CN112085597A

CN112085597A - Loan processing method and system

Info

Publication number: CN112085597A
Application number: CN202011057548.1A
Authority: CN
Inventors: 陈骜
Original assignee: Bank of China Ltd
Current assignee: Bank of China Ltd
Priority date: 2020-09-29
Filing date: 2020-09-29
Publication date: 2020-12-15

Abstract

The invention provides a loan processing method and a system, comprising a scheduling server obtaining an approval task uploaded by user interaction equipment; determining the execution time of the approval tasks and the processing priority of the approval tasks based on the approval data, the uploading time of the approval tasks, the current time of the approval tasks and the preset time limit; determining an approval process based on the approval data matching process rule base; determining the RPA capable of executing the approval task based on the execution time of the approval task, the processing priority of the approval task and the current working state of the RPA, and issuing an approval process to the RPA; the RPA performs the approval process. In the scheme, manual examination and verification are not needed, the examination and approval process corresponding to the examination and approval data can be determined through the process rule base, and the RPA capable of executing the examination and approval task is determined, so that the RPA can execute the examination and approval process corresponding to the examination and approval data, the manual examination and approval time is reduced, and the accuracy of examination and approval of the loan service can be improved.

Description

Loan processing method and system

Technical Field

The invention relates to the technical field of data processing, in particular to a loan processing method and system.

Background

With the increasing economic level, the scale of the loan consumption business is also continuously enlarged.

Currently, when a bank performs a loan transaction, a bank loan approval person of a commercial bank often approves various items of approval data such as credit conditions, loan amounts and the like in approval data provided by a client according to market rules to determine whether loan issuing operation can be performed. Because the change of the approval rules in the market is large and the data of the loan service is excessive, the manual approval of the loan service has the problems of long approval time and inaccurate approval of the loan service.

Disclosure of Invention

In view of this, embodiments of the present invention provide a loan processing method and system to solve the problems of long approval time and inaccurate approval of loan transactions in the prior art.

In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:

the first aspect of the embodiment of the invention discloses a loan processing method which is suitable for a loan processing system, wherein the loan processing system comprises user interaction equipment, a scheduling server and a process automation Robot (RPA), the user interaction equipment is connected with the scheduling server, the scheduling server is connected with the RPA, and the method comprises the following steps:

the scheduling server acquires an approval task uploaded by an approval person based on user interaction equipment, wherein the approval task carries approval data;

the scheduling server determines the execution time of the approval tasks and the processing priority of the approval tasks based on the approval data, the uploading time of the approval tasks, the current time of the approval tasks and a preset time limit, wherein the preset time limit refers to the preset processing time of the approval tasks;

the scheduling server determines an approval process corresponding to the approval task based on the approval data matching process rule base;

the scheduling server determines the RPA capable of executing the approval task based on the execution time of the approval task, the processing priority of the approval task and the current working state of the RPA, and issues an approval process to the RPA;

and the RPA calls the components in the RPA component library to execute an approval process, and an execution result obtained by executing the approval process is fed back to the user interaction equipment through the scheduling server so as to be conveniently checked by an approval person.

Optionally, before issuing the approval process to the RPA, the method further includes:

the scheduling server carries out wind control processing based on credit data of the applicant in the approval data to obtain a predicted risk value, wherein the credit data of the applicant is used for indicating the repayment condition of the loan service;

if the predicted risk value indicates that the loan service has risks, the scheduling server stops all examination and approval works of the examination and approval tasks and displays the examination and approval risks of the examination and approval tasks through the user interaction equipment;

and if the predicted risk value indicates that the loan service has no risk, the scheduling server issues an approval process to the RPA.

Optionally, the method further includes:

the scheduling server sends a repayment detection instruction to the RPA in the non-working state within a preset time period;

the RPA inquires repayment conditions of all loan businesses based on the repayment detection instruction and feeds back the repayment conditions to the scheduling server;

and the scheduling server determines the loan service of the repayment time to be reached based on the repayment conditions of all the loan services, and displays the information of the applicant corresponding to the loan service of the repayment time to be reached on the user interaction equipment.

Optionally, the determining, by the scheduling server, the execution time of the approval task and the processing priority of the approval task based on the approval data, the time for uploading the approval task, the current time of the approval task, and the preset time limit includes:

the scheduling server matches an approval task execution time database based on the loan type, the loan amount and the loan level, and determines the execution time of the approval task corresponding to the loan type, the loan amount and the loan level;

the scheduling server acquires the current time of the approval task and calculates the difference between the current time of the approval task and a preset time limit;

and the scheduling server determines the priority of processing the approval tasks according to the uploading time of the approval tasks, the difference between the current time of the approval tasks and the preset time limit and the user level of the applicant.

Optionally, the determining, by the scheduling server, an RPA that can execute the approval task based on the execution time of the approval task, the processing priority of the approval task, and the current state of the RPA includes:

determining whether an RPA in an idle working state exists currently;

if the RPA exists, the scheduling server determines that any RPA in an idle working state is the RPA capable of executing the approval task;

if not, calculating the time required by each RPA to process all the examination and approval tasks of the RPA;

sequencing the RPAs according to the time required for processing all the examination and approval tasks of the RPAs to obtain an RPA sequence table, wherein the RPA sequence table is used for referring to a table which is sequenced from low to high according to the time required for processing all the examination and approval tasks of the RPA;

and the scheduling server determines the RPA capable of executing the approval task from the sequence list based on the execution time of the approval task and the processing priority of the approval task.

The second aspect of the embodiment of the invention discloses a loan processing system, which comprises user interaction equipment, a scheduling server and an RPA, wherein the user interaction equipment is connected with the scheduling server;

the user interaction equipment is used for uploading an approval task, and the approval task carries approval data; displaying an execution result obtained by the RPA robot executing the approval process;

the scheduling server is used for acquiring an approval task uploaded by an approval person based on the user interaction equipment, wherein the approval task carries approval data; determining the execution time of the approval tasks and the processing priority of the approval tasks based on the approval data, the uploading time of the approval tasks, the current time of the approval tasks and a preset time limit, wherein the preset time limit refers to the preset processing time of the approval tasks; determining an approval process corresponding to the approval task based on the approval data matching process rule base; determining the RPA capable of executing the approval task based on the execution time of the approval task, the processing priority of the approval task and the current working state of the RPA, and issuing an approval process to the RPA;

and the RPA is used for calling the components in the RPA component library to execute the examination and approval process, and feeding back an execution result obtained by executing the examination and approval process to the user interaction equipment through the scheduling server so as to facilitate examination and approval personnel to check.

Optionally, the scheduling server is further configured to:

before issuing an approval process to the RPA, carrying out wind control processing based on credit data of an applicant in the approval data to obtain a predicted risk value, wherein the credit data of the applicant is used for indicating the repayment condition of the loan service; if the predicted risk value indicates that the loan service has risks, the scheduling server stops all examination and approval works of the examination and approval tasks and displays the examination and approval risks of the examination and approval tasks through the user interaction equipment; and if the predicted risk value indicates that the loan service has no risk, the scheduling server issues an approval process to the RPA.

Optionally, the scheduling server is further configured to:

sending a repayment detection instruction to the RPA in the non-working state within a preset time period; when the feedback repayment conditions of all the loan services are received, the loan service at the repayment time is determined based on the repayment conditions of all the loan services, and the information of the applicant corresponding to the loan service at the repayment time is displayed on the user interaction equipment;

correspondingly, the RPA is further configured to: and inquiring repayment conditions of all loan businesses based on the repayment detection instruction, and feeding back the repayment conditions to the scheduling server.

Optionally, the scheduling server for determining the execution time of the approval task and the processing priority of the approval task based on the approval data, the time for uploading the approval task, the current time of the approval task, and the preset time limit is specifically configured to:

matching an approval task execution time database based on the loan type, the loan amount and the loan level, and determining the execution time of the approval task corresponding to the loan type, the loan amount and the loan level; acquiring the current time of the approval task, and calculating the difference between the current time of the approval task and a preset time limit; and determining the priority of processing the approval tasks according to the uploading time of the approval tasks, the difference between the current time of the approval tasks and the preset time limit and the user level of the applicant.

Optionally, the scheduling server that determines an RPA that can execute the approval task based on the execution time of the approval task, the processing priority of the approval task, and the current state of the RPA is specifically configured to:

determining whether an RPA in an idle working state exists currently; if the RPA exists, the scheduling server determines that any RPA in an idle working state is the RPA capable of executing the approval task; if not, calculating the time required by each RPA to process all the examination and approval tasks of the RPA; sequencing the RPAs according to the time required for processing all the examination and approval tasks of the RPAs to obtain an RPA sequence table, wherein the RPA sequence table is used for referring to a table which is sequenced from low to high according to the time required for processing all the examination and approval tasks of the RPA; and the scheduling server determines the RPA capable of executing the approval task from the sequence list based on the execution time of the approval task and the processing priority of the approval task.

Based on the loan processing method and system provided by the embodiment of the invention, the method comprises the following steps: the scheduling server acquires an approval task uploaded by an approval person based on user interaction equipment, wherein the approval task carries approval data; the scheduling server determines the execution time of the approval tasks and the processing priority of the approval tasks based on the approval data, the uploading time of the approval tasks, the current time of the approval tasks and a preset time limit, wherein the preset time limit refers to the preset processing time of the approval tasks; the scheduling server matches a process rule base based on the approval data, and determines an approval process corresponding to the approval task; the scheduling server determines the RPA capable of executing the approval task based on the execution time of the approval task, the processing priority of the approval task and the current working state of the RPA, and issues an approval process to the RPA; and the RPA calls the components in the RPA component library to execute the examination and approval process, and an execution result obtained by executing the examination and approval process is fed back to the user interaction equipment through the scheduling server so as to be conveniently checked by the examination and approval personnel. In the embodiment of the invention, manual examination and verification are not needed, and the examination and approval process corresponding to the examination and approval data can be determined through the examination and approval data matching process rule base; determining the RPA capable of executing the approval task according to the approval data, the time uploaded by the approval task, the current time and preset time limit of the approval task and the current working state of the RPA; and then the approval process is sent to the RPA which can execute the approval task, so that the RPA can execute the approval process. Therefore, the time of manual examination and approval is reduced, and the accuracy of examination and approval of the loan service can be improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

Fig. 1 is a schematic diagram of a loan processing system according to an embodiment of the invention;

fig. 2 is a schematic structural diagram of a loan processing method according to an embodiment of the invention;

FIG. 3 is a schematic diagram of another loan processing method according to an embodiment of the invention;

fig. 4 is a schematic structural diagram of another loan processing method according to an embodiment of the invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In this application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

In the embodiment of the invention, manual examination and verification are not needed, and the examination and approval process corresponding to the examination and approval data can be determined through the examination and approval data matching process rule base; determining the RPA capable of executing the approval task according to the approval data, the time uploaded by the approval task, the current time and preset time limit of the approval task and the current working state of the RPA; and then the approval process is sent to the RPA which can execute the approval task, so that the RPA can execute the approval process. Therefore, the time of manual examination and approval is reduced, and the accuracy of examination and approval of the loan service can be improved.

Referring to fig. 1, which is a schematic structural diagram of a loan processing system according to an embodiment of the present invention, the loan processing system 10 includes: a user interaction device 20, a dispatch server 30, and a Process Automation robot RPA (Robotic Process Automation) 40.

The user interaction device 20 is connected to the dispatch server 30 and the dispatch server 30 is connected to the RPA 40.

The number of the RPAs 40 is plural, the RPA40 includes N RPAs including RPA41, RPA42.. and RPA4N, and specifically, the scheduling server 30 is connected to the N RPAs respectively.

The user interaction equipment 20 is used for uploading an approval task, and the approval task carries approval data; and displaying the execution result obtained by the RPA40 executing the approval process.

In a particular implementation, the user interaction device 20 receives approval data provided by the applicant of the loan transaction uploaded by an approver. And displaying the execution result after the RPA40 executes the approval process.

It should be noted that the approval data at least includes the loan type, the loan amount, the work type of the applicant, and the income data of the applicant, the loan amount, the loan level, and the credit data of the applicant.

The scheduling server 30 is used for acquiring the approval tasks uploaded by the approval personnel based on the user interaction equipment 20; determining the execution time of the approval tasks and the processing priority of the approval tasks based on the approval data, the uploading time of the approval tasks, the current time of the approval tasks and the preset time limit; matching a process rule base based on the approval data, and determining an approval process corresponding to the approval task; and determining RPA40 capable of executing the approval task based on the execution time of the approval task, the processing priority of the approval task and the current working state of the RPA40, and issuing an approval process to the RPA 40.

In the embodiment of the invention, the scheduling server is provided with a process rule base for storing the corresponding relation between the examination and approval data and the examination and approval process.

It should be noted that the approver configures the approval data and the approval process, and prestores the configured correspondence between the approval data and the approval process in the process rule base of the scheduling server 30 through the user interaction device 20.

It should be noted that the approval task carries approval data. The preset time limit refers to the preset processing time of the approval task.

Wherein the preset time limit may be set to 24 hours.

Optionally, when receiving the approval task carrying the approval data, the scheduling server 30 obtains the time for uploading the approval task and the current time of the approval task.

The time for uploading the approval task is the time required for uploading the approval task.

In a specific implementation, the scheduling server 30 obtains an approval task carrying approval data. Searching the execution time of the approval task corresponding to the approval data in an approval task execution time database; and then determining the processing priority of the approval tasks according to the uploading time of the approval tasks, the current time of the approval tasks and a preset time limit. The scheduling server 30 then traverses the process rule base using the loan type, the loan amount, the work type of the applicant, and the income data of the applicant to match the approval process corresponding to the type of the loan, the loan amount, the work type of the applicant, and the income data of the applicant. Secondly, the scheduling server 30 determines the working states of all the current RPAs 40, determines the RPAs 40 capable of executing the approval tasks according to the execution time of the approval tasks, the processing priority of the approval tasks and the current working state of the RPAs 40, and then issues the approval process to the RPAs 40.

The examination and approval task execution time database is used for storing the correspondence between the examination and approval data and the execution time of the examination and approval task.

The approval process is used for indicating steps required for performing approval and release operations.

And the RPA40 is used for calling the components in the RPA40 component library to execute the approval process, and feeding back an execution result obtained by executing the approval process to the user interaction equipment 20 through the scheduling server 30 so as to be conveniently viewed by an approval person.

In a specific implementation, the RPA invokes an approval process component in its RPA component library to execute an approval process based on its own automation process to complete approval and release operations, so that an obtained approval execution result is fed back to the user interaction device 20 through the scheduling server 30, and the user interaction device 20 displays the execution result to facilitate checking by an approval worker.

Optionally, based on the loan processing system shown in fig. 1, the scheduling server 30, which determines the execution time of the approval task and the processing priority of the approval task based on the approval data, the upload time of the approval task, the current time of the approval task, and the preset time limit, is specifically configured to:

matching an approval task execution time database based on the loan type, the loan amount and the loan level, and determining the execution time of the approval task corresponding to the loan type, the loan amount and the loan level; acquiring the current time of the approval task, and calculating the difference between the current time of the approval task and a preset time limit; and determining the processing priority of the approval tasks according to the uploading time of the approval tasks, the difference between the current time of the approval tasks and the preset time limit and the user level of the applicant.

It should be noted that the processing priority of the approval tasks can be divided into F level, D level, C level, a level and S level from low to high, and the levels indicate that the approval sequence of the approval tasks is more and more advanced from left to right.

In the embodiment of the invention, the corresponding relation between the uploading time of the approval task and the priority of the approval task is stored in the first relation table. And storing the corresponding relation between the difference between the current time of the approval task and the preset time limit and the priority of the approval task into a second relation table. And storing the corresponding relation between the user level and the priority of the approval task into a third relation table.

It should be noted that, in the first relation table, each time period corresponds to a priority, for example: the uploading time of the approval task belongs to a first time period within 0-40 minutes, and the corresponding priority is F level. The longer the uploading time of the approval task is, the higher the corresponding priority is.

In the second relation table, each time period also corresponds to a priority, for example: the difference between the current time of the approval task and the preset time limit is in a first time period of 0-10 minutes, and the corresponding priority is S level. The smaller the difference between the current time of the approval task and the preset time limit is, the higher the corresponding priority is.

The user grades can be divided into a common user grade, a silver user grade, a gold user grade, a diamond user grade, a super diamond user grade and the like, and the grades are sequentially increased from left to right.

Each user level corresponds to a priority. Such as: the priority corresponding to the common user level is F level.

In a specific implementation, the scheduling server 30 searches the time database of the execution of the approval task through the loan type, the loan amount, and the loan level in the approval data, and finds the execution time of the approval task corresponding to the loan type, the loan amount, and the loan level. And acquiring the current time of the approval task which is not subjected to the approval processing in time, and calculating the time difference between the current time of the approval task and the preset time limit. And searching a first relation table based on the time uploaded by the approval task, searching a second relation table based on the difference between the current time of the approval task and the preset time limit, searching a third relation table based on the user level of the applicant, and determining the highest priority among the priorities obtained by searching the first relation table, the second relation table and the third relation table as the priority for processing the approval task.

The approval task execution time database is used for storing the correspondence between the input loan type, loan amount, loan level, and the execution time of the output approval task.

In the embodiment of the invention, the execution time database of the approval task is matched according to the loan type, the loan amount and the loan level in the approval data, and the execution time of the approval task is determined; and searching respective relation tables based on the uploading time of the approval task, the current time of the approval task and the preset time limit to obtain the priorities corresponding to the respective relation tables, and determining the highest priority in the priorities corresponding to the respective relation tables as the priority for processing the approval task. Based on the obtained execution time of the approval task, the priority of the approval task processing and the current working state of the RPA, the RPA capable of executing the approval task can be further determined. Meanwhile, an approval process corresponding to the approval data is determined through the approval data matching process rule base; and finally, sending the approval process to the RPA capable of executing the approval task so that the RPA can execute the approval process. Therefore, the time of manual examination and approval is reduced, and the accuracy of examination and approval of the loan service can be improved.

Optionally, based on the loan system shown in fig. 1, the scheduling server 30 that determines the RPA40 that can execute the approval task based on the execution time of the approval task, the processing priority of the approval task, and the current state of the RPA is specifically configured to:

determining whether an RPA in an idle working state exists currently; if the RPA40 exists, the scheduling server 30 determines that any RPA40 in the idle working state is the RPA40 which can execute the approval task; if not, calculating the time required by each RPA40 to process all the approval tasks of the RPA 40; sequencing the RPA40 according to the time required for processing all the examination and approval tasks of the RPA40 to obtain an RPA sequence list; the scheduling server 30 determines RPAs that can execute the approval task from the sequence list based on the execution time of the approval task and the approval task processing priority.

In a specific implementation, the scheduling server 30 determines that the current working state is in an idle RPA40, and if it is determined that at least one RPA40 in the idle working state exists in the current RPA40, selects any one RPA40 from all RPAs 40 in the idle working state as the RPA40 for executing the approval task. If the current RPA40 is determined not to have the RPA40 in the idle working state, all the current RPAs 40 are determined to be in the working state, and the time required by all the examination and approval tasks which need to be processed currently by each RPA40 is calculated respectively. And sequencing the RPA40 from low to high according to the time required for processing all the approval tasks of the RPA40 to obtain an RPA sequence list. And sequencing based on the execution time of the approval tasks and the processing priority of the approval tasks, specifically sequencing the approval tasks from high to low according to the priority, and sequencing according to the execution time of the approval tasks from small to large if the priorities are the same to obtain the sequenced approval tasks. And based on the sorted approval tasks, determining the RPAs which can execute the approval tasks from the RPA sequence list, namely, sequentially allocating the sorted approval tasks to the RPAs sorted from low to high in the RPA sequence list.

It should be noted that the RPA sequence table is used to refer to a table sorted from low to high according to the time required for processing all approval tasks of the RPA sequence table.

In the embodiment of the invention, the RPA capable of executing the approval task is determined according to the current working state of the RPA, the obtained execution time of the approval task and the priority of the processing of the approval task. Meanwhile, an approval process corresponding to the approval data is determined through the approval data matching process rule base; and finally, sending the approval process to the RPA capable of executing the approval task so that the RPA can execute the approval process. Therefore, the time of manual examination and approval is reduced, and the accuracy of examination and approval of the loan service can be improved.

Optionally, based on the loan processing system shown in fig. 1, a wind control module for risk prediction of loan transaction is further disposed in the dispatch controller 30.

The dispatch server 30 is also configured to: before issuing the approval process to the RPA40, carrying out wind control processing based on the credit data of the applicant to obtain a predicted risk value; if the predicted risk value indicates that the loan transaction has risks, the scheduling server 30 stops all examination and approval works of the examination and approval tasks and displays the examination and approval risks of the examination and approval tasks through user interaction equipment; if the predicted risk value indicates that the loan transaction has no risk, the scheduling server 30 issues the approval process to the RPA 40.

Specifically, the credit data of the applicant is used as an input of the wind control module of the scheduling server 30, and the credit data of the applicant is processed based on the wind control module, so as to output a predicted risk value. And judging whether the predicted risk value is 1, if so, indicating that the predicted risk value indicates that the loan service has risk, stopping all approval works related to the approval task in the user interaction equipment 10 and the RPA40 by the scheduling server 30, and sending information corresponding to the approval risk of the approval task to the user interaction equipment 20, so that the user interaction equipment can display the approval risk in the information corresponding to the approval risk of the approval task. If the predicted risk value is not 1, the predicted risk value is 0, and at this time, the predicted risk value indicates that the loan service has no risk, and the scheduling server 30 issues the approval process to the RPA40 which can execute the approval task.

Note that the credit data of the applicant is used for indicating the repayment condition of the loan service

It should be noted that the output predicted risk value may be a value of 0 or 1, where a value of 1 is used to indicate that the loan transaction is at risk, and a value of 0 is used to indicate that the loan transaction is not at risk.

The wind control module is obtained by training by using credit data of historical applicants.

In the embodiment of the invention, manual examination and verification are not needed, and the examination and approval process corresponding to the examination and approval data can be determined through the examination and approval data matching process rule base; determining the RPA capable of executing the approval task according to the approval data, the time uploaded by the approval task, the current time and preset time limit of the approval task and the current working state of the RPA; at this time, the loan transaction is subjected to wind control processing based on the credit data of the applicant, and a predicted risk value is obtained. And when the predicted risk value indicates that the loan service has no risk, sending the approval process to the RPA capable of executing the approval task so that the RPA can execute the approval process. Therefore, the time of manual examination and approval is reduced, and the accuracy of examination and approval of the loan service can be improved.

Optionally, based on the loan processing system shown in fig. 1, the scheduling server 30 is further configured to:

sending a repayment detection instruction to the RPA in the non-working state within a preset time period; and when the feedback repayment conditions of all the loan services are received, determining the loan services at the repayment time to be reached based on the repayment conditions of all the loan services, and displaying the information of the applicant corresponding to the loan services at the repayment time to be reached on the user interaction equipment.

In a specific implementation, the scheduling server 30 determines the RPA40 currently in the idle working state within a preset time period, and sends a repayment detection instruction to any one or more RPA40 in the idle working state. The scheduling server 30 determines a loan transaction with a repayment time less than a preset time, that is, determines a loan transaction to arrive at the repayment time, based on the not yet repayment condition of all loan transactions fed back by the RPA40, and transmits the loan transaction with the repayment time less than the preset time to the user interaction device 20.

Accordingly, RPA40, is also configured to: and inquiring repayment conditions of all loan businesses based on the repayment detection instruction, and feeding back to the scheduling server 30.

Specifically, when receiving the repayment detection instruction, the RPA40 starts polling the repayment status of all loan services, and feeds back the repayment status to the scheduling server 30.

Note that the payment condition includes a overdue payment condition and a non-payment condition.

The preset time period is set by the skilled person according to experience, and can be set to 23 hours to 24 hours per day, for example.

The preset time is set by experience of a person skilled in the art, and may be set to 10 days, for example.

In the embodiment of the invention, a repayment detection instruction is sent to the RPA in the non-working state within a preset time period, so that any one or more RPAs in the idle working state can inquire the repayment conditions of all loan businesses based on the repayment detection instruction, and the repayment conditions of the loan businesses can be known in time.

Based on the loan processing system disclosed in the embodiment of the present invention, the present invention also discloses a loan processing method correspondingly, as shown in fig. 2, which is a schematic flow diagram of the loan processing method shown in the embodiment of the present invention, and the loan processing method includes:

step S201: and the scheduling server acquires the approval tasks uploaded by the approval personnel based on the user interaction equipment.

In step S201, the approval task carries approval data.

Optionally, the approver uploads approval data provided by the applicant of the loan service based on the user interaction device, and the user interaction device sends an approval task carrying the approval data to the scheduling server.

In the process of implementing step S201 specifically, the scheduling server obtains an approval task carrying approval data, and analyzes the approval task to obtain the approval data.

The approval data includes the loan type, the loan amount, the work type of the applicant, and the income data of the applicant, the loan amount, the loan level, and the credit data of the applicant.

Optionally, when receiving the approval task carrying the approval data, the scheduling server obtains the time for uploading the approval task and the current time of the approval task.

Step S202: and the scheduling server determines the execution time of the approval tasks and the processing priority of the approval tasks based on the approval data, the uploading time of the approval tasks, the current time of the approval tasks and the preset time limit.

In step S202, the preset time limit refers to a processing time of the approval task set in advance, wherein the preset time limit may be set to 24 hours.

In the process of implementing the step S202 specifically, the scheduling server searches the execution time of the approval task corresponding to the approval data in the approval task execution time database; and the scheduling server determines the processing priority of the approval tasks according to the uploading time of the approval tasks, the current time of the approval tasks and a preset time limit.

Step S203: and the scheduling server matches a process rule base based on the approval data and determines an approval process corresponding to the approval task.

In the process of implementing step S203 specifically, the scheduling server traverses the process rule base by using the loan type, the loan amount, the work type of the applicant and the income data of the applicant, and matches the approval process corresponding to the money type, the loan amount, the work type of the applicant and the income data of the applicant.

Step S204: and the scheduling server determines the RPA capable of executing the approval task based on the execution time of the approval task, the processing priority of the approval task and the current working state of the RPA, and issues the approval process to the RPA.

In the process of implementing step S204, the scheduling server determines the working states of all the current RPAs, then determines the RPAs that can execute the approval task according to the execution time of the approval task, the processing priority of the approval task, and the current working state of the RPAs, and then issues the approval process to the RPAs.

Step S205: and the RPA calls the components in the RPA component library to execute the examination and approval process, and an execution result obtained by executing the examination and approval process is fed back to the user interaction equipment through the scheduling server so as to be conveniently checked by the examination and approval personnel.

In the process of implementing step S205 specifically, the RPA calls the approval process component in its RPA component library to execute the approval process based on its own automation process to complete the approval and release operations, so as to feed back the obtained approval execution result to the user interaction device through the scheduling server, and enable the user interaction device to display the execution result, so as to facilitate the examination and approval staff to check.

Based on the loan processing method shown in the above embodiment of the present invention, in the step S202, the scheduling server determines the execution time of the approval task and the task processing priority based on the approval data and the preset time limit, including the following steps:

step S11: and the scheduling server determines the execution time of the approval task corresponding to the loan type, the loan amount and the loan level based on a database of the execution time of the approval task matched with the loan type, the loan amount and the loan level.

In the process of implementing step S11 specifically, the scheduling server traverses the time database of the approval task execution through the loan type, the loan amount, and the loan level in the approval data, and searches for the execution time of the approval task corresponding to the loan type, the loan amount, and the loan level.

Step S12: and the scheduling server acquires the current time of the approval task and calculates the difference between the current time of the approval task and the preset time limit.

In the process of specifically implementing step S12, the scheduling server obtains the current time of the approval task that has not been subjected to the approval processing in time, and calculates the time difference between the current time of the approval task and the preset time limit.

Step S13: and the scheduling server determines the processing priority of the approval tasks according to the uploading time of the approval tasks, the difference between the current time of the approval tasks and the preset time limit or the user level of the applicant.

In step S13, the approval task processing priorities can be divided into F-level, D-level, C-level, a-level and S-level from low to high, and the levels indicate from left to right that the approval sequence of the approval tasks is more and more advanced.

In the embodiment of the invention, when the uploading time of the approval task is too long, the smaller the time difference between the approval task and the preset time limit is, the higher the priority of the approval task is; at the moment, the corresponding relation between the uploading time of the examination and approval tasks and the priority of the examination and approval tasks is stored in a first relation table.

It should be noted that, in the first relation table, each time period corresponds to a priority, for example: the uploading time of the approval task belongs to a first time period within 0-40 minutes, and the corresponding priority is F level; and the uploading time of the approval task belongs to a second time period within 40-80 minutes, the corresponding priority is D level, and the higher the uploading time of the approval task is, the higher the corresponding priority is.

In the embodiment of the invention, when the scheduling server needs to process more approval tasks, the time difference between the current time of the approval tasks and the preset time limit is calculated, and when the current time of the approval tasks is closer to the preset time limit, the higher the priority of the approval tasks is; at the moment, the corresponding relation between the difference between the current time of the approval task and the preset time limit and the priority of the approval task is stored in a second relation table.

It should be noted that, in the second relation table, each time period also corresponds to a priority, for example: the difference between the current time of the approval task and the preset time limit is in a first time period of 0-10 minutes, and the corresponding priority is S level; the difference between the current time of the approval task and the preset time limit belongs to a second time period within 10-30 minutes, and the corresponding priority is A level; by analogy, the smaller the difference between the current time of the approval task and the preset time limit is, the higher the corresponding priority is.

In the embodiment of the invention, when the user level of the applicant is higher, the priority of the approval task is higher; at this time, the corresponding relation between the user level and the priority of the approval task is stored in the third relation table.

It should be noted that the user level refers to the size of a user with a special authority, and is set by a bank according to the consumption and business handling levels of the user, and the user level can be divided into a common user level, a silver user level, a gold user level, a diamond user level, a super diamond user level and the like, and the levels are sequentially increased from left to right.

Each user level corresponds to a priority.

Such as: the priority corresponding to the common user level is F level.

In the process of implementing step S13, the first relationship table is searched based on the time uploaded by the approval task, the second relationship table is searched based on the difference between the current time of the approval task and the preset time limit, the third relationship table is searched based on the user level of the applicant, and the highest priority among the priorities obtained by searching the first relationship table, the second relationship table and the third relationship table is determined as the priority of the approval task processing.

For example: if the task of examination and approval a₁Upload time 56 minutes, approveTask a₁The difference between the current time and the preset time limit is 8 minutes, and the approval task a₁The corresponding user rating of the applicant is a normal user rating. Based on approval task a₁The uploaded time is 56 minutes, a first relation table is searched, and a task a for examination and approval is obtained₁The priority corresponding to the uploading time is D level; based on approval task a₁The difference between the current time and the preset time limit is 8 minutes, a second relation table is searched, and an approval task a is obtained₁The priority corresponding to the difference between the current time and the preset time limit is S level; based on approval task a₁Searching a third relation table by the corresponding ordinary user grade of the applicant to obtain and approve the task a₁The priority corresponding to the user level of the corresponding applicant is F level; and determining the highest priority S level in the priority levels obtained by searching the first relation table, the second relation table and the third relation table as the priority level of the approval task processing.

Based on the loan processing method shown in the above embodiment of the present invention, in the step S204, the scheduling server determines the RPA capable of executing the approval task based on the execution time of the approval task, the processing priority of the approval task, and the current state of the RPA, and includes the following steps:

step S21: and determining whether the RPA in the idle working state exists currently, if so, executing the step S22, and if not, executing the steps S23 to S25.

In the process of implementing step S21, it is determined that the current working state is in an idle RPA, if it is determined that at least one RPA in the idle working state exists in the current RPA, step S22 is executed, and if it is determined that no RPA in the idle working state exists in the current RPA, steps S23 to S25 are executed.

Step S22: the scheduling server determines any RPA in the idle working state as the RPA which can execute the examination and approval task.

In the process of implementing step S22, the scheduling server selects any one of the RPAs in the idle working state as the RPA executing the approval task.

Step S23: and calculating the time required by each RPA to process all the approval tasks of the RPA.

In the process of implementing step S23, it is determined that all RPAs are currently in a working state, and the time required for all approval tasks currently required to be processed by each RPA is calculated respectively.

Optionally, if other tasks exist in the RPA itself, such as inquiring the repayment status of all loan services, etc., it is also necessary to calculate the time required for processing other applications.

For example: the RPAs in the working state are RPA1 and RPA 2. Wherein RPA1 needs to process approval task a₁Approval task a₂And approval task a₃And 3 approval tasks in total. Processing approval task a₁The time required was 65 minutes, and the approval task a was processed₂The time required was 70 minutes, and the approval task a was processed₃The time required was 35 minutes. RPA1 needs to process approval task b₁And approval task b₂And 2 approval tasks in total. Processing approval task b₁The time required was 50 minutes, and the approval task b was processed₂The time required was 45 minutes. Specifically, the time required for calculating that the RPA1 needs to process 3 approval tasks is 170 minutes; calculating RPA2 requires processingThe time required for 2 approval tasks was 95 minutes.

Step S24: and sequencing the RPAs according to the time required for processing all the approval tasks of the RPAs to obtain an RPA sequence list.

In step S24, the RPA sequence table is used to refer to a table sorted from low to high according to the time required to process all of the approval tasks of the RPA sequence table.

In the process of specifically implementing step S24, the RPAs are sorted from low to high according to the time required for processing all the approval tasks of the RPAs themselves, so as to obtain an RPA sequence table.

For example: if the time required by the RPA1 to process all the examination and approval tasks is 170 minutes, the time required by the RPA2 to process all the examination and approval tasks is 95 minutes, and the time required by the RPA3 to process all the examination and approval tasks is 153 minutes. And sequencing the RPA1, the RPA2 and the RPA3 from low to high according to the time required for processing all the approval tasks of the RPA, and obtaining an RPA sequence list which is sequenced into the sequence of RPA2, RPA3 to RPA 1.

Step S25: and the scheduling server determines the RPA capable of executing the approval task from the sequence table based on the execution time of the approval task and the processing priority of the approval task.

In the process of specifically implementing step S25, the scheduling server sorts the approval tasks based on the execution time of the approval tasks and the approval task processing priority, specifically, sorts the approval tasks from high to low according to the priority, and if the priorities are the same, sorts the approval tasks from small to large according to the execution time of the approval tasks, so as to obtain the sorted approval tasks. And based on the sorted approval tasks, determining the RPAs which can execute the approval tasks from the RPA sequence list, namely, sequentially allocating the sorted approval tasks to the RPAs sorted from low to high in the RPA sequence list.

For example: if approval task A₁The execution time of 40 minutes and the processing priority of the approval task are D level, and the approval task A₂The execution time of 60 minutes and the processing priority of the approval task are D level, and the approval task A₃The execution time of the system is 60 minutes, and the processing priority of the approval task is A level; the sequence of the RPA sequence listing is RPA2, RPA3 through RPA 1. Scheduling server based on approvalAffair A₁Approval task A₂Approval task A₃The execution time and the processing priority of the approval tasks are sorted to obtain a sorted approval task A₃Approval task A₁To approval task A₂Sequential approval tasks. And is based on the ordering as an approval task A₃Approval task A₁To approval task A₂Sequential approval tasks, determining from the RPA sequence list that approval task A can be performed₃The RPA of (1) is RPA2, and can execute examination and approval task A₁Is RPA3, and can perform approval task A₂The RPA of (a) is RPA 1.

Based on the loan processing method shown in fig. 2 in the embodiment of the invention described above, referring to fig. 3 in combination with fig. 2, the loan processing method includes:

step S206: and the scheduling server sends a repayment detection instruction to the RPA in the non-working state within a preset time period.

In the process of implementing step S206 specifically, the scheduling server determines the RPAs currently in the idle working state within a preset time period, and sends a repayment detection instruction to any one or more RPAs in the idle working state.

Optionally, if all the RPAs are in the working state within the preset time period, calculating the time required by each RPA to execute all its tasks, and sending a repayment detection instruction to the RPA with the shortest time required to execute all its tasks.

It should be noted that the preset time period is set by the skilled person according to experience, and may be set to 23 hours to 24 hours per day, for example.

Step S207: and the RPA inquires repayment conditions of all loan businesses based on the repayment detection instruction and feeds back the repayment conditions to the scheduling server.

In the process of implementing step S207 specifically, when receiving the repayment detection instruction, the RPA starts to poll the repayment status of all loan services, and feeds back the repayment status to the scheduling server.

Step S208: and the scheduling server determines the loan service of the repayment time to be reached based on the repayment conditions of all the loan services, and displays the information of the applicant corresponding to the loan service of the repayment time to be reached on the user interaction equipment.

In the process of implementing step S208 specifically, the scheduling server determines, based on the non-repayment condition of all the loan businesses, a loan business whose repayment time is less than the preset time, that is, determines a loan business whose repayment time is to be reached, and sends the loan business whose repayment time is less than the preset time to the user interaction device, so that the user interaction device displays the applicant information corresponding to the loan business whose repayment time is to be reached. So that the approver can pay the loan application according to the information of the applicant.

Optionally, the user interaction device displays the information of the applicant corresponding to the loan service at the repayment time, and sends information of reminding that the repayment is overdue to the applicant of the loan service according to the information of the applicant.

The preset time is preset by experience of a person skilled in the art, and may be set to 10 days, for example.

Based on the loan processing method shown in fig. 2 in the embodiment of the present invention, the present invention further discloses a flow diagram of another loan processing method, where the loan processing method includes:

s401: and the scheduling server acquires the approval tasks uploaded by the approval personnel based on the user interaction equipment.

In step S401, the approval task carries approval data.

S402: and the scheduling server determines the execution time of the approval tasks and the processing priority of the approval tasks based on the approval data, the uploading time of the approval tasks, the current time of the approval tasks and the preset time limit.

In step S402, the preset time limit refers to a processing time of the approval task set in advance.

Step S403: and the scheduling server matches a process rule base based on the approval data and determines an approval process corresponding to the approval task.

Step S404: and the scheduling server determines the RPA capable of executing the approval task based on the execution time of the approval task, the processing priority of the approval task and the current state of the RPA.

It should be noted that the specific implementation process of step S401 to step S404 is the same as the specific implementation process shown in step S201 to step S204, and can be referred to each other.

And S405, the dispatching server performs wind control processing based on the credit data of the applicant to obtain a predicted risk value.

In step S405, the credit data of the applicant is used to indicate the repayment of the loan transaction.

In the process of specifically implementing step S405, the credit data of the applicant is used as an input of the wind control module of the scheduling server, the credit data of the applicant is processed based on the wind control module, and a predicted risk value is output.

It should be noted that, the process of training the wind control module based on the credit data of the historical applicant is as follows:

when the wind control module is trained, firstly, feature data in the credit data of the historical applicant is extracted, and then the feature data in the credit data of the historical applicant is trained by using the recurrent neural network model to obtain the wind control module.

Optionally, after receiving the payment conditions of all the services, the scheduling server may further update the credit data of the historical applicant based on the overdue payment conditions, so as to optimize the wind control module.

It should be noted that the recurrent neural network model is one of the neural network models, in which the connection of some neurons forms a directed loop, so that an internal state or a structure with memory appears in the recurrent neural network model, so that there is an ability to model a dynamic sequence.

In the embodiment of the present invention, the wind control module may be constructed by using a recurrent neural network model, and may also be constructed by using other neural network models or machine learning models, and the embodiment of the present invention is not limited thereto.

Step S406: and determining whether the predicted risk value indicates that the loan transaction has a risk, if so, executing step S407, and if not, executing steps S408 to S409.

In the process of implementing step S406 specifically, it is determined whether the predicted risk value is 1, if the predicted risk value is 1, it indicates that the predicted risk value indicates that the loan transaction is risky, and step S407 is executed, if the predicted risk value is not 1, it indicates that the predicted risk value is 0, at this time, the predicted risk value indicates that the loan transaction is not risky, and steps S408 to S409 are executed.

Step S407: and the scheduling server stops all the approval works of the approval tasks and displays the approval risks of the approval tasks through the user interaction equipment.

In the process of implementing step S407 specifically, the scheduling server stops the user interaction device, all the approval jobs related to the approval task in the RPA, and sends information corresponding to the approval risk of the approval task to the user interaction device, so that the user interaction device displays the approval risk in the information corresponding to the approval risk of the approval task.

Step S408: and the scheduling server issues the approval process to the RPA which can execute the approval task.

Step S409: and the RPA calls the components in the RPA component library to execute the examination and approval process, and an execution result obtained by executing the examination and approval process is fed back to the user interaction equipment through the scheduling server so as to be conveniently checked by the examination and approval personnel.

It should be noted that the specific implementation process of step S409 is the same as the specific implementation process of step S205, and reference may be made to this.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A loan processing method adapted for a loan processing system including a user interaction device, a scheduling server, and a process automation robot, RPA, the user interaction device being connected to the scheduling server, the scheduling server being connected to the RPA, the method comprising:

2. The method of claim 1, wherein prior to issuing an approval process to the RPA, further comprising:

3. The method of claim 1, further comprising:

4. The method according to claim 1, wherein the scheduling server determines the execution time of the approval task and the priority of processing the approval task based on the approval data, the upload time of the approval task, the current time of the approval task, and a preset time limit, and comprises:

and the scheduling server determines the priority of processing the approval tasks according to the uploading time of the approval tasks, the difference between the current time of the approval tasks and the preset time limit and the user level of the applicant in the approval data.

5. The method of claim 1, wherein the scheduling server determines the RPAs that can execute the approval task based on the execution time of the approval task, the approval task processing priority, and the current state of the RPAs, comprising:

determining whether an RPA in an idle working state exists currently;

6. A loan processing system comprising a user interaction device, a dispatch server, and an RPA, the user interaction device being connected to the dispatch server, the dispatch server being connected to the RPA;

7. The system of claim 6, wherein the dispatch server is further configured to:

8. The system of claim 6, wherein the dispatch server is further configured to:

9. The system according to claim 6, wherein the scheduling server for determining the execution time of the approval task and the priority of processing the approval task based on the approval data, the upload time of the approval task, the current time of the approval task, and the preset time limit is specifically configured to:

10. The system according to claim 6, wherein the scheduling server determining the RPAs that can execute the approval task based on the execution time of the approval task, the approval task processing priority, and the current state of the RPAs is specifically configured to: