CN111275391A - Online asset intelligent distribution system and method - Google Patents

Abstract

The invention discloses an online asset intelligent distribution system and a method, wherein the system comprises: a distribution management system comprising: the flow center module is used for managing asset distribution flows; the model analysis module is used for analyzing the historical credit granting or credit using distribution result, completing modeling and outputting the matching degree scores of the user and each capital institution; the rule engine module is used for executing the distribution strategy so as to select a matched capital institution party for the user; the real-time counting module is used for completing real-time counting of capital information of the capital institution party in the distribution transaction process; the background management module is used for defining and managing an asset distribution process; the flow routing system is used for acquiring user information of credit or credit application in a scene and providing the user information for the distribution management system to acquire; and the fund routing system is used for connecting each fund institution and forwarding the credit or credit application of the user to the fund institution side. The technical problem that the borrowing user and the fund institution can not fast and accurately make a deal is solved.

Description

Online asset intelligent distribution system and method

Technical Field

The invention relates to the technical field of computer information processing, in particular to an online asset intelligent distribution system.

Background

Internet finance (ITFIN) refers to a novel financial business mode in which a traditional financial institution and an internet enterprise realize fund integration, payment, investment and information intermediary services by using internet technology and information communication technology. Internet finance is not a simple combination of internet and financial industry, but a new mode and a new service which are generated for adapting to new requirements naturally after being familiar and accepted by users (especially, the acceptance of electronic commerce) on the level of realizing network technologies such as security, mobility and the like.

With the rapid development of internet finance in China, the loan subject on the internet is greatly increased, so that a loan user cannot quickly find a proper fund institution among a large number of fund institutions, and meanwhile, the fund institution cannot quickly and accurately find the loan user meeting the demand of the loan user.

Disclosure of Invention

The invention aims to provide an online asset intelligent distribution system to solve the technical problem that a borrowing user and a capital institution cannot make a deal quickly and accurately.

To achieve the above object, the present invention provides an online asset intelligent distribution system, comprising: a distribution management system, the distribution management system comprising: a process center module for managing asset distribution processes; the model analysis module is used for analyzing a historical credit granting or credit using distribution result, completing modeling and outputting matching degree scores of the user and each capital institution; a rules engine module for executing a distribution policy to select a matching funding institution party for a user; the real-time counting module is used for completing real-time counting of capital information of a capital institution party in the distribution transaction process; the background management module is used for defining and managing an asset distribution process; the system comprises a flow routing system, a distribution management system and a data processing system, wherein the flow routing system is used for acquiring user information of credit or credit application in a consumption credit scene, a cash credit scene or other scenes and providing the user information for the distribution management system to acquire; and the fund routing system is used for connecting each fund institution and forwarding the credit or credit application of the user to the fund institution side.

Optionally or preferably, the asset distribution process is used for carrying out approval operation on the user credit or credit application according to the wind control credit strategy or the wind control credit strategy.

Optionally or preferably, the fund institution side fund information comprises position, fund amount and person number limit.

Optionally or preferably, the background management module is configured to set a capital position, a capital amount, a number limit, and an institution risk preference of the capital institution.

Optionally or preferably, the distribution policy comprises: whether the daily statistic of capital position, capital amount and person number limit of the capital institution meets the capital position, capital amount and person number limit of the capital institution set by the system or not; or whether the user information meets the risk preference of the capital institution; or the matching degree scores of the user and the fund institution side are ranked from high to low.

The invention also provides an online asset intelligent distribution method, which comprises the following steps:

step S1, the traffic routing system acquires user information of various scenes;

step S2, selecting matched capital organization parties according to the user information and the comprehensive preference matching result of each capital organization;

step S3, distributing the user credit or credit application to the fund institution through the fund routing system and completing the transaction;

and step S4, the real-time statistics of capital position, capital amount and number limit information of capital organization is completed in the distribution process for the subsequent distribution process.

Alternatively or preferably, the step S3 further includes:

judging whether the capital position, the capital amount and the person number limit of the capital institution meet the capital position, the capital amount and the person number limit set by the system on the same day, and filtering the capital institution side which does not meet the requirement;

and judging whether the user information meets the risk preference of the capital organization side, and filtering the capital organization sides which do not meet the user information and the risk preference of the capital organization side.

The technical scheme provided by the invention has the beneficial effects that: through the asset distribution system, the borrowing user does not need to select a proper mechanism from a plurality of fund institution parties to complete credit granting or credit application, and the fund institution parties do not need to select a target borrowing user through complex screening. And analyzing in real time according to the big data, and performing accurate matching according to the user data and the mechanism attribute.

Drawings

FIG. 1 is an architecture diagram of an online intelligent asset distribution system provided by an embodiment of the present invention;

FIG. 2 is a schematic diagram of an online intelligent asset distribution system provided by an embodiment of the present invention;

FIG. 3 is a schematic diagram of a physical deployment of an online asset intelligent distribution system provided by an embodiment of the invention;

FIG. 4 is a flow chart of online variable processing for an online intelligent asset distribution system provided by an embodiment of the present invention;

FIG. 5 is a flow chart of a model development process for an online intelligent asset distribution system provided by an embodiment of the present invention;

FIG. 6 is a flow chart of rule set backward for an online asset intelligent distribution system provided by an embodiment of the invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings. It is to be understood that the described embodiments are merely illustrative or exemplary in nature and are in no way intended to limit the invention, its application, or uses. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced without some or all of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by presenting examples of the invention. The present invention is in no way limited to any specific configuration and algorithm set forth below, but rather covers any modification, replacement or improvement of elements, components or algorithms without departing from the spirit of the invention.

The present invention will be described in further detail with reference to specific examples, but the embodiments of the present invention are not limited thereto.

Example 1

As shown in fig. 1, the present embodiment provides an online asset intelligent distribution system, which includes a distribution management system, a traffic routing system, and a fund routing system. The distribution management system comprises a flow center module, a model analysis module, a rule engine module, a real-time statistic module and a background management module, wherein the flow center module is used for managing asset distribution flows, the model analysis module is used for analyzing historical credit or credit distribution results and completing modeling and outputting matching degree scores of users and various capital organizations, the rule engine module is used for executing distribution strategies and further selecting matched capital organization parties for the users, the real-time statistic module is used for completing real-time statistics of capital information of the capital organization parties in the distribution transaction process, and the platform management module is used for defining and managing the asset distribution flows. The flow routing system is used for acquiring user information of credit or credit application in a consumption credit scene, a cash credit scene or other scenes and providing the user information for the distribution management system to acquire, and the fund routing system is used for connecting each fund institution and forwarding the credit or credit application of the user to the fund institution side.

The system construction scheme is described in detail below:

for the rules engine, the rules engine framework employs drools. drools has an open source business rule engine which is easy to access enterprise strategies, adjust and manage, meets the standards in the industry, and has high speed and high efficiency. Establishing a rule engine micro-service, and distributing the strategies in the original distribution engine: matching of the user pricing codes and the mechanism pricing codes, mechanism party quota, inter-layer weight, intra-layer weight and hierarchical sequencing immigration rule engine.

The execution of rule strategies is realized by configuring the rule script file, and the mechanism preference, the mechanism rule set and the prediction model score can be supported.

A distribution engine having the functions of:

1. intelligent distribution function

The distribution engine directly calls the machine learning model platform to obtain the model prediction scores, sends the model scores to the rule engine for analysis and judgment, executes corresponding distribution strategies to obtain distribution strategy results, and performs subsequent distribution tasks according to the distribution results.

2. Intelligent monitoring function

And monitoring the (configurable) credit passing rate condition of each partner within a period of time, and automatically triggering manual notification and early warning when the passing rate is lower than a set threshold value. In addition, the credit granting timeliness condition in a period of time (configurable) is monitored, and when the credit granting timeliness is lower than a set threshold value, manual notification early warning is automatically triggered.

About model construction

1. On-line variable machining

As shown in fig. 4, in online variable processing, a binlog log of a mysql data source is pulled to a kafka message queue through a large data streaming platform, a Flink streaming processing job is used as a consumer of the kafka message queue to consume kafka data, and a data source distribution variable (json form) is analyzed into a structured form and written into hbase for a model to obtain data.

2. Model score derivation

The distribution model uses a machine learning algorithm, credit investigation variables sent to a fund side are used as model entering information, a fund side historical distribution result is used as a sample, and the customer group to be distributed is ranked and scored. In actual business, policy personnel can make a specific distribution policy according to the model score and the online performance, and the distribution passing rate is improved.

Referring to fig. 5, the model development process is divided into three steps of data cleaning, algorithm screening, model training and tuning. After the development is completed, the model is deployed on an AI engineering platform.

3. Reverse pushing of rule set

Referring to fig. 6, the fund side rule set reverse engineering is to reverse the fund side possible rule set by using the existing distribution result of the fund side as a sample, using credit investigation variables sent to the fund side as analysis information, and adopting a manual interaction decision tree method through the SAS-EM component. Compared with the model method, the method has the advantages of small accidental injury, easy control and low deployment cost, but the manual analysis is needed at present, and the consumed time is long. And the analysis process is automatically carried out at the later stage according to the requirements.

For the system technology stack, see the following table:

design of interface

1. Basic principle of interface

In order to ensure the integrity and robustness of the system, the system interface should meet the following basic requirements:

the interface provides enterprise-level support for the access of an external system, and provides safe and reliable access on the basis of high concurrency and large capacity of the system;

a perfect information security mechanism is provided to realize the comprehensive protection of information, ensure the normal operation of the system, prevent the occurrence of a large amount of accesses and a large amount of occupied resources and ensure the robustness of the system;

an effective system monitoring mechanism is provided, so that the running condition of the interface can be monitored, and errors can be found and removed in time;

the system can realize smooth transplantation and expansion on the premise of fully utilizing system resources, and can provide dynamic expansion of the system resources when the system is concurrently increased so as to ensure the stability of the system;

when carrying out capacity expansion and new service expansion, a quick, convenient and accurate implementation mode can be provided.

2. Interface security

In order to ensure the safe operation of the system, various interface modes should ensure the safety of the access.

The security of the interface is an important component of system security. The safety of the interface is ensured, the technical safety control is realized through the interface, and the knowing, the controlling and the predicting of the safety event are realized, which is an important basis for realizing the system safety.

According to the interface connection characteristics and the service characteristics, a special safety technology implementation strategy is made, and the safety of data transmission and data processing of the interface is ensured.

The system should enforce interface security control at the network boundary of the access point.

The safety control of the interface logically comprises: security assessment, access control, intrusion detection, password authentication, security audit, malicious code prevention, encryption and the like.

3. External interface

The arrangement of all interfaces used to describe the system to the outside world includes the interfaces between software and hardware, and the interfacing relationships between the system and supporting software. The main interfaces are as follows:

3.1SSO interface

The function of unified login in the SSO is realized by the butt joint with the SSO unified login platform.

3.2AI engineering platform interface

And obtaining a model decision result through the butt joint with the AI engineering platform.

The online asset intelligent distribution system of the embodiment adopts a physical deployment scheme as shown in fig. 3, wherein a front gateway, a distribution engine, a rule engine, a comprehensive service, an automatic task and a mechanism gateway are deployed on different virtual machines respectively, and each application comprises 6 groups. Caching adopts redis, message queue adopts kafka, and database uses mySql.

Example 2

The embodiment provides an online asset intelligent distribution method, which comprises the following steps:

step S1, the traffic routing system obtains user information of various scenarios.

And step S2, selecting a most suitable capital institution side according to the user information and the comprehensive preference matching result of each capital institution.

And step S3, distributing the user credit or credit application to the fund institution through the fund routing system and completing the corresponding transaction.

And step S4, the real-time statistics of capital position, capital amount, number limit and other information of capital organization is completed in the distribution process for the subsequent distribution process.

Wherein step S3 further includes:

1) and judging whether the capital position, the capital amount and the number limit of people meet the capital position, the capital amount and the number limit set by the system or not by the capital institution on the same day, and filtering the capital institution side which does not meet the requirements.

2) And judging whether the user information meets the risk preference of the capital organization side, and filtering the capital organization sides which do not meet the user information and the risk preference of the capital organization side.

And ranking the matching degree scores of the user and the fund institution party from high to low according to the model analysis, and sending the user and the fund institution party to complete credit granting or credit using transaction through a fund routing system according to the sequence.

Description of safety

The asset distribution system guarantees service safety from measures such as user authentication and authority management, system sensitive operation audit, data desensitization, code safety test and the like. The security precautions are shown in the following table:

in the aspects of user identity authentication and session management, the existing single sign-on system SSO of the Baixin bank is used for identity authentication, so the security depends on the single sign-on system.

The system sensitive operation auditing measures ensure that a user can timely learn the dynamic state when accessing the limited operation, and record an operation log and change data to ensure data rollback. All operations of users in the asset distribution system can leave marks and are stored in an operation record table, and modification of key information of the users and record of the note information of business personnel can also be persisted in a database so as to facilitate tracking of the operation records and auditing of safety compliance departments in the future.

And desensitization treatment is carried out on sensitive information such as user information, service core data and the like in the service data by the data desensitization measure, so that the message is prevented from being directly displayed in the system. When logging, no user sensitive information is output.

The code safety testing measures are characterized in that source code safety scanning, automatic regression testing, pressure testing and performance testing are carried out on codes by means of a hundred-degree agile development tool chain. Meanwhile, a service security test on the project is carried out, a potential security vulnerability of the code is found, and the security of the service is ensured. In addition, the database hierarchical system executes the sql statement by using mybatis, so that sql injection can be prevented.

In conclusion, by building the online asset intelligent distribution system, the system provides a uniform credit platform for borrowing users and a plurality of fund institution parties with borrowing needs on the Internet. When the borrowing user submits the credit or credit application transaction, the system completes the matching of the borrowing user and the fund institution side through related computer intelligent algorithms, and distributes the credit or credit application transaction of the borrowing user to the most appropriate fund institution side, thereby not only finding an appropriate fund institution for the borrowing user, but also completing part of screening work for the fund institution side and finding an accurate target borrowing user, and further achieving the win-win effect of the borrowing user and the fund institution side.

Unless defined otherwise, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. The use of "first," "second," and similar terms in the description and claims of this patent does not denote any order, quantity, or importance, but rather the terms are used to distinguish one element from another. Also, the use of the terms "a" or "an" and the like do not denote a limitation of quantity, but rather denote the presence of at least one.

The above description is only exemplary embodiments of the present invention and should not be taken as limiting the invention, and any modifications, equivalents, improvements and the like that are within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (7)

1. An online intelligent asset distribution system, comprising:

a distribution management system, the distribution management system comprising:

a process center module for managing asset distribution processes;

the model analysis module is used for analyzing a historical credit granting or credit using distribution result, completing modeling and outputting matching degree scores of the user and each capital institution;

a rules engine module for executing a distribution policy to select a matching funding institution party for a user;

the real-time counting module is used for completing real-time counting of capital information of a capital institution party in the distribution transaction process; and

the background management module is used for defining and managing an asset distribution process;

the system comprises a flow routing system, a distribution management system and a data processing system, wherein the flow routing system is used for acquiring user information of credit or credit application in a consumption credit scene, a cash credit scene or other scenes and providing the user information for the distribution management system to acquire; and

and the fund routing system is used for connecting each fund institution and forwarding the credit or credit application of the user to the fund institution side.

2. The online intelligent asset distribution system according to claim 1, wherein the asset distribution process is used for conducting approval operation on user credit or credit application according to a wind control credit strategy or a wind control credit strategy.

3. The online intelligent asset distribution system according to claim 1, wherein the fund institution side fund information comprises position, fund amount and person limit.

4. The online intelligent asset distribution system according to claim 3, wherein the background management module is used for setting capital position, capital amount, number limit and risk preference of the capital organization.

5. The online intelligent asset distribution system of claim 4, wherein the distribution policy comprises: whether the daily statistic of capital position, capital amount and person number limit of the capital institution meets the capital position, capital amount and person number limit of the capital institution set by the system or not; or whether the user information meets the risk preference of the capital institution; or the matching degree scores of the user and the fund institution side are ranked from high to low.

6. An online asset intelligent distribution method is characterized by comprising the following steps:

step S1, the traffic routing system acquires user information of various scenes;

step S2, selecting matched capital organization parties according to the user information and the comprehensive preference matching result of each capital organization;

step S3, distributing the user credit or credit application to the fund institution through the fund routing system and completing the transaction;

and step S4, the real-time statistics of capital position, capital amount and number limit information of capital organization is completed in the distribution process for the subsequent distribution process.

7. The online intelligent asset distribution system according to claim 1, wherein said step S3 further comprises:

judging whether the capital position, the capital amount and the person number limit of the capital institution meet the capital position, the capital amount and the person number limit set by the system on the same day, and filtering the capital institution side which does not meet the requirement;

and judging whether the user information meets the risk preference of the capital organization side, and filtering the capital organization sides which do not meet the user information and the risk preference of the capital organization side.

Images