CN115526707A - Decision engine-based loan order dispatching method, server and storage medium - Google Patents
Decision engine-based loan order dispatching method, server and storage medium Download PDFInfo
- Publication number
- CN115526707A CN115526707A CN202211192686.XA CN202211192686A CN115526707A CN 115526707 A CN115526707 A CN 115526707A CN 202211192686 A CN202211192686 A CN 202211192686A CN 115526707 A CN115526707 A CN 115526707A
- Authority
- CN
- China
- Prior art keywords
- credit
- client
- information
- order
- decision engine
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application provides a decision engine-based credit check and dispatch method, a server and a storage medium, wherein the decision engine-based credit check and dispatch method comprises the following steps: in response to the obtaining of the credit and audit information, extracting the basic information and the order information of the client in the credit and audit information; according to the basic information of the client and the order information, calling a decision engine to carry out strategy matching so as to respectively and correspondingly obtain a client risk classification code and an order risk classification code; calling a decision engine to perform type matching according to the client risk classification code and the order risk classification code so as to obtain a credit and audit type corresponding to the credit and audit information; and calling a decision engine to perform order matching according to the credit review type so as to determine a credit review specialist corresponding to the credit review information. The decision engine-based credit check dispatching method, the server and the storage medium execute differential credit check, improve the efficiency of credit check, reduce the cost of credit check and provide better service for clients.
Description
Technical Field
The application relates to the technical field of financial credit auditing, in particular to a decision engine-based credit auditing and dispatching method, a server and a storage medium.
Background
In the process of examining and verifying the loan qualification of the client in the financial credit field, all fields or part of fields such as basic conditions, credit investigation conditions, asset conditions, engineering contracts, planned equipment use, financial schemes, guarantee conditions and the like of the client are generally investigated and known, and a third party credit investigation data source is accessed to comprehensively evaluate the risk condition of an applicant to determine whether to provide credit. The traditional financing leasing company surveys the credit qualification of the client, and adopts one credit loan auditing mode of loan officer on-site loan auditing, client on-line autonomous loan auditing, remote video loan auditing and the like according to the scale of the company, the product characteristics and the like.
In the course of conceiving and implementing the present application, the inventors found that at least the following problems existed: the client self-determination loan auditing method is only judged according to loan auditing information and internal and external credit investigation conditions submitted by the client self, and the client qualification and risk control are limited, so that the client can only meet the small bill with the loan amount below the medium scale. Compared with the independent loan auditing of a client, the remote video loan auditing method adopts a video call method and a client conversation method, so that the qualification and risk control of the client is improved, but the authenticity of the family condition, the property condition and the use of the equipment to be purchased of the client is still insufficient, and only medium and small bills with medium-scale and below loan limits can be met. The on-site loan auditing method of the loan officer adopts a method that the loan officer goes to the client site and the engineering site to understand on the site, so that the actual condition of the client can be better and more comprehensively understood and the risk of the client can be controlled, but when some small orders and the area of the client are far away, the loan auditing cost is high and the cost-effectiveness ratio is low, and in addition, due to special factors such as some special control, the on-site loan auditing of the client cannot be carried out, and part of services are lost.
The foregoing description is provided for general background information and is not admitted to be prior art.
Disclosure of Invention
To alleviate the above problems, the present application provides a decision engine-based credit submission method, server, and storage medium.
In one aspect, the present application provides a decision engine-based credit referral method, specifically comprising:
in response to the acquisition of the credit review information, extracting the basic information and the order information of the client in the credit review information;
calling a decision engine to perform strategy matching according to the basic customer information and the order information so as to respectively and correspondingly obtain a customer risk classification code and an order risk classification code;
calling a decision engine to perform type matching according to the client risk classification code and the order risk classification code so as to obtain a credit review type corresponding to the credit review information;
and calling a decision engine to perform order matching according to the credit review type so as to determine a credit review specialist corresponding to the credit review information.
Optionally, the step of calling the decision engine to perform policy matching to respectively and correspondingly obtain the client risk classification code and the order risk classification code when the decision engine-based credit-censoring method executes the policy matching according to the client basic information and the order information includes:
inquiring client credit records according to the client certificate number of the client basic information;
calling a client risk classification strategy set in the decision engine, and performing rule matching of the risk strategy set according to the client credit record to obtain a matched client risk classification code;
wherein the client credit record comprises at least one of client type, area, external credit investigation, property condition, internal credit investigation, internal historical purchasing record and historical repayment information.
Optionally, the step of executing the step of invoking the client risk classification policy set in the decision engine and performing rule matching of the risk policy set according to the client credit record by the credit trial and policy method based on the decision engine to obtain the matched client risk classification code includes the steps of:
reading credit records of historical clients, and respectively carrying out first weight assignment according to first weight dimensions of the historical clients, wherein the first weight dimensions comprise client types, areas where the clients are located, external credit investigation, asset conditions, internal credit investigation of enterprises, internal historical purchasing records of the enterprises and historical repayment information;
classifying different customers into a plurality of risk classifications according to the first weight assignment, and performing customer risk classification coding on the risk classifications;
and determining a risk classification code corresponding to the credit review information according to the first weight dimension of the credit record of the client of the credit review information.
Optionally, the step of calling the decision engine to perform policy matching to respectively and correspondingly obtain the client risk classification code and the order risk classification code when the decision engine-based credit-censoring method executes the policy matching according to the client basic information and the order information includes:
according to the purchase financial scheme of the order information, carrying out rule matching of a credit policy set on the order information by using the credit policy set in the decision engine so as to obtain a matched order risk classification code;
wherein the procurement financial scenario includes at least one of a procurement equipment type, an order amount, a first-payment proportion, a financial scenario type, and a warranty condition.
Optionally, the step of performing, by the decision engine-based credit-and-audit method, rule matching of the credit policy set on the order information by using the credit policy set in the decision engine to obtain a matched order risk classification code before executing the purchase finance scheme according to the order information includes:
reading a purchasing financial scheme of a historical client, and respectively carrying out second weight assignment according to a second weight dimension of the historical client, wherein the second weight dimension comprises a purchasing equipment type, an order amount, a first payment proportion, a financial scheme type and a guarantee condition;
classifying different orders into a plurality of risk classifications according to the second weight assignment, and performing order risk classification coding on the risk classifications;
and determining an order risk classification code corresponding to the order information according to a second weight dimension of the purchase financial scheme of the order information.
Optionally, the step of calling the decision engine to perform type matching to obtain the credit type corresponding to the credit information after the decision engine-based credit dispatching method executes the client risk classification code and the order risk classification code, includes:
calling a scoring card model, and inputting the client risk classification code and the order risk classification code so that the scoring card model outputs a score for the credit and audit information;
and reading the credit and review information and the scores, and performing rule matching by using a credit and review type strategy set in the decision engine to determine a credit and review type corresponding to the credit and review information.
Optionally, the type of credit in the decision engine-based credit approving method includes at least one of client-independent credit, remote video credit, credit-approval-specialist ground credit and double-person ground credit.
Optionally, the step of calling the decision engine to perform order matching to determine a credit special member corresponding to the credit information when the decision engine-based credit issuing method executes the credit according to the credit type includes:
calling a decision tree model, inputting the crediting information, and acquiring the qualification requirement of a credit manager corresponding to the crediting information;
and calling the current workload of the credit manager meeting the qualification requirements of the credit manager, and determining the credit manager with the least current workload as a credit examining specialist corresponding to the credit examining information.
In another aspect, the present application further provides a server, in particular, the server includes a processor and a storage medium connected to each other, wherein:
the storage medium is used for storing a computer program;
the processor is used for reading the computer program and running so as to enable the server to realize the credit and audit order method based on the decision engine.
In another aspect, the present application further provides a storage medium, in particular, a storage medium having a computer program stored thereon, which when executed by a processor, implements the steps of the decision engine-based credit-audit order assignment method as described above.
As described above, according to the decision engine-based order approving method, the server and the storage medium provided by the application, the decision engine is called for many times according to different dimensional attributes such as clients and orders, so that the best appropriate order type and the best responsible order specialist are automatically matched, differential order approvals are performed, the efficiency of the order approvals is improved, the cost of the order approvals is reduced, and better services are provided for the clients.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and, together with the description, serve to explain the principles of the application. In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the description of the embodiments will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive step.
FIG. 1 is a first flowchart of a decision engine-based order loan assignment method according to an embodiment of the present application.
FIG. 2 is a flowchart illustrating a decision engine based order lending method according to an embodiment of the present invention.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings. With the above figures, there are shown specific embodiments of the present application, which will be described in more detail below. The drawings and written description are not intended to limit the scope of the inventive concepts in any manner, but rather to illustrate the concepts of the application by those skilled in the art with reference to specific embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the recitation of a claim "comprising a" 8230a "\8230means" does not exclude the presence of additional identical elements in the process, method, article or apparatus in which the element is incorporated, and further, similarly named components, features, elements in different embodiments of the application may have the same meaning or may have different meanings, the specific meaning of which should be determined by its interpretation in the specific embodiment or by further combination with the context of the specific embodiment.
It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
First embodiment
In one aspect, the present application provides a decision engine-based credit approving method, fig. 1 is a flowchart of a decision engine-based credit approving method according to an embodiment of the present application, and fig. 2 is a flowchart of a decision engine-based credit approving method according to an embodiment of the present application.
Referring to fig. 1 and 2 in combination, in one embodiment, the decision engine based credit-censoring method includes:
s10: and in response to the acquisition of the credit review information, extracting the basic information and the order information of the client in the credit review information.
When a client needs a loan, it will submit loan approval information including the client's basic information and order information.
S20: and calling a decision engine to perform strategy matching according to the basic information of the client and the order information so as to respectively and correspondingly obtain a client risk classification code and an order risk classification code.
Illustratively, the decision engine includes various policies required for intelligent billing, such as a client risk classification policy, a credit policy, a credit audit type policy, a billing policy, and the like. The decision engine can carry out specific quantitative classification on the client risk and the order risk through the corresponding matching of the client risk classification strategy and the credit policy strategy according to specific conditions.
S30: and calling a decision engine to perform type matching according to the client risk classification code and the order risk classification code so as to obtain a credit review type corresponding to the credit review information.
Illustratively, the decision engine includes various policies required for intelligent billing, such as a customer risk classification policy, a credit policy, a crediting type policy, a billing policy, and the like. And the decision engine can carry out specific quantitative classification on the credit and audit information through the corresponding matching of the credit and audit type strategies according to specific conditions.
S40: and calling a decision engine to carry out order matching according to the credit review type so as to determine a credit review specialist corresponding to the credit review information.
Illustratively, the decision engine includes various policies required for intelligent billing, such as a client risk classification policy, a credit policy, a credit audit type policy, a billing policy, and the like. The decision engine can distribute proper credit and audit information to credit and audit professionals by carrying out corresponding matching according to the order dispatching strategy and the specific conditions of the credit and audit information and the credit and audit professionals.
In this embodiment, the decision engine-based credit and audit method automatically matches the best credit and audit type and the credit and audit specialist in the best decision charge by calling the decision engine for multiple times according to different dimensional attributes of the client, the order and the like, executes differential credit and audit, improves the efficiency of credit and audit, reduces the credit and audit cost, and provides better service for the client. Optionally, the differential credit review refers to integrating order customer information and credit policies, automatically matching customer independent credit review, remote video credit review, credit review specialist field credit review and double field credit review types, and executing a differential and fine credit review process.
In one embodiment, the decision engine-based credit-censoring method performs S20: the step of calling a decision engine to carry out strategy matching according to the basic information of the client and the order information so as to respectively and correspondingly obtain the risk classification code of the client and the risk classification code of the order comprises the following steps:
s21: inquiring the credit record of the client according to the client certificate number of the basic information of the client;
s22: and calling a client risk classification strategy set in the decision engine, and performing rule matching of the risk strategy set according to the client credit record to obtain a matched client risk classification code.
Optionally, the client credit record includes at least one of client type, location, external credit, asset condition, internal credit, internal historical purchase record and historical repayment information.
In this embodiment, a credit and audit policy dispatching method based on a decision engine queries client external credit investigation, enterprise internal credit investigation, and enterprise internal historical purchase record information and historical repayment information according to a client certificate number to call a client risk classification policy set in the decision engine, and comprehensively calculates client risk classification by matching client information with policy set rules to obtain a client risk classification code.
In one embodiment, decision engine based credit-order method performs S22: the steps of calling a client risk classification strategy set in a decision engine, and carrying out rule matching of the risk strategy set according to client credit records to obtain a matched client risk classification code comprise the following steps:
s220: reading credit records of historical clients, and performing first weight assignment according to first weight dimensions of the historical clients, wherein the first weight dimensions comprise client types, areas where the clients are located, external credit investigation, asset conditions, internal credit investigation of enterprises, historical purchasing records of the internal enterprises and historical repayment information;
s221: classifying different customers into a plurality of risk classifications according to the first weight assignment, and performing customer risk classification coding on the plurality of risk classifications;
s222: and determining a risk classification code corresponding to the credit review information according to the first weight dimension of the credit record of the client of the credit review information.
Illustratively, the client risk classification policy set classifies clients into 5 major classes of A, B, C, D and E, each major class comprises 3 minor classes of 0, 1 and 2, and 15 client risk classifications are calculated. And each client risk classification is comprehensively evaluated by taking a plurality of dimensions such as client type, client asset condition, enterprise internal credit investigation condition, client historical repayment condition and the like as a first weight dimension, and finally the client risk classification is determined. Alternatively, the client risk classification of the government class client can be an A01 code, the company alliance client, the internal credit of the enterprise is normal, the historical purchasing record is not overdue, and the client risk classification can be a B01 code.
In one embodiment, the decision engine-based credit-censoring method performs S20: the step of calling a decision engine to carry out strategy matching according to the basic information of the client and the order information so as to respectively and correspondingly obtain the risk classification code of the client and the risk classification code of the order comprises the following steps:
s23: and according to the purchase financial scheme of the order information, carrying out rule matching of a credit policy set on the order information by using the credit policy set in the decision engine so as to obtain a matched order risk classification code.
Optionally, the purchase financial scenario includes at least one of a purchase equipment type, an order amount, a first payment proportion, a financial scenario type, and a warranty condition.
In this embodiment, a credit policy set in a decision engine is called by a credit-audited policy method based on a decision engine according to indexes such as device information and financial schemes, order risk classification is comprehensively calculated by matching order information with rules in the policy set, and an order risk classification code is obtained.
In one embodiment, the decision engine-based credit-censoring method performs S23: the steps of using credit policy set in decision engine to carry out rule matching of credit policy set to order information according to purchase finance scheme of order information to obtain matched order risk classification code include:
s230: reading the purchasing financial scheme of the historical client, and respectively carrying out second weight assignment according to a second weight dimension of the historical client, wherein the second weight dimension comprises a purchasing equipment type, an order amount, a first payment proportion, a financial scheme type and a guarantee condition;
s231: classifying different orders into a plurality of risk classifications according to the second weight assignment, and performing order risk classification coding on the plurality of risk classifications;
s232: and determining an order risk classification code corresponding to the order information according to the second weight dimension of the purchase financial scheme of the order information.
Optionally, the credit policy set performs comprehensive evaluation by taking multiple dimensions such as a purchasing equipment type, a first payment proportion, a financial scheme type, a guarantee condition and the like as a second weight dimension, and finally determines 21 order risk classifications in total from a to U. For example, the order risk classification of the government class customer order can be A code, the enterprise customer purchases a large excavator and pays for 50% first, the financing lease mode is adopted, the actual controller of the enterprise guarantees, and the order risk classification can be B code.
In one embodiment, the decision engine-based credit-censoring method performs S30: the step of calling a decision engine to perform type matching according to the client risk classification code and the order risk classification code so as to obtain a credit type corresponding to the credit information comprises the following steps:
s31: calling a scoring card model, and inputting a client risk classification code and an order risk classification code so that the scoring card model outputs a score for the credit and audit information;
s32: and reading the credit and audit information and the score, and performing rule matching by using a credit and audit type strategy set in a decision engine to determine the credit and audit type corresponding to the credit and audit information.
In this embodiment, the policy engine takes the calculated risk classification code of the client and the calculated risk classification code of the order as a parameter of a rating card model, calculates the final rating of the client comprehensively, and matches a credit type policy centralization rule to calculate the credit type. Illustratively, the scoring card model calculates the risk score of the order of the client according to different business departments and different product types by adopting different weighting proportions according to two dimensions of the risk classification of the client and the risk classification of the order for judging a credit and audit type strategy. Optionally, products produced by some departments do not need to be detailed to product types for judgment, different types of products of some departments have large difference, judgment needs to be carried out according to the product types, and different weights are distributed according to the product types.
In one embodiment, the types of credit in the decision engine based credit assignment method include at least one of client-independent credit, remote video credit, credit specialist ground credit and double ground credit.
Illustratively, if the type of credit is one of "client-independent credit", "remote video credit", "credit-expert field credit", "double field credit", then 1, 2, 3, 4 are established, with four scores corresponding to four types of credit. And the credit examination type strategy set carries out comprehensive evaluation on multiple dimensions such as risk classification of the client, the area of the client, the purchase amount, the purchase equipment type and the like.
Illustratively, the first purchase amount is more than 1000 ten thousand, the client risk is classified as B0, the order risk is a new client with E, the credit check type score is 4, and the double field credit check is realized. The first-time purchase amount is less than 100 ten thousand, the purchase equipment type is an excavator, the client risk is classified into a new client with B0 order risk of C, the credit review type score is 2, and the remote video credit review method corresponds to remote video credit review. The first purchase amount is less than 20 ten thousand, the purchasing equipment type is a tractor, the client risk classification is a new client with B0 order risk of B, the credit check type score is 1, and the method corresponds to the client independent credit check.
In one embodiment, decision engine-based credit-order method performs S40: according to the credit review type, a decision engine is called to carry out order matching so as to determine a credit review specialist corresponding to the credit review information, and the steps comprise:
s41: calling a decision tree model, inputting credit review information, and acquiring the qualification requirement of a credit manager corresponding to the credit review information;
s42: and calling the current workload of the credit manager meeting the qualification requirements of the credit manager, and determining the credit manager with the least current workload as a credit examination specialist corresponding to the credit examination information.
In this embodiment, the decision engine-based credit-order dispatching method calls a decision tree model in the decision engine flow to match the optimal credit-audit officer according to different requirements of different credit-audit types and through index variables such as the grade and age of the credit-audit officer.
Illustratively, if the credit check type double credit check is adopted, the decision tree model is a senior credit manager according to the level of a main credit manager required by the double credit check, assists a common credit manager who enters the job within 2 years of the level of the credit manager to match all credit managers in the area where the order is located, and if a plurality of credit managers with rechecking conditions are matched, the credit managers are sorted in an ascending order according to the workload and the credit manager with the least workload is taken as the order credit check responsible person.
As described above, the credit and audit method based on the decision engine inputs variables and parameters required by the decision engine by calling the decision engine for multiple times, the decision engine calls the internal strategy set, and calculates the optimal credit and audit scheme according to the rules and the grading card model, so that better quality credit and audit service can be provided for the client, the risk of the client is better controlled, meanwhile, common credit and audit personnel are given the opportunity of participating in the credit and audit of complex orders, credit and audit experience is accumulated, and the service capability can be improved quickly.
Second embodiment
On the other hand, the application also provides a server.
In one embodiment, a server includes a processor and a storage medium coupled to each other. Wherein: a storage medium for storing a computer program; the processor is used for reading the computer program and running so as to enable the server to realize the credit and audit order method based on the decision engine.
Illustratively, the intelligent dispatching system used by the server in realizing the credit review dispatching method comprises the following steps:
the intelligent order dispatching system automatically judges the credit and audit types suitable for the orders according to the dimensional attributes of the clients, the orders and the like implanted in the system, and optimally decides the credit and audit specially-assigned personnel according to the dimension matching of the grades, the responsible areas, the workload and the like of the credit and audit specially-assigned personnel.
And the decision engine comprises various strategies required by intelligent dispatching, such as a client risk classification strategy, a credit policy strategy, a credit review type strategy, a dispatching strategy and the like.
The intelligent dispatching system transfers variables and parameters required by the decision engine by calling the decision engine for multiple times, the decision engine calls an internal strategy set, an optimal scheme is calculated according to rules and a grading card model, and a corresponding interface code is returned. The specific execution steps are as follows:
the method comprises the following steps that S1, a CRM system pushes business information to a financial credit and audit platform through an interface, and the financial credit and audit platform transmits basic information and order information of customers to an intelligent order system (the intelligent order system sequentially calls a strategy set and a model configured on a decision engine platform to perform automatic decision).
S2, after receiving the financial credit and audit platform information, the intelligent dispatching system inquires external credit investigation, internal credit investigation and internal historical purchasing record information of the client according to the client certificate number, calls a client risk classification strategy set in a decision engine, comprehensively calculates client risk classification by matching the client information with a strategy concentration rule, and returns a client risk classification code; the client risk classification strategy set divides clients into 5 major classes of A, B, C, D and E, each major class comprises 3 minor classes of 0, 1 and 2, and 15 client risk classifications are calculated. And each client risk classification carries out comprehensive evaluation from multiple dimensions such as client types, client asset conditions, enterprise internal credit investigation conditions, client historical repayment conditions and the like, and finally determines the client risk classification.
For example, a government class client directly returns a client risk classification A01 code; for example, a company joins clients, and the internal credit of the enterprise is normal, and the historical purchasing record is not overdue, the client risk classification B01 code is returned.
S3, calling a credit policy strategy set in a decision engine by the intelligent order dispatching system according to indexes such as equipment information, financial schemes and the like, comprehensively calculating order risk classification by matching order information with a strategy concentration rule, and returning an order risk classification code;
the credit policy strategy set carries out comprehensive evaluation on multiple dimensions such as purchasing equipment type, first payment proportion, financial scheme type and guarantee condition, and finally determines 21 order risk classifications A-U in total.
For example, if the order of the government class customer is received, the order risk classification A code is directly returned;
for example, when an enterprise client purchases a large excavator, 50% of the excavator is paid for the first time, a financing lease mode is adopted, and an actual controller of the enterprise guarantees, and then an order risk classification B code is returned.
S4, taking the index results calculated by the decision engine according to S2 and S3 as score card model variables, comprehensively calculating the final scores (1 \2\3\4, four scores) of the clients, matching with credit trial type strategy concentration rules, calculating one of a credit trial type of client autonomous credit trial, a remote video credit trial, a credit trial specialist field credit trial and a double field credit trial, and returning a credit trial type code;
the scoring card model calculates the risk score of the order of the client by adopting different weighting proportions according to different causes and different product types (products produced by some causes do not need to be detailed to the product types for judgment, and products of different types of the causes have large differences and need to be judged according to the product types) by using two dimensions of risk classification of the client and risk classification of the order.
And the credit examination type strategy set carries out comprehensive evaluation on multiple dimensions such as risk classification of the client, the area of the client, the purchase amount, the type of the purchase equipment and the like.
At this point, a credit review type code may be returned:
for example, if the first purchase amount is more than 1000 ten thousand, the client risk classification is B0, and the order risk is E, the new client returns to the double-person real credit check with the credit check type of 4.
For example, if the first purchase amount is less than 100 ten thousand, the purchase equipment type is an excavator, the client risk classification is a new client with the B0 order risk of C, the credit review type is returned to 2, and the remote video credit review is performed.
For example, if the first purchase amount is less than 20 ten thousand, the purchasing equipment type is a tractor, the client risk is classified as a new client with the B0 order risk of B, the credit type is returned to be 1, and the client performs the independent credit.
And S5, the intelligent order dispatching system calls a decision tree model in the decision engine flow to match the optimal credit special members according to different requirements of different credit types judged in the S4 and through index variables such as the grades and the ages of the credit special members, and finally returns decision results of the upstream financial credit platform. Optionally, the score of the scoring card is used for the determination of the credit-type policy.
For example, the credit type strategy set returns that the credit type is 4, double credit, the decision tree model is a senior credit manager according to the level of the main credit manager required by double credit, assists the ordinary credit manager (different credit manager level requirements) who enters the job within 2 years of the level of the credit manager to match all credit managers in the area where the order is located, and if a plurality of credit managers with rechecking conditions are matched, the credit managers are sorted in ascending order according to the workload and the credit manager with the least workload is taken as the order credit responsible person.
Illustratively, when the server implements a decision engine-based credit order dispatching method, the step of performing video credit comprises:
t1, a client opens a video loan audit small program, fills in a mobile phone number and a video invitation code, clicks a 'call video seat', and a system calls the video seat through IM (instant messaging) and in-time call signaling;
the T2 video seat receives IM (instant messaging) timely call signaling at a PC (personal computer) end of a financial credit and audit platform, a video call answering page and a credit and audit worksheet page are automatically opened, the video call page floats on the credit and audit worksheet page and can be freely placed through dragging, and the PC end plays a ring to remind the video seat to answer;
t3, the video seat clicks an answering button, a video call room is created by real-time audio and video service, and a client small program end user and a video seat PC end user are automatically pulled into the video call room;
after both sides of a T4 video call enter a room, mixed flow transcoding and video recording services are started, video and audio information of both sides of the video call are collected, mixed flow transcoding is carried out on the audio and video information of both sides into a path of video, and video flows are synchronously recorded into a video file;
t5, after the video call is successfully established, the video seat guides the customer to take the front and back photos of the identity card, and the system automatically calls OCR recognition service to recognize information such as the name, the identity card number and the effective time of the customer;
the T6 video seat guides the client to shoot a face picture of the client, and the system uses the client identity card picture and the face picture to call AI face recognition service for comparison and checks the identity of the client;
t7, if the client does not carry the identity card, the client provides the identity card number and the name, the video seat guides the client to shoot a face picture of the client, AI face recognition service is called, a person card verification mode is adopted, the face picture of the client is compared with the identity card picture of the client in the authority library, and the identity of the client is verified;
after the identity of the T8 client is verified, the video agent communicates information such as client purchasing equipment information, financial schemes, client assets, application of equipment to be purchased and the like in a video conversation mode, collected client crediting information can be synchronously input into a credit and audit worksheet page in the conversation process, and after the credit and audit information is collected, the client or the agent hangs up a video conversation to finish video crediting and auditing;
positive and negative pictures of the identity card, the face pictures, the face comparison result and double-record video files generated in the video call process, which are shot by the T9 client, are intensively displayed on a credit and audit worksheet page, so that the subsequent check and restoration process of the current credit and audit process are facilitated, and the subsequent legal litigation cases which possibly occur are favorably supported.
As described above, the server implementation of decision engine based credit referral summaries as described above creates 4 types of credit: the method comprises the following steps of client autonomous credit and audit, remote video credit and audit, credit and audit specialist field credit and double field credit and audit. Various strategies required for intelligent order dispatching, such as a client risk classification strategy, a credit policy strategy, a credit review type strategy, an order dispatching strategy and the like, are formulated through a decision engine. Through the intelligent order dispatching system, the credit and audit types suitable for orders are automatically judged according to dimensional attributes of clients, orders and the like implanted into the system, and the credit and audit experts are optimally decided according to the dimension matching of the grades, the responsible areas, the workload and the like of the credit and audit experts. The remote video credit and audit technical scheme is realized based on video streaming media and AI face recognition technology, remote video credit and audit work orders are creatively combined, synchronous remote video credit and audit and write credit and audit reports are realized, positive and negative photos of an identity card taken by a client, a face photo, a face comparison result and a double-record video file generated in a video call process are intensively displayed on a credit and audit work order page, and subsequent review and original credit and audit processes are facilitated.
Third embodiment
In another aspect, the present application further provides a storage medium.
In an embodiment, the storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the decision engine based credit audit method described above.
As described above, the decision engine-based credit approving method, the server and the storage medium provided by the application are practically applied to practical projects of some financing leasing companies, and compared with a traditional credit approving manner for a specially-assigned person on site, the remote video credit approving method can save the traveling cost of the specially-assigned person to a client on site for business, and the overall credit approving cost can be reduced by more than 98%. Compared with the traditional on-site loan audit of a loan audit specialist, the remote video loan audit is adopted, the loan audit specialist does not need to go to a client site, the loan audit task can be completed without leaving a house, and the overall loan audit duration can be reduced by more than 90%. Compared with a field credit review mode of a credit review specialist, double credit review can provide better quality credit review service and better control the risk of the client for some clients with large orders and higher risk, meanwhile, the common credit review specialist is given the opportunity of participating in complex order credit review, credit review experience is accumulated, and the service capacity can be improved quickly.
It should be noted that, in the present application, step numbers such as S10 and S20 are used for the purpose of more clearly and briefly describing corresponding contents, and do not constitute a substantial limitation on the sequence, and those skilled in the art may perform S20 first and then S10 in the specific implementation, but these should be within the protection scope of the present application.
In the embodiments of the server and the storage medium provided in the present application, all technical features of any one of the above-described method embodiments may be included, and the expanding and explaining contents of the specification are basically the same as those of each embodiment of the above-described method, and are not described herein again.
Embodiments of the present application further provide a computer program product, which includes computer program code, when the computer program code runs on a computer, the computer is caused to execute the method as in the above various possible embodiments.
Embodiments of the present application further provide a chip, which includes a memory and a processor, where the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that a device in which the chip is installed executes the method in the above various possible embodiments.
It should be understood that the foregoing scenarios are only examples, and do not constitute a limitation on application scenarios of the technical solutions provided in the embodiments of the present application, and the technical solutions of the present application may also be applied to other scenarios. For example, as a person having ordinary skill in the art can know, with the evolution of the system architecture and the emergence of new service scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
The steps in the method of the embodiment of the application can be sequentially adjusted, combined and deleted according to actual needs.
The units in the device in the embodiment of the application can be merged, divided and deleted according to actual needs.
In the present application, the same or similar term concepts, technical solutions and/or application scenario descriptions will be generally described only in detail at the first occurrence, and when the description is repeated later, the detailed description will not be repeated in general for brevity, and when understanding the technical solutions and the like of the present application, reference may be made to the related detailed description before the description for the same or similar term concepts, technical solutions and/or application scenario descriptions and the like which are not described in detail later.
In the present application, each embodiment is described with emphasis, and reference may be made to the description of other embodiments for parts that are not described or illustrated in any embodiment.
All possible combinations of the technical features in the embodiments are not described in the present application for the sake of brevity, but should be considered as the scope of the present application as long as there is no contradiction between the combinations of the technical features.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all the equivalent structures or equivalent processes that can be directly or indirectly applied to other related technical fields by using the contents of the specification and the drawings of the present application are also included in the scope of the present application.
Claims (10)
1. A decision engine based order lending method, comprising:
in response to the acquisition of the credit review information, extracting the basic information and the order information of the client in the credit review information;
according to the basic information of the client and the order information, calling a decision engine to carry out strategy matching so as to respectively and correspondingly obtain a client risk classification code and an order risk classification code;
calling a decision engine to perform type matching according to the client risk classification code and the order risk classification code so as to obtain a credit review type corresponding to the credit review information;
and calling a decision engine to carry out order matching according to the credit review type so as to determine a credit review specialist corresponding to the credit review information.
2. The decision engine-based credit and audit trail assignment method according to claim 1, wherein the step of invoking a decision engine to perform policy matching according to the basic customer information and the order information to respectively obtain a customer risk classification code and an order risk classification code comprises:
inquiring client credit records according to the client certificate number of the client basic information;
calling a client risk classification strategy set in the decision engine, and performing rule matching of the risk strategy set according to the client credit record to obtain a matched client risk classification code;
wherein the client credit record comprises at least one of client type, area, external credit investigation, property condition, internal credit investigation, internal historical purchasing record and historical repayment information.
3. The decision engine-based credit rating method of claim 2, wherein the step of invoking a client risk classification policy set in the decision engine, performing rule matching of the risk policy set according to the client credit record to obtain a matched client risk classification code comprises the steps of:
reading credit records of historical clients, and respectively performing first weight assignment according to first weight dimensions of the historical clients, wherein the first weight dimensions comprise client types, areas where the clients are located, external credit investigation, asset conditions, internal credit investigation of enterprises, internal historical purchase records of the enterprises and historical repayment information;
classifying different customers into a plurality of risk classifications according to the first weight assignment, and performing customer risk classification coding on the risk classifications;
and determining a risk classification code corresponding to the credit review information according to the first weight dimension of the credit record of the client of the credit review information.
4. The decision engine-based credit and audit method according to claim 1, wherein the step of invoking a decision engine to perform policy matching according to the basic information of the client and the order information to obtain a client risk classification code and an order risk classification code respectively comprises:
according to the purchase financial scheme of the order information, carrying out rule matching of a credit policy set on the order information by using the credit policy set in the decision engine so as to obtain a matched order risk classification code;
wherein the procurement financial scenario includes at least one of a procurement equipment type, an order amount, a first-payment proportion, a financial scenario type, and a warranty condition.
5. The decision engine-based credit review dispatch method of claim 4, wherein the step of matching the rules of the credit policy set against the order information using the credit policy set in the decision engine to obtain the matched order risk classification code according to the purchase finance plan of the order information previously comprises:
reading a purchasing financial scheme of a historical client, and respectively carrying out second weight assignment according to a second weight dimension of the historical client, wherein the second weight dimension comprises a purchasing equipment type, an order amount, a first payment proportion, a financial scheme type and a guarantee condition;
classifying different orders into a plurality of risk classifications according to the second weight assignment, and performing order risk classification coding on the plurality of risk classifications;
and determining an order risk classification code corresponding to the order information according to a second weight dimension of the purchase financial scheme of the order information.
6. The decision engine-based credit approving method according to claim 1, wherein the step of calling the decision engine to perform type matching according to the client risk classification code and the order risk classification code to obtain the credit type corresponding to the credit approving information comprises:
calling a scoring card model, and inputting the client risk classification code and the order risk classification code so that the scoring card model outputs a score for the credit and audit information;
and reading the credit and review information and the scores, and performing rule matching by using a credit and review type strategy set in the decision engine to determine a credit and review type corresponding to the credit and review information.
7. The decision engine-based credit delegation method of claim 1, wherein the credit types comprise at least one of customer-independent credit, remote video credit, credit-specialist field credit, and double field credit.
8. The decision engine-based order assignment method according to any one of claims 1-7, wherein the step of invoking a decision engine to perform order matching according to the order type to determine the order specialist corresponding to the order information comprises:
calling a decision tree model, inputting the crediting information, and acquiring the qualification requirement of a credit manager corresponding to the crediting information;
and calling the current workload of the credit manager meeting the qualification requirements of the credit manager, and determining the credit manager with the least current workload as a credit examining specialist corresponding to the credit examining information.
9. A server, comprising a processor and a storage medium coupled to each other, wherein:
the storage medium is used for storing a computer program;
the processor is configured to read the computer program and operate to cause the server to implement the decision engine-based credit and debit method according to any one of claims 1-8.
10. A storage medium, in particular having stored thereon a computer program which, when executed by a processor, carries out the steps of the decision engine based credit submission method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211192686.XA CN115526707A (en) | 2022-09-28 | 2022-09-28 | Decision engine-based loan order dispatching method, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211192686.XA CN115526707A (en) | 2022-09-28 | 2022-09-28 | Decision engine-based loan order dispatching method, server and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115526707A true CN115526707A (en) | 2022-12-27 |
Family
ID=84700652
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211192686.XA Pending CN115526707A (en) | 2022-09-28 | 2022-09-28 | Decision engine-based loan order dispatching method, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115526707A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116090888A (en) * | 2023-01-05 | 2023-05-09 | 中银金融科技有限公司 | Decision engine configuration management method, device, electronic equipment and program product |
| CN116308202A (en) * | 2023-03-29 | 2023-06-23 | 广州盖盟达工业品有限公司 | A rule engine execution method and device for different business scenarios |
| CN118037422A (en) * | 2024-01-30 | 2024-05-14 | 深圳信钛数科科技有限公司 | Online big data intelligent wind control system for banking industry |
-
2022
- 2022-09-28 CN CN202211192686.XA patent/CN115526707A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116090888A (en) * | 2023-01-05 | 2023-05-09 | 中银金融科技有限公司 | Decision engine configuration management method, device, electronic equipment and program product |
| CN116308202A (en) * | 2023-03-29 | 2023-06-23 | 广州盖盟达工业品有限公司 | A rule engine execution method and device for different business scenarios |
| CN118037422A (en) * | 2024-01-30 | 2024-05-14 | 深圳信钛数科科技有限公司 | Online big data intelligent wind control system for banking industry |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu | Assessing human information processing in lending decisions: A machine learning approach | |
| Belanger et al. | A framework for e‐government: privacy implications | |
| Parsons | Is accounting information from nonprofit organizations useful to donors? A review of charitable giving and value-relevance | |
| Slemrod | The economics of corporate tax selfishness | |
| Nelson et al. | How are earnings managed? Examples from auditors | |
| KR101277385B1 (en) | System and method for resolving transactions | |
| CN115526707A (en) | Decision engine-based loan order dispatching method, server and storage medium | |
| Chen et al. | Pure and hybrid crowds in crowdfunding markets | |
| US20210407000A1 (en) | Intelligent loan qualification based on future servicing capability | |
| US20140222716A1 (en) | Methods And Systems For Processing Debt Portfolios | |
| Nicoletti | Proposition of value and Fintech organizations in Banking 5.0 | |
| CN113743816A (en) | Vehicle rental risk control method and device, computer equipment and storage medium | |
| US20050283418A1 (en) | System and methodology for processing debt management plans | |
| US20150073873A1 (en) | Automated, self-learning tool for identifying impacted business parameters for a business change-event | |
| Mackie et al. | Understanding business dynamics: an integrated data system for America's future | |
| Keehley et al. | Can benchmarking for best practices work for government? | |
| Sinclair et al. | Understanding financial inclusion | |
| CN113436010A (en) | System and method for identifying public deposit payment loan fraud in real time | |
| US20020143679A1 (en) | Methods and systems for implementing a profitability model | |
| Amiri Jobani et al. | Designing a customer-oriented banking service model in Refah Bank with a content analysis approach | |
| Berger et al. | Credit scoring for microenterprise lenders | |
| Liu | Assessing the Strengths and Weaknesses of Human Information Processing in Lending Decisions: A Machine Learning Approach | |
| Ranger-Moore | Ecological dynamics and size distributions in the life insurance industry | |
| JP2002279059A (en) | Management analysis system | |
| Santos | The Impact of Big Data and Big Data Analytics in External Auditing Procedures |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |