CN112967131A

CN112967131A - Loan collection scheme pushing method and device

Info

Publication number: CN112967131A
Application number: CN202110312786.0A
Authority: CN
Inventors: 张珝; 李谊; 刘铁; 胡冰
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2021-03-24
Filing date: 2021-03-24
Publication date: 2021-06-15

Abstract

The embodiment of the application provides a loan collection proposal pushing method and a loan collection proposal pushing device, which can be used in the technical field of finance, and the method comprises the following steps: grouping the loan users according to the geographical position information respectively corresponding to the loan users to be promised to form loan user groups; determining unique identifiers of the corresponding expecting persons of the loan user groups respectively based on preset configuration rules of the expecting persons; and respectively pushing a corresponding loan acceptance proposal to each acceptance urging person according to the unique identification of the acceptance urging person, wherein the loan acceptance proposal comprises a corresponding loan user group, user information and the geographical position information of each loan user in the loan user group. The loan collection prompting scheme can effectively improve the applicability and the accuracy of the pushed loan collection prompting scheme, further can effectively improve the collection prompting efficiency and the success rate of collection prompting personnel who prompt collection according to the pushing scheme, and effectively improve the user experience of financial institutions and collection prompting personnel.

Description

Loan collection scheme pushing method and device

Technical Field

The application relates to the technical field of data processing, in particular to the technical field of finance, and particularly relates to a loan collection scheme pushing method and device.

Background

Due to the current complex operating environment and the change of the behavior characteristics of the customers, the credit risk expression forms are diversified, and unpredictable factors are increased. The post-loan management capability, particularly the overdue loan collection prompting capability, faces a serious examination, and an intensive, efficient and intelligent comprehensive management scheme needs to be formulated urgently to replace the traditional manual collection prompting task allocation and unified rule collection prompting strategy, so that the collection prompting cost is saved, the collection prompting efficiency is improved, and the collection prompting effect is optimized.

Currently, the push process of the existing loan collection scheme is generally: and sequentially pushing a plurality of loan users to the client equipment of each acquirer according to the list of the loan users to be earned out so that the acquirers can carry out loan acquisition processing on the loan users according to the received information of the loan users.

However, in the push process of the existing loan hasty-receiving scheme, due to the fact that the distribution logic is simple, the consideration factors are insufficient, the comprehensiveness is poor, the problem that the distribution of the hasty-receiving task is not reasonable is solved, and due to the fact that loan users to be hasty-received are scattered, the problems of poor applicability and low accuracy of the pushed loan hasty-receiving scheme are not considered in the push process of the loan hasty-receiving scheme, and the problems of low loan hasty-receiving efficiency, low success rate and the like are caused in the push mode of the existing loan hasty-receiving scheme.

Disclosure of Invention

Aiming at the problems in the prior art, the application provides a loan collection prompting scheme pushing method and device, which can effectively improve the applicability and accuracy of a pushed loan collection prompting scheme, further effectively improve the collection prompting efficiency and success rate of collection prompting personnel who perform collection prompting according to the pushing scheme, and effectively improve the user experience of financial institutions and collection prompting personnel.

In order to solve the technical problem, the application provides the following technical scheme:

in a first aspect, the present application provides a loan procurement plan pushing method, including:

grouping the loan users according to the geographical position information respectively corresponding to the loan users to be promised to form loan user groups;

determining unique identifiers of the corresponding expecting persons of the loan user groups respectively based on preset configuration rules of the expecting persons;

and respectively pushing a corresponding loan acceptance proposal to each acceptance urging person according to the unique identification of the acceptance urging person, wherein the loan acceptance proposal comprises a corresponding loan user group, user information and the geographical position information of each loan user in the loan user group.

Further, before pushing the corresponding loan settlement promoting scheme to each of the acquirer according to the unique identifier of the acquirer, the method further includes:

obtaining user types respectively corresponding to all loan users in all the loan user groups, and determining pre-stored acceptance policy recommendation schemes respectively corresponding to all the user types;

correspondingly, the loan hasty scheme also comprises the hasty strategy recommendation scheme corresponding to each loan user in the loan user group.

Further, the determining the unique identifier of the corresponding acquirer for the loan user group based on the preset configuration rule of the acquirer for the loan includes:

quantitatively scoring according to key features of the historical credit acquisition record information of each loan user, and respectively determining the credit acquisition difficulty level of each loan user based on a preset credit acquisition difficulty grading library of the loan user, wherein the credit acquisition difficulty grading library of the loan user is used for storing the corresponding relation between the quantitative scoring of the key features in the historical credit acquisition record information and the credit acquisition difficulty level;

respectively determining difficulty scores corresponding to the loan user groups according to the average value of the acceptance difficulty grades of the loan users in the loan user groups;

and respectively selecting corresponding configuration rules of the expecting persons for each loan user group based on the comparison result between the difficulty score and the difficulty threshold value corresponding to each loan user group, and determining the unique identification of the expecting person corresponding to each loan user group based on the preset configuration rules of the expecting persons.

Further, the selecting, for each loan user group, a configuration rule of an acquirer corresponding to each loan user group based on a comparison result between the difficulty score and the difficulty threshold corresponding to each loan user group, and determining, based on a preset configuration rule of an acquirer, a unique identifier of an acquirer corresponding to each loan user group, respectively, includes:

selecting a pre-stored configuration rule of low-difficulty acquirer hastening for the loan user group with the difficulty score smaller than or equal to the difficulty threshold;

according to the configuration rule of the low-difficulty acquirer hasten, selecting a matched target acquirer from each acquirer;

if the number of the target collection urging persons is multiple, selecting the target collection urging persons closest to the geographic distance between the current loan user group as collection urging persons corresponding to the current loan user group, and acquiring the unique identification of the collection urging persons corresponding to the current loan user group;

wherein, the configuration rule of the low-difficulty acquirer comprises:

configuring a single expecting person for each loan user in the loan user group;

the total number of the loan user groups corresponding to the collection urging persons is within the range of the total number of the preset loan user groups;

the total amount of the collection to be carried out corresponding to the collection urging person is within the preset total amount range of collection urging;

and the loan user group corresponding to the collection urging person in the current collection urging period does not appear in the last collection urging period of the collection urging person.

selecting a pre-stored configuration rule of high-difficulty acquirer hastening for the loan user group with the current difficulty score larger than the difficulty threshold;

according to the configuration rule of the high-difficulty acquirer hasten, selecting a matched target acquirer from all acquirers;

if the number of the target collection urging persons is multiple, acquiring preset capability ratings corresponding to the target collection urging persons;

taking the target expecting person closest to the geographic distance between the current loan user group and/or the highest matching degree between the capability rating and the difficulty score of the loan user group as an expecting person corresponding to the current loan user group, and acquiring the unique identification of the expecting person corresponding to the loan user group;

wherein the configuration rule of the high-difficulty acquirer comprises:

Further, the obtaining of the user type corresponding to each loan user in each loan user group and determining the pre-stored recommendation scheme of the hasten receipt policy corresponding to each user type includes:

obtaining index characteristics of historical collection urging record information corresponding to each loan user, wherein the index characteristics comprise: user information, payment willingness, collection urging performance and deterioration possibility;

according to the comprehensive scores of the index features of the historical collection urging record information corresponding to the loan users, respectively determining the user types corresponding to the loan users by using a preset classification model;

and respectively acquiring the collection urging strategy recommendation schemes of the loan users from a preset loan user collection urging recommendation scheme grading library based on the user types respectively corresponding to the loan users, wherein the collection urging recommendation scheme grading library is used for storing the corresponding relation between the user types and the collection urging strategy recommendation schemes.

Further, the grouping of the loan users according to the geographical location information corresponding to each loan user to be promised to form each loan user group includes:

acquiring address records corresponding to each loan user to be promised, wherein the address records comprise at least one of mortgage addresses, residential addresses and working unit addresses;

determining the geographical position information corresponding to each loan user based on the address record corresponding to each loan user;

and according to the geographical position information corresponding to each loan user, grouping the loan users by applying a preset clustering algorithm to form each loan user group.

In a second aspect, the present application provides a loan payment proposal pushing device, including:

the user grouping module is used for grouping the loan users according to the geographic position information respectively corresponding to the loan users to be collected so as to form loan user groups;

the system comprises a loan user group, a loan configuration module and a loan management module, wherein the loan user group comprises loan users, loan users and loan fee accounts;

and the scheme pushing module is used for pushing corresponding loan acceptance schemes to the corresponding acceptance persons respectively according to the unique identification of the acceptance persons, wherein the loan acceptance schemes comprise corresponding loan user groups, user information of the loan users in the loan user groups and the geographic position information.

In a third aspect, the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the loan payment proposal pushing method when executing the computer program.

In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the loan procurement proposal push method.

According to the technical scheme, the loan collection proposal pushing method and the loan collection proposal pushing device provided by the application comprise the following steps: grouping the loan users according to the geographical position information respectively corresponding to the loan users to be promised to form loan user groups; determining unique identifiers of the corresponding expecting persons of the loan user groups respectively based on preset configuration rules of the expecting persons; the method comprises the steps that corresponding loan collection schemes are respectively pushed to all the collection staff according to unique identification of the collection staff, wherein the loan collection schemes comprise corresponding loan user groups, user information and geographical location information of all the loan users in the loan user groups, the loan users are grouped according to the geographical location information corresponding to all the loan users to be collected, so that all the loan user groups are formed, the loan users to be collected in the same distance range can be divided into one group, the applicability and the accuracy of the pushed loan collection schemes can be effectively improved, the collection staff are respectively selected for each loan user group to collect the loan, and the collection convenience, the collection efficiency and the collection success rate of the collection staff for collecting the loan collection according to the pushing scheme can be effectively improved; through including in loan user group and this loan user group each loan user information of loan user with the customer end equipment who asks for receipts personnel that this loan user group corresponds is given in the loan of geographic position information's loan scheme propelling movement, can effectively improve the efficiency and the convenience that asks for receipts personnel to acquire required information, and the propelling movement process is high-efficient and with strong points, can further improve according to this propelling movement scheme that asks for receipts personnel's the efficiency and success rate of asking for receipts to effectively improve financial institution and ask for receipts personnel's user experience.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a first flowchart of a loan acceptance plan pushing method in an embodiment of the present application.

Fig. 2 is a second flowchart of the loan acceptance plan pushing method in the embodiment of the present application.

Fig. 3 is a schematic flow chart illustrating the step 200 of the loan procurement proposal pushing method in the embodiment of the application.

Fig. 4 is a first specific flowchart of step 230 in the loan procurement proposal pushing method in the embodiment of the application.

Fig. 5 is a second specific flowchart of step 230 in the loan procurement proposal pushing method in the embodiment of the application.

Fig. 6 is a schematic flow chart illustrating the step 400 of the loan procurement proposal pushing method in the embodiment of the application.

Fig. 7 is a schematic flow chart illustrating the step 100 of the loan procurement proposal pushing method in the embodiment of the application.

Fig. 8 is a schematic structural diagram of a loan procurement plan pushing device in the embodiment of the present application.

Fig. 9 is a schematic flow chart of scheduling and allocating an acquirer in an application example of the present application.

FIG. 10 is a schematic diagram of the output flow of the integrated hastening strategy in the application example of the present application.

FIG. 11 is a schematic diagram illustrating an example of an index system in an example of application of the present application.

Fig. 12 is a schematic structural diagram of an electronic device in an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all 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 application.

It should be noted that the loan collection proposal pushing method and device disclosed by the present application can be used in the field of financial technology, and can also be used in any field except the field of financial technology.

The traditional collection flow and means can not meet the requirement of risk management, and the overdue risk management after individual loan faces the following problems: firstly, because the task allocation mode of urging receipts that adopts at present is comparatively traditional, the consideration is not enough, lacks comprehensiveness, and it is reasonable inadequately to have the task allocation of urging receipts, can not satisfy fairness and urge the problem of receipts effect maximize. Secondly, because the manual allocation of the collection urging task cannot thoroughly solve the problems of high collection urging cost, low collection urging efficiency and the like caused by geographical positions, how to reasonably plan the collection urging route and how to save the collection urging time become one of the problems that collection urging personnel face numerous customers due to the fact that the distribution of customers is messy and the collection urging time is long when the customers go to the home. The intensification degree of the collection management needs to be improved. Thirdly, according to the internal risk control management requirements, the collection urging personnel regularly change hands to urge collection, so that the original collection urging chain is broken, and the response condition of a client cannot be predicted. The question about who is urged by priority, who is urged mainly and who can not urge becomes the question about the list of urging to be accepted by the urging personnel. Fourthly, the collection urging personnel mainly make a fixed collection urging mode according to the overdue time to urge collection. For different customers who urge to receive response types, the acceptance degrees of different customers to urge to receive modes are different, and a more scientific differentiation and intelligent urging strategy and flow are urgently needed.

Based on this, aiming at the existing loan collection prompting scheme pushing mode, the problems of poor applicability and low accuracy of the pushed loan collection prompting scheme due to the over-simple designated logic of the scheme, and further the problems of low efficiency and low success rate of loan collection prompting are caused, the application provides a loan collection prompting scheme pushing method, a loan collection prompting scheme pushing device, an electronic device and a computer readable storage medium Efficiency and success rate; through including in loan user group and this loan user group each loan user information of loan user with the customer end equipment who asks for receipts personnel that this loan user group corresponds is given in the loan of geographic position information's loan scheme propelling movement, can effectively improve the efficiency and the convenience that asks for receipts personnel to acquire required information, and the propelling movement process is high-efficient and with strong points, can further improve according to this propelling movement scheme that asks for receipts personnel's the efficiency and success rate of asking for receipts to effectively improve financial institution and ask for receipts personnel's user experience.

Based on the above, the present application further provides a credit settlement scenario push device for implementing the method for pushing the credit settlement scenario provided in one or more embodiments of the present application, the loan collection proposal pushing device can be in communication connection with client equipment, financial institution systems and the like by itself or through a third-party server and the like, to receive the loan procurement proposal push request sent by the client device or the financial institution system, and after obtaining the loan procurement proposal push result according to the loan procurement proposal push request, sending the loan collection proposal to the client device or the financial institution system of the collection staff for display, and the on-site loan collection prompting processing is carried out on the loan user to be promoted according to the loan collection prompting scheme by a collector holding the client device or a collector viewing the display content of the financial institution system.

It is understood that the client devices may include smart phones, tablet electronic devices, network set-top boxes, portable computers, desktop computers, Personal Digital Assistants (PDAs), in-vehicle devices, smart wearable devices, and the like. Wherein, intelligence wearing equipment can include intelligent glasses, intelligent wrist-watch, intelligent bracelet etc..

The loan collection proposal pushing device can be a server or a client device, namely all the operations are completed in the client device. If all the operations are completed in the client device, the client device may further include a processor for performing a specific process of pushing the loan procurement plan. In another practical application scenario, the selection may be specifically performed according to the processing capability of the client device, the limitation of the user usage scenario, and the like. This is not a limitation of the present application.

The client device may have a communication module (i.e., a communication unit), and may be communicatively connected to a remote server to implement data transmission with the server. The server may include a server on the task scheduling center side, and in other implementation scenarios, the server may also include a server on an intermediate platform, for example, a server on a third-party server platform that is communicatively linked to the task scheduling center server. The server may include a single computer device, or may include a server cluster formed by a plurality of servers, or a server structure of a distributed apparatus.

The server and the client device may communicate using any suitable network protocol, including network protocols not yet developed at the filing date of this application. The network protocol may include, for example, a TCP/IP protocol, a UDP/IP protocol, an HTTP protocol, an HTTPS protocol, or the like. Of course, the network Protocol may also include, for example, an RPC Protocol (Remote Procedure Call Protocol), a REST Protocol (Representational State Transfer Protocol), and the like used above the above Protocol.

The following embodiments and application examples are specifically and individually described in detail.

In order to solve the problems of poor applicability and low accuracy of the pushed loan payment due to the fact that the designated logic of the scheme of the conventional loan payment due proposal pushing mode is too simple, and further the problems of low efficiency and low success rate of loan payment due proposal and the like, the application provides an embodiment of the loan payment due proposal pushing method, and referring to fig. 1, the loan payment due proposal pushing method executed by the loan payment due proposal pushing device specifically comprises the following contents:

step 100: and grouping the loan users according to the geographical position information respectively corresponding to the loan users to be promised to form each loan user group.

In step 100, a plurality of loan users to be earned and received corresponding to the financial institution may be obtained in advance, and specifically, software such as statistical ANALYSIS software sas (statistical ANALYSIS system) may be connected to a database of the financial institution to extract information of overdue customers in the loan repayment record data table. According to the standard of the receiving-hastening business, compiling client screening conditions, extracting a client set to be hastened, such as extracting loan client groups which are overdue for more than 15 days every month, and removing overdue clients which do not need to be hastened, and the like.

Then, the geographic position information corresponding to each loan user can be directly obtained from a pre-stored database, and the geographic position information refers to longitude and latitude information; the method can also be used for acquiring the address information corresponding to each loan user firstly and then acquiring the geographical position information corresponding to each loan user according to the address information. For example, address information pre-stored in a financial institution by a loan user can be obtained, and then a request can be sent to a map API interface by writing python codes, the address information of the loan user is input, and the result of fuzzy matching address information and the longitude and latitude corresponding to the address are output by the interface.

In step 100, the loan user grouping is performed by dividing a plurality of loan users with similar geographic location information into the same loan user group, specifically, determining whether the geographic location information is similar by performing keyword extraction and keyword similarity calculation on the geographic location information, and grouping the loan users in a clustering manner. It can be understood that the loan user group includes a plurality of loan users, and the total number of loan users and the total number of loan user groups in each loan user group may be preset, and may be specifically set according to an actual application situation.

Step 200: and determining the unique identification of the corresponding acquirer for each loan user group based on the preset configuration rule of the acquirer.

In step 200, after the grouping of the loan users is completed, a collection urging person needs to be assigned to each loan user group, specifically, the correspondence between the loan user groups and the collection urging persons may be a one-to-one, one-to-many or many-to-one relationship, but in order to avoid the loan users from being collected by a plurality of collection urging persons in a collection urging period as much as possible, in a preferred mode of step 200, the correspondence between the loan user groups and the collection urging persons only selects a one-to-one or many-to-one relationship, that is, in a collection urging period, one collection urging person may be responsible for the loan collection urging work of a single loan user group or a plurality of loan user groups, but one loan user group only assigns one collection urging person to provide the user experience of the loan users who are collected as much as possible.

It should be understood that the unique identifier of the acquirer is an identifier that the acquirer can represent its unique identity in the financial institution, and may specifically be a work number, an identification number, or a code combination of a name and a number of the acquirer at the financial institution, and the like.

Step 300: and respectively pushing a corresponding loan acceptance proposal to each acceptance urging person according to the unique identification of the acceptance urging person, wherein the loan acceptance proposal comprises a corresponding loan user group, user information and the geographical position information of each loan user in the loan user group.

In an example of the step 300, if it is determined that the loan user groups D1, D2, and D5 all correspond to the lender C123 through the

steps

100 and 200, a loan lending scheme including the user information and the geographic location information of each of the loan user groups D1, D2, and D5 is sent to the client device according to a unique identifier (such as an IP address or a telephone number, etc.) of the client device that is pre-recorded in the financial institution system by the lender C123.

Further, if the loan user groups pushed to one lending person are multiple, the loan user groups can be sorted and displayed according to the distance between the loan user groups and the geographic position of the lending person, so that the lending person can more intuitively and quickly acquire the recommended lending order of the loan user groups according to the loan lending scheme. For example, if the distances between the loan user groups D1, D2, and D5 and the geographical location of the acquirer are D2, D1, and D5 in sequence from near to far, the loan acquirer may sort the loan user groups D1, D2, and D5 in the sequence of D2, D1, and D5 according to the distances between the loan user groups D1, D2, and D5 and the geographical location of the acquirer, so that the acquirer C123 may immediately know that the loan acquirer is D2, D1, and D5 according to the sequence from near to far when seeing the loan acquirer.

In addition, in step 300, in order to avoid leakage of the data of the loan user, before the corresponding loan acceptance schemes are respectively pushed to the client devices corresponding to the respective acceptance urging persons, the loan acceptance schemes are encrypted according to a preset encryption mode, and then the encrypted loan acceptance schemes are sent to the client devices of the corresponding acceptance urging persons, so that the acceptance urging persons decrypt the encrypted loan acceptance schemes according to a decryption mode which is obtained from a financial institution in advance and uniquely corresponds to the encryption mode to obtain the loan acceptance schemes, and then the security of the data of the loan user can be effectively improved, the privacy data of the loan user is effectively protected, and the user experience of the loan user is improved.

As can be seen from the above description, according to the loan collection prompting scheme pushing method provided in the embodiment of the present application, the loan users are grouped according to the geographic location information corresponding to each loan user to be collected, so as to form each loan user group, and the loan users to be collected within the same distance range can be grouped into one group, so that the applicability and accuracy of the pushed loan collection prompting scheme can be effectively improved, and collection prompting staff for collection according to the pushing scheme can be effectively improved by selecting collection prompting staff for each loan user group to collect the loan; through including in loan user group and this loan user group each loan user information of loan user with the customer end equipment who asks for receipts personnel that this loan user group corresponds is given in the loan of geographic position information's loan scheme propelling movement, can effectively improve the efficiency and the convenience that asks for receipts personnel to acquire required information, and the propelling movement process is high-efficient and with strong points, can further improve according to this propelling movement scheme that asks for receipts personnel's the efficiency and success rate of asking for receipts to effectively improve financial institution and ask for receipts personnel's user experience.

In order to provide a configuration manner of the real loan recommendation scheme, referring to fig. 2, an embodiment of the method for pushing the real loan scheme provided by the present application further includes the following steps after step 100 and before step 300:

step 400: and obtaining the user types respectively corresponding to the loan users in the loan user groups, and determining the pre-stored acceptance policy recommendation scheme respectively corresponding to the user types.

It is understood that in one example, the user types can be divided into three categories, respectively: the system comprises a database of the financial institution, a prompt returning type, a frequently returning type and a frequently returning type, wherein a recommendation scheme of a collection strategy corresponding to each of the prompt returning type, the frequently returning type and the frequently returning type is respectively stored in the database of the financial institution.

As can be seen from the above description, according to the loan collection prompting scheme pushing method provided in the embodiment of the present application, by determining the collection prompting strategy recommendation scheme corresponding to each loan user in the loan user group and pushing the collection prompting strategy recommendation scheme to the corresponding collection prompting staff, the applicability, pertinence, and accuracy of the pushed loan collection prompting scheme can be further improved, and further, the collection prompting convenience, efficiency, and success rate of the collection prompting staff who performs collection prompting according to the pushing scheme can be further improved.

In order to provide a preferred way for the real-time loan payment plan delivery method, referring to fig. 3, an embodiment of the real-time loan payment plan delivery method provided in the present application includes the following steps in step 200:

step 210: and quantitatively scoring according to the key features of the historical credit record information of each loan user, and respectively determining the credit difficulty grade of each loan user based on a preset credit user credit difficulty grading library, wherein the credit user credit difficulty grading library is used for storing the corresponding relationship between the quantitative score of the key features in the historical credit record information and the credit difficulty grade.

In an implementation manner of step 210, the quantitative scoring of the key features may be entered into a database of the financial institution by a staff of the financial institution in advance, and the loan prompt receipt scheme pushing device may directly invoke the quantitative scoring of the key features of the historical prompt receipt record information of each loan user from the database.

Wherein the key feature quantification score may be the same as the index feature mentioned in one or more embodiments of the present application, namely: the key feature may be an index, the index including: user information indicators, payment willingness, collection urging performance, and deterioration possibility.

Step 220: and respectively determining the difficulty scores corresponding to the loan user groups according to the average value of the acceptance difficulty grades of the loan users in the loan user groups.

Step 230: and respectively selecting corresponding configuration rules of the expecting persons for each loan user group based on the comparison result between the difficulty score and the difficulty threshold value corresponding to each loan user group, and determining the unique identification of the expecting person corresponding to each loan user group based on the preset configuration rules of the expecting persons.

As can be seen from the above description, the loan collection prompting scheme pushing method provided in the embodiment of the present application can effectively increase the pertinence and effectiveness of the loan collection prompting scheme pushing by differentially selecting different configuration schemes of collectors according to the difficulty of collection prompting of the user, and further can further improve the convenience, efficiency and success rate of collection prompting of collectors who perform collection prompting according to the pushing scheme.

In order to provide a preferred way to select different configuration schemes of the acquirer according to the difficulty of user acquisition, in an embodiment of the loan acquisition scheme pushing method provided by the present application, referring to fig. 4, the step 230 of the loan acquisition scheme pushing method specifically includes the following contents:

step 2311: and selecting a pre-stored configuration rule of the low-difficulty acquirer for the loan user group with the difficulty score smaller than or equal to the difficulty threshold value.

Step 2312: and selecting matched target collection urging personnel from the collection urging personnel according to the configuration rule of the low-difficulty collection urging personnel.

It is understood that the low difficulty configuration rule of the acquirer can refer to constraint conditions, that is, firstly, the acquirer who meets the constraint conditions is selected from the acquirers, and if there is more than one person after the selection, the person closest to the geographical distance between the current loan user group can be selected from the selected acquirers as the acquirer corresponding to the current loan user group through the execution of step 2313.

Step 2313: and if the number of the target collection urging persons is multiple, selecting the target collection urging persons closest to the geographic distance between the current loan user group as collection urging persons corresponding to the current loan user group, and acquiring the unique identification of the collection urging persons corresponding to the current loan user group.

Wherein, the configuration rule of the low-difficulty acquirer comprises:

(1) and configuring a single acquirer for each loan user in the loan user group.

(2) And the total number of the loan user groups corresponding to the collection urging person is within the range of the total number of the preset loan user groups.

(3) The total amount of the collection to be collected corresponding to the collection urging person is within the preset total amount range of collection urging.

(4) And the loan user group corresponding to the collection urging person in the current collection urging period does not appear in the last collection urging period of the collection urging person.

Specifically, an objective function representing the sum of the distances between the collection urging personnel and the clients can be set first, and the objective function is guaranteed to be preferentially distributed to the collection urging personnel by the client clusters close to each other in order to meet the requirement that the collection urging service is highest in efficiency, so that the overall collection urging distance is shortest, and the collection urging cost is reduced.

Then, the constraint conditions of the objective function are set as follows: each customer can only be urged to be collected by one urging person; the total collection cluster of each collection urging person is within the total number range of the preset loan user group, so that the collection urging workload of each collection urging person is ensured to be not greatly different, and the fairness of task allocation is met; the total amount of the hasten receipts of each hasten receipts is in the preset total amount range of hasten receipts, so that the task allocation needs to ensure that the distribution of the hasten receipts has little difference, and the fairness of the task allocation is met; in order to prevent and control risks, the hand-off principle is satisfied, the distribution result is different from the historical distribution result, and the fact that the person who hastens the receipts in a period on the same cluster is different is guaranteed. The problem that the risk problem of a person who urges to collect the same client cluster and the same client for a long time is solved, and the person who urges to collect is enabled to replace the urging cluster when a new task is distributed. The constraint condition may further include a decision variable for determining whether the customer is urged to be received by the acquirer and a variable for determining whether the customer is urged to be received by the acquirer in the previous period.

As can be seen from the above description, the loan collection prompting scheme pushing method provided in the embodiment of the present application can further increase the pertinence and effectiveness of the loan collection prompting scheme pushing by executing the low-difficulty loan prompt collector configuration rule for the loan user group with low difficulty, and further can further improve the convenience, efficiency and success rate of collection prompting by the loan prompt collector according to the pushing scheme.

In order to provide a preferred way to select different configuration schemes of the acquirer according to the difficulty of user acquisition, in an embodiment of the loan acquisition scheme pushing method provided in the present application, referring to fig. 5, the step 230 of the loan acquisition scheme pushing method further includes the following steps:

step 2321: and selecting a pre-stored configuration rule of the high-difficulty acquirer for the loan user group with the difficulty score larger than the difficulty threshold value.

Step 2322: and selecting matched target collection urging personnel from all collection urging personnel according to the configuration rule of the high-difficulty collection urging personnel.

Step 2323: and if the number of the target collection urging persons is multiple, acquiring preset capability ratings corresponding to the target collection urging persons.

It can be understood that the ability rating of the target acquirer can be set by a financial institution worker in advance according to pre-acquired historical data of the target acquirer and stored in a database of the financial institution, and the loan acquirer pushing device can directly extract the ability rating corresponding to each target acquirer from the database of the financial institution.

It is understood that the configuration rule of the highly difficult acquirer may refer to constraint conditions, that is, firstly, the acquirer who meets the constraint conditions is selected from the acquirers, and if there is more than one person after the selection, the method may go through the execution of step 2323 and step 2324, and select one of the target acquirers who is closest to the geographic distance between the current loan user group and/or has the highest matching degree between the capability rating and the difficulty score of the loan user group as the acquirer corresponding to the current loan user group.

The calculation method of the matching degree between the capability rating and the difficulty score of the loan user group may be as follows: if the expression form of the ability rating is a score, calculating the product between the ability rating and the difficulty score of the loan user group, wherein the larger the product is, the higher the matching degree between the ability rating and the difficulty score of the loan user group can be considered, and vice versa. In addition, if the performance form of the ability rating is a score, the ratio between the ability rating and the difficulty score of the loan user group can be calculated. Or a comparison table among the capability rating, the difficulty score and the matching degree is called from a database of the financial institution, and the corresponding matching degree is directly inquired.

Step 2324: and taking the target expecting person closest to the geographic distance between the current loan user group and/or the highest matching degree between the capability rating and the difficulty score of the loan user group as the expecting person corresponding to the current loan user group, and acquiring the unique identification of the expecting person corresponding to the loan user group.

Wherein the configuration rule of the high-difficulty acquirer comprises:

(1) configuring a single expecting person for each loan user in the loan user group;

(2) the total number of the loan user groups corresponding to the collection urging persons is within the range of the total number of the preset loan user groups;

(3) and the loan user group corresponding to the collection urging person in the current collection urging period does not appear in the last collection urging period of the collection urging person.

Particularly, the distance between the customer and the person who hastens the receipts can be set and expressed in advance, and the objective function of the matching degree of the customer cluster and the person who hastens the receipts is maximized, and on the premise that the distance that hastens the receipts is minimum, the cluster that hastens the difficulty is higher is distributed to the person who hastens the receipts with stronger ability, so that the matching degree that hastens the receipts is higher is achieved, and the success rate of hastening the receipts as a whole is improved. So that the objective function can simultaneously satisfy the principles of highest catalytic yield efficiency and maximum efficiency.

Then, the constraint conditions of the objective function are set as follows: each customer can only be urged to be collected by one urging person; the total collection cluster of each collection urging person is within the total number range of the preset loan user group, so that the collection urging workload of each collection urging person is ensured to be not greatly different, and the fairness of task allocation is met; in order to prevent and control risks, the hand-off principle is satisfied, the distribution result is different from the historical distribution result, and the fact that the person who hastens the receipts in a period on the same cluster is different is guaranteed. The problem that the risk problem of a person who urges to collect the same client cluster and the same client for a long time is solved, and the person who urges to collect is enabled to replace the urging cluster when a new task is distributed. The constraint condition may also include a decision variable for determining whether the customer is urged by the acquirer.

As can be seen from the above description, the loan collection prompting scheme pushing method provided in the embodiment of the present application can further increase the pertinence and effectiveness of the loan collection prompting scheme pushing by executing the high-difficulty loan prompt collector configuration rule for the loan user group with high difficulty, and further can further improve the convenience, efficiency and success rate of collection prompting by the loan prompt collector according to the pushing scheme.

In order to provide a preferred mode of the recommendation scheme of the claim of credit, referring to fig. 6, in an embodiment of the method for pushing the claim of credit provided by the present application, the step 400 of the method for pushing the claim of credit specifically includes the following steps:

step 410: obtaining index characteristics of historical collection urging record information corresponding to each loan user, wherein the index characteristics comprise: user information, payment willingness, collection hastening performance and deterioration possibility.

Specifically, the financial institution can pay attention to the fund change and the repayment habit of the customer from four dimensions of basic information, the repayment willingness, the deterioration possibility and the historical behavior of the user according to the business experience and the collection prompting scene in advance, extracts a plurality of characteristic indexes, and constructs an index system capable of truly reflecting the characteristics, the fund change and the repayment performance of the user.

Step 420: and respectively determining the user types respectively corresponding to the loan users by utilizing a preset classification model according to the comprehensive scores of the index characteristics of the historical collection urging record information respectively corresponding to the loan users.

In step 420, the database of the financial institution may be pre-stored with a corresponding relationship between each numerical range of the total score of the index features and the user type, for example, a total score of 0 to 30 points, and a preset classification model is used to determine that the user type is the frequent urge type.

Step 430: and respectively acquiring the collection urging strategy recommendation schemes of the loan users from a preset loan user collection urging recommendation scheme grading library based on the user types respectively corresponding to the loan users, wherein the collection urging recommendation scheme grading library is used for storing the corresponding relation between the user types and the collection urging strategy recommendation schemes.

It can be known from the above description that the loan collection prompting scheme pushing method provided by the embodiment of the application determines the user types by index classification of the users, and then respectively acquires each loan user collection prompting strategy recommendation scheme in the preset loan user collection prompting recommendation scheme classification library according to different user types, so that the pertinence and effectiveness of selection of the collection prompting strategy recommendation scheme can be effectively improved, and the collection prompting convenience, efficiency and success rate of collection prompting personnel who perform collection prompting according to the pushing scheme can be further improved.

In order to provide a preferred way of grouping loan users, referring to fig. 7, an embodiment of the loan procurement plan pushing method provided in the present application includes the following steps in step 100:

step 110: and acquiring address records corresponding to each loan user to be promised, wherein the address records comprise at least one of mortgage addresses, living addresses and working unit addresses.

In step 110, the system may first connect to the database server, write sql scripts, extract the client mortgage address, the residential address, and the work unit address from the database, and finally obtain a complete and real client address.

Step 120: and determining the geographical position information corresponding to each loan user based on the address record corresponding to each loan user.

Step 130: and according to the geographical position information corresponding to each loan user, grouping the loan users by applying a preset clustering algorithm to form each loan user group.

In step 130, the clustering algorithm may employ a K-means clustering algorithm K-means or a constrained K-means clustering algorithm K-means _ constrained, etc.

According to the loan collection prompting scheme pushing method, the loan users respectively correspond to the geographic position information and the preset clustering algorithm is applied to each loan user grouping is performed, the loan user grouping accuracy, reliability and efficiency can be effectively improved, the loan collection prompting scheme can be effectively improved, the loan collection prompting convenience, efficiency and success rate of collection prompting personnel who prompt collection according to the pushing scheme can be further improved.

In terms of software, in order to solve the problems of poor applicability and low accuracy of the pushed loan payment due to the fact that the designated logic of the scheme is too simple in the existing loan payment due proposal pushing mode, and further the problems of low efficiency and low success rate of loan payment due proposal, the application provides an embodiment of a loan payment due proposal pushing device for executing all or part of the contents in the loan payment due proposal pushing method, and referring to fig. 8, the loan payment due proposal pushing device specifically comprises the following contents:

and the user grouping module 10 is used for grouping the loan users according to the geographical position information corresponding to each loan user to be collected so as to form each loan user group.

In the user grouping module 10, a plurality of loan users to be earned and received corresponding to the financial institution may be obtained in advance, and specifically, the loan users may be connected to a database of the financial institution by using software such as statistical ANALYSIS software sas (statistical ANALYSIS system), and the like, to extract overdue customer information in the loan repayment record data table. According to the standard of the receiving-hastening business, compiling client screening conditions, extracting a client set to be hastened, such as extracting loan client groups which are overdue for more than 15 days every month, and removing overdue clients which do not need to be hastened, and the like.

In the user grouping module 10, the loan user grouping is performed in such a way that a plurality of loan users with similar geographic location information are grouped into the same loan user group, and whether the geographic location information is similar or not can be confirmed by performing keyword extraction and keyword similarity calculation on the geographic location information or by determining the longitude and latitude distance of the geographic location, and each loan user can be grouped in a clustering way. It can be understood that the loan user group includes a plurality of loan users, and the total number of loan users and the total number of loan user groups in each loan user group may be preset, and may be specifically set according to an actual application situation.

And the personnel configuration module 20 is configured to determine unique identifiers of the corresponding expecting personnel of each loan user group based on preset configuration rules of the expecting personnel.

In the staffing configuration module 20, after the grouping of the loan users is completed, it is necessary to assign an expecting person to each loan user group, specifically, the correspondence between the loan user group and the expecting person may be a one-to-one, one-to-many or many-to-one relationship, but in order to avoid the loan users from being expecting to be accepted by a plurality of expecting persons in an expecting period as much as possible, in a preferred mode of the staffing configuration module 20, the correspondence between the loan user group and the expecting person only selects a one-to-one or many-to-one relationship, that is, in an expecting period, one expecting person may be responsible for the loan expecting work of a single or multiple loan user groups, but one loan user group only assigns one expecting person to provide the expecting user experience as much as possible.

And the scheme pushing module 30 is configured to respectively push a corresponding loan acceptance scheme to each of the recipients according to the unique identifier of the recipient, where the loan acceptance scheme includes a corresponding loan user group, user information of each loan user in the loan user group, and the geographic location information.

In an example of the scenario push module 30, if it is determined that the loan subscriber groups D1, D2, and D5 all correspond to the lending person C123 through

steps

100 and 200, a loan lending scenario including the user information and the geographic location information of each of the loan subscriber groups D1, D2, and D5 is sent to the client device according to a unique identifier (such as an IP address or a phone number, etc.) of the client device that is pre-recorded in the financial institution system by the lending person C123.

Further, if the loan user groups pushed to one lending person are multiple, the loan user groups can be sorted and displayed according to the distance between the loan user groups and the geographic position of the lending person, so that the lending person can more intuitively and quickly acquire the recommended lending order of the loan user groups according to the loan lending scheme. For example, if the distances between the loan user groups D1, D2, and D5 and the geographic location of the acquirer are D2, D1, and D5 in sequence from near to far, the loan acquirer may sort the loan user groups D1, D2, and D5 in the sequence of D2, D1, and D5 according to the distances between the loan user groups D1, D2, and D5 and the geographic location of the acquirer, so that the acquirer C123 can immediately know that the loan acquirer is D2, D1, or D5 according to the sequence from near to far when seeing the loan acquirer.

In addition, in the scheme pushing module 30, in order to avoid leakage of the data of the loan user, before the corresponding loan acceptance schemes are respectively pushed to the client devices corresponding to the respective acceptance urging persons, the loan acceptance urging scheme is encrypted according to a preset encryption mode, and then the encrypted loan acceptance urging scheme is sent to the client devices of the corresponding acceptance urging persons, so that the acceptance urging persons decrypt the encrypted loan acceptance urging scheme according to a decryption mode which is obtained from a financial institution in advance and uniquely corresponds to the encryption mode to obtain the loan acceptance urging scheme, and then the security of the data of the loan user can be effectively improved, the privacy data of the loan user is effectively protected, and the user experience of the loan user is improved at the same time.

The embodiment of the loan collection proposal pushing apparatus provided in the present application may be specifically used for executing the processing flow of the embodiment of the loan collection proposal pushing method in the foregoing embodiment, and the functions thereof are not described herein again, and reference may be made to the detailed description of the embodiment of the method.

As can be seen from the above description, the loan collection plan pushing device provided in the embodiment of the present application divides each loan user into groups according to the geographic location information corresponding to each loan user to be collected, so as to form each loan user group, and divides the loan users to be collected within the same distance range into one group, so as to effectively improve the applicability and accuracy of the pushed loan collection plan; through including in loan user group and this loan user group each loan user information of loan user with the customer end equipment who asks for receipts personnel that this loan user group corresponds is given in the loan of geographic position information's loan scheme propelling movement, can effectively improve the efficiency and the convenience that asks for receipts personnel to acquire required information, and the propelling movement process is high-efficient and with strong points, can further improve according to this propelling movement scheme that asks for receipts personnel's the efficiency and success rate of asking for receipts to effectively improve financial institution and ask for receipts personnel's user experience.

In order to provide a configuration manner of the real loan payment proposal, in an embodiment of the real loan proposal pushing device provided by the present application, the real loan proposal pushing device is further specifically configured to execute the following steps after step 100 and before step 300:

It can be known from the above description that the loan collection prompting scheme pushing device provided in the embodiment of the present application can further improve the applicability, pertinence and accuracy of the pushed loan collection prompting scheme by determining each loan user group corresponding to each loan user and pushing the collection prompting strategy recommendation scheme to the corresponding collection prompting person, thereby further improving the collection prompting convenience, efficiency and success rate of the collection prompting person who performs collection prompting according to the pushing scheme.

In order to provide a preferred way for the real-time loan payment proposal delivery device, in an embodiment of the real-time loan proposal delivery device provided by the present application, the staff configuration module 20 of the real-time loan proposal delivery device is specifically configured to perform the following:

Wherein, the quantitative scoring of the key features can be the same as the index features mentioned in one or more embodiments of the application, namely: the key feature may be an index, the index including: user information indicators, payment willingness, collection urging performance, and deterioration possibility.

As can be seen from the above description, the loan collection prompting scheme pushing device provided in the embodiment of the present application can effectively increase the pertinence and effectiveness of the loan collection prompting scheme pushing by differentially selecting different collection prompting personnel configuration schemes according to the collection prompting difficulty of the user, and further can further improve the collection prompting convenience, efficiency and success rate of the collection prompting personnel who perform collection prompting according to the pushing scheme.

In order to provide a preferred way to select different configuration schemes for the payee-urged person according to the difficulty of the user in urging receipt, in an embodiment of the loan-urge-receipt-scheme pushing device provided by the present application, the person configuration module 20 in the loan-urge-receipt-scheme pushing device is further specifically configured to execute the following contents in step 230:

Wherein, the configuration rule of the low-difficulty acquirer comprises:

As can be seen from the above description, the loan collection prompting scheme pushing device provided in the embodiment of the present application can further increase the pertinence and validity of the loan collection prompting scheme pushing by executing the low-difficulty collection prompting person configuration rule for the loan user group with low collection prompting difficulty, and further can further improve the collection prompting convenience, efficiency and success rate of the collection prompting person who performs collection prompting according to the pushing scheme.

The calculation method of the matching degree between the capability rating and the difficulty score of the loan user group may be as follows: if the expression form of the ability rating is a score, calculating the product between the ability rating and the difficulty score of the loan user group, wherein the larger the product is, the higher the matching degree between the ability rating and the difficulty score of the loan user group can be considered, and vice versa. In addition, if the performance of the ability rating is expressed as a score, a ratio or difference between the ability rating and the difficulty score of the loan user group may be calculated. Or a comparison table among the capability rating, the difficulty score and the matching degree is called from a database of the financial institution, and the corresponding matching degree is directly inquired.

Wherein the configuration rule of the high-difficulty acquirer comprises:

As can be seen from the above description, the loan collection prompting scheme pushing device provided in the embodiment of the present application can further increase the pertinence and effectiveness of the loan collection prompting scheme pushing by executing the high-difficulty collection prompting staff configuration rule for the loan user group with high collection prompting difficulty, and further can further improve the collection prompting convenience, efficiency and success rate of the collection prompting staff performing collection prompting according to the pushing scheme.

In order to provide a preferred mode of the recommendation scheme of the claim of credit policy, in an embodiment of the loan claim plan pushing device provided in the present application, the loan claim plan pushing device is further specifically configured to perform the following steps in step 400:

It can be known from the above description that the loan collection prompting scheme pushing device provided by the embodiment of the application determines the user type by grading the indexes of the user, and then respectively acquires each in the preset loan user collection prompting recommendation scheme grading library according to different user types the loan user's collection prompting strategy recommendation scheme can effectively improve the pertinence and effectiveness of the selection of the collection prompting strategy recommendation scheme, and further can further improve the collection prompting convenience, efficiency and success rate of collection prompting personnel who carry out collection prompting according to the pushing scheme.

In order to provide a preferred way of grouping loan users, in an embodiment of the loan procurement plan pushing apparatus provided by the present application, the user grouping module 10 of the loan procurement plan pushing apparatus is specifically configured to perform the following:

According to the description, the loan collection prompting scheme pushing device provided by the embodiment of the application is used for obtaining the geographic position information corresponding to each loan user and applying the preset clustering algorithm to each loan user to group the loan users, so that the accuracy, reliability and efficiency of grouping the loan users can be effectively improved, the accuracy and reliability of making the loan collection prompting scheme can be effectively improved, and the collection prompting convenience, efficiency and success rate of collection prompting personnel who prompt collection according to the pushing scheme can be further improved.

In order to further explain the scheme, the application also provides a specific application example of the loan hasty-receipts scheme pushing method, and the application example respectively provides two major schemes of 'hasty-receipts staff scheduling and distribution' optimization management and 'hasty-receipts comprehensive strategy' service guidance around the core problem in the whole process of hasty-receipts, and designs four models to realize the intensive scheduling and efficient and scientific distribution of hasty-receipts tasks of the hasty-receipts staff, so that a targeted, strategic and personalized hasty-receipts mode is formed, the hasty-receipts strategy is optimized, the working efficiency is improved, and the management mode is improved.

In the scheduling and distribution of the receiver, the scheduling is to divide the distributed centralized clients into uniform client clusters by using a client clustering model based on geographic positions, and the receiver performs centralized reception by taking the client clusters as units. The change from a dispersed customer-by-customer collection mode to a customer group intensive collection mode is realized, so that collection personnel can collect customers in a centralized manner, and the dispatching is more scientific and standard. The 'allocation' is the 'task allocation based on multi-objective optimization' designed, and the traditional manual work is replaced by a big data + model algorithm. The model comprehensively considers four aspects of collection efficiency, collection effect, assessment and risk control, and provides four major factors of the distance between a collector and a client, the matching degree of the capacity of the collector and the task difficulty, the collection amount and the collection period. Not only realizes better collection accelerating efficiency and collection accelerating effect, but also meets the requirements of risk prevention and control.

The comprehensive collection strategy aims to solve the problems of how to judge whether the customer needs collection, how to collect the response effect, how to collect the collection and effectively collect the debt, and the like. And the refined classification of the client types is realized, and different receiving strategies are adopted aiming at different clients of different types to become the research center of gravity of comprehensive strategy management. The application example of the application designs a client type judgment model, and the client is divided into a client who prompts the payment to be made, a client who frequently prompts the payment to be made and a client who loses the payment to be made according to different response types of the client. After knowing the type of the customer, the recommendation of the collection urging mode is that the collection urging mode with the best response effect can be adopted for the customer in a targeted manner to urge collection, and the most appropriate collection urging mode for the individual customer is provided for collection urging personnel. This application example help the personnel of urging to accept to judge that urges who preferentially, whether need urge to accept the scheduling problem to behind the response type of urging to accept repayment of known customer, can be pertinence take differentiated urge to accept the tactics, the equitable time of receiving of distributing urges, the maximize effect of urging to accept. The application example of the application is based on two major schemes of 'scheduling and allocation of the receivable persons' optimization management and 'comprehensive receivable strategy' service guidance, and four major models of 'customer grouping based on geographic positions', 'task allocation based on multi-objective optimization', 'customer type judgment' and 'receivable mode recommendation' are researched and designed.

Based on this, the specific application example of the loan procurement proposal pushing method specifically includes the following contents:

the application example of the application realizes the scheduling and distribution of the hasty personnel by constructing two models of 'customer clustering based on geographic position' and 'task distribution based on multi-objective optimization', and is specifically realized in the following steps 101 to 106 by referring to fig. 9.

Step 101: and screening and preprocessing customer data, and extracting a task set to be distributed. And connecting the SAS to a database, and extracting overdue customer information in the loan repayment record data table. According to the standard of the receiving-hastening business, compiling client screening conditions, extracting a client set to be hastened, such as extracting loan client groups which are overdue for more than 15 days every month, and removing overdue clients which do not need to be hastened, and the like.

Step 102: identification and quantification of the geographic location of the customer. The application example of the application utilizes the SAS to be connected to a database server, writes the sql script, extracts the client mortgage address, the living address and the working unit address from the database, and finally obtains the complete and real client address.

In order to quantize the client address, the application example of the application sends a request to a map API interface by writing python codes, the input is the client address, and the output of the interface is a fuzzy matching address information result and the longitude and latitude corresponding to the address. Specific examples are shown in table 1:

TABLE 1

Address information	Longitude (G)	Latitude
			Building and floor in certain street and in certain city in Beijing city	116.364*	39.883*
Certain number of building and certain door in Haihe district	116.292*	39.929*
			One street (one section) of one number in Xingxing area	116.338*	39.744*
Xinyue family of a number in the south of the Fengcai district	116.240*	39.851*
			One apartment in the morning sun	116.490*	39.980*
A certain merchant and a certain household	116.490*	39.980*
			One unit in three areas of one town of seven town north	116.446*	40.081*
One family at certain layer of commercial building in southeast side of one city in Liang-Shang province	116.154*	39.726*
			Building of one number in one district of one sea lake area of Beijing City	116.353*	40.022*
Building door of second district and first building of economic technology development area	116.498*	39.804*

It should be noted that "+" in table 1 above represents any positive integer from 0 to 9.

Step 103: and clustering the customers. The application example of the application takes the distance as the measurement standard, and utilizes a longitude and latitude distance formula (see formula 1) to calculate the distance between two points, wherein (A)_w,A_j) Represents the latitude and longitude position of client A, (B)_w,B_j) Representing the latitude and longitude location of client B. And calculating the distance between the clients by using the improved clustering model K-means-constrained, and continuously adjusting by considering the number of the clients in each category to obtain a final clustering result.

d_AB＝R_E*arccos(sin(A_w)sin(B_w)+cos(A_w)cos(B_w)*cos(B_j-A_j) Equation 1)

R_EIs the radius of the earth, A_wRepresents the latitude value of A point, A_jRepresents the A-point longitude value.

Step 104: and setting and quantifying optimization model variables.

According to the actual scene conditions of the collection service, under the condition that the constraint conditions of the number of collection urging personnel, the average number of collection urging personnel, the scheduled collection urging and hand-changing and the like distributed for the client are met, on the premise that the relative fairness is ensured, the client can be efficiently and conveniently collected, and the maximum collection urging efficiency of the collection urging personnel is exerted.

The application example of the application provides the following four task allocation principles, and the corresponding principles are matched and used under different conditions according to actual business requirements, so that the effects of actually solving business problems and optimizing task allocation are achieved:

principle one: the efficiency is highest. The customer cluster close to the distance is preferentially distributed to the collection urging personnel, so that the overall collection urging distance is shortest, and the collection urging cost is reduced.

Principle two: the efficacy is maximal. The collection accelerating clusters with higher difficulty are distributed to collection accelerating personnel with stronger capacity, so that higher collection accelerating matching degree is achieved, and the overall collection accelerating success rate is improved.

Principle three: and (5) checking fairness. The collection urging personnel currently take collection urging success amount as a performance assessment standard, and in order to prevent the assessment result from being greatly different, task allocation needs to ensure that the distribution of collection urging amount is not greatly different.

Principle four: and (4) controlling the risk. The method comprises the steps that a customer cluster is collected by a collection staff for a long time, and the same customer has a risk problem, so that the collection staff needs to consider whether the same customer cluster is collected by the collection staff in the previous period, and if the collection staff is collected, the collection staff is replaced when a new task is distributed.

Based on the task allocation principle, the application example of the application provides four task allocation principles of quantifying the distance between the acquirer and the client cluster, the acquisition matching degree, the acquisition amount and the acquisition period respectively, and achieves the optimal allocation effect by taking the acquisition cluster as a unit. Wherein the distance is measured by the distance between the person who urges the recipient and the center of the customer cluster. The collection amount is the sum of the amount to be collected in the collection cluster. The matching degree of the hasten receipts is measured by the ability of the hasten receipts staff and the hasten receipts difficulty. Whether the hasten income experience is rich or not is quantified by adopting the historical hasten income times and the historical average hasten income amount; the average number of the hastening receipts of the customer is adopted to quantify the degree of seriousness, so that the comprehensive capacity of the hastening and receiving personnel is measured. The difficulty of the client cluster collection is comprehensively considered according to the current overdue condition and the historical overdue condition. The collection period mainly takes whether the history collected the customer as the quantitative index.

The following are the relevant variables for this model expressed as follows:

and N represents the number of the client clusters.

M represents the number of the persons who are required to receive.

Size N × M, representing the distribution result matrix, element a_ij indicates whether the ith customer cluster is assigned to the jth acquirer.

Size NxM, representing a distance matrix, element d_ijIndicating the distance between the ith customer cluster center and the jth acquirer.

Size N M, representing historical allocation result matrix, element h_ijIndicating whether the ith customer cluster in the previous period is allocated to the jth acquirer.

The size is 1 × M, which represents the ability matrix, and the element cj represents the ability value of the jth person to be admitted.

Size 1 XN, representing difficulty matrix, element diff_iThe value of the shrinkage-induced difficulty of the ith cluster is shown.

Size 1 XN, number matrix of clients representing catalyst clusters, element cn_iIndicating the number of clients contained in the ith cluster.

Epsilon: represents an arbitrarily small positive number, the catalyst withdrawal difficulty threshold;

μ: representing an arbitrarily small positive number, and urging to accept a customer number threshold;

θ: represents a positive number of any small, lower limit of hastening receipt of a client cluster;

eta: representing an arbitrarily small positive number, the upper limit of the customer cluster to be charged;

α: represents an arbitrarily small positive number, the lower limit of the amount of the collection of the money;

beta: indicating an arbitrarily small positive number, the upper limit of the amount of the collection.

The model aims to realize efficient and convenient customer collection and give full play to the maximum collection efficiency of collection personnel on the premise of ensuring relative fairness. Therefore, the optimization target of the model is to minimize the distance between the collection urging personnel and the collection urging task (client) so as to ensure that the collection urging personnel can urge to collect nearby and achieve the optimal collection urging efficiency. Meanwhile, for the customers with higher hasty of collection, the matching requirement of hasty of collection and task difficulty is increased, the matching degree of the maximum hasty of collection and task difficulty is increased by the optimization goal of the model, and the maximum hasty of collection is achieved. And finally, limiting constraint conditions of the model, including the number of the collection hastening clusters, the number of the collection hastening credits, the collection hastening risks and the like to meet business principles of actual management needs.

Step 105: establishing a collection urging task distribution model based on an optimal decision theory:

firstly, a task allocation model of a client cluster with the collection difficulty lower than or equal to epsilon is constructed as follows:

h_ija_ij＜1 a_ij∈A,h_ij∈H (1-7)

a_ij∈{0,1} a_ij∈A (1-8)

h_ij∈{0,1} h_ij∈H (1-9)

wherein the formula (1-1) is an objective function representing minimizing the sum of distances between the person who hastens the receipts and the customer. The target function formula ensures that the customer cluster close to the target function formula is preferentially distributed to the collection urging personnel in order to meet the requirement of the highest efficiency of the collection urging service, so that the overall collection urging distance is shortest, and the collection urging cost is reduced.

The formula (1-2) shows that each customer can only be charged by one person.

The formulas (1-3) and (1-4) show that the total collection cluster of each collection urging personnel is within the range of theta and eta, so that the collection urging workload of each collection urging personnel is ensured to be not greatly different, and the fairness of task allocation is met.

The formulas (1-5) and (1-6) show that the total amount of the receipts of each person is within the range of alpha and beta, so that the distribution of the amount of the receipts needs to be ensured to be not greatly different, and the fairness of task distribution is met.

The formulas (1-7) are used for preventing and controlling risks and meeting the hand-off principle, so that the distribution result is different from the historical distribution result, and the fact that the persons who are hasten to receive in a period on the same cluster are different is guaranteed. The problem that the risk problem of a person who urges to collect the same client cluster and the same client for a long time is solved, and the person who urges to collect is enabled to replace the urging cluster when a new task is distributed.

Equations (1-8) represent the decision variable a_ij is a variable of 0 to 1 for judging whether the customer is urged to be collected by the urging personnel.

The equations (1-9) represent the variable h_ijIs a variable of 0 to 1 and is used for judging whether the customer is urged to be collected by the urging personnel in the last period.

Secondly, a task allocation model of the client cluster with the hastening difficulty higher than epsilon is constructed as follows:

h_ija_ij＜1 a_ij∈A h_ij∈H (2-5)

h_ij∈{0,1} h_ij∈H (2-6)

a_ij∈{0,1} a_ij∈A (2-7)

the formula (2-1) is an objective function, and represents that the distance between the client and the collection staff is minimized, and the matching degree between the client cluster and the collection staff is maximized. On the premise of ensuring the minimum collection distance, the collection cluster with higher difficulty is distributed to collection personnel with stronger capacity, so that higher collection matching degree is achieved, and the overall collection success rate is improved. So that the objective function can simultaneously satisfy the principles of highest catalytic yield efficiency and maximum efficiency.

The formula (2-2) shows that each customer can only be charged by one person.

The formula (2-3) and the formula (2-4) show that the total collection cluster of each collection urging personnel is within the range of theta and eta, so that the collection urging workload of each collection urging personnel is ensured to be not greatly different, and certain fairness of task allocation is met.

The formula (2-5) is used for preventing and controlling risks, meeting the hand-changing principle and ensuring that the person who hasten the harvest in one period on the same cluster is different from the harvest at this time.

The formula (2-6) represents the variable h_ijIs a variable of 0 to 1 and is used for judging whether the customer is urged to be collected by the urging personnel in the last period.

Equations (2-7) represent the decision variable a_ijIs a variable of 0 to 1 and is used for judging whether the customer is urged to be collected by the urging personnel.

Step 106: coding solution models are written through sas and python, and model optimal solutions are provided to be applied to task allocation decision bases: and adjusting the parameters of the model and modifying the objective function and the constraint condition of the model according to the actual needs of the service until the requirements of the service are met.

And step 107, not shown in FIG. 9: a task allocation scheme is provided.

In order to simultaneously meet four principles of highest efficiency, maximum efficiency, fair examination and risk control, the application example of the application provides a classification optimization strategy. On the basis of 'highest efficiency' and 'risk control', a task allocation principle mainly based on 'fair examination' is implemented for a client cluster with low hastening difficulty; and for the client cluster with higher promotion difficulty, the task allocation principle of 'efficiency maximization' is implemented.

The application example of the application realizes the output of the comprehensive collection urging strategy by constructing two models of 'customer type judgment' and 'collection urging mode recommendation', and is specifically realized in the following steps 201 to 206 by referring to fig. 10.

Step 201: selecting a client set: the steps are the same as step 101 and need not be repeated.

Step 202: and (5) carrying out quantitative analysis on the client label indexes.

To clearly classify customers from the data, label data is provided for training the classification model. According to the application example, obvious characteristic expressions are extracted to serve as quantitative indexes according to business experiences and the behavior expressions of customer historical payment urging response, customer types are distinguished through a clustering algorithm, and clear division values are obtained according to clustering results, so that customer samples are labeled.

Step 203: and constructing a customer classification model index system.

According to business experience and collection prompting scenes, the application example of the application focuses on fund change and payment habits of customers from four dimensions of basic information, payment willingness, deterioration possibility and historical collection prompting expression conditions of the customers, extracts a plurality of (such as 216) characteristic indexes, and constructs a set of index system capable of truly reflecting characteristics, fund change and payment expression of the customers with reference to fig. 11.

Step 204: a customer classification model.

Three types of clients, namely 'prompt and return', 'prompt and return' and 'prompt and return', are researched from the business meaning, and the three types of clients are found to have the nested relation. Therefore, the three-classification problem of the application example to the client is realized by two-classification models together. First, the model identifies "frequent" customers among the total number of customers. Then, the model II is divided into two types of' one-time-to-. Meanwhile, in order to ensure the balance of data quantity and prevent greatly different data proportions from directly entering the model to influence the model effect, the data proportion of the first model is adjusted in a down-sampling and SMOTE up-sampling mode, so that the effect of data balance is achieved. The model cleans extracted data through steps of data duplication removal and marking, single value processing, missing value supplement and the like, performs characteristic engineering on the data of the client set, sequentially performs steps of classified variable mapping, variable correlation judgment, continuous variable binning, variable screening based on an IV value, collinearity diagnosis and the like to complete integration, compression and screening of variables, finally screens characteristic variables respectively for constructing the model, and selects a random forest model from a plurality of classified models to realize classification of clients.

Step 205: and (5) recommending a scheme for the collection strategy.

According to the client type judging model, the client is divided into three categories of 'prompt to return', 'frequently prompt to return' and 'frequently prompt to not return', the core of client classification, namely the repayment habit and the repayment capacity of the client are used as the division basis of the strategy recommendation, the actual business collection experiential is combined, and the collection strategy is judged according to the category of the client and the historical response condition of the client.

For the customer who returns the money immediately, the historical repayment will and the repayment ability are both excellent, and the current repayment ability is higher. From the historical collection response, almost all customers can collect the success in a short message mode. Combining three points, the model adopts a collection urging strategy which mainly adopts short messages to finish collection urging for customers who urge to return.

For the frequently-urging frequently-returning customers, the historical repayment willingness is good, and the repayment capacity is weaker than that of the first class of customers. From the historical collection response, the successful collection of the customers is mainly realized by short messages and is assisted by telephone collection. And gradually increasing the intensity of the collection-urging strategy according to the current repayment capacity of the customer, enhancing the collection-urging force, and urging collection by adopting short messages, combination of the short messages and the telephone in sequence.

For the frequently-delayed customers, the historical repayment willingness is weak, the repayment capacity is poor, the prompt receipt effect of the short message can be seen from the historical prompt receipt response, and the telephone is taken as the main successful prompt receipt means, so that the telephone and the prompt receipt strategies are directly adopted in combination with the repayment capacity.

Step 206: and the collection urging personnel refers to the client type and the strategy for collection urging.

According to the application example, the client types of the clients to be urged to be accepted are judged one by one, the corresponding urging strategy is recommended to be used as reference, and the urging personnel can urge the clients differently according to the provided client characteristic information, client category information and the recommended urging strategy and by combining with the own urging experience.

In summary, the application example of the present application may have the following effects and advantages:

1. the application example integrates and innovates a machine learning technology and an operation and research optimization technology, is used for collection promotion business in the post-loan wind control field, and combines management difficulties and business pain points to construct an advanced intelligent collection promotion comprehensive system in the industry.

2. By utilizing the application example of the application, the core problem of the whole flow of collection promotion is solved for relevant business departments, an intensive, refined and intelligent comprehensive collection promotion system is realized, and the upgrading transformation from traditional collection promotion to intelligent collection promotion is realized.

3. Utilize this application example, divide into unified customer cluster with the comparatively concentrated customer of distribution, urge the personnel of receiving to use customer cluster to urge to receive in the unit is concentrated to the realization urges to receive the transition of the intensive mode of urging of customer group type from decentralized customer one by one, promote and urge to receive intensification degree.

4. A new task allocation mode is realized in the field of loan collection by using the application example of the application, and an effective intelligent task allocation scheme is provided for relevant business departments, so that decision reference is provided. The traditional manual task allocation is replaced by the big data + model algorithm, the manpower is liberated by science and technology, the subjective influence is reduced, and the efficient, objective and fair task allocation is realized.

5. By using the application example of the application, reference is provided for the collection strategy of a first-line collection staff. Through the model algorithm and experience judgment, the customer type classification is refined, so that the problem that the receiver is helped to judge who is preferred to be called, whether the receiver needs to be called or not and the like is solved, and the reference of a differentiated receiving calling strategy is provided.

In terms of hardware, in order to solve the problems of poor applicability and low accuracy of the pushed loan payment due to the fact that the designated logic of the scheme is too simple in the conventional loan payment due proposal pushing method, and further the problems of low efficiency and low success rate of loan payment due, the application provides an embodiment of an electronic device for implementing all or part of the contents in the loan payment due proposal pushing method, and the electronic device specifically includes the following contents:

fig. 12 is a schematic block diagram of a system configuration of an electronic device 9600 according to an embodiment of the present application. As shown in fig. 12, the electronic device 9600 can include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. Notably, this fig. 12 is exemplary; other types of structures may also be used in addition to or in place of the structure to implement telecommunications or other functions.

In one embodiment, the credit collection proposal push feature may be integrated into the central processor. Wherein the central processor may be configured to control:

steps

As can be seen from the above description, the electronic device provided in the embodiment of the present application groups the loan users to be collected according to the geographic location information corresponding to the loan users to form loan user groups, and can divide the loan users to be collected belonging to the same distance range into a group, so as to effectively improve the applicability and accuracy of the pushed loan collection scheme, and effectively improve the collection convenience, efficiency and success rate of the collection staff for collecting the loan according to the push scheme by selecting the collection staff for collecting the loan for each loan user group; through including in loan user group and this loan user group each loan user information of loan user with the customer end equipment who asks for receipts personnel that this loan user group corresponds is given in the loan of geographic position information's loan scheme propelling movement, can effectively improve the efficiency and the convenience that asks for receipts personnel to acquire required information, and the propelling movement process is high-efficient and with strong points, can further improve according to this propelling movement scheme that asks for receipts personnel's the efficiency and success rate of asking for receipts to effectively improve financial institution and ask for receipts personnel's user experience.

In another embodiment, the loan payment proposal pushing device may be configured separately from the central processor 9100, for example, the loan payment proposal pushing device may be configured as a chip connected to the central processor 9100, and the loan payment proposal pushing function is realized under the control of the central processor.

As shown in fig. 12, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is noted that the electronic device 9600 also does not necessarily include all of the components shown in fig. 12; further, the electronic device 9600 may further include components not shown in fig. 12, which can be referred to in the related art.

As shown in fig. 12, a central processor 9100, sometimes referred to as a controller or operational control, can include a microprocessor or other processor device and/or logic device, which central processor 9100 receives input and controls the operation of the various components of the electronic device 9600.

The memory 9140 can be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the central processing unit 9100 can execute the program stored in the memory 9140 to realize information storage or processing, or the like.

The input unit 9120 provides input to the central processor 9100. The input unit 9120 is, for example, a key or a touch input device. Power supply 9170 is used to provide power to electronic device 9600. The display 9160 is used for displaying display objects such as images and characters. The display may be, for example, an LCD display, but is not limited thereto.

The memory 9140 can be a solid state memory, e.g., Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. The memory 9140 could also be some other type of device. Memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application/function storage portion 9142, the application/function storage portion 9142 being used for storing application programs and function programs or for executing a flow of operations of the electronic device 9600 by the central processor 9100.

The memory 9140 can also include a data store 9143, the data store 9143 being used to store data, such as contacts, digital data, pictures, sounds, and/or any other data used by an electronic device. The driver storage portion 9144 of the memory 9140 may include various drivers for the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, contact book applications, etc.).

The communication module 9110 is a transmitter/receiver 9110 that transmits and receives signals via an antenna 9111. The communication module (transmitter/receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as in the case of a conventional mobile communication terminal.

Based on different communication technologies, a plurality of communication modules 9110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby implementing ordinary telecommunications functions. The audio processor 9130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 9130 is also coupled to the central processor 9100, thereby enabling recording locally through the microphone 9132 and enabling locally stored sounds to be played through the speaker 9131.

An embodiment of the present application further provides a computer-readable storage medium capable of implementing all the steps in the loan receipt plan pushing method in the foregoing embodiment, where the computer-readable storage medium stores a computer program, and the computer program, when executed by a processor, implements all the steps of the loan receipt plan pushing method in the foregoing embodiment, where the execution subject is a server or a client, for example, the processor implements the following steps when executing the computer program:

steps

As can be seen from the above description, the computer-readable storage medium provided in the embodiment of the present application groups the loan users to be collected according to the geographic location information corresponding to each loan user to form each loan user group, and can divide the loan users to be collected belonging to the same distance range into a group, so as to effectively improve the applicability and accuracy of the pushed loan collection scheme, and can effectively improve the convenience, efficiency, and success rate of collection of the collection staff who collects the loan according to the push scheme by selecting the collection staff for each loan user group to collect the loan; through including in loan user group and this loan user group each loan user information of loan user with the customer end equipment who asks for receipts personnel that this loan user group corresponds is given in the loan of geographic position information's loan scheme propelling movement, can effectively improve the efficiency and the convenience that asks for receipts personnel to acquire required information, and the propelling movement process is high-efficient and with strong points, can further improve according to this propelling movement scheme that asks for receipts personnel's the efficiency and success rate of asking for receipts to effectively improve financial institution and ask for receipts personnel's user experience.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for those skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should be understood as a limitation to the present invention.

Claims

1. A loan collection proposal pushing method is characterized by comprising the following steps:

2. The loan procurement proposal push method according to claim 1, wherein before pushing the corresponding loan procurement proposal to each of the lenders according to the unique identifier of the lender, the method further comprises:

3. The loan procurement proposal push method according to claim 1, wherein the determining of the unique identifier of the lender corresponding to each loan user group based on the preset configuration rules of the lender comprises:

performing quantitative grading according to key features of the historical credit acquisition record information of each loan user, and respectively determining the credit acquisition difficulty level of each loan user based on a preset credit acquisition difficulty grading library of the loan user, wherein the credit acquisition difficulty grading library of the loan user is used for storing the corresponding relationship between the quantitative grading of the key features in the historical credit acquisition record information and the credit acquisition difficulty level;

4. The loan procurement plan pushing method according to claim 3, wherein the selecting a corresponding configuration rule of an acquirer for each loan user group based on a comparison result between a difficulty score and a difficulty threshold corresponding to each loan user group, and determining a unique identifier of an acquirer corresponding to each loan user group based on a preset allocation rule of an acquirer, comprises:

wherein, the configuration rule of the low-difficulty acquirer comprises:

5. The loan procurement plan pushing method according to claim 3, wherein the selecting a corresponding configuration rule of an acquirer for each loan user group based on a comparison result between a difficulty score and a difficulty threshold corresponding to each loan user group, and determining a unique identifier of an acquirer corresponding to each loan user group based on a preset allocation rule of an acquirer, comprises:

wherein the configuration rule of the high-difficulty acquirer comprises:

6. The loan procurement proposal push method according to claim 2, characterized in that the obtaining of the user type corresponding to each loan user in each loan user group and the determining of the prestored procurement proposal of the loan expediting proposal corresponding to each user type comprises:

7. The loan procurement plan push method according to any one of claims 1 to 6, wherein the grouping of the loan users according to the geographic location information corresponding to each loan user to be procured to form each loan user group comprises:

8. The utility model provides a loan is urged and is received scheme pusher which characterized in that includes:

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the loan procurement proposal pushing method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the loan real estate delivery method according to any of claims 1 to 7.