performance problems, etc. For the first abnormal type, the approval adjustment information that the system can generate includes: optimizing the task allocation strategy of the approval node, that is, by reallocating the approval tasks, ensuring the balance of the workload of the approval personnel, and avoiding approval delays due to task overload of a certain person; simplifying the approval process, that is, analyzing the redundant steps in the approval process, simplifying or deleting unnecessary processes; improving system performance, which can appropriately improve the server processing capacity, optimize the database query efficiency or increase the bandwidth, etc. For example, if the system monitors that the average approval time of the credit evaluation node is greater than the preset approval time, and the fluctuation range of the approval time is greater than the preset fluctuation range, the number of credit request data required to be processed by each approval node is determined. If the number of credit request data required to be processed by the approval node is unevenly distributed, the generated approval adjustment information will suggest dispersing the workload, that is, when allocating approval nodes, preferentially allocate the credit request data to those approval nodes with a smaller number of credit request data to be processed; or, according to the type of credit request data, allocate it to the approval node that requires a shorter time to approve this type of credit request data.

[0068] Optionally, in this embodiment, the second abnormality type of the target approval node may be that the approval decision does not match the risk assessment, that is, when the approval pass rate of the target approval node is abnormally high or low, and the risk assessment data is relatively stable, the system will judge it as the second abnormality type. This means that the approval decision is too loose or too strict, which is inconsistent with the risk assessment results, and may lead to loan losses or loss of high-quality customers. For the second abnormality type, the approval adjustment information that the system can generate includes but is not limited to adjusting the approval standards, that is, recommending adjustment of the approval standards to ensure that the decision matches the risk situation; optimizing the decision support model, checking and adjusting the machine learning model or risk scoring algorithm to ensure that it accurately reflects the credit risk. For example, when the approval pass rate of the target approval node is much higher than that of other nodes, but the risk score has not been significantly improved, the relevant approval personnel can be trained in compliance and risk awareness.

[0069] Optionally, in this embodiment, the third abnormality type of the target approval node may be poor customer experience, which may be caused by reasons such as long approval time, poor communication, and complicated approval process, which affects the customer experience. For the third abnormality type, the approval adjustment information generated includes but is not limited to optimizing the user communication process, that is, improving the communication channel between the user and the approval personnel, or increasing the frequency of communication with the user; improving the user interface, optimizing the user interface design, and simplifying the loan application process. For example, when it is determined that the abnormality of the target approval node is the third abnormality type, further analyze the user's feedback data. If the user feedback repeatedly mentions that the application operation is cumbersome and the interface is easy to touch by mistake, the user's interface design can be optimized.

[0070] Optionally, in this embodiment, the fourth abnormal type of the target approval node may be the failure of the information transmission and feedback mechanism between the approval nodes, indicating that there are information islands in the approval process, affecting the overall approval efficiency and quality. For the fourth abnormal type, the approval adjustment information that the system can generate includes but is not limited to data flow optimization, reviewing and optimizing data flow, ensuring timely and accurate data transmission between approval nodes, and avoiding information delays or errors; approval process coordination, redesigning or adjusting the approval process, ensuring that the decision-making basis of upstream and downstream approval nodes is interrelated, and improving the coordination and efficiency of the process. For example, in the case of determining that the abnormality of the target approval node is the fourth abnormal type, further detection determines that the actual problem is that the loan issuance node fails to adjust the loan conditions according to the risk score of the credit assessment node. The generated approval adjustment information is to recommend adding an automatic adjustment mechanism to the process design to dynamically adjust the loan interest rate, repayment method, etc. according to the credit score.

[0071] Through the above steps, abnormal judgments are made on approval time, pass rate and risk assessment, user evaluation, feedback from other approval nodes, etc., and the corresponding abnormal types are determined according to the abnormal situations of different data. This can more specifically identify problems in the approval process, and by classifying abnormal types, a more accurate and effective process adjustment strategy can be implemented.

[0072] The above method is explained below with a specific example. Figure 3 This is a flow chart of a method for generating approval adjustment information of a credit approval system implemented according to this application, such as Figure 3 As shown, a commercial bank is using a credit approval system based on big data and artificial intelligence. The system is designed with multiple approval nodes, including customer information verification, credit scoring, loan amount assessment, compliance check and final approval.

[0073] Step S302, receiving a node approval request, wherein the node approval request is used to request approval of the "credit score" node (i.e., the above-mentioned target approval node);

[0074] Step S304, obtaining credit approval data from the target database, and obtaining the target approval log of the "credit scoring" node from the credit approval system according to the credit approval data, wherein the target approval log includes N approval records that have passed through the "credit scoring" node in the past 30 days, N=1200 (i.e., 1200 approval cases are collected);

[0075] Step S306, the target approval log is structured and converted into a database format suitable for analysis. In this process, the system checks the data integrity to confirm that there are no missing fields, and standardizes all data to ensure consistent format for subsequent analysis;

[0076] Step S308, extract the approval efficiency data of the "credit score" node from the structured data, including: approval time, approval pass rate. Analysis shows that the average approval time of the "credit score" node is 70 minutes, which is much higher than the preset 45-minute standard, and the fluctuation range is also large; the approval pass rate is 75%, and the difference with the pass rate (72%) predicted by the risk assessment model meets the threshold (within 5% error), indicating that the decision matches the risk assessment.

[0077] Step S310, use the approval efficiency data to generate the approval adjustment information of the "credit score" node. Based on the above analysis results, determine that the "credit score" node is the first abnormal type, and generate approval adjustment information: increase the "credit score" node approval personnel, optimize the approval algorithm to improve the processing speed, and at the same time, train the approval personnel of the node so that they can perform the review operation proficiently.

[0078] Through the above steps, banks can promptly identify efficiency bottlenecks and decision-making deviations in the credit approval process. By generating and implementing approval adjustment information, they can effectively improve the approval quality and efficiency and enhance the user experience.

[0079] It should be noted that, through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented 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, a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0080] In this embodiment, a device for generating approval adjustment information is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0081] Figure 4 is a structural block diagram of a device for generating approval adjustment information according to an embodiment of the present application, such as Figure 4 As shown, the device comprises:

[0082] The first acquisition module 402 is used to acquire N credit approval data, wherein the N credit approval data include process data of approving credit applications of N users, and the N credit approval data are data of approval operations performed by M approval nodes in the credit approval system, and both N and M are natural numbers greater than 1;

[0083] A second acquisition module 404 is used to acquire a target approval log of a target approval node from the credit approval system according to the N credit approval data, wherein the target approval node is any one of the M approval nodes;

[0084] The determination module 406 is used to determine the approval efficiency data of the target approval node from the target approval log, wherein the approval efficiency data includes at least one of the following: approval time, approval pass rate, credit risk assessment data, evaluation data of the user, and feedback data of other approval nodes;

[0085] The generating module 408 is used to generate the approval adjustment information of the target approval node using the approval efficiency data, wherein the approval adjustment information is used to instruct the target approval node to adjust the process of executing the approval operation.

[0086] In an exemplary embodiment, the first acquisition module 402 further includes: receiving credit requests sent by N users; parsing the user information and credit fund information included in the N credit requests to obtain N groups of initial credit request data; performing data processing operations on the N groups of initial credit request data to obtain N groups of credit request data, wherein the data processing operations include data verification operations and data format conversion operations, and the data verification operations include verification of data integrity and verification of data logic; respectively inputting the N groups of credit request data into the credit approval system to respectively perform the approval operations on the N groups of credit request data through the M approval nodes; collecting process data when the M approval nodes respectively perform the approval operations on the N groups of credit request data through the data collection service provided in the approval system to obtain the N groups of credit approval data; converting the N groups of credit approval data into data in a target format and storing them in a target database.

[0087] In an exemplary embodiment, the first acquisition module 402 further includes: a first receiving unit, used to receive a node approval request, wherein the node approval request is used to request approval of the target approval node; a first responding unit, used to respond to the node approval request, and obtain credit approval data that matches the target node information of the target approval node, the target approval process of the target node, and the approval time period included in the node approval request from the target database to obtain N groups of the credit approval data.

[0088] In an exemplary embodiment, the determination module 406 further includes: a first conversion unit, configured to convert the target approval log into a structured data format to obtain target approval data; a first extraction unit, configured to extract the approval process of the target approval node from the target approval data, and calculate the approval time from the approval process, wherein the approval time includes: approval start time, approval end time, and pause or waiting time during the approval process; a first calculation unit, configured to calculate the average approval time using the approval start time, approval end time, and pause or waiting time during the approval process; a second calculation unit, configured to count the approval result data of the target approval node from the target approval data, and calculate the ratio between the number of approved credit approval data in N groups and N from the approval result data to obtain the approval pass rate; a second extraction unit, configured to extract the risk score of the target approval node based on the user information and the user's historical credit data, and the historical repayment data of the user from the target approval data; a third calculation unit, configured to calculate the average approval time using the approval start time, approval end time, and pause or waiting time during the approval process; The above-mentioned risk score and the above-mentioned historical repayment data calculate the proportion of credit overdue and / or credit default of the above-mentioned users, and determine the frequency of the above-mentioned target approval node triggering the credit risk early warning mechanism and the corresponding processing result after triggering the above-mentioned credit risk early warning mechanism; the first determination unit is used to determine the credit risk assessment data based on the above-mentioned proportion and the above-mentioned processing result; the third extraction unit is used to extract the satisfaction score data and approval feedback data of the above-mentioned user from the above-mentioned target approval data, wherein the above-mentioned satisfaction score data is data collected from the approval questionnaire or the user feedback system; the first quantification unit is used to quantify the above-mentioned satisfaction score data and approval feedback data to obtain the evaluation data of the above-mentioned user; the first acquisition unit is used to obtain the feedback data of the upstream approval node and the feedback data of the downstream approval node of the above-mentioned target approval node from the above-mentioned target approval data to obtain the feedback data of other approval nodes, wherein the feedback data of the above-mentioned upstream approval node includes the preparation data transferred to the above-mentioned target approval node, and the feedback data of the above-mentioned downstream approval node includes the evaluation data of the approval decision made for the above-mentioned target approval node.

[0089] In an exemplary embodiment, the determination module 406 further includes: a first generation unit for generating a distribution trend graph of approval time; and a first identification unit for identifying the time delay in the approval process of the target approval node from the distribution trend graph and marking the time delay.

[0090] In an exemplary embodiment, the generation module 408 further includes: a second determination unit for determining the abnormality type of the target approval node according to the approval efficiency data; and a second generation unit for generating approval adjustment information of the target approval node according to the abnormality type.

[0091] In an exemplary embodiment, the generation module 408 further includes: a third determination unit for determining that the abnormality of the target approval node is a first abnormality type when the approval efficiency data includes approval time, and the average approval time in the approval time is greater than the preset approval time, and the fluctuation range of the approval time is greater than the preset fluctuation range; a fourth determination unit for determining that the abnormality of the target approval node is a second abnormality type when the approval efficiency data includes approval pass rate and credit risk assessment data, and there is an abnormality in the data association relationship between the approval pass rate and the credit risk assessment data; a fifth determination unit for determining that the abnormality of the target approval node is a third abnormality type when the approval efficiency data includes the user's evaluation data, and the probability that the user satisfaction in the evaluation data is greater than the preset satisfaction is less than the preset probability; a sixth determination unit for determining that the abnormality of the target approval node is a fourth abnormality type when the approval efficiency data includes feedback data of other approval nodes, and there is no association between the feedback data of the other approval nodes and the approval result of the target approval node.

[0092] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0093] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0094] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0095] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0096] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0097] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any one of the above method embodiments are implemented.

[0098] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0099] The embodiments of the present application also provide a computer program, which includes computer instructions, which are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps of any one of the above method embodiments.

[0100] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0101] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0102] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for generating approval adjustment information, characterized in that: The method comprises: Acquire N groups of credit approval data, wherein the N groups of credit approval data include process data of approving credit applications of N users, and the N groups of credit approval data are data of approval operations performed by M approval nodes in a credit approval system, and both N and M are natural numbers greater than 1; Acquire a target approval log of a target approval node from the credit approval system according to the N groups of credit approval data, wherein the target approval node is any one of the M approval nodes; Determining the approval efficiency data of the target approval node from the target approval log, wherein the approval efficiency data includes at least one of the following: approval time, approval pass rate, credit risk assessment data, the user's evaluation data, and feedback data from other approval nodes; The approval efficiency data is used to generate approval adjustment information of the target approval node, wherein the approval adjustment information is used to instruct the target approval node to adjust the process of executing the approval operation.

2. The method according to claim 1, characterized in that Before obtaining N sets of credit approval data, the method further includes: Receive credit requests sent by N users; Parsing the user information and credit fund information included in the N credit requests to obtain N groups of credit request initial data; Performing data processing operations on the N groups of initial credit request data to obtain N groups of credit request data, wherein the data processing operations include data verification operations and data format conversion operations, and the data verification operations include verification of data integrity and verification of data logic; Inputting the N groups of credit request data into the credit approval system respectively, so as to perform the approval operation on the N groups of credit request data respectively through the M approval nodes; Collecting, by means of a data collection service provided in the approval system, process data when the M approval nodes respectively perform the approval operation on the N groups of the credit request data, to obtain the N groups of the credit approval data; The N groups of credit approval data are converted into data in a target format and stored in a target database.

3. The method according to claim 1, characterized in that Get N sets of credit approval data, including: Receiving a node approval request, wherein the node approval request is used to request approval of the target approval node; In response to the node approval request, the credit approval data matching the target node information of the target approval node, the target approval process of the target node and the approval time period included in the node approval request are obtained from the target database to obtain N groups of the credit approval data.

4. The method according to claim 1, characterized in that Determining the approval efficiency data of the target approval node from the target approval log includes: Convert the target approval log into a structured data format to obtain target approval data; Extracting the approval process of the target approval node from the target approval data, and calculating the approval time from the approval process, wherein the approval time includes: approval start time, approval end time, and pause or waiting time during the approval process; Calculate the average approval time by using the approval start time, the approval end time, and the pause or waiting time during the approval process; Counting the approval result data of the target approval node from the target approval data, and calculating the ratio between the number of approved credit approval data in N groups and N from the approval result data to obtain the approval pass rate; Extracting the risk score made by the target approval node based on the user information and the user's historical credit data, and the user's historical repayment data from the target approval data; Calculate the proportion of credit overdue and / or credit default of the user by using the risk score and the historical repayment data, and determine the frequency of the target approval node triggering the credit risk early warning mechanism and the corresponding processing result after the credit risk early warning mechanism is triggered; determining credit risk assessment data based on the ratio and the processing result; Extracting the user's satisfaction score data and approval feedback data from the target approval data, wherein the satisfaction score data is data collected from an approval questionnaire or a user feedback system; Quantitatively process the satisfaction rating data and approval feedback data to obtain the user's evaluation data; Acquire feedback data of an upstream approval node and feedback data of a downstream approval node of the target approval node from the target approval data to obtain feedback data of other approval nodes, wherein the feedback data of the upstream approval node includes preparation data transferred to the target approval node, and the feedback data of the downstream approval node includes evaluation data of an approval decision made for the target approval node.

5. The method according to claim 4, characterized in that After calculating the average approval time using the approval start time, the approval end time, and the pause or waiting time during the approval process, the method further includes: Generate a distribution trend chart of approval time; A time delay in the approval process of the target approval node is identified from the distribution trend graph, and the time delay is marked.

6. The method according to claim 1, characterized in that Generating the approval adjustment information of the target approval node using the approval efficiency data includes: Determine the abnormal type of the target approval node according to the approval efficiency data; The approval adjustment information of the target approval node is generated according to the exception type.

7. The method according to claim 6, characterized in that Determining the abnormal type of the target approval node according to the approval efficiency data includes: When the approval efficiency data includes approval time, and the average approval time in the approval time is greater than the preset approval time, and the fluctuation range of the approval time is greater than the preset fluctuation range, determining that the abnormality of the target approval node is a first abnormality type; When the approval efficiency data includes approval pass rate and credit risk assessment data, and there is an abnormality in the data association relationship between the approval pass rate and the credit risk assessment data, determining that the abnormality of the target approval node is a second abnormality type; When the approval efficiency data includes the evaluation data of the user, and the probability that the user satisfaction in the evaluation data is greater than the preset satisfaction is less than the preset probability, determining that the abnormality of the target approval node is a third abnormality type; When the approval efficiency data includes feedback data of other approval nodes, and there is no correlation between the feedback data of other approval nodes and the approval result of the target approval node, it is determined that the abnormality of the target approval node is a fourth abnormality type.

8. A device for generating approval adjustment information, characterized in that: include: A first acquisition module is used to acquire N credit approval data, wherein the N credit approval data include process data of approving credit applications of N users, and the N credit approval data are data of approval operations performed by M approval nodes in a credit approval system, and both N and M are natural numbers greater than 1; A second acquisition module is used to acquire a target approval log of a target approval node from the credit approval system according to the N credit approval data, wherein the target approval node is any one of the M approval nodes; A determination module, used to determine the approval efficiency data of the target approval node from the target approval log, wherein the approval efficiency data includes at least one of the following: approval time, approval pass rate, credit risk assessment data, the user's evaluation data, and feedback data of other approval nodes; A generating module is used to generate the approval adjustment information of the target approval node by using the approval efficiency data, wherein the approval adjustment information is used to instruct the target approval node to adjust the process of executing the approval operation.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program implements the steps of the method described in any one of claims 1 to 7 when executed by a processor.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method described in any one of claims 1 to 7 are implemented.

Images