CN110197429B - Consumption and finance combined loan intelligent routing method and system - Google Patents
Consumption and finance combined loan intelligent routing method and system Download PDFInfo
- Publication number
- CN110197429B CN110197429B CN201910491321.9A CN201910491321A CN110197429B CN 110197429 B CN110197429 B CN 110197429B CN 201910491321 A CN201910491321 A CN 201910491321A CN 110197429 B CN110197429 B CN 110197429B
- Authority
- CN
- China
- Prior art keywords
- loan
- score
- item
- scoring
- preselected
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Abstract
The invention discloses an intelligent routing method for a consumption and finance combined loan, which is characterized in that a plurality of scoring items are set for each loan item, each scoring item has an independent admission score and an independent interval base number, sub-recommendation scores of the loan application relative to all scoring items of each loan item are calculated by combining the interval base numbers, the admission scores are adopted to adjust the sub-recommendation scores so as to obtain more reasonable recommendation scores, the problem that users with low scores have no routable fund is avoided, and the most appropriate loan institution is selected for the users to the maximum extent by adding an institution-user dimension scoring system; meanwhile, the loan project is evaluated in real time, and the scoring result is corrected by adopting the surplus and the system service quality information, so that the user experience is improved, and the user routing proportion of each mechanism is balanced to the maximum extent; in addition, results such as examination and approval results, system success rate, time consumption, loan balance and the like are processed periodically, and scoring rules are optimized.
Description
Technical Field
The invention relates to the technical field of consumption finance, in particular to an intelligent routing method and system for consumption finance combined loan.
Background
With the continuous increase of the scale of the financial loan service of the Sunning consumption, the fund reserve capacity tends to be the limit, the self loan-holding balance approaches the standard upper limit, and in order to solve the pain points, a joint loan mode is applied to serve more potential customers together with the same-industry financial institutions.
According to the traditional routing system, corresponding routing rules are configured according to different loan institutions, after a user initiates a loan, most of the users meeting the verification rules can be matched with institutions with low priority, if the institution is used to the end, the users with low scores can have no routable fund, the loan institutions have low system rate, long approval time and no approval result, which affect the user experience, but the traditional routing system can only change the routing rules through a manual intervention method and adjust the approval and payment success rate of the users.
Disclosure of Invention
The invention aims to provide an intelligent routing method for a consumption finance combined loan, which is characterized in that a plurality of scoring items are set for each loan item, each scoring item has an independent admission score and an interval base number, sub-recommendation scores of the loan application relative to all the scoring items of each loan item are calculated by combining the interval base numbers, and the sub-recommendation scores are adjusted by adopting the admission scores to obtain more reasonable recommendation scores, so that the problem that a user with low score cannot route fund parties is avoided, and the most appropriate loan institution is selected for the user to the greatest extent by adding an institution-user dimension scoring system; meanwhile, the loan project is evaluated in real time, and the scoring result is corrected by adopting the surplus and the system service quality information, so that the user experience is improved, and the user routing proportion of each mechanism is balanced to the maximum extent; in addition, results such as examination and approval results, system success rate, time consumption, loan balance and the like are processed periodically, and scoring rules are optimized.
To achieve the above object, with reference to fig. 1, the present invention provides an intelligent routing method for a consumption finance combination loan, including:
s1: receiving a loan application sent by a user, wherein the loan application at least comprises user credit related information and a loan amount applied by the user.
S2: and obtaining loan information of a plurality of loan items, wherein the loan information at least comprises the remaining amount of each loan item, and the access points and interval cardinality of the scoring items.
S3: analyzing the credit related information of the user by combining the scoring items of each loan item, screening out the pre-selected loan items meeting the loan application requirement, and generating a pre-selected loan item database matched with the loan application, wherein the pre-selected loan items meet the following conditions: 1) the credit line applied by the user is less than or equal to the corresponding surplus line, and 2) the score of each score item in the credit related information of the user is greater than or equal to the corresponding admission score.
S4: and optionally selecting one pre-selected loan item from a pre-selected loan item database, and calculating the sub-recommendation score of the loan application relative to each score item of the pre-selected loan item by combining the interval base number.
S5: taking the admission score of each score of the preselected credit item as an adjusting factor, adjusting the sub-recommendation score of the corresponding score, and calculating to obtain the recommendation score of the loan application relative to the preselected credit item by combining the sub-recommendation scores of all adjusted scores, wherein the regulation and control rule is as follows: the higher the admission score is, the larger the amplitude of the regulated sub-recommendation score is.
S6: repeating the steps S4-S5 until the recommendation score of the loan application relative to all the preselected loan items corresponding to the loan application is calculated.
S7: the preselected loan item with the highest recommended score is assigned to the loan application.
Based on the method, the invention also provides an intelligent routing system for the consumption and finance combined loan, which comprises a routing subsystem, a loan application management subsystem, a loan project management subsystem, a scoring subsystem and a scoring rule management subsystem.
The loan application management subsystem comprises a loan application receiving module, a loan application screening module and a loan application processing module.
The loan project management subsystem is used for storing and managing related parameters of each loan project, and the related parameters of the loan project at least comprise a residual amount, a grading item category, an admission score of each grading item and an interval cardinality.
The scoring rule management subsystem is connected with the scoring subsystem and is used for setting and modifying scoring rules of the scoring subsystem.
The loan application receiving module is used for receiving loan applications sent by a user, sending the loan applications to the loan application analysis module for screening, sending the loan applications meeting application conditions to the loan application processing module, preprocessing the received loan applications by the loan application processing module, and sending the preprocessed loan applications and corresponding processing requests to the routing subsystem.
The routing subsystem responds to the received processing request, combines the received preprocessed loan application, calls loan items meeting the loan application requirement from the loan item management subsystem, generates a preselected loan item database matched with the loan application, and sends the generated preselected loan item database and the corresponding loan application to the scoring subsystem.
The scoring subsystem receives a loan application and a preselected loan item database, calculates a recommendation score of each preselected loan item in the preselected loan item database corresponding to the loan application, and feeds back a calculation result to the routing subsystem.
The routing subsystem screens out the loan item with the highest recommended score according to the calculation result, sends the loan application to the loan institution corresponding to the loan item with the highest recommended score, and
and receiving a loan application auditing result fed back by the loan institution, feeding back the loan application auditing result to the user side, and storing the processing process and the processing result of the loan application in a log.
After receiving the loan application sent by the user, the routing system needs to go through the following steps.
The method comprises the steps of preprocessing loan application, for example, judging whether a user initiating the loan application belongs to a blacklist user, whether a loan application amount exceeds a set amount range, whether loan information and credit information are completely filled, and the like, wherein the steps are to quickly filter out the loan application which does not meet the requirements and reduce the calculation amount of a routing system.
Secondly, according to the information contained in the loan application, screening out a plurality of loan items meeting the loan application requirements, wherein the loan items correspond to loan institutions, and one loan institution may correspond to a plurality of loan items.
The specific process is as follows: and obtaining loan information of all loan items, wherein the loan information at least comprises the remaining amount of each loan item, and the access points and interval cardinality of the scoring items. Analyzing the credit related information of the user by combining the scoring items of each loan item, screening out the pre-selected loan items meeting the loan application requirement, and generating a pre-selected loan item database matched with the loan application, wherein the pre-selected loan items meet the following conditions: 1) the credit line applied by the user is less than or equal to the corresponding surplus line, and 2) the score of each score item in the credit related information of the user is greater than or equal to the corresponding admission score.
The scoring items comprise a user sesame score, a user calendar, a user online time, a user behavior score and the like.
For example, the currently existing loan items are loan item a, loan item B, loan item C, loan item D, and loan item E, the corresponding remaining amount is 80W, 50W, 40W, 30W, and 10W, the scoring items are only sesame-based, and the admission points are 800, 700, 500, 600, and 500, respectively.
If the first user initiates a loan application I at this time, the applied loan amount is 40W, the sesame of the first user is 650, and the selected pre-selected loan item corresponding to the loan application I is a loan item C.
And if the user B initiates a loan application II at the moment, the applied loan amount is 10W, and the sesame of the user B is 650, the screened preselected loan items corresponding to the loan application II are a loan item C, a loan item D and a loan item E.
And finally, calculating the recommendation score of the loan application relative to all the corresponding preselected loan items, and distributing the preselected loan item with the highest recommendation score to the loan application. Wherein the process of calculating the recommended score of the loan application relative to one of the preselected loan terms comprises:
and optionally selecting one preselected loan item from a preselected loan item database, and calculating the sub-recommendation score of the loan application relative to each score item of the preselected loan item by combining the interval base number. For the same user, the interval level occupied by the user in the loan project with the lower admission score is higher, namely the obtained interval base number is higher, so that the user can more easily route to the loan project with the lower admission score, and the resource allocation of the loan project is uneven. Therefore, the invention provides that the admission score of each score item of the preselected loan item is used as an adjusting factor, the sub-recommendation scores of the corresponding score item are adjusted, and the recommendation score of the loan application relative to the preselected loan item is calculated by combining the sub-recommendation scores of all the adjusted score items, wherein the adjusting rule is as follows: the higher the admission score is, the larger the amplitude of the regulated sub-recommendation score is. By regulating the sub recommendation scores, the finally obtained recommendation scores are more reasonable, the user routing proportion of each mechanism is balanced to the maximum extent, meanwhile, as many user loan applications as possible are passed through, and the user experience is enhanced.
Compared with the prior art, the technical scheme of the invention has the following remarkable beneficial effects:
(1) and adjusting the sub-recommendation score by adopting the admission score to obtain a more reasonable recommendation score, avoiding the problem that the user with low score has no routable fund party, and maximizing the selection of the most appropriate loan institution for the user by adding a grading system with institution-user dimensionality.
(2) Meanwhile, the loan items are evaluated in real time, and the scoring result is corrected by adopting the surplus and the system service quality information, so that the user experience is improved, and the user routing proportion of each mechanism is balanced to the maximum extent.
(3) In addition, results such as approval results, system success rate, time consumption, loan balance and the like are processed periodically, and scoring rules are optimized.
It should be understood that all combinations of the foregoing concepts and additional concepts described in greater detail below can be considered as part of the inventive subject matter of this disclosure unless such concepts are mutually inconsistent. In addition, all combinations of claimed subject matter are considered a part of the presently disclosed subject matter.
The foregoing and other aspects, embodiments and features of the present teachings will be more fully understood from the following description taken in conjunction with the accompanying drawings. Additional aspects of the present invention, such as features and/or advantages of exemplary embodiments, will be apparent from the description which follows, or may be learned by practice of the specific embodiments according to the teachings of the present invention.
Drawings
The drawings are not intended to be drawn to scale. In the drawings, each identical or nearly identical component that is illustrated in various figures may be represented by a like numeral. For purposes of clarity, not every component may be labeled in every drawing. Embodiments of various aspects of the present invention will now be described, by way of example, with reference to the accompanying drawings, in which:
FIG. 1 is a flowchart of a method according to a first embodiment of the present invention.
FIG. 2 is a flowchart of a second embodiment of the method of the present invention.
Fig. 3 is a schematic diagram of the intelligent routing system for the consumption finance combination loan of the invention.
Fig. 4 is a schematic workflow diagram of the intelligent routing system for the consumption finance integrated loan of the invention.
Detailed Description
In order to better understand the technical content of the present invention, specific embodiments are described below with reference to the accompanying drawings.
Detailed description of the preferred embodiment
With reference to fig. 1, the present invention provides an intelligent routing method for a joint loan of consumption finance, which comprises:
s1: receiving a loan application sent by a user, wherein the loan application at least comprises credit related information of the user and a loan amount applied by the user.
S2: and obtaining loan information of a plurality of loan items, wherein the loan information at least comprises the remaining amount of each loan item, and the admittance scores and interval cardinality of the scoring items.
S3: analyzing the credit related information of the user by combining the scoring items of each loan item, screening out the preselected loan items meeting the loan application requirements, and generating a preselected loan item database matched with the loan application, wherein the preselected loan items meet the following conditions: 1) the credit line applied by the user is less than or equal to the corresponding surplus line, and 2) the score of each scoring item in the credit related information of the user is more than or equal to the corresponding admission score.
S4: and optionally selecting one preselected loan item from a preselected loan item database, and calculating the sub-recommendation score of the loan application relative to each score item of the preselected loan item by combining the interval base number.
S5: taking the admission score of each score of the preselected loan item as an adjustment factor, adjusting the sub-recommendation scores of the corresponding score, and calculating to obtain the recommendation score of the loan application relative to the preselected loan item by combining the sub-recommendation scores of all adjusted scores, wherein the regulation and control rule is as follows: the higher the access score is, the larger the amplitude of the regulated sub recommendation score is.
S6: repeating steps S4-S5 until a recommendation score is calculated for the loan application with respect to all of the pre-selected loan terms to which it corresponds.
S7: the preselected loan terms with the highest recommended score are assigned to the loan application.
Preferably, in step S5, the step of adjusting the sub-recommendation score of each score item of the pre-selected credit item by using the admission score of each score item as an adjustment factor,
s51: calculating the adjusted sub-recommendation score alpha according to the following formulai：
Wherein alpha isｉIs a sub-recommendation score of the ith score, SiIs an admission score, p, of the ith score itemiIs the score, h, of the loan application corresponding to the ith scoring termiIs the base of the interval corresponding to the ith score for the loan application.
More preferably, in step S5, the calculating the recommendation score of the loan application relative to the preselected loan amount item by combining the sub-recommendation scores of all the adjusted score items,
s52: calculating a recommended Score for said loan application corresponding to said preselected loan term according to the following formula*：
Wherein beta isiIs the weight value of the ith score, i ═ 1, 2.
The foregoing method is illustrated by one of the examples below.
The two existing joint loan institutions comprise sesame scoring items, the sesame scoring admission scores of the two institutions are respectively 600 and 700, the higher the sesame scoring admission score is, the higher the initial score of a user in the institution is, the judgment interval standard of the user sesame scoring and the value-added base number of each interval are shown in table 1, and the sesame scoring factor score is corrected correspondingly according to the item sesame scoring in which the user sesame scoring falls.
Table 1 sesame point admission standards for items a and B and sesame point setting intervals
| Admission | In | High (a) | Extreme high | |
| Item A | 600 | 650 | 700 | 750 |
| Item B | 700 | 750 | 800 | 850 |
| Interval cardinality | 0.8 | 1.0 | 1.1 | 1.15 |
The scoring formula for calculating the sub-recommendation score of the user sesame scoring item is as follows:
1) judging the admission score, and eliminating the item if the user score is less than the admission score
2) Sub-recommendation score of sesame score item (admittance score/user score) + interval base number
TABLE 2
| User nail 800 | User B680 | User C750 | |
| Item A | 1.9 | 1.882 | 1.95 |
| Item B | 1.975 | - | 1.93 |
Table 2 shows the sesame score sub-recommendation scores of user a, user B, and user c corresponding to item a and item B, respectively.
When only one sesame item is scored, according to the calculation result, the first user with a high score scores higher in the high-limit item A; the user B with low score fails the limit requirement of the project B, and the score in the project A is relatively low; users with moderate scores prefer item a. Through the processing, the high-sesame users can be preferentially pushed to the high-access mechanism, and the common users can be preferentially pushed to the high-scoring interval mechanism, so that the loan resources are reasonably distributed.
When a plurality of scoring items comprising sesame items exist, the sub-recommendation score of each scoring item is calculated by adopting the method, the recommendation score is calculated in a weight adding mode, and loan item resources are distributed according to the recommendation score.
Detailed description of the preferred embodiment
The invention provides an intelligent routing method for a consumption and finance combined loan, which comprises the following steps:
s1: receiving a loan application sent by a user, wherein the loan application at least comprises user credit related information and a loan amount applied by the user.
S2: and obtaining loan information of a plurality of loan items, wherein the loan information at least comprises the remaining amount of each loan item, and the admittance scores and interval cardinality of the scoring items.
S3: analyzing the credit related information of the user by combining the scoring items of each loan item, screening out the pre-selected loan items meeting the loan application requirement, and generating a pre-selected loan item database matched with the loan application, wherein the pre-selected loan items meet the following conditions: 1) the credit line applied by the user is less than or equal to the corresponding surplus line, and 2) the score of each scoring item in the credit related information of the user is more than or equal to the corresponding admission score.
S4: and optionally selecting one preselected loan item from a preselected loan item database, and calculating the sub-recommendation score of the loan application relative to each score item of the preselected loan item by combining the interval base number.
S5: taking the admission score of each score of the preselected credit item as an adjusting factor, adjusting the sub-recommendation score of the corresponding score, and calculating to obtain the recommendation score of the loan application relative to the preselected credit item by combining the sub-recommendation scores of all adjusted scores, wherein the regulation and control rule is as follows: the higher the admission score is, the larger the amplitude of the regulated sub-recommendation score is.
S6: repeating steps S4-S5 until a recommendation score is calculated for the loan application with respect to all of the pre-selected loan terms to which it corresponds.
S7: the preselected loan terms with the highest recommended score are assigned to the loan application.
In conjunction with fig. 2, the method further comprises:
and obtaining system service quality information corresponding to each pre-selected loan item, correcting the recommended points by adopting the remaining amount and the system service quality information, and allocating the loan item with the highest corrected recommended point to the loan application.
Preferably, the modifying the recommendation score means,
and calculating the corrected recommended Score according to the following formula:
Score＝r*mt*Score*
where r is a dynamic intervening routing result modification value, mtIs the correction base number at the current moment, is influenced by the remaining amount of the pre-selected loan item and the corresponding system service quality information, and is Score*Is a recommended score for the preselected credit item.
The system service quality information comprises system success rate, network delay and TPS.
More preferably, the method further comprises:
calculating a correction base number m at the t-th time according to the following formulat：
mt＝(ω1·x1t+ω2·x2t+ω3·x3t)/(ω1+ω2+ω2)
Wherein x is1tIs the system success rate at time t, x2tIs the remaining amount ratio at time t, x3tIs 5 minutes at the t-th timeCorrecting the time-consuming average value of the interface; omega1、ω2、ω3Respectively, a success rate weight, a proportion weight and a time consumption weight.
The correction method includes two reasons, firstly, the remaining amount of the loan item, and secondly, the system service quality corresponding to the loan item, such as the system success rate, the network delay, the TPS, etc., namely, the system failure rate, the network delay, the fund reduction, etc., all of which will correspondingly reduce the value of the credit of the user at the institution.
In order to balance the loan proportion of each loan item as much as possible, maximize the utilization of loan funds and improve the passing rate of user loans, the invention provides that the remaining amount of the loan item is taken as one of correction factors to correct the recommendation score, and the reduction of the loan balance reduces the user score of the loan item to avoid routing the user to low-requirement institutions, thereby maximally balancing the user routing proportion of each institution.
Another correction factor is selected from the loan institution's perspective, such as the system quality of service, e.g., 5 minutes interface elapsed average correction rate, etc., the system failure rate (i.e., the rate of pass of the route to the loan term), etc. The loan institution with higher network delay has lower score, the loan institution with higher system failure rate has lower score, and a fund provider with high success rate and fast approval is provided for the user through the score correction of the service success rate, so that the user experience is increased.
Example (c): assume that the user has a 30 point recommendation score for loan item a and loan item B.
The corrected score is the original score (system success rate, success rate weight + remaining amount of the day to be compared, proportion weight +5 minutes interface time-consuming average correction rate, time-consuming weight)/(success rate weight + proportion weight + time-consuming weight).
Table 3 is the score after correction based on the corrected real-time returned routing results.
TABLE 3
The user is assigned to project A based on the revised score.
The modified dynamic intervention routing result is used for the administrator to perform human intervention on the scoring rules of each item, for example, if it is desired to increase the recommendation ratio or decrease the recommendation ratio for some items, the modified dynamic intervention routing result may be modified to achieve the modified dynamic intervention routing result, and otherwise, the modified dynamic intervention routing result is 1.
Detailed description of the invention
The invention provides an intelligent routing method for a consumption and finance combined loan, which comprises the following steps:
s1: receiving a loan application sent by a user, wherein the loan application at least comprises user credit related information and a loan amount applied by the user.
S2: and obtaining loan information of a plurality of loan items, wherein the loan information at least comprises the remaining amount of each loan item, and the access points and interval cardinality of the scoring items.
S3: analyzing the credit related information of the user by combining the scoring items of each loan item, screening out the pre-selected loan items meeting the loan application requirement, and generating a pre-selected loan item database matched with the loan application, wherein the pre-selected loan items meet the following conditions: 1) the credit line applied by the user is less than or equal to the corresponding surplus line, and 2) the score of each score item in the credit related information of the user is greater than or equal to the corresponding admission score.
S4: and optionally selecting one preselected loan item from a preselected loan item database, and calculating the sub-recommendation score of the loan application relative to each score item of the preselected loan item by combining the interval base number.
S5: taking the admission score of each score of the preselected loan item as an adjustment factor, adjusting the sub-recommendation scores of the corresponding score, and calculating to obtain the recommendation score of the loan application relative to the preselected loan item by combining the sub-recommendation scores of all adjusted scores, wherein the regulation and control rule is as follows: the higher the admission score is, the larger the amplitude of the regulated sub-recommendation score is.
S6: repeating the steps S4-S5 until the recommendation score of the loan application relative to all the preselected loan items corresponding to the loan application is calculated.
S7: the preselected loan item with the highest recommended score is assigned to the loan application.
The method further comprises the following steps:
and analyzing the loan failure data of each loan item according to a set period, counting failure reasons, and adjusting the calculation rule of the recommendation score if the failure reasons are that the total number of the failure loan applications with insufficient recommendation score exceeds a set time threshold.
For example, the routing system processes the data of the T +1 day payment failure regularly, statistically analyzes the failure reasons, and adjusts the scoring rules of the corresponding scoring factors according to different reasons, that is, the routing system: and performing previous data offline approval operation through T +1, correcting a project scoring factor according to an approval result, and improving the approval success rate of a user pushing mechanism and the payment speed of a user. For example, if the mechanism a has a large number of reasons for rejecting the mechanism a due to low sesame score, the admission score and the sesame partition of the mechanism a are corrected accordingly.
Preferably, the calculation rule for adjusting the recommendation score includes:
and setting a plurality of scoring items corresponding to the loan items as dynamic scoring items, configuring at least two scoring levels for each dynamic scoring item, wherein each scoring level corresponds to different interval cardinality and/or admission score, and the higher the scoring level is, the lower the interval cardinality and/or admission score is.
And if the total number of the failed loan applications is greater than a set time threshold because of insufficient recommendation scores due to the failure reason, reducing the scoring level of one or more dynamic scoring items.
More preferably, the dynamic scoring item is provided with a priority;
if the total number of the failed loan applications is larger than a set time threshold because of insufficient recommendation scores due to the failure reason, the scoring levels of one or more dynamic scoring items are sequentially reduced from high to low according to the priority.
The loan institution can select some of the scoring items to be dynamic scoring items according to actual requirements, the rest scoring items are relatively more important and do not change, when the failure rate is higher and the failure reason is that the recommendation score is insufficient, the routing system sequentially selects one or more dynamic scoring items according to the priority, the scoring level is reduced, the user recommendation score is improved, the failure rate is adjusted, and automatic correction of scoring rules is achieved.
Detailed description of the invention
With reference to fig. 3 and fig. 4, based on the foregoing method, the present invention further provides an intelligent routing system for joint consumption finance loan, which includes a routing subsystem, a loan application management subsystem, a loan project management subsystem, a scoring subsystem, and a scoring rule management subsystem.
The loan application management subsystem comprises a loan application receiving module, a loan application screening module and a loan application processing module.
The loan project management subsystem is used for storing and managing related parameters of each loan project, and the related parameters of the loan project at least comprise a residual amount, a grading item category, an admission score of each grading item and an interval cardinality.
The scoring rule management subsystem is connected with the scoring subsystem and used for setting and modifying scoring rules of the scoring subsystem.
The loan application receiving module is used for receiving loan applications sent by a user, sending the loan applications to the loan application analysis module for screening, sending the loan applications meeting application conditions to the loan application processing module, preprocessing the received loan applications by the loan application processing module, and sending the preprocessed loan applications and the corresponding processing requests to the routing subsystem.
The routing subsystem responds to the received processing request, combines the received preprocessed loan application, calls loan items meeting the loan application requirement from the loan item management subsystem, generates a preselected loan item database matched with the loan application, and sends the generated preselected loan item database and the corresponding loan application to the scoring subsystem.
The scoring subsystem receives a loan application and a preselected loan item database, calculates a recommendation score of each preselected loan item in the preselected loan item database corresponding to the loan application, and feeds back a calculation result to the routing subsystem.
The routing subsystem screens out the loan item with the highest recommended score according to the calculation result, and sends the loan application to the loan institution corresponding to the loan item with the highest recommended score, and
and receiving a loan application auditing result fed back by the loan institution, feeding back the loan application auditing result to the user side, and storing the processing process and the processing result of the loan application in a log.
In this disclosure, aspects of the present invention are described with reference to the accompanying drawings, in which a number of illustrative embodiments are shown. Embodiments of the present disclosure are not necessarily defined to include all aspects of the invention. It should be appreciated that the various concepts and embodiments described above, as well as those described in greater detail below, may be implemented in any of numerous ways, as the disclosed concepts and embodiments are not limited to any one implementation. In addition, some aspects of the present disclosure may be used alone, or in any suitable combination with other aspects of the present disclosure.
Although the invention has been described with reference to preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the invention. Therefore, the protection scope of the present invention should be determined by the appended claims.
Claims (8)
1. An intelligent routing method for consumption finance combination loan, which is characterized by comprising the following steps:
s1: receiving a loan application sent by a user, wherein the loan application at least comprises credit related information of the user and a loan amount applied by the user;
s2: obtaining loan information of a plurality of loan items, wherein the loan information at least comprises the remaining amount of each loan item, and the admittance scores and interval cardinality of the scoring items;
s3: analyzing the credit related information of the user by combining the scoring items of each loan item, screening out the preselected loan items meeting the loan application requirements, and generating a preselected loan item database matched with the loan application, wherein the preselected loan items meet the following conditions: 1) the credit line applied by the user is less than or equal to the corresponding surplus line, and 2) the score of each score item in the credit related information of the user is more than or equal to the corresponding admission score;
s4: randomly selecting one of the preselected loan items from a preselected loan item database, and calculating a sub-recommendation score of the loan application relative to each score item of the preselected loan items according to the interval base number;
s5: taking the admission score of each score of the preselected credit item as an adjusting factor, adjusting the sub-recommendation score of the corresponding score, and calculating to obtain the recommendation score of the loan application relative to the preselected credit item by combining the sub-recommendation scores of all adjusted scores, wherein the regulation and control rule is as follows: the higher the admission score is, the larger the amplitude of the regulated sub-recommendation score is;
s6: repeating the steps S4-S5 until the recommendation scores of the loan application relative to all the corresponding preselected loan items are calculated;
s7: assigning a preselected loan item with the highest recommended score to the loan application;
the method further comprises the following steps:
analyzing the loan failure data of each loan item according to a set period, counting failure reasons, and if the failure reasons are that the total number of the failure loan applications lack due to the recommendation score exceeds a set time threshold, adjusting the calculation rule of the recommendation score;
the calculation rule for adjusting the recommendation score comprises the following steps:
setting a plurality of scoring items corresponding to the loan items as dynamic scoring items, configuring at least two scoring levels for each dynamic scoring item, wherein each scoring level corresponds to different interval cardinality and/or admission score, and the higher the scoring level is, the lower the interval cardinality and/or admission score is;
and if the total number of the failed loan applications is greater than a set time threshold because of insufficient recommendation scores due to the failure reason, reducing the scoring level of one or more dynamic scoring items.
2. The intelligent routing method for consumer-financial combination loan according to claim 1, wherein in step S5, the adjusting the admission score of each score item of the preselected loan item as an adjusting factor and the adjusting the sub-recommendation score of the corresponding score item means,
s51: calculating the adjusted sub-recommendation score alpha according to the following formulai：
Wherein alpha isiIs a sub-recommendation score, S, of the ith scoreiIs an admission score, p, of the ith score itemiIs the score, h, of the loan application corresponding to the ith scoring termiIs the interval base of the loan application corresponding to the ith scoring term.
3. The intelligent routing method for consumption finance combination loan according to claim 2, wherein, in step S5, the calculation of the recommended score of the loan application relative to the preselected loan item is performed in combination with the sub-recommended scores of all the adjusted score items,
s52: calculating a recommended Score for said loan application corresponding to said preselected loan terms according to the following formula*：
Wherein beta isiIs the weight value of the ith score, i is 1,2, …, n.
4. The intelligent routing method for the consumption finance combination loan according to any one of claims 1-3, characterized in that the method further comprises:
and obtaining system service quality information corresponding to each pre-selected loan item, correcting the recommended points by adopting the remaining amount and the system service quality information, and allocating the loan item with the highest corrected recommended point to the loan application.
5. The intelligent routing method for consumption finance combination loan according to claim 4, wherein the modifying of the recommendation score is to,
and calculating the corrected recommended Score according to the following formula:
Score＝r*mt*Score*
where r is a dynamic intervening routing result modification value, mtIs the correction base number at the current moment, is influenced by the remaining amount of the preselected loan item and the corresponding system service quality information, and is Score*Is a recommended score for said preselected credit item;
the system service quality information comprises a system success rate, network delay and TPS.
6. The intelligent routing method for consumption finance combination loan according to claim 4, wherein the method further comprises:
calculating a correction base number m at the t-th time according to the following formulat：
mt＝(ω1·x1t+ω2·x2t+ω3·x3t)/(ω1+ω2+ω2)
Wherein x is1tIs the system success rate at time t, x2tIs the remaining amount ratio at time t, x3tThe time-consuming average correction rate of the 5-minute interface at the t moment is obtained; omega1、ω2、ω3Respectively, a success rate weight, a proportion weight and a time consumption weight.
7. The intelligent routing method for the consumption finance combination loan according to claim 1, wherein the dynamic scoring item is provided with a priority;
if the total number of the failed loan applications is larger than a set time threshold because of insufficient recommendation scores due to the failure reason, the scoring levels of one or more dynamic scoring items are sequentially reduced from high to low according to the priority.
8. The consumption finance combination loan intelligent routing system based on the method of claim 1 is characterized by comprising a routing subsystem, a loan application management subsystem, a loan project management subsystem, a scoring subsystem and a scoring rule management subsystem;
the loan application management subsystem comprises a loan application receiving module, a loan application screening module and a loan application processing module;
the loan project management subsystem is used for storing and managing related parameters of each loan project, and the related parameters of the loan project at least comprise a residual amount, a rating item category, an admission score of each rating item and an interval cardinality;
the scoring rule management subsystem is connected with the scoring subsystem and is used for setting and modifying scoring rules of the scoring subsystem;
the loan application receiving module is used for receiving loan applications sent by a user, sending the loan applications to the loan application analyzing module for screening, sending the loan applications meeting application conditions to the loan application processing module, preprocessing the received loan applications by the loan application processing module, and sending the preprocessed loan applications and corresponding processing requests to the routing subsystem;
the routing subsystem responds to the received processing request, combines the received preprocessed loan application, calls loan items meeting the loan application requirement from the loan item management subsystem, generates a pre-selected loan item database matched with the loan application, and sends the generated pre-selected loan item database and the corresponding loan application to the scoring subsystem;
the scoring subsystem receives a loan application and a preselected loan item database, calculates a recommendation score of each preselected loan item in the preselected loan item database corresponding to the loan application, and feeds back a calculation result to the routing subsystem;
the routing subsystem screens out the loan item with the highest recommended score according to the calculation result, and sends the loan application to the loan institution corresponding to the loan item with the highest recommended score, and
and receiving a loan application auditing result fed back by the loan institution, feeding back the loan application auditing result to the user side, and storing the processing process and the processing result of the loan application in a log.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910491321.9A CN110197429B (en) | 2019-06-06 | 2019-06-06 | Consumption and finance combined loan intelligent routing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910491321.9A CN110197429B (en) | 2019-06-06 | 2019-06-06 | Consumption and finance combined loan intelligent routing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110197429A CN110197429A (en) | 2019-09-03 |
| CN110197429B true CN110197429B (en) | 2022-07-15 |
Family
ID=67754022
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910491321.9A Active CN110197429B (en) | 2019-06-06 | 2019-06-06 | Consumption and finance combined loan intelligent routing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110197429B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111008897B (en) * | 2019-12-23 | 2023-08-25 | 集奥聚合(北京)人工智能科技有限公司 | Bank card refusing diversion method based on radar technology |
| CN112634031A (en) * | 2020-12-31 | 2021-04-09 | 中国农业银行股份有限公司 | Credit service data matching method and device |
| CN113077339A (en) * | 2021-06-04 | 2021-07-06 | 武汉众邦银行股份有限公司 | Method for constructing intelligent fund routing model |
| CN114549170B (en) * | 2021-11-19 | 2022-11-22 | 北京宇信科技集团股份有限公司 | Data processing method, medium, equipment and system for joint loan |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108335189A (en) * | 2017-09-19 | 2018-07-27 | 平安普惠企业管理有限公司 | Loan processing method, server and readable storage medium storing program for executing on line |
| CN108346029A (en) * | 2017-01-23 | 2018-07-31 | 纬创软件（北京）有限公司 | A kind of customization credit system of support credit factory mode |
| CN109191109A (en) * | 2018-08-30 | 2019-01-11 | 中国平安人寿保险股份有限公司 | The self-adapting regulation method and device of transaction routing rule |
| CN109816515A (en) * | 2018-12-24 | 2019-05-28 | 天翼电子商务有限公司 | Credit class product Internet-based selects system and method |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120179598A1 (en) * | 2011-01-07 | 2012-07-12 | Jason Roth | Systems and Methods for Assessing Metrics of Loans, Financial Instruments and Financial Entities |
| US20140143128A1 (en) * | 2012-11-16 | 2014-05-22 | Capital One Financial Corporation | Unsecured to secured loan conversion in automobile finance |
| CN104182883A (en) * | 2014-08-22 | 2014-12-03 | 北京迈伴客金融信息服务有限公司 | Financial service trading system based on cloud computing and trading method adopting financial service trading system |
| CN107967649A (en) * | 2017-11-07 | 2018-04-27 | 深圳市天下房仓科技有限公司 | A kind of the tourism industry loan measures and procedures for the examination and approval, system, terminal and storage medium |
| CN108256991A (en) * | 2017-12-18 | 2018-07-06 | 四川省大益科技有限公司 | A kind of banking management system applied to construction project |
| CN108389123A (en) * | 2018-02-12 | 2018-08-10 | 中科柏诚科技（北京）股份有限公司 | A kind of internet syndicated loan system and method |
-
2019
- 2019-06-06 CN CN201910491321.9A patent/CN110197429B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108346029A (en) * | 2017-01-23 | 2018-07-31 | 纬创软件（北京）有限公司 | A kind of customization credit system of support credit factory mode |
| CN108335189A (en) * | 2017-09-19 | 2018-07-27 | 平安普惠企业管理有限公司 | Loan processing method, server and readable storage medium storing program for executing on line |
| CN109191109A (en) * | 2018-08-30 | 2019-01-11 | 中国平安人寿保险股份有限公司 | The self-adapting regulation method and device of transaction routing rule |
| CN109816515A (en) * | 2018-12-24 | 2019-05-28 | 天翼电子商务有限公司 | Credit class product Internet-based selects system and method |
Non-Patent Citations (1)
| Title |
|---|
| "银行移动营销平台安全机制研究与系统实现";戴百林;《中国优秀硕士学位论文全文数据库（信息科技辑）》;20160815(第8期);第I138-259页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110197429A (en) | 2019-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110197429B (en) | Consumption and finance combined loan intelligent routing method and system | |
| CN107169756B (en) | Payment channel distribution method, device, storage medium and payment routing system | |
| US6742100B1 (en) | Method and system for managing memory pools in a partitioned computer system | |
| US6968441B1 (en) | Method and system for managing interdependent resources of a computer system | |
| CN108600014B (en) | Stackelberg game-based storage resource allocation method | |
| Fandel et al. | Redistribution of funds for teaching and research among universities: The case of North Rhine-Westphalia | |
| WO2020233318A1 (en) | Data adjustment method based on data analysis and related devices | |
| CN108921309A (en) | Meeting room subscribes optimization method, system, readable storage medium storing program for executing and computer equipment | |
| CN116167452A (en) | Cluster federation learning method based on model similarity | |
| JP2005196777A (en) | Information distribution system, its method, program realizing it, and information medium concerning it | |
| CN111445329A (en) | Block chain transaction processing method and system | |
| CN107092998A (en) | Resource allocation methods and device | |
| Sahraie et al. | Development of a multi‐objective framework for the separate active and reactive power market clearing with index‐based vision | |
| Orji et al. | Empirical analysis of the impact of population increase on the economic growth of Africa’s most populous country | |
| CN112949996A (en) | Product and channel distribution method and system applied to cross marketing | |
| Takahata et al. | Intergovernmental Transfers in Indonesia | |
| CN111738865A (en) | Net value curve generation method and device, readable storage medium and computing equipment | |
| WO2003088046A1 (en) | Tuning memory resources in partitioned computer | |
| CN112132446A (en) | Power grid technical improvement investment allocation method based on Gini coefficient theory | |
| US20120123966A1 (en) | Multidirectional distributed recursive portfolio allocation | |
| Papapetrou et al. | The Greek labour market during the crisis: unemployment, employment and labour force participation | |
| CN116074262B (en) | Resource optimization allocation method based on big data platform | |
| KR102609900B1 (en) | An apparatus and a method for recommending goods and services | |
| CN115545910A (en) | Growth management system and method based on full life cycle limit | |
| JP2024011886A (en) | Work allocation program, information processing device, and work allocation method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: No.88, Huaihai Road, Qinhuai District, Nanjing City, Jiangsu Province, 210000 Patentee after: Nanyin Faba Consumer Finance Co.,Ltd. Address before: No.88, Huaihai Road, Qinhuai District, Nanjing City, Jiangsu Province, 210000 Patentee before: SUNING CONSUMER FINANCE Co.,Ltd. |